diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index 51bc3c413415c0bdedd40922e4f8d6ffdf952873..bc1d46aec6bd8b1fb035d6d8a2db1ef51a21d38d 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": "20260601T120028Z", - "generated_at": "2026-06-01T12:07:56Z", + "snapshot_id": "20260601T180035Z", + "generated_at": "2026-06-01T18:10:35Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ @@ -1888,35 +1888,6 @@ ] } ] - }, - { - "cluster_id": "cluster-44027-2", - "summary": "Cluster of 2 related pull requests linked by soft_similarity.", - "status": "open", - "confidence": 0.5, - "canonical_issue_number": null, - "canonical_pr_number": 44027, - "issue_numbers": [], - "pr_numbers": [ - 44027, - 44029 - ], - "evidence_types": [ - "soft_similarity" - ], - "pr_comparisons": [ - { - "left_pr_number": 44027, - "right_pr_number": 44029, - "code_similarity": 0.122, - "size_similarity": 0.442, - "file_overlap": 0.0, - "area_overlap": 0.0, - "patch_similarity": 0.221, - "shared_filenames": [], - "shared_file_areas": [] - } - ] } ], "duplicate_issues": [], @@ -1983,15 +1954,6 @@ "target_issue_number": null, "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." }, - { - "cluster_id": "cluster-44027-2", - "canonical_pr_number": 44027, - "duplicate_pr_numbers": [ - 44029 - ], - "target_issue_number": null, - "reason": "PRs in cluster-44027-2 are treated as duplicates because they share soft_similarity evidence." - }, { "cluster_id": "cluster-45081-3", "canonical_pr_number": 45317, diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index 1d4bdcf75f30803aaf3d0fa0c94383d6d5597342..9cab89331f95a9c19a0270d01666f673a58d2db8 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": "20260601T120028Z", - "generated_at": "2026-06-01T12:07:56Z", + "snapshot_id": "20260601T180035Z", + "generated_at": "2026-06-01T18:10:35Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -10,13 +10,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 1, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:24643", "issue:30277", @@ -80,8 +80,8 @@ "issue:45901|issue:46015", "issue:44509|issue:44512", "issue:35545|issue:36010", - "issue:44805|issue:45823", "issue:44918|issue:46165", + "issue:44805|issue:45823", "issue:43638|issue:44805", "issue:43638|issue:46165", "issue:44805|issue:46294", @@ -114,8 +114,8 @@ "issue:43716|issue:45685", "issue:44918|issue:45161", "issue:43716|issue:44292", - "issue:45507|issue:45685", "issue:44292|issue:44918", + "issue:45507|issue:45685", "issue:43039|issue:44918", "issue:41762|issue:43638", "issue:43827|issue:44512", @@ -132,446 +132,428 @@ "issue:41762|issue:43596", "issue:39290|issue:41720", "issue:43901|issue:44512", - "issue:45823|issue:46294", "issue:44589|issue:46304", + "issue:45823|issue:46294", "issue:45237|issue:45901" ], - "prepared_review_unit_hash": "a0c29e3fbe0ce9219ed947900dda07734e03eb5142ddc79c476d513e10a90b7e", + "prepared_review_unit_hash": "7e71c731fa2d8e67e4bcd8005016539595c7ea54268134d7db30ca1f0966aa6c", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 67, - "serialized_chars": 47824, - "estimated_input_tokens": 11956, - "estimated_eval_tokens": 24168 + "serialized_chars": 47828, + "estimated_input_tokens": 11957, + "estimated_eval_tokens": 24170 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many items share broad themes like ZeRO-3, device/dtype mismatch, or v5 docs cleanup, but they are not the same bug. The only strong duplicate-like pair is the two BERT + DeepSpeed ZeRO-3 index-out-of-bounds reports.", - "confidence": 0.79, - "canonical_issue_reason": "issue:43596 is the cleanest representative of the only clear duplicate family here: the ZeRO-3 empty-index crash during BERT model loading.", + "summary": "Mostly heterogeneous cluster. The only clear duplicate family is the DeepSpeed ZeRO-3 \"index 0 is out of bounds\" reports around model init/loading; most other pairs are different models, APIs, or docs changes.", + "confidence": 0.66, + "canonical_issue_reason": "issue:43596 is the broadest representative of the ZeRO-3 index-out-of-bounds family, and it matches the accepted BERT/Gemma3-style reports on the same failure mode.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the best global issue representative because it captures the narrow duplicate cluster most likely to be one root cause, while the rest of the items are mostly separate regressions.", + "best_issue_reason": "issue:43596 best captures the shared DeepSpeed ZeRO-3 init/loading bug with a concise, generic title; it is the most reusable canonical issue among the close matches.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different failures and code paths; only both involve Qwen3.5-family inference." + "reason": "Different failure modes: missing Qwen3.5 config attribute vs streaming chat/completions error." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Different model/hardware bug vs. MPS histogram op error; too broad to merge." + "reason": "Unrelated problems: AMD GPU support for GPT-OSS vs an MPS histogram kernel error." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different model-specific device/dtype problem from AMD GPU support issue." + "reason": "Different model families and different error paths (dtype mismatch vs AMD GPU runtime failure)." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Both are dtype/device issues, but on different models and execution paths." + "reason": "Different concrete bug: autocast dtype mismatch in Phi-tiny-MoE vs GPT-OSS on AMD GPUs." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Unrelated model-specific failures; no shared concrete bug." + "reason": "Different model-specific runtime issues; no shared code path is evident." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Same model family only at a very high level; distinct runtime failures." + "reason": "Different models and errors: Qwen-3 NVFP4 failure vs GPT-OSS AMD GPU failure." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch vs ONNX export error; unrelated." + "reason": "Both are failures, but on unrelated paths: DeepSpeed collective mismatch vs ONNX export." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "Different model export/runtime issues; no shared fix path." + "reason": "Different models and subsystems: export-to-ONNX vs FineGrainedFP8 runtime failure." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "ONNX export vs auto device-map CUDA assert; unrelated." + "reason": "No common concrete bug; ONNX export error vs Qwen3 auto device-map cuda assert." }, { "left": "issue:45901", "right": "issue:46015", "accept": false, - "reason": "Both are docs-related but about different topics and fixes." + "reason": "Different topics: table QA crash vs stale RAG examples documentation." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are v5 docs cleanup, but different removed references and separate edits." + "reason": "Both are docs regressions after v5, but they are different removed features and different docs surfaces." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "Export error vs import error; no common code path." + "reason": "Different issues: ModernBERT ONNX export vs GenerationMixin import failure." }, { - "left": "issue:44805", - "right": "issue:45823", + "left": "issue:44918", + "right": "issue:46165", "accept": false, - "reason": "Different shape/indexing issue vs device-mapping mismatch." + "reason": "Different training problems: Qwen3.5 input embedding unpacking vs resume/trust_remote_code behavior." }, { - "left": "issue:44918", - "right": "issue:46165", + "left": "issue:44805", + "right": "issue:45823", "accept": false, - "reason": "Different training/resume problems; only loosely trainer-related." + "reason": "Different tensor mismatch complaints on different models and code paths." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Both are IndexErrors, but in different subsystems and with different failure shapes." + "reason": "Both are IndexError-style reports, but the underlying path and model family differ." }, { "left": "issue:43638", "right": "issue:46165", "accept": false, - "reason": "BERT ZeRO-3 init crash vs resume-training/trust-remote-code issue." + "reason": "Unrelated: ZeRO-3 BERT index error vs training-resume/trust_remote_code issue." }, { "left": "issue:44805", "right": "issue:46294", "accept": false, - "reason": "Mask-shape mismatch vs video chat template token/feature mismatch." + "reason": "Different models and failure mechanisms; no shared underlying bug is apparent." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Different IndexError mechanisms; not the same bug." + "reason": "Different error shapes: ZeRO-3 init IndexError vs mask/tensor shape mismatch." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "Both are indexing-related, but in different model paths and likely different root causes." + "reason": "Shape mismatch crash vs GPT-OSS tensor-parallel issue; different code paths." }, { "left": "issue:44560", "right": "issue:46165", "accept": false, - "reason": "Video chat template failure vs training resume issue." + "reason": "Different features: Qwen3-VL video StopIteration vs training resume/trust_remote_code." }, { "left": "issue:43596", "right": "issue:46165", "accept": false, - "reason": "Different bug categories; only superficial transformer/training overlap." + "reason": "ZeRO-3 BERT init error is unrelated to the resume/trust_remote_code problem." }, { "left": "issue:43572", "right": "issue:46165", "accept": false, - "reason": "Config regression vs training resume problem; unrelated." + "reason": "Config regression (missing pad_token_idx) is unrelated to training resume behavior." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "BarkProcessor voice preset issue is unrelated to ModernBERT ONNX export." + "reason": "Different subsystems: BarkProcessor voice preset vs ModernBERT ONNX export." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Both mention DeepSpeed, but the concrete failures differ." + "reason": "Both involve DeepSpeed, but the specific failures and model paths are different." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same concrete ZeRO-3 index-out-of-bounds crash during BERT model loading; these look like duplicates." + "reason": "Same ZeRO-3 index-0-out-of-bounds failure during model init/loading; likely the same underlying DeepSpeed bug." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Detokenization bug vs LoRA merge/save/load inconsistency; different problem." + "reason": "Different problems: detokenization bug vs LoRA merge/save/reload mismatch." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger kernel cross-entropy call vs GPT-OSS TP issue; unrelated." + "reason": "Different issues: Liger Kernel cross-entropy call vs GPT-OSS tensor-parallel failure." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Different Qwen/GPT-related failures with no shared code path." + "reason": "Different models and bug classes; not a duplicate." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Different DeepSpeed runtime errors; not the same underlying defect." + "reason": "Different DeepSpeed training failures and different concrete error messages." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Activation-checkpointing FSDP mismatch vs mask/tensor shape error." + "reason": "FSDP/activation-checkpoint recomputation mismatch vs generic tensor mask shape mismatch." }, { "left": "issue:45859", "right": "issue:45902", "accept": false, - "reason": "Same class/module, but different offload/materialization bugs and not clearly one fix." + "reason": "Same model family, but different bugs: CPU offload incompatibility vs uninitialized-memory after materialization." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "BERT ZeRO-3 loading crash vs GPT-OSS tensor-parallel issue." + "reason": "ZeRO-3 BERT index error is unrelated to GPT-OSS tensor-parallel failure." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "FSDP checkpointing bug vs trainer API incompatibility." + "reason": "Different training stack problems: checkpointing/FSDP mismatch vs custom trainer signature change." }, { - "left": "issue:43596", - "right": "issue:45161", - "accept": false, - "reason": "BERT ZeRO-3 init crash vs GPT-OSS MoE parallelism issue." - }, - { - "left": "issue:43716", - "right": "issue:45507", - "accept": false, - "reason": "Different model-specific errors; no common bug." - }, - { - "left": "issue:45874", - "right": "issue:46294", + "left": "issue:45237", + "right": "issue:46015", "accept": false, - "reason": "Both involve Gemma/Qwen multimodal models, but the concrete failures are different." + "reason": "Different topics: AMD GPU support vs outdated RAG examples docs." }, { - "left": "issue:39290", - "right": "issue:45081", + "left": "issue:43039", + "right": "issue:44805", "accept": false, - "reason": "Different regression classes: missing config attr vs tokenizer patch crash." + "reason": "Liger Kernel cross-entropy issue and tensor shape mismatch are unrelated." }, { - "left": "issue:45823", - "right": "issue:45874", + "left": "issue:45800", + "right": "issue:46304", "accept": false, - "reason": "Device-map forward mismatch vs expensive reverse embedding lookup; separate issues." + "reason": "Version compatibility complaints, but about different version pairs and different failures." }, { - "left": "issue:43425", - "right": "issue:44292", + "left": "issue:43296", + "right": "issue:46304", "accept": false, - "reason": "Torch version incompatibility vs model runtime error." + "reason": "Different incompatibilities: vLLM/PaddleOCR-VL loading vs USE_DISTRIBUTED=0 regression." }, { - "left": "issue:34928", - "right": "issue:41720", - "accept": false, - "reason": "FSDP checkpointing issue vs Qwen3 auto device-map CUDA assert." + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds error during model loading/init; Gemma3 and BERT look like repros of the same bug." }, { - "left": "issue:43828", - "right": "issue:45161", + "left": "issue:43827", + "right": "issue:44512", "accept": false, - "reason": "Different dtype/device bugs on different model families." + "reason": "Both are v5 docs cleanup items, but they refer to different removed APIs and different documentation pages." }, { - "left": "issue:43541", - "right": "issue:43716", + "left": "issue:43716", + "right": "issue:44560", "accept": false, - "reason": "Mixtral grouped_mm tracing error vs Mistral image-preprocessor dtype mismatch." + "reason": "Different model-specific failures: image preprocessor dtype mismatch vs video StopIteration." }, { "left": "issue:43828", - "right": "issue:44292", - "accept": false, - "reason": "Different models and different failure modes." - }, - { - "left": "issue:43716", "right": "issue:45685", "accept": false, - "reason": "dtype mismatch vs MPS histogram op not implemented; unrelated." + "reason": "Different kernel/runtime bugs: autocast dtype mismatch vs MPS histogram not implemented." }, { "left": "issue:44918", - "right": "issue:45161", + "right": "issue:45685", "accept": false, - "reason": "Trainer embedding unpacking bug vs GPT-OSS MoE parallelism issue." + "reason": "Unrelated: Qwen3.5 SFT trainer input handling vs MPS MoE histogram error." }, { - "left": "issue:43716", - "right": "issue:44292", + "left": "issue:43039", + "right": "issue:43828", "accept": false, - "reason": "Different model-specific runtime errors." + "reason": "Different concrete paths: Liger Kernel cross_entropy vs Phi-tiny-MoE autocast mismatch." }, { - "left": "issue:45507", - "right": "issue:45685", + "left": "issue:30277", + "right": "issue:36331", "accept": false, - "reason": "Invalid method call in GraniteMoEHybrid vs MPS histogram failure." + "reason": "DeepSpeed collective mismatch and trainer signature error are unrelated." }, { - "left": "issue:44292", - "right": "issue:44918", + "left": "issue:34928", + "right": "issue:36010", "accept": false, - "reason": "Different Qwen-related issues with distinct stack paths." + "reason": "FSDP checkpointing mismatch vs missing GenerationMixin import." }, { - "left": "issue:43039", - "right": "issue:44918", + "left": "issue:45237", + "right": "issue:45901", "accept": false, - "reason": "Liger kernel cross-entropy call vs SFT trainer embedding unpacking." + "reason": "Different features and errors: GPT-OSS on AMD vs table-question-answering crash." }, { - "left": "issue:41762", - "right": "issue:43638", + "left": "issue:45823", + "right": "issue:45874", "accept": false, - "reason": "Both are ZeRO-3 index errors, but on different model families and not clearly one fix." + "reason": "Same model family, but different bugs: device mismatch with auto device_map vs expensive reverse embedding lookup." }, { - "left": "issue:43827", - "right": "issue:44512", + "left": "issue:43425", + "right": "issue:44292", "accept": false, - "reason": "Both are docs regressions, but about different removed features." + "reason": "Version incompatibility vs model-specific NVFP4 runtime error." }, { - "left": "issue:43716", - "right": "issue:44560", + "left": "issue:34928", + "right": "issue:41720", "accept": false, - "reason": "Different multimodal model bugs and different failure points." + "reason": "Different issues: activation checkpointing/FSDP mismatch vs Qwen3 auto device mapping cuda assert." }, { "left": "issue:43828", - "right": "issue:45685", + "right": "issue:45161", "accept": false, - "reason": "Device/dtype mismatch vs MPS histogram op error; unrelated." + "reason": "Different model/runtime failures with no clear shared code path." }, { - "left": "issue:44918", - "right": "issue:45685", + "left": "issue:43541", + "right": "issue:43716", "accept": false, - "reason": "Trainer bug vs MPS MoE histogram issue." + "reason": "Different model families and failure mechanisms." }, { - "left": "issue:43039", - "right": "issue:43828", + "left": "issue:43828", + "right": "issue:44292", "accept": false, - "reason": "Different models and different call sites." + "reason": "Different MoE/dtype issue vs Qwen NVFP4 runtime error." }, { - "left": "issue:30277", - "right": "issue:36331", + "left": "issue:43716", + "right": "issue:45685", "accept": false, - "reason": "DeepSpeed collective mismatch vs custom trainer signature change." + "reason": "Different bugs: image-preprocessor/model dtype mismatch vs MPS histogram kernel limitation." }, { - "left": "issue:34928", - "right": "issue:36010", + "left": "issue:44918", + "right": "issue:45161", "accept": false, - "reason": "Activation checkpointing bug vs import regression." + "reason": "Different training/inference problems on different models." }, { - "left": "issue:45237", - "right": "issue:46015", + "left": "issue:43716", + "right": "issue:44292", "accept": false, - "reason": "AMD GPU support issue vs outdated RAG examples; unrelated." + "reason": "Different model-specific runtime errors; no duplicate relationship is evident." }, { - "left": "issue:43039", - "right": "issue:44805", + "left": "issue:44292", + "right": "issue:44918", "accept": false, - "reason": "Kernel/cross-entropy routing issue vs mask-shape indexing error." + "reason": "Different failures: Qwen-3 NVFP4 runtime error vs TRL SFT unpacking issue." }, { - "left": "issue:45800", - "right": "issue:46304", + "left": "issue:45507", + "right": "issue:45685", "accept": false, - "reason": "Torch version incompatibility vs USE_DISTRIBUTED=0 regression; not the same bug." + "reason": "GraniteMoEHybrid invalid method and MPS histogram Int error are unrelated." }, { - "left": "issue:43296", - "right": "issue:46304", + "left": "issue:43039", + "right": "issue:44918", "accept": false, - "reason": "vLLM model load failure vs PyTorch distributed build regression." + "reason": "Liger Kernel cross-entropy issue vs TRL SFT trainer embedding unpacking are unrelated." }, { "left": "issue:41762", "right": "issue:43596", - "accept": false, - "reason": "Same broad ZeRO-3 area, but different models and not clearly one concrete bug." + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds error during model loading/init; both look like the same DeepSpeed issue." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Different model/version regressions; no shared code path." + "reason": "Different config/runtime problems: Gemma3TextConfig missing field vs Qwen3 device-map cuda assert." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "Docs mention different deprecated API surfaces." + "reason": "Different docs mismatches: return_all_scores behavior vs removed run command." }, { - "left": "issue:45823", - "right": "issue:46294", + "left": "issue:44589", + "right": "issue:46304", "accept": false, - "reason": "Device-map forward mismatch vs video chat template token mismatch." + "reason": "Different runtime problems: missing Float8 storage type vs USE_DISTRIBUTED=0 regression." }, { - "left": "issue:44589", - "right": "issue:46304", + "left": "issue:45823", + "right": "issue:46294", "accept": false, - "reason": "Float8 storage lookup error vs distributed-support regression." + "reason": "Different model paths and symptoms: Gemma4 device mismatch vs Qwen3.5 video token/template mismatch." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "Unrelated model deployment issue vs table QA crash." + "reason": "Different model/runtime issues with no shared root cause." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it correctly treats the cluster as mostly heterogeneous, and the only accepted duplicate pair (issue:43596 / issue:43638) is well-supported by the very similar ZeRO-3/BERT index-out-of-bounds reports. No soft-edge verdict appears overstated, and the canonical issue choice is reasonable." + "feedback": "Grounded overall. The ZeRO-3 index-out-of-bounds cluster around 43596/43638/41762 is supported by the packet, and the rest of the pairwise rejections are conservative given the differing titles/subsystems. No obvious overstatement of evidence." }, "evaluator_used": true, "retried": false, @@ -584,13 +566,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 2, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36010", "issue:39290", @@ -672,8 +654,8 @@ "issue:43296|issue:43366", "issue:43572|issue:45070", "issue:43541|issue:45161", - "issue:44387|issue:45005", "issue:44805|issue:44918", + "issue:44387|issue:45005", "issue:43828|issue:45464", "issue:44291|issue:45070", "issue:43366|issue:45464", @@ -684,284 +666,293 @@ "issue:43541|issue:44589", "issue:41093|issue:43596" ], - "prepared_review_unit_hash": "49a38f881d5c3042fd1d3e4c9b735ee4a1723d9095e8addf5cae970b44c10432", + "prepared_review_unit_hash": "b11c274fc829410e66a64e4aaff96a2ebf072f3d8c31270976e55a5a2ff455c7", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 42, - "serialized_chars": 39564, - "estimated_input_tokens": 9891, - "estimated_eval_tokens": 20038 + "serialized_chars": 39560, + "estimated_input_tokens": 9890, + "estimated_eval_tokens": 20036 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a collection of separate model- or environment-specific regressions. The clearest duplicate-looking pairs are the v5 AutoTokenizer token-ID regression reports and the Qwen video-input/template regression reports.", - "confidence": 0.79, - "canonical_issue_reason": "Issue 45920 is the best anchor: it is the broadest open report of the AutoTokenizer wrong-token-IDs regression across multiple model families, with active discussion and inbound references.", + "summary": "This cluster is a loose collection of mostly unrelated Transformers regressions and model-specific bugs. The soft pairs share superficial similarity, but they do not look like the same concrete underlying issue or change, so none should be merged.", + "confidence": 0.62, + "canonical_issue_reason": "issue:45020 is the broadest umbrella here: it describes a recent-version regression affecting remote-code models, which is the closest high-level match to the cluster\u2019s recurring compatibility/theme issues.", "canonical_pr_reason": null, - "best_issue_reason": "Same as canonical: it is the most general, high-signal issue in the tokenizer-regression subcluster and is likely the right long-term tracking issue.", + "best_issue_reason": "issue:45020 is the best single representative issue because it is broad, version-regression oriented, and open-ended enough to subsume multiple related compatibility reports without overfitting to one model.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Different models and symptoms; both are loading/forward issues, but not the same bug." + "reason": "Different failures: processor handling for Voxtral vs Gemma4 PLE device-map mismatch." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Unrelated failures: Liger cross-entropy call vs Qwen video StopIteration." + "reason": "Different subsystems and symptoms: Liger Kernel cross-entropy routing vs Qwen3.5 video StopIteration." }, { "left": "issue:43975", "right": "issue:46015", "accept": false, - "reason": "Detokenization bug and RAG docs issue are unrelated." + "reason": "Different bugs: detokenization regression for DeepSeek coder vs outdated RAG examples/docs." }, { "left": "issue:45812", "right": "issue:45920", - "accept": true, - "reason": "Both report the same v5 AutoTokenizer regression producing wrong token IDs across multiple model families." + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and likely different code paths." }, { "left": "issue:44863", "right": "issue:46015", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to outdated RAG examples." + "reason": "NemotronH checkpoint loading failure is unrelated to documentation/example updates." }, { "left": "issue:45020", "right": "issue:46304", "accept": false, - "reason": "Remote_code breakage and USE_DISTRIBUTED=0 support are different incompatibility classes." + "reason": "Broad similarity around version breakage, but one is remote_code model support and the other is a USE_DISTRIBUTED=0 PyTorch compatibility issue." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Different model-specific loading problems; no clear shared code path." + "reason": "Corrupted checkpoint / model artifact issue vs loader implementation failure for a different architecture." }, { "left": "issue:44292", "right": "issue:46015", "accept": false, - "reason": "Qwen NVFP4 runtime error is unrelated to RAG documentation." + "reason": "Model loading/runtime error versus docs/example maintenance; no shared concrete code path." }, { "left": "issue:43872", "right": "issue:46304", "accept": false, - "reason": "bitsandbytes constructor incompatibility is not the same as the distributed-disabled PyTorch issue." + "reason": "bitsandbytes Int8Params signature breakage is unrelated to PyTorch distributed support changes." }, { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding_window, but the affected models and failure modes differ." + "reason": "Both mention sliding-window-related config issues, but they involve different models and distinct integration failures." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "GLM-4.7 loading failure and corrupted Ovis2 checkpoint are distinct issues." + "reason": "Unit-test model loading regression for GLM-4.7-Flash is unrelated to a corrupted Ovis2 checkpoint." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Both are index/shape errors, but the symptoms and contexts are different enough that they do not look like one bug." + "reason": "Both are IndexErrors with zero-sized tensors, but they occur in different Bert/deepspeed scenarios and are not the same bug." }, { "left": "issue:43792", "right": "issue:45901", "accept": false, - "reason": "Whisper loading failure and table QA crash are unrelated." + "reason": "Whisper model loading failure is unrelated to table-question-answering task crashes." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch version incompatibility and pydantic PretrainedConfig regression are separate problems." + "reason": "Torch version incompatibility and pydantic PretrainedConfig breakage are separate compatibility regressions." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "Zero-3 Bert loading error and torch/transformers version incompatibility are different issues." + "reason": "Both involve runtime/compatibility issues, but one is DeepSpeed ZeRO-3 with Bert and the other is torch 2.4.1 vs transformers 5.8.0." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Detokenization regression and table QA crash are unrelated." + "reason": "Different failure domains: model detokenization regression versus QA pipeline crash." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "No shared underlying bug; one is model loading, the other is config schema handling." + "reason": "Whisper loading failure and pydantic config regression are unrelated code paths." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both involve Qwen3.5 chat paths, but the exact failures and code paths are not clearly the same." + "reason": "Different Qwen3.5 problems: chat template crash versus streaming inference API failure." }, { "left": "issue:44292", "right": "issue:45901", "accept": false, - "reason": "Unrelated model/runtime error versus task crash." + "reason": "Model loading error and table QA crash do not share a concrete underlying bug." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Gemma3/vLLM config issue and Gemma4 device mismatch are different regressions." + "reason": "Different models and failure modes: Gemma3 config attribute error vs Gemma4 device placement bug." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Tied lm_head bug and checkpoint corruption are unrelated." + "reason": "Tied-weight bug in Mistral3 is unrelated to a corrupted Ovis2 checkpoint." }, { "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Chat streaming failure and MPS histogram Int error are different failures." + "reason": "Streaming chat/completions failure is unrelated to MPS histogram_int support in moe models." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Both are MoE-related, but the ops and failure modes are unrelated." + "reason": "Torch dynamo tracing grouped_mm error is a different code path from the MPS Int histogram failure." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Grouped_mm tracing error and autocast dtype mismatch are not the same bug." + "reason": "Different precision/runtime issues: dynamo tracing grouped_mm vs autocast dtype mismatch." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor loading failure vs compile-time template-node error; unrelated." + "reason": "Processor/model loading failure for Voxtral is unrelated to compilation errors for non-template nodes." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin and Gemma3 sliding_window_pattern are unrelated." + "reason": "ImportError for GenerationMixin and Gemma3 sliding_window_pattern are different API regressions." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Torch version incompatibility and Gemma4 device mismatch are different problems." + "reason": "One is a torch/transformers compatibility issue; the other is a Gemma4 forward device-map mismatch." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both are zero-3-related index errors, but they appear to be separate model-specific failures." + "reason": "Both are IndexErrors, but they involve different models and different zero-length tensor scenarios." }, { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "PaddleOCR-VL load failure and GGUF gpt-oss support are unrelated." + "reason": "PaddleOCR-VL loading failure and GGUF gpt-oss support are separate model-format issues." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig and PretrainedConfig pydantic regression are distinct config issues." + "reason": "Missing pad_token_idx in StableLmConfig is not the same as the pydantic PretrainedConfig regression." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "MoE tracing error and GPT-OSS TP issue do not share the same underlying bug." + "reason": "Torch dynamo grouped_mm tracing error is unrelated to GPT-OSS MoE tensor-parallel behavior." }, { - "left": "issue:44387", - "right": "issue:45005", + "left": "issue:44805", + "right": "issue:44918", "accept": false, - "reason": "Int4 OOM and tied-weights translation regression are unrelated." + "reason": "Both mention shape/index errors, but they arise from different models and workflows." }, { - "left": "issue:44805", - "right": "issue:44918", + "left": "issue:44387", + "right": "issue:45005", "accept": false, - "reason": "Both mention index/shape problems, but one is a mask mismatch and the other is an SFT unpacking failure." + "reason": "Int4 quantization OOM is a different problem from tied-weights translation-model regressions." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Autocast dtype mismatch and Qwen3.5 streaming chat failure are different issues." + "reason": "Autocast dtype mismatch and streaming inference API failure are unrelated." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Unexpected _is_hf_initialized argument and PretrainedConfig field breakage are different regression surfaces." + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different issue than the pydantic config regression." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GGUF model architecture support and Qwen3.5 streaming chat failure are unrelated." + "reason": "GGUF gpt-oss support is unrelated to Qwen3.5 streaming chat/completions failures." }, { "left": "issue:43716", "right": "issue:46294", "accept": false, - "reason": "Both are multimodal issues, but the model families and concrete failures differ." + "reason": "Different multimodal bugs: image preprocessor dtype mismatch vs video chat-template feature/token mismatch." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and pydantic PretrainedConfig breakage are distinct regressions." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Both are version regressions, but one targets remote_code models and the other targets PyTorch/USE_DISTRIBUTED compatibility." }, { "left": "issue:44479", "right": "issue:46294", - "accept": true, - "reason": "Both describe the same Qwen video-input/template regression: mismatched video features versus video tokens in Qwen3.5/Qwen VL paths." + "accept": false, + "reason": "Both involve video input on Qwen variants, but one is a broad v5.3.0 regression and the other is a specific apply_chat_template feature/token mismatch." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Grouped_mm tracing and missing Float8 storage type are unrelated runtime issues." + "reason": "Torch dynamo grouped_mm tracing error is unrelated to missing Float8 storage type support." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are index errors, but there is no clear evidence they are the same underlying bug." + "reason": "Both are zero-size IndexErrors, but they occur in different models and initialization flows." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The canonical choice of 45920 is well supported by its broader title and inbound references, and the accepted duplicate pairings (45812\u219445920, 44479\u219446294) look reasonable. The other soft-edge rejections are cautious rather than overstated." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -970,13 +961,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 3, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36331", "issue:38175", @@ -1061,20 +1052,20 @@ "issue:44910|issue:45859", "issue:42947|issue:44387" ], - "prepared_review_unit_hash": "027cc0ce9caf5e6e210365c3aea95e7c2ce8ec45a1aa04c5b4b58c7a011a738c", + "prepared_review_unit_hash": "a2b79151a67fbadd21e8558fc30c59b7cd3bc9729d6cbbe78fc3703657801113", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37144, + "serialized_chars": 37142, "estimated_input_tokens": 9286, "estimated_eval_tokens": 18828 }, @@ -1083,210 +1074,204 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of unrelated issue reports. The only clear duplicate subcluster is the v5 non-persistent-buffer regression around issues 43644, 43950, and 44534; the rest do not look like the same underlying bug/change.", - "confidence": 0.86, - "canonical_issue_reason": "43950 is the best anchor for the only clearly duplicated bug cluster: it directly describes the v5 non-persistent-buffer corruption/regression and is the most general formulation among the matching reports.", + "summary": "Most items are unrelated bug reports. The only clear duplicate cluster is the Transformers 5.x non-persistent buffer regression: issues 43644, 43950, and 44534 describe the same underlying `register_buffer(persistent=False)` corruption/junk-fill problem.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 43950 is the most explicit root-cause report for the non-persistent buffer regression (`from_pretrained()` corrupts `register_buffer(persistent=False)` buffers) and subsumes the related reports in 43644 and 44534.", "canonical_pr_reason": null, - "best_issue_reason": "43950 is the strongest overall issue representative because it is the clearest, broadest statement of the only evident duplicate-worthy problem in this set.", + "best_issue_reason": "43950 is the best global issue candidate because it is the clearest, most specific statement of the shared bug and is central to the only accepted duplicate cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43054", "right": "issue:43994", "accept": false, - "reason": "Both involve SigLIP2 output quality, but one is a text-embedding regression complaint and the other is a nonsensical AutoModel/pipeline result; not enough evidence of the same bug." + "reason": "Both mention SigLIP2, but one is about degraded text embeddings while the other is about nonsensical AutoModel/pipeline outputs; related area, not clearly the same bug." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Different code paths: multimodal config unwrapping vs rotary-embedding materialization/uninitialized memory." + "reason": "Different failures: multimodal `from_config` not unwrapping `text_config` versus `inv_freq` reading uninitialized memory after `to_empty(cuda)` materialization." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "Unrelated: TensorBoard/TensorFlow backend detection vs a torch/transformers version incompatibility report." + "reason": "One is a missing TensorFlow backend / tensorboard-only environment issue; the other is a torch-transformers version incompatibility." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Different models and failures: Mistral-3 image dtype mismatch vs Qwen3.5 embedding unpacking in TRL SFT." + "reason": "Different code paths: image preprocessor/model dtype mismatch versus TRL SFT embedding unpacking failure." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "FSDP weight-shape error and Qwen3.5/TRl embedding unpacking are unrelated." + "reason": "FSDP `'weight' must be 2-D` and Qwen3.5 embedding unpacking are distinct training/loading bugs." }, { "left": "issue:45632", "right": "issue:45698", "accept": false, - "reason": "Both involve custom-code loading, but one is a leaf-directory cache collision and the other is wrong module selection after save/load; not clearly the same bug." + "reason": "Both involve custom model loading, but one is a cache-path collision and the other loads the wrong module after save/load; not the same defect." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "One is a Jupyter/custom-model initialization regression; the other is flash-attn2 fallback gating." + "reason": "Notebook custom-model initialization failure and flash-attn fallback gating are unrelated." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Both mention tied weights, but they concern different model families and different failure modes." + "reason": "Both concern tied weights, but they affect different models and different tying paths; too broad to treat as one bug." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "Completely different model reports with no shared failure mechanism." + "reason": "High perplexity on GPT-OSS and a generic GLM5 issue are not the same underlying problem." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache linear_attention crash is unrelated to tied-weight issues." + "reason": "PagedAttentionCache group-type crash is unrelated to tied-weight handling." }, { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "FP8 quantization failure vs flash-attn2 fallback gating are separate problems." + "reason": "FineGrainedFP8Config failure and flash-attn fallback blocking are separate quantization/runtime issues." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to tied-weight handling." + "reason": "Quantization offloading behavior and tied-weights handling are different problems." }, { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer discussion and a removed docs command are unrelated." + "reason": "DSA indexer ReLU discussion and a docs typo are unrelated." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to tied-weight translation-model issues." + "reason": "NemotronH checkpoint loading failure is not the same as translation-model tied-weight issues." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Qwen3.5 embedding unpacking and GraniteMoEHybrid invalid method calls are different failures." + "reason": "Qwen3.5 SFT embedding unpacking and GraniteMoEHybrid invalid method calls are unrelated." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategies is not the same as stale docs mentioning the removed run command." + "reason": "Cache-strategy typo and removed run-command docs are separate documentation issues." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "Different model-specific runtime issues with no shared code-path evidence." + "reason": "Detokenization regression and Qwen-3 NVFP4 runtime error are different bugs." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Different model/runtime failures." + "reason": "No shared underlying code-path problem is evident." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Same underlying v5 regression: non-persistent buffers are mishandled/corrupted during loading/initialization." - }, - { - "left": "issue:39692", - "right": "issue:43054", - "accept": false, - "reason": "Docs/example errors for SigLIP2 are not the same as a broader text-embedding quality regression." - }, - { - "left": "issue:43644", - "right": "issue:43950", - "accept": true, - "reason": "Both describe the same non-persistent-buffer junk/corruption regression in Transformers 5.x." - }, - { - "left": "issue:43828", - "right": "issue:44928", - "accept": false, - "reason": "Different model-specific dtype/NaN issues with no shared code path." - }, - { - "left": "issue:36331", - "right": "issue:41762", - "accept": false, - "reason": "Trainer API keyword mismatch and DeepSpeed ZeRO-3 loading error are unrelated." - }, - { - "left": "issue:43950", - "right": "issue:45902", - "accept": false, - "reason": "Both mention buffer initialization, but one is a global from_pretrained regression and the other is a specific Qwen3_5Moe rotary-buffer materialization bug." + "reason": "Both report the same Transformers 5.x regression where non-persistent buffers are mishandled/corrupted during loading." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Different quantization/storage errors." + "reason": "Different low-level bitsandbytes/storage errors with different symptoms and causes." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Checkpoint corruption and loading noise are not the same bug." + "reason": "Checkpoint corruption and generic loading noise are not the same bug." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Both are SigLIP2-related, but one reports zero probabilities and the other lower text embeddings; not enough evidence they share the same underlying defect." + "reason": "Both are SigLIP2-related, but one is a model output-quality complaint and the other is a text-embedding degradation issue; insufficient evidence they are the same defect." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Tokenizer error messaging and missing tied-weights metadata are unrelated." + "reason": "AutoTokenizer loading error for Voxtral and missing `all_tied_weights_keys` on MolmoForCausalLM are unrelated." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality is unrelated to version-dependent tokenization changes." + "reason": "Model-quality regression and tokenization-version change are different problems." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states bug is unrelated to Qwen3_5Moe buffer materialization." + "reason": "Gemma4 FSDP2 shared-state rebuild bug and Qwen3_5Moe rotary embedding uninitialized memory are distinct." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Both touch Qwen3.5, but one is flash-attn sequence handling and the other is CPU-offload compatibility in rotary embedding; different bugs." + "reason": "Flash-Attention illegal memory access from 3D position_ids is not the same as CPU offload incompatibility in rotary embedding." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Gradient checkpointing/LoRA behavior is unrelated to int4 quantization memory growth." + "reason": "Gradient checkpointing ineffective with LoRA and increased reserved memory under int4 quantization are different regressions." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same Transformers 5.x non-persistent buffer corruption/junk-fill regression, described from different angles." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch and RLHF NaN explosion are related only at a very high level; the concrete bugs differ." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Unexpected `num_items_in_batch` argument and DeepSpeed ZeRO-3 loading index error are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "Both involve initialization/materialization, but one is a non-persistent buffer regression and the other is a Qwen rotary-embedding uninitialized-memory bug." } ] }, "evaluator_result": { "accept": true, - "feedback": "The analyst summary is grounded in the packet and stays conservative. The only clearly supported duplicate cluster is the Transformers v5 non-persistent-buffer regression around 43644, 43950, and 44534, and the accepted/rejected soft pairs are mostly well-justified by the issue titles and descriptions. No obvious overstatement of evidence." + "feedback": "Accepted. The summary is grounded in the packet: the only clearly supported duplicate cluster is 43644/43950/44534 around the Transformers v5 non-persistent buffer corruption regression. The soft-edge rejections are conservative and do not overclaim equivalence from broad thematic similarity alone." }, "evaluator_used": true, "retried": false, @@ -1299,16 +1284,14 @@ "component_index": 1, "component_count": 18, "review_unit_index": 4, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ - "issue:36331", - "issue:41093", "issue:41553", "issue:41762", "issue:42491", @@ -1341,15 +1324,16 @@ "issue:44488", "issue:44509", "issue:44661", + "issue:44928", "issue:44960", "issue:44991", "issue:45020", "issue:45081", - "issue:45305", "issue:45313", "issue:45356", "issue:45399", "issue:45520", + "issue:45588", "issue:45685", "issue:45715", "issue:45823", @@ -1386,139 +1370,138 @@ "issue:42915|issue:43872", "issue:42947|issue:45923", "issue:43940|issue:45313", - "issue:36331|issue:41093", - "issue:43257|issue:45305" + "issue:44928|issue:45588" ], - "prepared_review_unit_hash": "89e586966030bfcd234d6dfb28cc11c1bab8192d873ef52190fc164d8ab3ee1e", + "prepared_review_unit_hash": "e89a74dcbcb99a2136ebbd45c0180585026579f6892174cafbf35e6ce12f9245", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37243, - "estimated_input_tokens": 9311, - "estimated_eval_tokens": 18878 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36355, + "estimated_input_tokens": 9089, + "estimated_eval_tokens": 18434 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a mix of unrelated model-loading, tokenizer, and training regressions. Only one soft pair looks like a true duplicate: the `_is_hf_initialized` / `init_empty_weights` TypeError reports.", - "confidence": 0.82, - "canonical_issue_reason": "issue:44291 is the best canonical issue because it states the concrete regression (`init_empty_weights` / unexpected `_is_hf_initialized` argument) and cleanly subsumes the near-identical TypeError report in 43872.", + "summary": "This cluster is mostly a loose set of transformer loading/tokenizer regression reports, not a single duplicate set. The strongest common thread is recent v5 loading regressions, but most pairs are model-specific and should stay separate. I only accepted the clearest same-bug pairs.", + "confidence": 0.43, + "canonical_issue_reason": "Issue 45020 is the best umbrella representative of the cluster\u2019s main theme: recent transformers versions breaking model loading, especially around remote_code and related load-time regressions.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44291 is the strongest representative issue in this set: it is specific, actionable, and captures the shared root cause more clearly than the symptom-focused duplicate report.", + "best_issue_reason": "Issue 45020 is the most general and reusable issue in the set, so it is the best overall issue representative for triage among these reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44403", "right": "issue:44451", "accept": false, - "reason": "Generic loading noise vs a specific model-loading failure; same broad area, not the same bug." + "reason": "Both involve loading behavior, but one is a generic noise/UX complaint and the other is a specific model load failure; not the same bug." }, { "left": "issue:41553", "right": "issue:43881", "accept": false, - "reason": "Different models and different failure modes; no shared concrete code path is evident." + "reason": "Different models and different failure modes; the titles do not point to the same underlying loader bug." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Tokenizer detokenization regression vs an import error in import_utils; unrelated defects." + "reason": "Tokenizer detokenization behavior and a flash_attn import KeyError are unrelated issues." }, { "left": "issue:43054", "right": "issue:43493", - "accept": false, - "reason": "Both involve SigLIP2, but the titles describe different symptoms without enough evidence of one exact shared bug." + "accept": true, + "reason": "Both point to the same SigLIP2 HF-vs-reference implementation discrepancy, with worse text embeddings as a symptom of that mismatch." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "Both mention memory, but one is gradient checkpointing behavior and the other is MoE training memory usage; not the same issue." + "reason": "One is about gradient checkpointing with PEFT LoRA; the other is about Qwen3 MoE memory usage. Different bugs." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both are model-loading related, but one is a generic warning/noise report and the other is a specific model load failure." + "reason": "Generic loading noise vs a specific model that fails to load; no evidence they are the same defect." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Remote-code config field loss and broader remote_code breakage are related, but not the same concrete bug." + "reason": "The first is a specific missing-fields bug in AutoConfig with trust_remote_code; the second is a broad umbrella about remote_code breakages, not the same concrete issue." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Different models, different loading paths, different errors." + "reason": "Gemma3 ZeRO-3 index error and Qwen3 MoE FP8 failure are distinct model-specific problems." }, { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "MPS int histogram failure and device_map forward mismatch are separate hardware/runtime bugs." + "reason": "MPS histogram-on-int error and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "LoRA compatibility across versions and a tied-embeddings warning are not the same bug." + "reason": "A broken LoRA checkpoint migration issue is not the same as a tie_word_embeddings warning during fine-tuning." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading failure and flash-attn fallback gating are unrelated." + "reason": "Tokenizer loading failure and flash-attn fallback gating are different code paths." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Import error for a missing class and a bitsandbytes constructor incompatibility are different issues." + "reason": "ImportError for a missing model class and a bitsandbytes Int8Params constructor mismatch are unrelated." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "Different model families and different loading failures." + "reason": "A model loading failure and a missing all_tied_weights_keys attribute are not the same bug." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Remote-code regressions and a Gemma4 device mismatch are unrelated." + "reason": "Remote_code loading regressions and a Gemma4 device_map forward mismatch are unrelated." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Model-registration logic failure and remote_code loading breakage are distinct bugs." + "reason": "A tokenizer-mapping edge case in add-new-model-like is different from the broader remote_code loading regression." }, { "left": "issue:45715", "right": "issue:46315", "accept": false, - "reason": "Both are tokenizer performance regressions, but they hit different APIs and likely different code paths." + "reason": "Both are tokenizer performance regressions, but they affect different directions and likely different loops; not enough to merge." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Dtype mismatch under autocast is not the same as a device placement mismatch." + "reason": "Autocast dtype mismatch and PLE device mismatch are different runtime problems." }, { "left": "issue:45081", @@ -1530,61 +1513,79 @@ "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Different models and different failure classes." + "reason": "Different models and different failure categories; no shared underlying bug is evident." }, { - "left": "issue:44220", - "right": "issue:43792", + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "A broad remote_code regression and a tokenizer codec/regression issue are not the same defect." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Model loading KeyError and flash-attn fallback checks are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "A missing lm_head tying bug and a non-persistent buffer corruption regression are different code-path problems." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": false, + "reason": "These are related docs-only pipeline references, but they are different documentation cleanup reports rather than one duplicate bug." + }, + { + "left": "issue:43792", + "right": "issue:44220", "accept": false, - "reason": "The Whisper failure may be related, but the titles do not establish the same concrete `_torch_extract_fbank_features()` bug with enough certainty." + "reason": "Whisper model runtime failure and a fbank feature extraction issue are not the same bug." }, { "left": "issue:43872", "right": "issue:44291", - "accept": true, - "reason": "These describe the same `_is_hf_initialized` / `init_empty_weights` TypeError regression, with 44291 spelling out the root cause more clearly." + "accept": false, + "reason": "Both mention _is_hf_initialized, but one is a bitsandbytes compatibility issue and the other is an init_empty_weights type error; close in theme but not the same concrete defect." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight-conversion loading issue vs a corrupted Ovis2 checkpoint; different problems." + "reason": "Qwen3 MoE weight conversion/load behavior and an Ovis2 corrupted checkpoint are unrelated." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "FineGrainedFP8Config failure and the bitsandbytes `_is_hf_initialized` incompatibility are separate bugs." + "reason": "Qwen3 MoE FP8 failure and bitsandbytes _is_hf_initialized incompatibility are different bugs." }, { "left": "issue:42947", "right": "issue:45923", "accept": false, - "reason": "Gradient checkpointing effectiveness and a missing `supports_gradient_checkpointing` flag are not the same issue." + "reason": "Gradient checkpointing with LoRA and a missing supports_gradient_checkpointing flag are different issues even if both mention checkpointing." }, { "left": "issue:43940", "right": "issue:45313", - "accept": false, - "reason": "Both are DeepSpeed ZeRO-3 loading problems, but they involve different models and distinct missing-weight symptoms." + "accept": true, + "reason": "Both describe the same class of Qwen3-family DeepSpeed ZeRO-3 weight-loading failure, with parameters ending up missing during load; the model variant differs but the underlying loader problem is the same." }, { - "left": "issue:36331", - "right": "issue:41093", - "accept": false, - "reason": "Unexpected trainer kwarg vs tensor mask shape mismatch; unrelated errors." - }, - { - "left": "issue:43257", - "right": "issue:45305", + "left": "issue:44928", + "right": "issue:45588", "accept": false, - "reason": "Weight conversion/loading under accelerate+deepspeed is not the same as gradient averaging with GAS." + "reason": "RLHF gradient explosion from Qwen3.5 position_ids is unrelated to the flash_attention sinkless-model crash." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative on the soft edges. The single accepted duplicate pair (`issue:43872` / `issue:44291`) is well supported by the titles, and the other rejects do not overclaim shared root cause." + "feedback": "The summary is grounded in the packet and stays conservative about duplicate links. The umbrella choice for issue 45020 is plausible as a broad representative of the remote_code / loading-regression theme, and the two accepted soft pairs are the clearest same-bug candidates. No obvious overstatement of evidence." }, "evaluator_used": true, "retried": false, @@ -1597,23 +1598,24 @@ "component_index": 1, "component_count": 18, "review_unit_index": 5, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:24643", "issue:30064", "issue:36010", + "issue:36331", "issue:38175", - "issue:39692", "issue:41093", "issue:41553", "issue:42617", "issue:42915", + "issue:43257", "issue:43317", "issue:43366", "issue:43531", @@ -1642,12 +1644,11 @@ "issue:44877", "issue:44910", "issue:44918", - "issue:44928", "issue:44991", "issue:45030", + "issue:45305", "issue:45325", "issue:45584", - "issue:45588", "issue:45663", "issue:45685", "issue:45823", @@ -1655,8 +1656,9 @@ "issue:45902" ], "soft_pairs": [ + "issue:36331|issue:41093", "issue:43854|issue:44863", - "issue:44928|issue:45588", + "issue:43257|issue:45305", "issue:41553|issue:44991", "issue:41093|issue:44805", "issue:44479|issue:44560", @@ -1669,8 +1671,8 @@ "issue:43366|issue:43531", "issue:43950|issue:45834", "issue:43550|issue:44910", - "issue:43645|issue:43646", "issue:44560|issue:45685", + "issue:43645|issue:43646", "issue:43366|issue:44589", "issue:42915|issue:43957", "issue:44560|issue:44918", @@ -1686,241 +1688,240 @@ "issue:43638|issue:44661", "issue:43596|issue:44661", "issue:44661|issue:44805", - "issue:43317|issue:44756", - "issue:38175|issue:39692" + "issue:43317|issue:44756" ], - "prepared_review_unit_hash": "50bdc192655993179fdbf4f220d0d178e994727b8e543cfd82b66d28c1840a3e", + "prepared_review_unit_hash": "5d3eb8c8d5d28d45656a8c779ab2534bbc3222482d41305e199e48d7f757a820", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37723, - "estimated_input_tokens": 9431, - "estimated_eval_tokens": 19118 + "serialized_chars": 37670, + "estimated_input_tokens": 9418, + "estimated_eval_tokens": 19092 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose set of unrelated Transformers bug reports; only a couple of soft pairs look like true duplicates. The clearest duplicate is the Transformers 5.0 custom model initialization regression, and there is also a likely duplicate around the same generic mask-shape IndexError and a probable SigLIP2 output regression pair.", - "confidence": 0.52, - "canonical_issue_reason": "Issue 43646 is the broadest, most representative statement of the clearest duplicate pair (43645/43646) and reads like the main regression; the notebook-specific version is a narrower variant.", + "summary": "Mostly heterogeneous bug reports; only two soft duplicate pairs stand out: the custom model-initialization regressions and the repeated mask-shape IndexError. Everything else looks like separate model- or subsystem-specific issues.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 43646 is the cleanest and broadest statement of the shared custom-model initialization regression, without the notebook-specific framing from 43645.", "canonical_pr_reason": null, - "best_issue_reason": "43646 is the best single issue to anchor the cluster because it states the underlying regression more generally than the notebook-specific report and is the cleanest duplicate-style representative among the items.", + "best_issue_reason": "43646 is the best representative issue in the set because it states the underlying regression most generally and is the most suitable duplicate target among the accepted overlaps.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Different failures and likely different code paths: trainer API keyword mismatch vs a tensor mask-shape IndexError." + }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "Both are model-loading failures, but they concern different architectures and failure modes; not the same concrete bug." + "reason": "Different problems: one is a model-loading test failure for GLM-4.7, the other is a NemotronH checkpoint-loading bug." }, { - "left": "issue:44928", - "right": "issue:45588", + "left": "issue:43257", + "right": "issue:45305", "accept": false, - "reason": "Completely different code paths: Qwen3.5 RLHF/position_ids vs Flash Attention sink handling." + "reason": "Both involve Qwen/DeepSpeed, but the concrete bugs differ: weight conversion vs gradient averaging with GAS." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading complaints, but they target different models and different symptoms." + "reason": "Both are tokenizer-loading related, but they target different models and different failure modes; not enough evidence of the same bug." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same generic mask-shape IndexError with the same off-by-one style mismatch; very likely the same underlying bug." + "reason": "Same underlying mask-shape mismatch IndexError; 44805 looks like a later/generalized report of the same runtime bug." }, { "left": "issue:44479", "right": "issue:44560", "accept": false, - "reason": "Both involve Qwen video-related regressions, but the reported failures are different and not enough to treat as one bug." + "reason": "Both touch Qwen video inputs, but one is a broad regression report and the other is a specific StopIteration symptom; not clearly the same code-path bug." }, { "left": "issue:44530", "right": "issue:44863", "accept": false, - "reason": "PagedAttentionCache linear_attention crash vs checkpoint loading failure; unrelated." + "reason": "Different subsystems and symptoms: PagedAttentionCache/group-type handling vs NemotronH checkpoint loading." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Different model loading failures with no shared concrete code path." + "reason": "Both are load failures, but the titles point to different models and different loader issues." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "Training with DeepSpeed and void segmentation map processing are unrelated." + "reason": "Unrelated domains: DeepSpeed training RuntimeError vs image-processor segmentation-map handling." }, { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Both touch rotary/position-related internals, but one is a rope-index scaling bug and the other is uninitialized-memory materialization; different bugs." + "reason": "Different bugs in different components: Qwen2.5-VL rope-index scaling vs Qwen3.5-MoE rotary embedding materialization." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF/gpt-oss support is unrelated to Phi MoE autocast dtype mismatch." + "reason": "GGUF/gpt-oss support is unrelated to the Phi-tiny-MoE autocast dtype mismatch." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Same model family (Gemma4), but training/FSDP2 KeyError and device-map forward mismatch are different failures." + "reason": "Both are Gemma4-related, but one is an FSDP2 shared-kv state bug and the other is a device-map mismatch during forward." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "Different Qwen/GGUF issues with no shared concrete change or code path." + "reason": "One is GGUF architecture support; the other is a Qwen3-MoE sliding_window behavior bug." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "A from_pretrained buffer regression is unrelated to long OCR input indexing." + "reason": "Non-persistent buffer corruption and Kosmos2.5 OCR index errors are different regressions." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Different models and different failures: torch.compile SDPA vs Flash Attention position_ids crash." - }, - { - "left": "issue:43645", - "right": "issue:43646", - "accept": true, - "reason": "Clear duplicate pair: both report Transformers 5.0 breaking custom model initialization; 43645 is just the notebook-specific framing." + "reason": "Different model families and failure modes: Bamba torch.compile/SDPA vs Qwen3.5 flash-attention position_ids handling." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Video input StopIteration and MPS histogram on Int are unrelated." + "reason": "Video-embedding StopIteration and MPS histogram-not-implemented are unrelated bugs." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Same underlying custom model initialization regression; 43646 is just the broader, cleaner wording." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "GGUF architecture support and Float8 storage lookup are unrelated." + "reason": "GGUF architecture support and missing Float8 storage are unrelated issues." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Different failures: Qwen3Moe FP8 config vs meta-device loading regression." + "reason": "Both are load/config problems around Qwen-like models, but the concrete bugs differ: FineGrainedFP8Config vs meta-device loading." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Both mention Qwen3.5/video-ish workflows, but one is a video embedding StopIteration and the other is an SFT unpacking failure." + "reason": "Both mention Qwen3.5 video/input behavior, but one is a video StopIteration regression and the other is an embedding unpacking failure; insufficient evidence of one bug." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "Importing a missing class and meta-device loading are different problems." + "reason": "Importing a missing Qwen2.5-VL class is not the same as meta-device loading breakage." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3d_parallel.py runtime failure is unrelated to GGUF gpt-oss support." + "reason": "3d_parallel.py execution failure is unrelated to GGUF gpt-oss support." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import error and Qwen3Moe FP8 config failure are unrelated." + "reason": "ImportError for GenerationMixin and Qwen3Moe FineGrainedFP8Config failures are different regressions." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer mapping logic and Gemma4 device-mismatch forward failure are unrelated." + "reason": "Tokenizer-mapping-name failure and Gemma4 PLE device mismatch are unrelated." }, { - "left": "issue:43632", + "left": "issue:43638", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized regression and OCR long-input index error are unrelated." + "reason": "Both are IndexError reports, but they involve different models and different failure contexts." }, { "left": "issue:38175", "right": "issue:43994", - "accept": true, - "reason": "Same SigLIP2 base model with incorrect/wrong outputs; likely the same regression in model/processor handling." + "accept": false, + "reason": "Same model family, but the reports are too different\u2014zero probabilities vs nonsensical AutoModel/pipeline results\u2014to treat as the same bug." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "AudioFlamingo3 track leakage and Whisper empty-transcription failure are unrelated." + "reason": "AudioFlamingo3 batched-inference leakage and Whisper empty-transcription generation are unrelated." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different error classes and code paths; video-input StopIteration is not the same as a mask-shape IndexError." + "reason": "Both are runtime errors, but the video StopIteration and mask-shape IndexError point to different code paths." }, { "left": "issue:44877", "right": "issue:45030", "accept": false, - "reason": "Strict config loading and glm4v config validation are different config regressions." + "reason": "Strict config blocking granite_speech and tiny-random glm4v config validation are different config-loading regressions." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "DeepSpeed zero3/Bert index error and tokenizer-mapping add-new-model-like failure are unrelated." + "reason": "Both involve model init/load failures, but one is a deepspeed zero3 Bert index error and the other is a tokenizer-mapping-name issue." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Both involve initialization/loading, but the concrete failures are different and not the same bug." + "reason": "Zero-sized tensor/indexing with deepspeed zero3 is unrelated to tokenizer mapping registration." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer mapping logic vs mask-shape IndexError; unrelated." + "reason": "Tokenizer-mapping registration and mask-shape IndexError are different bugs." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "gpu+cpu offload loading failure and Strix Halo mmap OOM are different resource-loading issues." - }, - { - "left": "issue:38175", - "right": "issue:39692", - "accept": false, - "reason": "Both involve SigLIP2, but one is a wrong-output regression and the other is a documentation example with model/processor mismatch and quantization failure; not the same bug." + "reason": "Device-map offload loading and mmap OOM on Strix Halo are different memory-management issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The anchor choice is grounded in the packet, and the duplicate/near-duplicate calls are conservative overall. The 43645/43646 pair is clearly the strongest match, and the 41093/44805 and 38175/43994 calls are reasonably cautious given the shared error/model wording. I don\u2019t see an overstatement that would warrant rejection." + "feedback": "The summary is grounded in the packet and stays conservative. The two accepted pairs are well-supported by the titles/body-level signals, and the rejections do not overclaim duplicate status for clearly different failures. No soft-edge verdict appears overstated." }, "evaluator_used": true, "retried": false, @@ -1933,15 +1934,16 @@ "component_index": 1, "component_count": 18, "review_unit_index": 6, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36010", + "issue:38175", "issue:39404", "issue:39692", "issue:41720", @@ -1987,10 +1989,10 @@ "issue:45663", "issue:45704", "issue:45759", - "issue:45812", - "issue:45859" + "issue:45812" ], "soft_pairs": [ + "issue:38175|issue:39692", "issue:42491|issue:43720", "issue:44960|issue:44977", "issue:41720|issue:42915", @@ -2001,8 +2003,8 @@ "issue:43644|issue:44534", "issue:42915|issue:44756", "issue:39692|issue:43994", - "issue:45488|issue:45812", "issue:43854|issue:43931", + "issue:45488|issue:45812", "issue:43257|issue:43854", "issue:43856|issue:43873", "issue:42491|issue:43931", @@ -2020,234 +2022,232 @@ "issue:42947|issue:45704", "issue:43425|issue:43957", "issue:44402|issue:44488", - "issue:45663|issue:45759", - "issue:45663|issue:45859", - "issue:43873|issue:44387" + "issue:45663|issue:45759" ], - "prepared_review_unit_hash": "aa4b0e9d112cc083e61c6254ed7e5762155bd95ad979e4ae50c92124658384d8", + "prepared_review_unit_hash": "eae3b60588c8a12bba190c01403c894d9dcb7edd56547b211f292d78f9af5fac", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37349, - "estimated_input_tokens": 9338, - "estimated_eval_tokens": 18932 + "soft_pair_count": 31, + "serialized_chars": 37040, + "estimated_input_tokens": 9260, + "estimated_eval_tokens": 18776 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a heterogeneous collection of unrelated Transformers issues, with one clear duplicate pair around the v5 non-persistent buffer regression. Most other soft edges are only loosely similar by subsystem or model family, not the same concrete bug.", - "confidence": 0.82, - "canonical_issue_reason": "issue:43644 is the strongest canonical representative because it has the clearest near-verbatim duplicate in issue:44534 and directly names the underlying Transformers v5 buffer initialization regression.", + "summary": "The cluster is a mixed bag of model-loading, tokenizer, training, and v5-regression reports. A few issue pairs are superficially similar, but the evidence is generally too thin to call them true duplicates; I would not collapse the cluster around a broad duplicate family.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43644 is the best representative issue because it is a clear, self-contained Transformers v5 regression with a broad symptom description. It is the most general issue in the set, but the cluster overall still looks heterogeneous rather than a single duplicate chain.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43644 is the best issue candidate overall because it is the most clearly supported by a duplicate-style twin and describes the bug in the broadest, most reusable way.", + "best_issue_reason": "issue:43644 is the strongest global issue candidate because it is broad, concrete, and centrally about a v5 buffer-initialization regression. It best captures one of the recurring subthemes without overstating the whole cluster as one duplicate family.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same model family, but the problems differ: zero probabilities vs. docs/example model-processor and quantization failures." + }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Different bugs: qwen3_moe LoRA incompatibility across HF versions vs BitNet packed-weight handling during accelerate loading." + "reason": "Different code paths and failure modes: Qwen3 MoE LoRA compatibility vs. BitNet packed-weight loading." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "Different models and failure modes: GLM5 vs Qwen3.5 flash-attention generation behavior." + "reason": "Different models and symptoms: GLM5 vs. Qwen3.5 flash-attention generation." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Different code paths: device-mapping cuda assert on Qwen3 vs FineGrainedFP8Config failure on Qwen3Moe." + "reason": "Both are Qwen-related, but one is an auto device-mapping CUDA assert and the other is a FineGrainedFP8Config loading issue." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "Different regressions: DeepSpeed ZeRO-3 loading of language_model weights vs save_pretrained writing wrong visual encoder keys." + "reason": "Both touch Qwen3.5, but one is ZeRO-3 weight loading and the other is incorrect save_pretrained visual-encoder keys." }, { "left": "issue:44451", "right": "issue:44488", "accept": false, - "reason": "Both are load failures for different BERT models, but the titles do not indicate the same underlying cause." + "reason": "Similar wording around loading failures, but they involve different model families and no shared concrete code path is shown." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "Unrelated issues: qwen3_moe LoRA on hf4.x vs Gemma4 resize_token_embeddings propagation." + "reason": "Qwen3 MoE LoRA compatibility is unrelated to Gemma4 resize_token_embeddings propagation." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Trainer checkpoint math and optimizer argument usage are separate problems." + "reason": "Trainer resume/max_steps logic is unrelated to SGD argument handling." }, { "left": "issue:43644", "right": "issue:44534", - "accept": true, - "reason": "Near-identical regression about non-persistent buffers being filled with junk in Transformers v5." + "accept": false, + "reason": "The symptoms overlap, but the packet does not show enough evidence that these are the same non-persistent-buffer bug rather than two similar v5 regressions." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "Different failures: Qwen3Moe FP8 config vs mmap-related OOM on Strix Halo." + "reason": "Qwen3 MoE FP8 failure is unrelated to disabling mmap to avoid OOM on Strix Halo." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs/example mismatch and quantization failure while the other is bad inference output." + "reason": "Same SigLIP2 family, but one is a docs/example issue and the other is a runtime inference correctness problem." }, { - "left": "issue:45488", - "right": "issue:45812", + "left": "issue:43854", + "right": "issue:43931", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and different tokenization behaviors." + "reason": "Different models and failures: GLM-4.7-Flash test loading vs. Qwen3-VL weight-shape mismatch." }, { - "left": "issue:43854", - "right": "issue:43931", + "left": "issue:45488", + "right": "issue:45812", "accept": false, - "reason": "Different models and distinct loading errors: GLM-4.7-Flash unit-test loading vs Qwen3-VL shape mismatch." + "reason": "Both are tokenizer regressions, but they affect different tokenizer/model families with different symptoms." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different bugs: Qwen3 MoE weight conversion with accelerate/deepspeed vs GLM-4.7-Flash loading in tests." + "reason": "Qwen3 MoE accelerate/deepspeed conversion is unrelated to GLM-4.7-Flash loading." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both are memory-related, but one is Qwen3 MoE training inefficiency and the other is quantization offloading behavior." + "reason": "Related to memory/offloading broadly, but these are different regression types and not the same concrete bug." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Different model families and distinct failures: qwen3_moe LoRA portability vs Qwen3-VL weight shape mismatch." + "reason": "Qwen3 MoE LoRA compatibility is unrelated to a generic model shape-mismatch load failure." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both mention memory, but the causes differ: MoE training inefficiency vs int4 quantization reserved-memory/OOM regression." + "reason": "Different performance regressions: Qwen3 MoE training memory vs. int4 reserved-memory growth." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Related Transformer 5 regressions, but one is buffer initialization and the other is custom-model initialization in Jupyter." + "reason": "Both are Transformers v5 regressions, but one is buffer junk initialization and the other is custom-model initialization in Jupyter notebooks." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "Different issues: qwen3_moe LoRA compatibility vs resize_token_embeddings not updating output embeddings." + "reason": "Qwen3 MoE LoRA compatibility is unrelated to a resize_token_embeddings output_embeddings bug." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both are flash-attention crashes, but the concrete failure modes differ: illegal memory access from packed-sequence handling vs AttributeError on s_aux=None." + "reason": "Both mention flash attention, but the concrete faults differ: packed-sequence position_ids vs. s_aux=None on sink-less models." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Different tokenizer/loading bugs affecting different models." + "reason": "Both are loading regressions, but they affect different tokenizer/model paths and the packet does not show a shared root cause." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Different mechanics: extra_state save/load handling vs init_empty_weights argument compatibility." + "reason": "Saving/loading extra_state and init_empty_weights/_is_hf_initialized are different serialization/init issues." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Separate crashes in different serving/chat paths and different model classes." + "reason": "Qwen3.5 chat crash and Gemma4Processor missing _tokenizer are unrelated." }, { "left": "issue:45276", "right": "issue:45335", "accept": false, - "reason": "Both concern resize_token_embeddings, but the affected model structures differ and the titles do not show the same concrete bug." + "reason": "The titles are very similar, but they point to different model families and different embedding targets, so the evidence is not strong enough to merge them." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are lm_head weight-tying issues, but they affect different architectures and are not clearly the same code-path bug." + "reason": "Similar symptom around lm_head tying, but different model implementations and not clearly the same code path." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "Completely different problems: import failure for GenerationMixin vs Whisper pipeline return_language regression." + "reason": "Importing GenerationMixin and Whisper return_language pipeline behavior are unrelated." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "Different issues and model families; only superficial similarity in being model-related." + "reason": "SigLIP2 docs/model issues are unrelated to GLM5." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Unrelated regressions: LoRA gradient checkpointing behavior vs apex RMSNorm memory leak." + "reason": "Gradient checkpointing/PEFT LoRA is unrelated to T5 using apex.FusedRMSNorm." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "Torch version compatibility issue vs meta-device loading regression; different root causes." + "reason": "Torch version compatibility and torch.device('meta') loading regressions are different problems." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Token-vocab mismatch in one model vs inability to load a different model." + "reason": "Tokenizer vocab-size violation and a model loading failure are only broadly related, not the same bug." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different bugs in different model families: FSDP2 shared_kv_states rebuild vs composite-config unwrapping." - }, - { - "left": "issue:45663", - "right": "issue:45859", - "accept": false, - "reason": "Different issues: Gemma-4 FSDP2 KeyError vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + "reason": "Gemma4 FSDP2 shared_kv_states is unrelated to Qwen 3.5/3.6 text_config unwrapping." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft edge is well supported by the near-identical 43644/44534 titles, and the rejected pairs are generally justified by distinct model families or failure modes." + "accept": false, + "feedback": "The overall framing is mostly grounded, but the soft-edge judgments are not conservative enough. In particular, the analyst marked several pairs as true duplicates even though the packet labels them deterministic_accept=false, including issue:44451/issue:44488 and issue:45276/issue:45335, and also issue:43644/issue:44534. Those pairs may be similar, but the evidence in the packet is not strong enough to promote them to accept. The cluster summary also slightly overstates the duplicate/regression cohesion by calling the issue set a broad v5 regression pattern rather than a mixed bag with only a few similar pairs." }, "evaluator_used": true, - "retried": false, - "accepted_nontrivial_soft_edge": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -2256,13 +2256,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 7, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:39404", "issue:41720", @@ -2278,7 +2278,7 @@ "issue:43716", "issue:43828", "issue:43854", - "issue:43906", + "issue:43873", "issue:43957", "issue:44155", "issue:44164", @@ -2309,10 +2309,13 @@ "issue:45701", "issue:45812", "issue:45823", + "issue:45859", "issue:46050", "issue:46315" ], "soft_pairs": [ + "issue:45663|issue:45859", + "issue:43873|issue:44387", "issue:44155|issue:45823", "issue:44291|issue:44756", "issue:44292|issue:44912", @@ -2333,8 +2336,8 @@ "issue:45812|issue:46315", "issue:45292|issue:45335", "issue:43645|issue:44164", - "issue:44402|issue:44451", "issue:43828|issue:43957", + "issue:44402|issue:44451", "issue:43425|issue:43828", "issue:44589|issue:44756", "issue:43257|issue:44863", @@ -2343,187 +2346,180 @@ "issue:43611|issue:43645", "issue:43425|issue:45823", "issue:44530|issue:45084", - "issue:43425|issue:43716", - "issue:43906|issue:44530" + "issue:43425|issue:43716" ], - "prepared_review_unit_hash": "7d05dadc71879b93fe367ecddce9083489bbef16491ae3308a506628ecf41ea2", + "prepared_review_unit_hash": "c3efc77e37542580c1f7ff8a28de7b58007a499844d96b5c3343e94df1041485", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36690, - "estimated_input_tokens": 9173, - "estimated_eval_tokens": 18602 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37529, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous, with one clear duplicate family around `resize_token_embeddings` not updating model outputs/embeddings. Most other pairs are adjacent but distinct regressions in different models or subsystems.", - "confidence": 0.82, - "canonical_issue_reason": "`issue:45292` is the broadest, cleanest statement of the shared bug: `resize_token_embeddings` fails to update output embeddings. The Gemma4 and t5gemma reports are narrower model-specific manifestations of the same API regression.", + "summary": "Mostly heterogeneous issue set. The only clear duplicate chain is the `resize_token_embeddings` regression cluster, where the generic report is the best representative; most other soft pairs share a subsystem label but not the same underlying bug.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 45292 is the most generic and central wording in the clear duplicate chain (`resize_token_embeddings` not updating outputs), while 45276 and 45335 look like model-specific manifestations of the same API regression.", "canonical_pr_reason": null, - "best_issue_reason": "`issue:45292` best represents the duplicate set because it captures the underlying resize-token-embeddings regression without model-specific noise, and the other accepted issues read like variants of the same failure.", + "best_issue_reason": "45292 best represents the cluster because it states the core failure without narrowing to a specific model field, making it the most reusable duplicate target among the issue set.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different model families and failures: Gemma4 FSDP/shared_kv_state bug vs Qwen3.5 MoE rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both mention quantization/OOM, but one is offloading behavior and the other is increased reserved memory under int4; not the same concrete bug." + }, { "left": "issue:44155", "right": "issue:45823", "accept": false, - "reason": "Different models and failures: batched inference token/embedding leak vs Gemma4 device mismatch. No shared code-path bug." + "reason": "AudioFlamingo3 batched inference token leak and Gemma4 device-map mismatch are unrelated code-paths." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "`init_empty_weights` argument handling and Strix Halo OOM/mmap are unrelated." + "reason": "Unexpected `_is_hf_initialized` arg during init_empty_weights is unrelated to Strix Halo mmap/OOM handling." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both involve quantized models, but the models and failure modes differ; not the same underlying bug." + "reason": "Different quantization/loading problems on different models; no evidence of the same code path or fix." }, { "left": "issue:44960", "right": "issue:46050", "accept": false, - "reason": "GLM5 loading issue and sinq save/load regression are unrelated." + "reason": "GLM5 model-loading issue and sinq save/load breakage are separate bugs." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Sparse-layer config bug and Gemma4 FSDP2 attention state bug are different code paths." + "reason": "Sparse-layer config bug in SwitchTransformers vs Gemma4 FSDP attention-state rebuild; unrelated." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "Both mention OOM, but one is int4 reserved-memory growth and the other is mmap on Strix Halo; not duplicates." + "reason": "OOM symptoms overlap, but the causes are different: int4 reserved-memory regression vs mmap on Strix Halo." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Both touch gradient checkpointing, but one is ineffective LoRA checkpointing and the other is eval-mode usage restriction." + "reason": "Both involve gradient checkpointing, but one is ineffective LoRA checkpointing and the other is eval-mode restriction." }, { "left": "issue:45276", "right": "issue:45292", "accept": true, - "reason": "Same `resize_token_embeddings` regression: both report embeddings/output heads not being updated, with 45276 being a Gemma4-specific variant." + "reason": "Same underlying resize_token_embeddings regression affecting output embeddings; 45276 is a model-specific variant of 45292." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Different regressions: GLM-4.7 model loading vs Qwen3.5 checkpoint save format." + "reason": "One is a GLM-4.7-Flash loading problem; the other is a Qwen3.5 save_pretrained regression." }, { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Unrelated gradient-checkpointing restriction vs RLHF NaN/SDPA fallback issue." + "reason": "Gradient checkpointing eval-mode issue and RLHF NaN/SDPA math fallback issue are distinct." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "Save/load extra_state handling is unrelated to the Strix Halo mmap/OOM report." + "reason": "extra_state save/from_pretrained handling is unrelated to Strix Halo mmap OOM." }, { "left": "issue:45684", "right": "issue:45698", "accept": false, - "reason": "Both involve custom-model serialization, but one is file-permission propagation and the other is wrong module loading; different bugs." + "reason": "Both concern custom-model save/load, but one is file permission propagation and the other is loading the wrong module; different bugs." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Qwen3 device-map assert and AudioFlamingo3 batching corruption are unrelated." + "reason": "Qwen3 device-map assert and AudioFlamingo3 batch leak are unrelated." }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Video-input regression in Qwen VL models and Granite speech config strictness are separate issues." + "reason": "Video-input regression and strict config loading are separate model/config issues." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "Flash-attention `s_aux=None` crash and Gemma4 FSDP2 shared state rebuild are different failures." + "reason": "Flash-attention sink handling bug vs Gemma4 FSDP shared_kv_states bug; different paths." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "Meta-device loading regression and Strix Halo mmap/OOM are unrelated." + "reason": "Meta-device model loading and Strix Halo mmap OOM are unrelated." }, { - "left": "issue:43646", + "left": "issue:43645", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization regression and Trainer `max_steps` resume logic are different subsystems." - }, - { - "left": "issue:45812", - "right": "issue:46315", - "accept": false, - "reason": "Tokenizer wrong-ID regression vs tokenizer performance slowdown; not the same bug." - }, - { - "left": "issue:45292", - "right": "issue:45335", - "accept": true, - "reason": "Same underlying `resize_token_embeddings` bug: 45292 covers output embeddings generally, while 45335 is the t5gemma-specific decoder embedding manifestation." + "reason": "Custom model initialization in Jupyter and Trainer resume max_steps calculation are different problems." }, { - "left": "issue:43645", - "right": "issue:44164", + "left": "issue:43828", + "right": "issue:43957", "accept": false, - "reason": "Notebook custom model initialization and extra_state save/load are distinct problems." + "reason": "Autocast dtype mismatch on Phi-tiny-MoE is not the same as meta-device loading breakage." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Tokenizer vocab-size mismatch and a generic model load failure are not clearly the same bug." - }, - { - "left": "issue:43828", - "right": "issue:43957", - "accept": false, - "reason": "Autocast dtype mismatch and meta-device loading are different failure modes." + "reason": "Both are tokenizer/model loading failures, but they involve different models and likely different root causes." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch version incompatibility is too broad and not the same concrete bug as the autocast dtype mismatch." + "reason": "Torch version incompatibility is too broad and does not match the specific autocast dtype mismatch bug." }, { "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "Float8 storage lookup failure and mmap/OOM are unrelated." + "reason": "Float8 storage lookup failure is unrelated to Strix Halo mmap OOM." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Different models and different load-path failures; not the same underlying issue." + "reason": "Qwen3 MOE conversion under accelerate+deepspeed and NemotronH checkpoint loading are separate model-loading failures." }, { "left": "issue:44683", @@ -2535,31 +2531,43 @@ "left": "issue:39404", "right": "issue:45701", "accept": false, - "reason": "Whisper pipeline `return_language` regression and tokenizer-version behavior change are unrelated." + "reason": "Whisper pipeline return_language regression and tokenizer-version behavior change are unrelated." }, { "left": "issue:43611", "right": "issue:43645", "accept": false, - "reason": "Both concern custom models in Transformers 5.0, but one is `base_model_prefix` loading and the other is notebook initialization; not enough evidence of the same bug." + "reason": "Both are Transformers 5.0 custom-model regressions, but one is base_model_prefix loading and the other is notebook initialization; different concrete failures." }, { "left": "issue:43425", - "right": "issue:43716", + "right": "issue:45823", "accept": false, - "reason": "Torch compatibility report and Mistral-3 image-preprocessor dtype mismatch are separate issues." + "reason": "Torch 2.10 incompatibility and Gemma4 PLE device mismatch are not the same bug." }, { - "left": "issue:43906", - "right": "issue:44530", + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and non-template-node compile error are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43716", "accept": false, - "reason": "Isolated reproduction of another issue and Qwen3.5 PagedAttentionCache group-type crash are different problems." + "reason": "Torch version incompatibility and Mistral-3 image-preprocessor dtype mismatch are separate issues." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same resize_token_embeddings regression family; 45335 is another manifestation where decoder.embed_tokens is not updated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative. The only clearly supported duplicate family is the `resize_token_embeddings` set around `issue:45292`, `issue:45276`, and `issue:45335`, and the canonical choice of `issue:45292` is reasonable. The other pair judgments are cautious and consistent with the issue titles. No mergeability problem applies here because these are issue pairs, not PR pairs." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edges are the two resize_token_embeddings pairs, which are strongly supported by the titles and similarity signal. The rest of the verdicts avoid overclaiming by treating shared subsystems as insufficient for duplication, which matches the evidence." }, "evaluator_used": true, "retried": false, @@ -2572,13 +2580,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 8, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:32090", "issue:34567", @@ -2591,7 +2599,6 @@ "issue:43421", "issue:43425", "issue:43452", - "issue:43541", "issue:43582", "issue:43596", "issue:43611", @@ -2601,6 +2608,7 @@ "issue:43716", "issue:43856", "issue:43901", + "issue:43906", "issue:43931", "issue:43994", "issue:44079", @@ -2617,7 +2625,6 @@ "issue:44737", "issue:44756", "issue:44805", - "issue:44811", "issue:44898", "issue:44912", "issue:44918", @@ -2625,11 +2632,13 @@ "issue:44991", "issue:45081", "issue:45084", - "issue:45584", "issue:45759", - "issue:45859" + "issue:45859", + "issue:46050", + "issue:46326" ], "soft_pairs": [ + "issue:43906|issue:44530", "issue:44265|issue:44898", "issue:39404|issue:44912", "issue:44479|issue:44805", @@ -2637,245 +2646,244 @@ "issue:44589|issue:45084", "issue:43425|issue:44918", "issue:44164|issue:45759", - "issue:36032|issue:43452", "issue:43299|issue:43931", + "issue:36032|issue:43452", "issue:43596|issue:44683", "issue:43994|issue:44079", "issue:43856|issue:44756", "issue:44671|issue:44991", "issue:44991|issue:45081", + "issue:43906|issue:46326", "issue:39404|issue:44671", "issue:44737|issue:45859", "issue:44164|issue:44479", "issue:44488|issue:45081", "issue:43582|issue:43632", - "issue:43611|issue:43644", "issue:44661|issue:44683", + "issue:43611|issue:43644", "issue:40990|issue:43421", "issue:32090|issue:39404", "issue:43716|issue:45084", + "issue:46050|issue:46326", "issue:44488|issue:44987", "issue:43643|issue:44530", "issue:34567|issue:40444", - "issue:36032|issue:42915", - "issue:44811|issue:45584", - "issue:42915|issue:44530", - "issue:43541|issue:45084" + "issue:36032|issue:42915" ], - "prepared_review_unit_hash": "5b4c15c43bc24cea938fb767f64c5dc66dcc24510be20c0d328c0e8e223a56b8", + "prepared_review_unit_hash": "2169594f1ab50ca33d3c02ee3a5414ae81113dc3bb6725d8fbcb48ff16ec7e1e", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37062, - "estimated_input_tokens": 9266, - "estimated_eval_tokens": 18788 + "serialized_chars": 37051, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous: mostly unrelated bug reports spanning Whisper, Qwen, tokenizer loading, torch/v5 regressions, docs, and model-specific failures. No soft pairs look like the same underlying defect/change, so none are accepted.", - "confidence": 0.82, - "canonical_issue_reason": "issue:43611 is the most broadly representative issue in the cluster: a clear, actionable Transformers v5 model-loading regression affecting any model using `base_model_prefix`. The other issues are either narrower, model-specific, documentation-only, or unrelated runtime failures.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions: model/tokenizer loading failures, a few training/inference bugs, and some docs-only issues. The soft edges are mostly topical similarity rather than the same concrete defect, so I would not merge any of them.", + "confidence": 0.42, + "canonical_issue_reason": "Issue 43611 is the broadest representative of the cluster: a Transformers v5 model-loading regression affecting a generic code path (`base_model_prefix`) that matches the overall theme better than the narrower model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43611 is the best single issue to anchor the cluster because it describes a general loading breakage with wide user impact and is more central than the highly specific model/tokenizer edge cases elsewhere in the set.", + "best_issue_reason": "Issue 43611 is the best single issue to anchor this set because it describes a general v5 loading breakage rather than a one-off model or tokenizer symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "Different problems: an isolated reproduction of an older issue vs a Qwen3.5 PagedAttentionCache crash with linear_attention." + }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "Different failures: `torch_compilable_check` export handling vs Perceiver resolution/interpolation mismatch. Not the same bug path." + "reason": "Both are runtime failures, but one is torch.export/checkable-model logic and the other is Perceiver image-classification resolution handling." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline language return regression is unrelated to MXFP4 quantization fallback for gpt-oss-20b." + "reason": "Whisper pipeline language-return regression and git-oss-20b MXFP4 quantization fallback are unrelated." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "Qwen video-input regression and a generic mask-shape IndexError are different code paths and symptoms." + "reason": "Video-input regression for Qwen VL models vs a generic mask-shape IndexError; different code paths and symptoms." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both are docs-related, but they concern different pipeline APIs and different outdated text; not one underlying issue." + "reason": "Both are docs issues, but one is about `return_all_scores` text and the other about removed pipeline tasks; not the same fix." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "One is a missing Float8 storage type error, the other a compilation/template-node error; distinct runtime problems." + "reason": "Float8 storage lookup failure and template-node compilation error are distinct failures." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch 2.10 incompatibility is not the same as Qwen3.5 embedding unpacking failure in TRL SFT." + "reason": "Torch 2.10 compatibility vs TRL SFT trainer embedding unpacking are unrelated." }, { "left": "issue:44164", "right": "issue:45759", "accept": false, - "reason": "`extra_state` save/load handling differs from `from_config` text_config unwrapping; different API surfaces and bugs." + "reason": "Saving/loading `extra_state` and unwrapping `text_config` are different serialization/config bugs." }, { - "left": "issue:36032", - "right": "issue:43452", + "left": "issue:43299", + "right": "issue:43931", "accept": false, - "reason": "Tokenizer special-token method conflict is unrelated to `gguf_file` breaking model/tokenizer loading." + "reason": "Both concern Qwen3-VL loading, but one is a broad v5 dev regression and the other is a specific checkpoint weight-shape mismatch." }, { - "left": "issue:43299", - "right": "issue:43931", + "left": "issue:36032", + "right": "issue:43452", "accept": false, - "reason": "Both involve Qwen3-VL family loading, but one is a v5 regression claim and the other is a specific weight-shape mismatch; too different to merge." + "reason": "T5 tokenizer special-token method conflict is not the same as gguf_file breaking AutoTokenizer/AutoModel loading." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "Deepspeed ZeRO-3 init index error is unrelated to compiled flex_attention failures on torch>=2.9." + "reason": "DeepSpeed ZeRO-3/BertModel index error and compiled flex_attention failing on newer torch are unrelated." }, { "left": "issue:43994", "right": "issue:44079", "accept": false, - "reason": "Siglip2 bad outputs are not the same as `ModelOutput` key assignment when values were previously `None`." + "reason": "SigLIP2 bad outputs and ModelOutput key assignment with `None` are different bugs." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Qwen3 MoE memory inefficiency and Strix Halo mmap OOM avoidance are separate memory-related problems with different causes." + "reason": "Qwen3 MoE training memory use and Strix Halo mmap OOM avoidance are not the same defect." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "CamemBERT MLM prediction regression and tokenizer-loading failure for est-roberta are different model/tokenizer bugs." + "reason": "CamemBERT masked-LM regression and est-roberta tokenizer load failure are separate model-specific issues." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both hit tokenizer loading, but one is a generic v5 tokenizer load failure and the other is a Mistral-specific regex patch crash." + "reason": "Tokenizer load failure for est-roberta vs a Mistral regex patch crash; same area, different root cause." + }, + { + "left": "issue:43906", + "right": "issue:46326", + "accept": false, + "reason": "An isolated reproduction issue and a mistral_common continue_final_message bug do not share the same code path." }, { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Whisper pipeline language return and CamemBERT MLM predictions are unrelated model families and failure modes." + "reason": "Whisper pipeline language return and CamemBERT masked-LM predictions are unrelated." }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "CPU device placement bug in XLNet is unrelated to Qwen3.5 MoE CPU-offload rotary embedding incompatibility." + "reason": "Both are device/offload-related, but XLNet positional encoding CPU placement and Qwen3.5 MoE rotary embedding offload compatibility are distinct." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "Save/load `extra_state` handling and Qwen video-input regression do not share the same underlying code path." + "reason": "Serialization of `extra_state` vs Qwen VL video-input regression are different bugs." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "`cjvt/sleng-bert` loading failure is not the same issue as the Mistral regex patch crash." + "reason": "Loading cjvt/sleng-bert and a Mistral tokenizer regex patch crash are unrelated." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and `_is_hf_initialized` flag breakage are distinct internal issues." + "reason": "Apple Silicon warmup TypeError and `_is_hf_initialized` flag breakage are different low-level regressions." }, { - "left": "issue:43611", - "right": "issue:43644", + "left": "issue:44661", + "right": "issue:44683", "accept": false, - "reason": "Both are v5 regressions, but one is model-loading via `base_model_prefix` and the other is non-persistent buffer initialization; different defects." + "reason": "Model registry generation failure and compiled flex_attention failure are unrelated." }, { - "left": "issue:44661", - "right": "issue:44683", + "left": "issue:43611", + "right": "issue:43644", "accept": false, - "reason": "Tokenizer mapping-name guard failure is unrelated to torch.compile/flex_attention compilation failure." + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer corruption; different underlying bugs." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "High perplexity on a model/dataset is not the same as runtime post-processor updates for special tokens." + "reason": "High perplexity on gpt-oss and tokenizer post-processor refresh logic are not the same issue." }, { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast TypeError and Whisper pipeline language regression are unrelated subsystems." + "reason": "Trainer GPU broadcast NoneType error and Whisper pipeline `return_language` regression are unrelated." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Image preprocessor/model dtype mismatch is not the same as a template-node compilation TypeError." + "reason": "Mistral-3 image-preprocessor dtype mismatch and a template compilation TypeError are different problems." + }, + { + "left": "issue:46050", + "right": "issue:46326", + "accept": false, + "reason": "Quantized model save/load breakage and mistral_common final-message handling are unrelated." }, { "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Two separate model-loading regressions for different repositories; no shared underlying bug is evident." + "reason": "Tokenizer load failure for cjvt/sleng-bert and physical-intelligence/fast loading failure are distinct model-specific issues." }, { "left": "issue:43643", "right": "issue:44530", "accept": false, - "reason": "`trust_remote_code` missing fields and PagedAttentionCache linear_attention crash are unrelated config vs cache issues." + "reason": "Missing fields from `trust_remote_code=True` config loading and Qwen3.5 PagedAttentionCache crash are unrelated." }, { "left": "issue:34567", "right": "issue:40444", "accept": false, - "reason": "Trainer token-count tracking bug and Qwen2.5-VL iterable dataset multi-image failure are different training path issues." + "reason": "TrainerState token accounting and Qwen2.5-VL iterable-dataset multi-image finetuning are different bugs." }, { "left": "issue:36032", "right": "issue:42915", "accept": false, - "reason": "Tokenizer method conflict for T5 is unrelated to Qwen3 MoE fine-grained FP8 config failure." - }, - { - "left": "issue:44811", - "right": "issue:45584", - "accept": false, - "reason": "Whisper batch_decode special-token handling and empty transcription generation after align_special_tokens are related by model family only, not the same concrete bug." - }, - { - "left": "issue:42915", - "right": "issue:44530", - "accept": false, - "reason": "Qwen3 MoE FP8 config failure and Qwen3.5 PagedAttentionCache linear_attention crash are different model/runtime issues." - }, - { - "left": "issue:43541", - "right": "issue:45084", - "accept": false, - "reason": "Mixtral grouped_mm tracing failure is unrelated to the template-node compilation error." + "reason": "T5 tokenizer special-token conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." } ] }, @@ -2891,15 +2899,16 @@ "component_index": 1, "component_count": 18, "review_unit_index": 9, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36032", + "issue:40444", "issue:42175", "issue:42915", "issue:43089", @@ -2911,7 +2920,7 @@ "issue:43452", "issue:43482", "issue:43540", - "issue:43632", + "issue:43541", "issue:43644", "issue:43645", "issue:43646", @@ -2919,36 +2928,38 @@ "issue:43819", "issue:43883", "issue:43994", - "issue:44062", "issue:44206", "issue:44220", "issue:44265", - "issue:44291", "issue:44403", "issue:44451", "issue:44464", "issue:44466", "issue:44488", + "issue:44530", "issue:44534", - "issue:44589", "issue:44610", "issue:44683", - "issue:44756", + "issue:44811", "issue:44849", "issue:44987", "issue:44991", "issue:45081", "issue:45084", - "issue:45127", "issue:45216", "issue:45325", "issue:45357", "issue:45507", + "issue:45584", "issue:45987", "issue:46178", - "issue:46315" + "issue:46315", + "issue:46326" ], "soft_pairs": [ + "issue:44811|issue:45584", + "issue:42915|issue:44530", + "issue:43541|issue:45084", "issue:44451|issue:44987", "issue:43644|issue:43646", "issue:44206|issue:44220", @@ -2965,8 +2976,8 @@ "issue:43646|issue:44534", "issue:43089|issue:45987", "issue:43404|issue:44466", - "issue:43322|issue:43540", "issue:43994|issue:44610", + "issue:43322|issue:43540", "issue:44403|issue:45081", "issue:43883|issue:44991", "issue:42915|issue:45084", @@ -2978,260 +2989,232 @@ "issue:44987|issue:45081", "issue:45216|issue:45357", "issue:44220|issue:44683", - "issue:36032|issue:43742", - "issue:42915|issue:44291", - "issue:43632|issue:44756", - "issue:42915|issue:44589", - "issue:43404|issue:45127", - "issue:44062|issue:44987" + "issue:40444|issue:46326", + "issue:36032|issue:43742" ], - "prepared_review_unit_hash": "25cd8a6f2c5dce668b2db42906332aa945ac05cbc0981a746d2b9581c7019f1a", + "prepared_review_unit_hash": "4c889e8818ef1d2a0a3cdbc797ba6ef8c595c94dadcce4decb978c4d559088c8", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38265, - "estimated_input_tokens": 9567, - "estimated_eval_tokens": 19390 + "soft_pair_count": 34, + "serialized_chars": 37939, + "estimated_input_tokens": 9485, + "estimated_eval_tokens": 19226 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly distinct Transformers v5 regressions. The clearest duplicate-like pairs remain GGUF loading and Qwen3.5 save_pretrained; the EMBEDDIA/physical-intelligence loading issues are similar in theme but not conservatively the same bug.", - "confidence": 0.79, - "canonical_issue_reason": "Issue 44991 is still the best single anchor because it is a concrete, user-facing v5 tokenizer-loading regression and representative of the cluster\u2019s broad load-failure theme.", + "summary": "Most items are unrelated one-off Transformers bugs. The only clear duplicate-like soft edge is the Qwen3.5 save_pretrained regression pair; the rest are too model-/path-specific or describe different failures.", + "confidence": 0.63, + "canonical_issue_reason": "issue:45216 is the broader, earlier report of the Qwen3.5 save_pretrained checkpoint corruption; it best captures the underlying regression.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44991 is the strongest standalone issue for the cluster because it captures a clear, actionable tokenizer-load regression without being overly model-specific.", + "best_issue_reason": "issue:45216 is the best cluster anchor because it states the core save_pretrained regression in a general way, while issue:45357 is a narrower follow-up.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both involve Whisper, but one is batch_decode skip_special_tokens behavior and the other is empty-transcription generation after align_special_tokens; different bugs." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Different subsystems and failures: FineGrainedFP8Config vs PagedAttentionCache linear_attention group handling." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch Dynamo grouped_mm tracing failure is unrelated to template-node compilation errors." + }, { "left": "issue:44451", "right": "issue:44987", "accept": false, - "reason": "Both are loading failures, but they involve different models and no evidence of the same root cause." + "reason": "Both are load failures, but for different models and likely different code paths." }, { "left": "issue:43644", "right": "issue:43646", "accept": false, - "reason": "Related to v5 init behavior, but the specific failure modes are different and do not clearly share one fix." + "reason": "Both are v5 regressions around custom models, but one is non-persistent buffer corruption and the other is custom model initialization; not the same bug." }, { "left": "issue:44206", "right": "issue:44220", "accept": false, - "reason": "Both are audio-related, but one is a processor argument crash and the other is a feature-extraction helper issue." + "reason": "Same audio area, but the first is an unsupported center arg crash and the second is a generic fbank feature extraction issue; not clearly the same defect." }, { "left": "issue:44464", "right": "issue:45987", "accept": false, - "reason": "Chunked generation/compiled forward inconsistency is a different bug from a cache-length type contract issue." + "reason": "Chunked generation inconsistency and StaticCache seq_length return type are different issues." }, { "left": "issue:43452", "right": "issue:43482", - "accept": true, - "reason": "Both point to the same GGUF loading path breaking in v5, with 43482 looking like a model-specific manifestation of the same regression." + "accept": false, + "reason": "Both involve GGUF loading, but one is a broad from_pretrained breakage and the other is a Qwen2.5-specific v5 failure; too little evidence they are the same bug." }, { "left": "issue:43317", "right": "issue:43482", "accept": false, - "reason": "Dequantized device_map offload failure is unrelated to GGUF loading." + "reason": "gpu/cpu offload dequantized loading and Qwen2.5-GGUF loading are different failure modes." }, { "left": "issue:43883", "right": "issue:44488", "accept": false, - "reason": "A missing tied-weights attribute and a model-specific loading failure are different root causes." + "reason": "Missing all_tied_weights_keys in Molmo and inability to load a specific BERT model are unrelated." }, { "left": "issue:44849", "right": "issue:45325", "accept": false, - "reason": "Different Qwen model families and different failure types." + "reason": "Qwen3.5 hidden_states output bug and Qwen2.5-VL rope index scaling are different code paths." }, { "left": "issue:36032", "right": "issue:43645", "accept": false, - "reason": "Tokenizer method conflict and custom model initialization in notebooks are unrelated regressions." + "reason": "Tokenizer add_special_tokens conflict and custom model initialization in notebooks are unrelated." }, { "left": "issue:45084", "right": "issue:45507", "accept": false, - "reason": "Different errors in different components; no shared concrete bug path." + "reason": "Template compilation failure and GraniteMoEHybrid invalid method calls are different problems." }, { "left": "issue:42175", "right": "issue:46178", "accept": false, - "reason": "One is about missing tensorflow in install extras, the other about an undefined tensorflow_text backend." + "reason": "Both mention backend registration, but one is missing tensorflow from extras and the other is an unsupported tensorflow_text backend entry." }, { "left": "issue:43262", "right": "issue:43377", "accept": false, - "reason": "Audio chat-template sampling-rate default and MIMI batching mismatch are separate issues." + "reason": "Audio chat-template sample rate default and MIMI batch padding-mask behavior are unrelated." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Both are model-loading regressions, but the titles show different models and different failure descriptions; the packet does not establish the same underlying tokenizer bug." + "reason": "Different model-loading failures for different models; no clear shared concrete bug." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Both are init-related v5 regressions, but the failure modes differ and do not clearly share one fix." + "reason": "Both are v5 custom-model regressions, but one is generic initialization and the other is non-persistent buffer junk; not the same defect." }, { "left": "issue:43089", "right": "issue:45987", "accept": false, - "reason": "Generation performance overhead is not the same as a cache-length type contract bug." + "reason": "Generation performance overhead is unrelated to StaticCache.get_seq_length return semantics." }, { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both involve tied weights/lm_head, but one is a model implementation bug and the other is save_pretrained serialization behavior." + "reason": "Both mention lm_head weight/tied weights, but one is a missing tie in Mistral3 and the other is inconsistent serialization by device." }, { - "left": "issue:43322", - "right": "issue:43540", + "left": "issue:43994", + "right": "issue:44610", "accept": false, - "reason": "Llava Next load segfault and Qwen3OmniMoe video-input validation are unrelated multimodal failures." + "reason": "Different models and symptoms: SigLIP2 nonsensical outputs vs OmDet-Turbo input-size mismatch." }, { - "left": "issue:43994", - "right": "issue:44610", + "left": "issue:43322", + "right": "issue:43540", "accept": false, - "reason": "Wrong outputs from a vision model and a processor resizing mismatch are different problems." + "reason": "Llava Next loading segfault and Qwen3OmniMoe video-processing ValueError are unrelated." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Load-time noise and a Mistral regex crash are not the same bug." + "reason": "Generic load noise and a specific Mistral regex patch crash are not the same bug." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "They are both loading failures, but the evidence does not show a shared underlying cause." + "reason": "Molmo tied-weights attribute error and tokenizer load failure for EMBEDDIA/est-roberta are unrelated." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "FP8 config failure and template compilation failure are unrelated." + "reason": "FineGrainedFP8Config and non-template-node compilation are completely different issues." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Both are output mismatches, but one is due to padding masks and the other to missing STE." + "reason": "MIMI padding-mask batching and DAC from_latents/STE mismatch are different model bugs." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Custom-model notebook init and junk-filled non-persistent buffers are distinct v5 regressions." + "reason": "Notebook custom model initialization and non-persistent buffer junk are related only at a high level, not the same concrete bug." }, { "left": "issue:44265", - "right": "issue:44683", + "right": "issue:44610", "accept": false, - "reason": "torch.export and compiled flex_attention failures are different code paths and different fixes." + "reason": "torch.export / torch_compilable_check and OmDet-Turbo processor image sizing are unrelated." }, { "left": "issue:44991", "right": "issue:46315", "accept": false, - "reason": "Tokenizer loading regression and slow convert_tokens_to_ids performance are separate tokenizer issues." + "reason": "Tokenizer load failure for a specific model and slow convert_tokens_to_ids are different problems." }, { "left": "issue:44451", "right": "issue:45081", "accept": false, - "reason": "Different models and different failure mechanisms." + "reason": "Different models and code paths: ScandiBERT loading vs Mistral tokenizer regex patching." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Tokenizer loading for EMBEDDIA/est-roberta is unrelated to the Mistral regex patch crash." + "reason": "General model load failure vs Mistral tokenizer patch crash; not the same underlying bug." }, { "left": "issue:45216", "right": "issue:45357", "accept": true, - "reason": "Both report the same Qwen3.5 save_pretrained regression producing incorrect checkpoints/visual encoder keys." - }, - { - "left": "issue:44220", - "right": "issue:44683", - "accept": false, - "reason": "Audio fbank extraction and compiled flex_attention are unrelated." - }, - { - "left": "issue:36032", - "right": "issue:43742", - "accept": false, - "reason": "T5 tokenizer special-token conflict and MobileLLM key error are different loading bugs." - }, - { - "left": "issue:42915", - "right": "issue:44291", - "accept": false, - "reason": "FineGrainedFP8Config failure and unexpected _is_hf_initialized argument are separate regression classes." - }, - { - "left": "issue:43632", - "right": "issue:44756", - "accept": false, - "reason": "_is_hf_initialized flag breakage and mmap OOM on Strix Halo are unrelated." - }, - { - "left": "issue:42915", - "right": "issue:44589", - "accept": false, - "reason": "FP8 config failure and Float8 storage deserialization failure are different issues." - }, - { - "left": "issue:43404", - "right": "issue:45127", - "accept": false, - "reason": "Both involve tied embeddings, but one is a missing tie in a model class and the other is LoRA merge collapse with extended vocab." - }, - { - "left": "issue:44062", - "right": "issue:44987", - "accept": false, - "reason": "AddedToken constructor argument conflict is unrelated to the EMBEDDIA tokenizer-loading regression." + "reason": "Both describe the same Qwen3.5 save_pretrained checkpoint corruption; 45357 is a narrower continuation about visual encoder keys." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but at least one soft-edge acceptance is too aggressive for the evidence in the packet. In particular, issue:44987 vs issue:44991 are both loading regressions, but the titles only show different models and different failure descriptions; the packet does not conservatively establish the same underlying tokenizer bug. Because the analyst accepted that pair, the cluster verdict is not conservative enough. The GGUF and Qwen3.5 save_pretrained pairings are more defensible, but this one overstates the evidence." + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it only treats the Qwen3.5 save_pretrained pair as a likely duplicate-like match, and the other soft-edge rejections are plausibly cautious given the issue titles/descriptions. No overstatement of evidence is apparent." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -3241,38 +3224,37 @@ "component_index": 1, "component_count": 18, "review_unit_index": 10, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:33666", "issue:36032", "issue:40444", "issue:40990", - "issue:41553", "issue:41720", - "issue:42175", + "issue:42915", "issue:43296", "issue:43317", - "issue:43377", "issue:43381", + "issue:43404", "issue:43421", "issue:43425", "issue:43482", "issue:43525", "issue:43531", - "issue:43582", "issue:43611", "issue:43632", + "issue:43746", "issue:43792", "issue:43818", "issue:43856", + "issue:44062", "issue:44079", - "issue:44265", "issue:44291", "issue:44403", "issue:44462", @@ -3281,256 +3263,264 @@ "issue:44568", "issue:44589", "issue:44683", + "issue:44756", "issue:44811", "issue:44829", "issue:44877", + "issue:44977", + "issue:44987", "issue:44991", "issue:45020", - "issue:45072", - "issue:45081", + "issue:45127", "issue:45325", "issue:45357", "issue:45479", - "issue:45491", "issue:45538", - "issue:45542", "issue:45663", "issue:45812", - "issue:45923" + "issue:45923", + "issue:46326" ], "soft_pairs": [ + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:42915|issue:44589", + "issue:43404|issue:45127", + "issue:44062|issue:44987", "issue:43611|issue:44534", "issue:43531|issue:44877", "issue:43296|issue:43531", "issue:36032|issue:41720", "issue:44479|issue:45325", + "issue:44977|issue:46326", "issue:43425|issue:44403", "issue:40990|issue:44811", - "issue:33666|issue:40444", + "issue:43746|issue:46326", "issue:43792|issue:44589", + "issue:33666|issue:40444", "issue:43421|issue:44568", "issue:44403|issue:44991", "issue:43632|issue:44534", "issue:44079|issue:45663", - "issue:43381|issue:45923", "issue:44683|issue:45020", + "issue:43381|issue:45923", "issue:44462|issue:45812", "issue:44829|issue:45479", - "issue:40444|issue:45325", "issue:43482|issue:45538", + "issue:40444|issue:45325", "issue:43317|issue:43856", "issue:44291|issue:44589", "issue:43482|issue:43525", - "issue:43818|issue:45357", - "issue:42175|issue:45542", - "issue:41553|issue:43582", - "issue:43377|issue:45491", - "issue:41720|issue:45081", - "issue:43531|issue:44291", - "issue:44265|issue:45072" + "issue:43818|issue:45357" ], - "prepared_review_unit_hash": "a91fa1d5ba980f6b3ebc2fbcfba86bf6a593c67a6f1bf4b7749ee69571126934", + "prepared_review_unit_hash": "3245dcf64a1d65a3e4cacd83bd3c8e55c49bfea648546de97ca38da4a085272b", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36600, - "estimated_input_tokens": 9150, - "estimated_eval_tokens": 18556 + "soft_pair_count": 30, + "serialized_chars": 36734, + "estimated_input_tokens": 9184, + "estimated_eval_tokens": 18624 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of loosely related Transformers regressions (tokenizer/model loading, v5 compatibility, Qwen/VL variants, attention/training edge cases). The soft matches are lexical/theme similarities rather than the same underlying bug.", - "confidence": 0.27, - "canonical_issue_reason": "issue:45020 is the broadest umbrella complaint in the set and best fits the cluster\u2019s general theme of recent-version loading regressions, even though the cluster is heterogeneous.", + "summary": "This set is mostly a loose collection of unrelated bug reports, with only superficial overlap around Transformers v5 regressions, Qwen/VL models, tokenizers, and checkpointing. None of the soft pairs look like the same concrete bug/change, so I would keep them separate.", + "confidence": 0.18, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the most suitable representative because it captures the widest user-facing regression pattern among the issues here; the rest are mostly narrower or unrelated variants.", + "best_issue_reason": "issue:45812 is the strongest standalone representative: it is a concrete, high-impact AutoTokenizer regression affecting all Granite models and is better scoped than the broader, noisier reports here.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Both are Transformers v5 loading/init regressions, but one is about FineGrainedFP8Config and the other about init_empty_weights/_is_hf_initialized; different failure modes." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "One is an init flag regression in Transformers v5; the other is a Strix Halo mmap OOM workaround. No shared underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Different model/runtime failures: FP8 config vs missing Float8 storage. Same broad era, not the same defect." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention weights/tied embeddings, but one is a missing lm_head tie in Mistral3 and the other is LoRA merge collapse with extended vocabulary. Not the same bug." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer AddedToken special-arg conflict vs a model-loading failure for physical-intelligence/fast; unrelated issues." + }, { "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 defects." + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization junk. Different code paths." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior is unrelated to Granite speech config loading/strict config validation." + "reason": "Qwen3-MoE sliding_window behavior and GraniteSpeech strict config loading are separate model/config problems." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "Different model families and failure modes: PaddleOCR-VL load failure vs Qwen3-MoE sliding_window issue." + "reason": "PaddleOCR-VL/vLLM load failure is unrelated to Qwen3-MoE sliding_window behavior." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer class-name conflict is unrelated to Qwen3 auto device mapping CUDA assert." + "reason": "Tokenizer load conflict and cudaErrorAssert under auto device mapping are completely different bugs." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "Both concern Qwen VL/video, but one is a video input regression and the other is temporal position_id scaling; not the same bug." + "reason": "Both are Qwen2.5-VL video/temporal-position issues, but one is a broad video-input regression and the other is a specific still-image rope-index scaling bug; not clearly the same failure." + }, + { + "left": "issue:44977", + "right": "issue:46326", + "accept": false, + "reason": "Qwen3.5 flash-attention generation failure vs mistral_common continue_final_message tokenizer behavior. Different subsystems and symptoms." }, { "left": "issue:43425", "right": "issue:44403", "accept": false, - "reason": "Torch 2.10 compatibility is a separate compatibility issue from noisy transformer loading messages." + "reason": "Torch 2.10 compatibility is unrelated to noisy transformer loading logs." }, { "left": "issue:40990", "right": "issue:44811", "accept": false, - "reason": "Perplexity on gpt-oss and Whisper batch_decode special-token handling are unrelated." + "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens handling are unrelated." }, { - "left": "issue:33666", - "right": "issue:40444", + "left": "issue:43746", + "right": "issue:46326", "accept": false, - "reason": "Both are Qwen2-VL fine-tuning problems, but multi-GPU training and multi-image iterable-dataset failure are distinct issues." + "reason": "GraniteSpeech PEFT local checkpoint loading and mistral_common continue_final_message are different tokenizer/model-loading paths." }, { "left": "issue:43792", "right": "issue:44589", "accept": false, - "reason": "Whisper runtime failure and missing Float8 storage object are different error paths." + "reason": "Whisper runtime failure and Float8 storage lookup failure do not share the same concrete root cause." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both involve Qwen2-VL/Qwen2.5-VL, but one is multi-GPU training and the other is IterableDataset multi-image finetuning; too different to merge." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Runtime post-processor refresh for special tokens is not the same as add_special_tokens failing to add BOS/EOS." + "reason": "Runtime special-token post-processing updates and add_special_tokens not adding BOS/EOS are related to tokens, but not the same bug." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Generic loading noise and specific tokenizer-loading failure for est-roberta are not the same defect." + "reason": "Generic loading noise and a tokenizer-load regression for EMBEDDIA/est-roberta are unrelated." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "_is_hf_initialized flag handling and junk-filled non-persistent buffers are separate v5 regressions." + "reason": "Both are Transformers v5 regressions, but one concerns _is_hf_initialized and the other non-persistent buffers. Different defects." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment and Gemma-4 FSDP2 shared_kv_states rebuilding are unrelated." + "reason": "ModelOutput key assignment and Gemma4 FSDP2 shared_kv_states KeyError are unrelated." }, { - "left": "issue:43381", - "right": "issue:45923", + "left": "issue:44683", + "right": "issue:45020", "accept": false, - "reason": "Eval-mode gradient checkpointing restriction is not the same as a missing supports_gradient_checkpointing flag." + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading breakage are separate compatibility problems." }, { - "left": "issue:44683", - "right": "issue:45020", + "left": "issue:43381", + "right": "issue:45923", "accept": false, - "reason": "Compiled flex_attention torch-version breakage is separate from remote_code model-loading breakage." + "reason": "Eval-mode gradient checkpointing restriction and missing supports_gradient_checkpointing flag are different feature/flag bugs." }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Ignoring tokenizer.json and wrong token IDs for Granite models are both tokenizer issues but different bugs." + "reason": "Both are tokenizer-related, but one ignores tokenizer.json while the other returns wrong token IDs for Granite models. Not the same bug." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "FlashAttention-3 training degeneration is unrelated to single-label classification with num_labels=1 zero loss." + "reason": "Degenerate training under flash_attention_3 and zero-loss classification with num_labels=1 are different training pathologies." }, { - "left": "issue:40444", - "right": "issue:45325", + "left": "issue:43482", + "right": "issue:45538", "accept": false, - "reason": "Multiple-images iterable-dataset finetuning and still-image temporal position scaling are distinct Qwen2.5-VL bugs." + "reason": "GGUF loading under Transformers v5 and CLIPTokenizer model_max_length behavior are unrelated." }, { - "left": "issue:43482", - "right": "issue:45538", + "left": "issue:40444", + "right": "issue:45325", "accept": false, - "reason": "Qwen2.5-GGUF loading failure and CLIPTokenizer max_length behavior are unrelated." + "reason": "Qwen2.5-VL multi-image IterableDataset finetuning failure and rope-index temporal scaling are distinct issues." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "device_map/offload loading failure is unrelated to Qwen3 MoE training memory usage." + "reason": "device_map auto offload failure and Qwen3 MoE memory inefficiency are not the same bug." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized and Float8 storage lookup are separate initialization/storage issues." + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights and missing Float8 storage are unrelated Transformers v5 breakages." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "GGUF loading failure and missing pad_token_id on Llama4Config are unrelated." + "reason": "Qwen2.5-GGUF loading and Llama4Config missing pad_token_id are separate model/config issues." }, { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Video-LLaVA temporal-attention/weight-sharing bug is different from Qwen3.5 save_pretrained key regression." - }, - { - "left": "issue:42175", - "right": "issue:45542", - "accept": false, - "reason": "Missing TensorFlow in torch extra and tensorboard-without-TF backend error are related packaging area, but not the same bug." - }, - { - "left": "issue:41553", - "right": "issue:43582", - "accept": false, - "reason": "Bad AutoTokenizer error for Voxtral is unrelated to Apple Silicon caching_allocator_warmup TypeError." - }, - { - "left": "issue:43377", - "right": "issue:45491", - "accept": false, - "reason": "MIMI batched-vs-single padding-mask mismatch and Gemma3 NaN embeddings from sliding-window/all-padding windows are different bugs." - }, - { - "left": "issue:41720", - "right": "issue:45081", - "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert and Mistral regex patch crash are unrelated." - }, - { - "left": "issue:43531", - "right": "issue:44291", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights/_is_hf_initialized are different regression classes." - }, - { - "left": "issue:44265", - "right": "issue:45072", - "accept": false, - "reason": "torch.export failure on torch_compilable_check and dtype mismatch in bfloat16 inference are separate problems." + "reason": "Video-LLaVA temporal-attention/weight-sharing bug and Qwen3.5 save_pretrained visual-key regression are different model families and code paths." } ] }, @@ -3546,17 +3536,17 @@ "component_index": 1, "component_count": 18, "review_unit_index": 11, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:35707", - "issue:39692", "issue:40444", + "issue:41553", "issue:41720", "issue:42175", "issue:42915", @@ -3565,7 +3555,9 @@ "issue:43377", "issue:43454", "issue:43482", + "issue:43531", "issue:43550", + "issue:43582", "issue:43606", "issue:43611", "issue:43632", @@ -3576,7 +3568,6 @@ "issue:43761", "issue:43792", "issue:43819", - "issue:43881", "issue:43957", "issue:43994", "issue:44079", @@ -3586,24 +3577,29 @@ "issue:44387", "issue:44466", "issue:44479", - "issue:44488", "issue:44534", "issue:44568", - "issue:44610", "issue:44617", "issue:44877", "issue:44898", "issue:45072", + "issue:45081", "issue:45325", "issue:45381", + "issue:45491", + "issue:45542", "issue:45800", "issue:45823", "issue:45834", - "issue:45920", - "issue:46305", - "issue:46315" + "issue:45920" ], "soft_pairs": [ + "issue:42175|issue:45542", + "issue:41553|issue:43582", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:43531|issue:44291", + "issue:44265|issue:45072", "issue:43611|issue:43646", "issue:43632|issue:45072", "issue:43994|issue:44898", @@ -3616,240 +3612,241 @@ "issue:40444|issue:45381", "issue:45325|issue:45381", "issue:43644|issue:44079", - "issue:35707|issue:40444", "issue:43761|issue:44079", - "issue:44479|issue:45823", "issue:44387|issue:44617", + "issue:35707|issue:40444", + "issue:44479|issue:45823", "issue:43606|issue:44265", "issue:44291|issue:44877", "issue:43296|issue:45800", "issue:43701|issue:45325", "issue:44568|issue:45920", - "issue:43606|issue:43819", "issue:41720|issue:45823", - "issue:44186|issue:44265", + "issue:43606|issue:43819", "issue:43454|issue:43550", - "issue:43262|issue:43746", - "issue:46305|issue:46315", - "issue:39692|issue:40444", - "issue:43881|issue:44488", - "issue:43377|issue:44610", - "issue:43454|issue:45072" + "issue:44186|issue:44265", + "issue:43262|issue:43746" ], - "prepared_review_unit_hash": "1f6a7df3ba618392caa71c40f63842b8f5d3f30ec3770e06d363ae496c816824", + "prepared_review_unit_hash": "951d5c8b1c57bfb37f10309458e091959a5af984e4269457bc5a199749fd0981", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37162, - "estimated_input_tokens": 9291, - "estimated_eval_tokens": 18838 + "soft_pair_count": 32, + "serialized_chars": 37503, + "estimated_input_tokens": 9376, + "estimated_eval_tokens": 19008 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: most items are distinct regressions or docs/model-specific bugs, not true duplicates. I did not find any soft pair that looks like the same concrete bug/change.", - "confidence": 0.93, - "canonical_issue_reason": "No single canonical issue stands out; the items span unrelated failure modes (model loading/init, multimodal preprocessing, tokenizer behavior, device-map, and docs issues).", + "summary": "This cluster is mostly a grab bag of unrelated Transformers v5 regression reports across tokenizers, model loading/init, multimodal position IDs, device maps, and memory behavior. The soft edges are mostly theme-level similarities, not same underlying bugs, so they should all be rejected.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43646 is the broadest representative of the v5 model-initialization regression family, which is the closest shared thread among the cluster items, even though the cluster is still heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "If a representative issue is needed, issue:43611 is the broadest v5 loading/init regression in the set, but it is still not a good duplicate anchor for the whole cluster.", + "best_issue_reason": "issue:43646 is the best umbrella issue because it is generic, high-impact, and closest to the common v5 loading/initialization breakages represented here.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both concern TensorFlow/backend packaging, but one is an install-extra omission and the other is a runtime backend detection error; different bugs." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "AutoTokenizer/Voxtral error messaging and an Apple Silicon allocator TypeError are unrelated code paths." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both mention batching-related incorrect outputs, but they affect different models and different mechanisms (padding mask vs sliding-window/all-padding NaNs)." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 device-map CUDA assert and a Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Both are v5 regressions, but sliding-window handling and init_empty_weights argument handling are distinct bugs." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export failures via torch_compilable_check and bfloat16 dtype mismatches are different failure modes." + }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are v5 loading/init regressions, but they describe different code paths and symptoms (base_model_prefix loading vs custom model initialization)." + "reason": "Both are loading/init regressions, but base_model_prefix handling and custom model initialization are not the same concrete bug." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "Different problems: `_is_hf_initialized` flag handling vs dtype mismatches in bfloat16 inference." + "reason": "_is_hf_initialized breakage and bfloat16 dtype mismatch are unrelated." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "Both are vision-model issues, but one is SigLIP2 output quality and the other is Perceiver resolution handling; not the same bug." + "reason": "Different vision-model bugs on different architectures; no shared concrete code path." }, { "left": "issue:42175", "right": "issue:43296", "accept": false, - "reason": "Unrelated: missing TensorFlow backend in installation vs PaddleOCR-VL model load failure in vLLM." + "reason": "Packaging/backends versus model-loading compatibility in vLLM are separate issues." }, { "left": "issue:45325", "right": "issue:45834", "accept": false, - "reason": "Both involve multimodal position/index logic, but they target different models and different failure modes." + "reason": "Both affect multimodal models, but one is a Qwen2.5-VL rope-index scaling bug and the other is a Kosmos2.5 OCR index error." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper runtime failure and meta-device loading breakage are distinct issues." + "reason": "Whisper runtime failure and meta-device loading breakage are unrelated." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Both mention tied lm_head weights, but one is a model-specific untied-weight generation bug and the other is device-dependent serialization inconsistency." + "reason": "Both mention tied lm_head weights, but one is a missing tie causing bad generation and the other is a serialization inconsistency depending on device." }, { "left": "issue:44079", "right": "issue:44534", "accept": false, - "reason": "Different internal regressions: ModelOutput key assignment vs non-persistent buffer initialization." + "reason": "ModelOutput key assignment and non-persistent buffer initialization are different internal behaviors." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Different model families and different failures: FP8 config crash vs GGUF loading in v5." + "reason": "Qwen3MoE FP8 config failure and Qwen2.5-GGUF loading failure are unrelated." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "One is finetuning with multiple images per prompt; the other is video vision-position-id regression." + "reason": "Both involve Qwen2.5-VL multimodal inputs, but multi-image iterable finetuning and video position_id calculation are distinct bugs." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Same model family, but one bug is still-image temporal scaling and the other is video position-id computation." + "reason": "Both are Qwen2.5-VL position-id issues, but one is still-image temporal scaling and the other is video-input vision_position_ids; not the same fix." }, { "left": "issue:43644", "right": "issue:44079", "accept": false, - "reason": "These are separate v5 regressions with different code paths: buffer junk filling vs ModelOutput key handling." + "reason": "Non-persistent buffer junk and ModelOutput key assignment are unrelated." }, { - "left": "issue:35707", - "right": "issue:40444", + "left": "issue:43761", + "right": "issue:44079", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to multi-image IterableDataset finetuning." + "reason": "CLIPVisionModel hidden_states regression and ModelOutput key assignment are different problems." }, { - "left": "issue:43761", - "right": "issue:44079", + "left": "issue:44387", + "right": "issue:44617", "accept": false, - "reason": "Different issues: CLIPVision hidden_states omission vs ModelOutput key bookkeeping." + "reason": "General int4 memory growth and a Sam3Video OOM are not the same underlying bug." }, { - "left": "issue:44479", - "right": "issue:45823", + "left": "issue:35707", + "right": "issue:40444", "accept": false, - "reason": "Both are forward-pass regressions, but one is Qwen video input handling and the other is Gemma4 device-map mismatch." + "reason": "Progressive generation with inputs_embeds/past_key_values and multi-image finetuning failures are unrelated." }, { - "left": "issue:44387", - "right": "issue:44617", + "left": "issue:44479", + "right": "issue:45823", "accept": false, - "reason": "Both mention OOM, but the contexts are different (int4 quantization memory growth vs Sam3Video workload size)." + "reason": "Qwen video-input regression and Gemma4 PLE device mismatch are different model-specific bugs." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "Device-mismatch under CPU offload is unrelated to torch.export failing on torch_compilable_check." + "reason": "CPU offload device mismatch and torch.export failures via torch_compilable_check are unrelated." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "Both involve loading/configuration in v5, but one is an init_empty_weights argument error and the other is strict config validation for granite_speech." + "reason": "Unexpected init_empty_weights argument and strict config loading for granite_speech are different loading issues." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "Different failures: PaddleOCR-VL model loading in vLLM vs torch/transformers version incompatibility." + "reason": "PaddleOCR-VL loading in vLLM and torch/transformers version incompatibility are too broad and not the same concrete bug." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "resume_from_checkpoint key mismatch is unrelated to Qwen2.5-VL rope index scaling." + "reason": "resume_from_checkpoint key mismatch and Qwen2.5-VL rope-index scaling are unrelated." }, { "left": "issue:44568", "right": "issue:45920", "accept": false, - "reason": "Tokenizer special-token insertion regression and AutoTokenizer wrong token IDs are different bugs." - }, - { - "left": "issue:43606", - "right": "issue:43819", - "accept": false, - "reason": "Device-mismatch offload bug and DAC from_latents forward mismatch are unrelated." + "reason": "Both are tokenizer regressions in v5, but one is missing special tokens on one tokenizer and the other is wrong token IDs across multiple tokenizers." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Both are device-related, but one is a CUDA assert during auto-mapping and the other is a forward device mismatch in Gemma4 PLE." + "reason": "Both mention device mapping, but one is a CUDA assert in Qwen3 and the other is a forward-time device mismatch in Gemma4 PLE." }, { - "left": "issue:44186", - "right": "issue:44265", + "left": "issue:43606", + "right": "issue:43819", "accept": false, - "reason": "Tokenizer padding/crash issues are not the same as export-time torch_compilable_check failures." + "reason": "CPU offload device mismatch and DAC.from_latents/forward divergence are unrelated." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "Tied lm_head weight handling and Bamba torch.compile SDPA failure are different code paths." - }, - { - "left": "issue:43262", - "right": "issue:43746", - "accept": false, - "reason": "Audio chat-template sampling-rate defaulting is unrelated to GraniteSpeech PEFT checkpoint loading." + "reason": "lm_head tying/generation issues and Bamba torch.compile SDPA failure are different bugs." }, { - "left": "issue:46305", - "right": "issue:46315", + "left": "issue:44186", + "right": "issue:44265", "accept": false, - "reason": "Different regressions: sliding-window mask off-by-one vs tokenizer speed slowdown." + "reason": "LayoutLMv2 tokenizer padding/NER crashes and torch.export torch_compilable_check failures are unrelated." }, { - "left": "issue:39692", - "right": "issue:40444", + "left": "issue:43262", + "right": "issue:43746", "accept": false, - "reason": "Doc example errors for SigLIP2 are unrelated to Qwen2.5-VL finetuning failures." - }, - { - "left": "issue:43881", - "right": "issue:44488", - "accept": false, - "reason": "Both are load failures, but they affect different models and likely different breakpoints." - }, - { - "left": "issue:43377", - "right": "issue:44610", - "accept": false, - "reason": "Padding-mask batching bug in MIMI encoder and OmDet-Turbo processor/model size mismatch are not the same issue." - }, - { - "left": "issue:43454", - "right": "issue:45072", - "accept": false, - "reason": "Different regression classes: tied-weight generation bug vs dtype mismatch in inference." + "reason": "Audio chat-template sampling-rate defaulting and GraniteSpeech PEFT checkpoint loading are separate issues." } ] }, @@ -3865,17 +3862,19 @@ "component_index": 1, "component_count": 18, "review_unit_index": 12, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:34634", "issue:35707", "issue:36331", + "issue:39692", + "issue:40444", "issue:40990", "issue:41720", "issue:42175", @@ -3899,11 +3898,10 @@ "issue:43883", "issue:44008", "issue:44186", - "issue:44387", "issue:44423", "issue:44466", + "issue:44488", "issue:44610", - "issue:44756", "issue:44877", "issue:44898", "issue:44977", @@ -3914,16 +3912,21 @@ "issue:45406", "issue:45584", "issue:45701", - "issue:45704", "issue:45759", "issue:45823", "issue:45923", "issue:46291", + "issue:46305", "issue:46315" ], "soft_pairs": [ - "issue:40990|issue:45584", + "issue:46305|issue:46315", + "issue:39692|issue:40444", + "issue:43881|issue:44488", + "issue:43377|issue:44610", + "issue:43454|issue:45072", "issue:43257|issue:45923", + "issue:40990|issue:45584", "issue:43317|issue:43873", "issue:43572|issue:45759", "issue:40990|issue:42947", @@ -3931,15 +3934,15 @@ "issue:43873|issue:45701", "issue:43454|issue:43720", "issue:45325|issue:46315", - "issue:41720|issue:44977", "issue:44466|issue:45357", + "issue:41720|issue:44977", "issue:44991|issue:46291", "issue:43526|issue:43883", "issue:42617|issue:42915", "issue:35707|issue:41720", - "issue:34634|issue:35707", "issue:43881|issue:44991", "issue:43577|issue:43708", + "issue:34634|issue:35707", "issue:44008|issue:45823", "issue:43404|issue:45357", "issue:43450|issue:45701", @@ -3947,227 +3950,206 @@ "issue:44877|issue:44991", "issue:43550|issue:43720", "issue:36331|issue:42915", - "issue:44423|issue:45406", "issue:36331|issue:42617", "issue:42175|issue:46291", - "issue:43873|issue:44756", - "issue:44387|issue:45704", - "issue:44610|issue:44898" + "issue:44423|issue:45406" ], - "prepared_review_unit_hash": "2029289e1886fc47f77d098db7050cb38076f8c3223590eeb35b5c344df1feed", + "prepared_review_unit_hash": "a2bb4f298566693659b5741f85135524198ccb6e257728c15b8d532b1ba39293", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36692, - "estimated_input_tokens": 9173, - "estimated_eval_tokens": 18602 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37946, + "estimated_input_tokens": 9487, + "estimated_eval_tokens": 19230 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is a loose collection of unrelated bug reports; there is no strong duplicate cluster. The closest theme is offloading/quantization/loading behavior, but the paired items still describe different concrete failures and should not be merged.", - "confidence": 0.91, - "canonical_issue_reason": "43873 is the broadest representative issue in the set, centered on offloading/quantization behavior and closest to the few related candidates.", + "summary": "This cluster is mostly a set of unrelated Transformers bugs that only share broad themes like loading, offloading, multimodal models, or dtype/config issues. I found no soft pair that clearly describes the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43873 is the broadest and most central umbrella in this noisy cluster: it covers offloading/quantization behavior, which is the closest shared theme among the nearby loading/offload reports.", "canonical_pr_reason": null, - "best_issue_reason": "43873 is the best umbrella representative for triage because it is open, broad, and nearest to the recurring device/offload/quantization theme.", + "best_issue_reason": "Issue 43873 is the best representative issue because it is open, clearly actionable, and has the widest scope among the candidates without being tied to a single narrow model or example.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:40990", - "right": "issue:45584", + "left": "issue:46305", + "right": "issue:46315", + "accept": false, + "reason": "One is a Moonshine streaming mask off-by-one bug; the other is tokenizer slowdown with many added tokens. Different code paths and symptoms." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc example errors and Qwen2.5-VL IterableDataset failures are different multimodal scenarios with different failure modes." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading failures, but they target different models and likely different model-specific config/tokenizer issues." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI batched-output inconsistency from padding masks is unrelated to OmDet-Turbo\u2019s processor/model image-size mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", "accept": false, - "reason": "Different models and failures: perplexity evaluation vs Whisper empty-transcription generation." + "reason": "One is a tied-weights serialization bug; the other is a bfloat16 dtype mismatch in inference. Same broad area, but not the same defect." }, { "left": "issue:43257", "right": "issue:45923", "accept": false, - "reason": "Unrelated root causes: MoE weight conversion/loading vs missing gradient-checkpointing flag." + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and Nemotron gradient-checkpointing metadata are unrelated implementation issues." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on GPT-OSS and Whisper empty-transcription generation failure are different model/task bugs." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both mention offloading, but one is dequantized model loading on CPU/GPU offload while the other is a broader quantization/offloading complaint." + "reason": "Both mention offloading/quantization, but one is a device_map loading failure and the other is a broader offloading regression; not clearly the same bug." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "StableLm config pad_token_idx regression is unrelated to Qwen multimodal text_config unwrapping." + "reason": "StableLm pad_token_idx config regression and Qwen composite-config unwrapping are separate config-loading problems." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "Perplexity anomaly and gradient-checkpointing behavior are different bugs." + "reason": "Perplexity regression and LoRA gradient-checkpointing ineffectiveness are unrelated trainer/model-behavior bugs." }, { "left": "issue:43377", "right": "issue:44898", "accept": false, - "reason": "Both are shape/batching-related, but they affect different models and different preprocessing paths." + "reason": "Both involve image-processing behavior, but one is batched-padding support and the other is non-default image resolution handling." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Quantization/offloading behavior is unrelated to tokenizer version-dependent tokenization changes." + "reason": "Quantized offloading behavior and tokenization changes across versions are different subsystems and failure modes." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Tied lm_head weights and unpacking packed weights are different model-loading issues." + "reason": "Tied-weight serialization and packed-weight unpacking on accelerate load are different weight-management bugs." }, { "left": "issue:45325", "right": "issue:46315", "accept": false, - "reason": "RoPE index scaling bug is unrelated to tokenizer conversion performance." + "reason": "Qwen2.5-VL rope index scaling and tokenizer conversion slowdown are unrelated; one is multimodal positional math, the other is tokenizer performance." }, { - "left": "issue:41720", - "right": "issue:44977", + "left": "issue:44466", + "right": "issue:45357", "accept": false, - "reason": "Different Qwen versions and different failure modes: CUDA assert during auto device mapping vs flash-attention generation issues." + "reason": "Inconsistent lm_head serialization by device and incorrect visual encoder keys in Qwen3.5 save_pretrained are both save issues, but not the same underlying bug." }, { - "left": "issue:44466", - "right": "issue:45357", + "left": "issue:41720", + "right": "issue:44977", "accept": false, - "reason": "Both involve save/serialization, but one is tied-weight serialization and the other is incorrect visual encoder keys." + "reason": "Both involve Qwen3.5/auto device mapping/flash-attention, but one is a cudaErrorAssert on A800 and the other is generation misbehavior with flash-attention." }, { "left": "issue:44991", "right": "issue:46291", "accept": false, - "reason": "Tokenizer loading failure and kernels import/version-revision failure are unrelated." + "reason": "Tokenizer loading for a specific model and evaluate import failing due to kernels metadata are unrelated package-loading issues." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BEiT label reduction bug is unrelated to Molmo tied-weights metadata." + "reason": "BeitImageProcessorFast label reduction and Molmo tied-weights metadata are entirely different components." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "3d_parallel script execution failure and Qwen3Moe FP8 loading failure are different code paths." + "reason": "A 3d_parallel.py runtime problem and a Qwen3Moe FP8 configuration failure are different execution paths and bugs." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen auto device-mapping CUDA asserts." - }, - { - "left": "issue:34634", - "right": "issue:35707", - "accept": false, - "reason": "Voice preset handling in BarkProcessor is unrelated to generation with inputs_embeds and past_key_values." + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device mapping cudaErrorAssert." }, { "left": "issue:43881", "right": "issue:44991", "accept": false, - "reason": "Different failure domains: GLM model loading vs tokenizer loading." + "reason": "Different failing artifacts and different error classes: model loading for glm-4v-9b versus tokenizer loading for est-roberta." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Dtype propagation in Blip2 loading is unrelated to resume_from_checkpoint max_steps calculation." + "reason": "BLIP2 dtype propagation and Trainer resume/max_steps accounting are separate bugs in different subsystems." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset and progressive generation with past_key_values do not describe the same code path or symptom." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma-family multimodal issues, but one is a variable-name collision in forward and the other is a device mismatch in PLE forward." + "reason": "Gemma3n variable-name collision in forward and Gemma4 PLE device mismatch are distinct model-specific forward bugs." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Tied lm_head weights in Mistral3 is unrelated to Qwen3.5 visual encoder save keys." - }, - { - "left": "issue:43450", - "right": "issue:45701", - "accept": false, - "reason": "Video processor batch-shape bug is unrelated to tokenizer changes across versions." + "reason": "Mistral3 tied lm_head weights and Qwen3.5 visual encoder save keys are different model serialization/tie-weight issues." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer padding/truncation crashes and bf16 dtype mismatches are different bugs." + "reason": "LayoutLMv2 tokenizer crashes and bfloat16 dtype mismatches are unrelated tokenizer versus inference-type bugs." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Strict config loading for granite_speech is unrelated to est-roberta tokenizer loading." - }, - { - "left": "issue:43550", - "right": "issue:43720", - "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to accelerate loading of packed BitNet weights." - }, - { - "left": "issue:36331", - "right": "issue:42915", - "accept": false, - "reason": "Trainer compute_loss signature incompatibility is unrelated to Qwen3Moe FP8 loading." - }, - { - "left": "issue:44423", - "right": "issue:45406", - "accept": false, - "reason": "Both crash in serve with multimodal processors, but the concrete failures and code paths differ." - }, - { - "left": "issue:36331", - "right": "issue:42617", - "accept": false, - "reason": "Trainer loss-signature API mismatch is unrelated to the 3d_parallel script failure." - }, - { - "left": "issue:42175", - "right": "issue:46291", - "accept": false, - "reason": "Backend installation omission and kernels version/revision import failure are unrelated." - }, - { - "left": "issue:43873", - "right": "issue:44756", - "accept": false, - "reason": "Both involve memory/offload concerns, but Strix Halo mmap OOM is a platform-specific OOM issue, not the same quantization offloading bug." - }, - { - "left": "issue:44387", - "right": "issue:45704", - "accept": false, - "reason": "CUDA reserved-memory growth under int4 quantization is unrelated to T5 apex RMSNorm memory leak." + "reason": "Strict config loading for granite_speech and tokenizer loading for est-roberta are separate config/tokenizer compatibility issues." }, { - "left": "issue:44610", - "right": "issue:44898", + "left": "issue:43450", + "right": "issue:45701", "accept": false, - "reason": "Different vision preprocessing bugs: OmDet-Turbo output size mismatch vs Perceiver non-default resolution interpolation failure." + "reason": "Batched video processor shape bug and tokenizer behavior changes across versions are unrelated." } ] }, @@ -4183,13 +4165,13 @@ "component_index": 1, "component_count": 18, "review_unit_index": 13, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:29159", "issue:30064", @@ -4214,19 +4196,19 @@ "issue:43572", "issue:43606", "issue:43653", - "issue:43720", "issue:43749", "issue:43782", + "issue:43873", "issue:43881", "issue:44186", "issue:44361", - "issue:44492", - "issue:44509", - "issue:44530", + "issue:44387", "issue:44534", "issue:44610", "issue:44671", "issue:44743", + "issue:44756", + "issue:44898", "issue:44913", "issue:45081", "issue:45161", @@ -4235,17 +4217,20 @@ "issue:45632", "issue:45684", "issue:45701", - "issue:45759", + "issue:45704", "issue:45812", "issue:46050", "issue:46291" ], "soft_pairs": [ + "issue:43873|issue:44756", + "issue:44387|issue:45704", + "issue:44610|issue:44898", "issue:43749|issue:44534", - "issue:43550|issue:43606", "issue:44186|issue:44610", - "issue:43322|issue:46050", + "issue:43550|issue:43606", "issue:45632|issue:45684", + "issue:43322|issue:46050", "issue:42915|issue:43317", "issue:43295|issue:45701", "issue:41720|issue:43322", @@ -4256,251 +4241,226 @@ "issue:43425|issue:46291", "issue:45081|issue:45812", "issue:43525|issue:46291", - "issue:43316|issue:44913", "issue:43531|issue:43572", - "issue:44671|issue:44743", + "issue:43316|issue:44913", "issue:43540|issue:43782", + "issue:44671|issue:44743", "issue:43421|issue:45812", "issue:44186|issue:44361", "issue:43526|issue:43881", "issue:29159|issue:36032", "issue:45406|issue:45464", - "issue:30064|issue:34634", "issue:43550|issue:43653", - "issue:43606|issue:43720", - "issue:43421|issue:45701", - "issue:44530|issue:46291", - "issue:42915|issue:43322", - "issue:43606|issue:43653", - "issue:43531|issue:45759", - "issue:44492|issue:44509" + "issue:30064|issue:34634" ], - "prepared_review_unit_hash": "4eb16ac09f90c101275c24ce9cca3f2d3be9a001d582cd98fe67386038111736", + "prepared_review_unit_hash": "83f4e29f240462dc7f97da6179a8e36a3888a9eeb8ca8fe755b8d3bd069e5034", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37419, - "estimated_input_tokens": 9355, - "estimated_eval_tokens": 18966 + "soft_pair_count": 29, + "serialized_chars": 36120, + "estimated_input_tokens": 9030, + "estimated_eval_tokens": 18316 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Heterogeneous cluster of mostly unrelated Transformers issues. The only common thread is broad tokenization/model-loading regressions, but none of the soft pairs look like the same underlying bug or change.", - "confidence": 0.82, - "canonical_issue_reason": "Issue 45812 is the strongest cluster representative: it describes a concrete, broad tokenizer regression affecting all Granite models and is more actionable than the more generic or model-specific reports.", + "summary": "The cluster is mostly a set of superficially similar but actually unrelated regression reports across tokenizers, model loading, quantization/offloading, and vision processors. I do not see any soft pair that clearly describes the same underlying bug or a PR that could plausibly cover both sides, so all soft edges should be rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents the cluster; the items are too heterogeneous to normalize around one canonical bug.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45812 is the best single issue to anchor the cluster because it is specific, regression-oriented, and spans a wider surface than most others in the set.", + "best_issue_reason": "No strong best issue candidate. If forced, issue 45701 is the broadest tokenizer-regression report, but it does not subsume the rest of the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43749", - "right": "issue:44534", + "left": "issue:43873", + "right": "issue:44756", "accept": false, - "reason": "CPU RAM-efficient loading breakage is a different failure mode from non-persistent buffer corruption; they affect different code paths." + "reason": "Both are offload/memory-related, but one is general quantization offloading and the other is a Strix Halo mmap OOM workaround; different bugs and fixes." }, { - "left": "issue:43550", - "right": "issue:43606", + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both mention memory, but one is an int4 CUDA reserved-memory/OOM regression and the other is a T5-specific apex FusedRMSNorm leak; not the same code path." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are image-size/preprocessing mismatches, but they affect different model families and different processor/model contracts." + }, + { + "left": "issue:43749", + "right": "issue:44534", "accept": false, - "reason": "One is a torch.compile SDPA issue on Bamba, the other is a CPU offload device mismatch on Bark; not the same bug." + "reason": "Both are v5 regressions, but one is FSDP CPU RAM efficient loading and the other is non-persistent buffer initialization; too different to merge." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "LayoutLMv2 tokenizer crashes on NER/padding, while OmDet-Turbo has an image-size mismatch; unrelated symptoms and components." + "reason": "LayoutLMv2 tokenizer crashes on task padding/truncation; OmDet-Turbo is a processor resolution mismatch. Unrelated failure modes." }, { - "left": "issue:43322", - "right": "issue:46050", + "left": "issue:43550", + "right": "issue:43606", "accept": false, - "reason": "Llava Next segfault on load is not the same as sinq quantization save/load corruption." + "reason": "Different models and runtime paths: torch.compile+SDPA vs CPU offload device mismatch." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache path collisions and read-only permission propagation are distinct filesystem issues." + "reason": "Both touch filesystem behavior, but cache-path collisions and read-only permission propagation are distinct bugs." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Segfault loading Llava Next is unrelated to sinq save/load breakage." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure and dequantized model CPU/GPU offload loading are different quantization/loading problems." + "reason": "Different quantization/offload failures on different models; no shared concrete defect." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor/tokenizer regression in v4.57.5 is not the same as a general claim that version changes tokenization." + "reason": "Both involve tokenization regressions, but one is processor.tokenizer/API breakage and the other is a broad tokenization-change report; not the same issue." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Auto device mapping cuda assert on Qwen3 and a Llava Next load segfault are separate model-loading failures." + "reason": "CUDA assert on Qwen3 auto device mapping is unrelated to Llava Next segfaults." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "High perplexity on GPT-OSS is a model quality/regression report, not the same as a tokenization version discrepancy." + "reason": "High perplexity could be caused by many things; the report does not match the broader tokenization-change issue concretely." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Qwen3 auto device mapping failure and inability to run 3d_parallel.py are unrelated." + "reason": "Different models and different distributed/runtime failures." }, { "left": "issue:41720", "right": "issue:45161", "accept": false, - "reason": "Auto device-map cuda errors and TP-only GPT-OSS MoE failures are different parallelism issues." + "reason": "Both mention parallelism/device mapping, but the concrete failures and affected models differ." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "GenerationMixin import breakage is unrelated to the 3d_parallel.py execution problem." + "reason": "GenerationMixin import failure is unrelated to not being able to run 3d_parallel.py." }, { "left": "issue:43425", "right": "issue:46291", "accept": false, - "reason": "Torch version incompatibility and kernels import requirements are different dependency issues." + "reason": "Both are dependency-compatibility issues, but Torch 2.10 incompatibility and kernels version/revision requirements are unrelated." }, { "left": "issue:45081", "right": "issue:45812", "accept": false, - "reason": "Mistral regex patch crashing during tokenizer load is a different tokenizer path than the Granite token-ID regression." + "reason": "Both are tokenizer regressions, but one is a Mistral regex patch crash and the other is wrong Granite token IDs; different models and fixes." }, { "left": "issue:43525", "right": "issue:46291", "accept": false, - "reason": "Missing pad_token_id on Llama4Config is unrelated to evaluate/kernels import version constraints." - }, - { - "left": "issue:43316", - "right": "issue:44913", - "accept": false, - "reason": "Gemma3TextConfig API mismatch and GPTNeoX rotary_pct reload behavior are different config serialization issues." + "reason": "A missing pad_token_id config field is unrelated to the kernels import/version error." }, { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and StableLm pad_token_idx regression are unrelated model/config bugs." + "reason": "Both are config-related, but sliding_window behavior and missing pad_token_idx are separate API issues." }, { - "left": "issue:44671", - "right": "issue:44743", + "left": "issue:43316", + "right": "issue:44913", "accept": false, - "reason": "CamemBERT masked-LM prediction errors and Qwen3.5 recurrent state resets do not share the same code path." + "reason": "Config API inconsistency for Gemma3TextConfig is not the same as GPTNeoX rotary_pct not persisting on reload." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Video-input processing errors in Qwen3OmniMoe are not the same as weight_only loading failures in Qwen3VL." + "reason": "Both are Qwen3 multimodal loading/processing issues, but one is video input handling and the other is weight_only from_pretrained failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM predictions and Qwen3.5 recurrent-state reset are completely different model behaviors." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Runtime special-token post-processor updates and Granite wrong token IDs are both tokenizer-related, but they are different bugs." + "reason": "Runtime post-processor updates for special tokens are not the same bug as Granite token IDs being wrong." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "LayoutLMv2 tokenizer NER/padding crashes and MLukeTokenizer AttributeError are separate tokenizer implementations and failures." + "reason": "Different tokenizer implementations, different task failures, and different exception modes." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "BeitImageProcessorFast label reduction and glm-4v-9b loading failure are unrelated image-processing/model-loading issues." + "reason": "BEiT reduce_labels behavior is unrelated to glm-4v-9b loading failure." }, { "left": "issue:29159", "right": "issue:36032", "accept": false, - "reason": "Slow-vs-fast tokenizer inconsistency is broader and different from the T5Tokenizer add_special_tokens name conflict." + "reason": "General slow/fast tokenizer inconsistency does not match the specific T5 add_special_tokens load conflict." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Gemma4Processor missing _tokenizer crashes transformers serve, while the Qwen3.5 streaming issue is a separate serving/runtime problem." + "reason": "Gemma4Processor _tokenizer missing and Qwen3.5 streaming API failure are unrelated." }, { - "left": "issue:30064", - "right": "issue:34634", + "left": "issue:45632", + "right": "issue:45684", "accept": false, - "reason": "Void segmentation map processing and BarkProcessor voice_preset are unrelated processor bugs." + "reason": "Cache-path collision and read-only permission propagation are distinct filesystem issues." }, { "left": "issue:43550", "right": "issue:43653", "accept": false, - "reason": "torch.compile/SDPA failure is unrelated to BigBirdTokenizer mask token registration and decode behavior." - }, - { - "left": "issue:43606", - "right": "issue:43720", - "accept": false, - "reason": "CPU offload device mismatch and packed-weights unpacking during accelerate loading are different loading/quantization issues." - }, - { - "left": "issue:43421", - "right": "issue:45701", - "accept": false, - "reason": "Special-token post-processor update bug is not the same as a broad tokenization-version complaint." - }, - { - "left": "issue:44530", - "right": "issue:46291", - "accept": false, - "reason": "PagedAttentionCache linear_attention failure is unrelated to the kernels version/revision import error." - }, - { - "left": "issue:42915", - "right": "issue:43322", - "accept": false, - "reason": "Qwen3Moe FP8 config failure and Llava Next segfault are different model-specific problems." - }, - { - "left": "issue:43606", - "right": "issue:43653", - "accept": false, - "reason": "CPU offload device mismatch is unrelated to BigBirdTokenizer special-token decode issues." - }, - { - "left": "issue:43531", - "right": "issue:45759", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and AutoModelForCausalLM config unwrapping are different code paths." + "reason": "torch.compile+SDPA failure in Bamba is unrelated to BigBirdTokenizer special-token registration." }, { - "left": "issue:44492", - "right": "issue:44509", + "left": "issue:30064", + "right": "issue:34634", "accept": false, - "reason": "A cache-strategy typo and docs mentioning removed pipeline tasks are not the same issue." + "reason": "Image processor void-segmentation-map handling and Bark voice_preset behavior share no underlying bug." } ] }, @@ -4516,315 +4476,301 @@ "component_index": 1, "component_count": 18, "review_unit_index": 14, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:33666", "issue:34567", - "issue:34634", "issue:35707", "issue:39692", "issue:41720", "issue:42490", "issue:42886", + "issue:42915", + "issue:43322", "issue:43329", "issue:43381", "issue:43388", "issue:43421", - "issue:43525", "issue:43531", - "issue:43540", + "issue:43606", "issue:43653", + "issue:43720", "issue:43746", "issue:43844", "issue:43873", "issue:43927", "issue:44062", - "issue:44186", "issue:44368", "issue:44451", + "issue:44492", + "issue:44509", "issue:44514", + "issue:44530", "issue:44545", "issue:44589", "issue:44610", "issue:44843", "issue:44898", - "issue:44918", - "issue:44936", "issue:44987", "issue:44991", "issue:45042", "issue:45059", "issue:45072", - "issue:45081", - "issue:45356", "issue:45357", "issue:45588", "issue:45663", + "issue:45701", "issue:45704", "issue:45759", "issue:45859", "issue:45923", - "issue:46294" + "issue:46291" ], "soft_pairs": [ + "issue:43606|issue:43720", + "issue:44530|issue:46291", + "issue:43421|issue:45701", + "issue:42915|issue:43322", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:44492|issue:44509", "issue:34567|issue:35707", "issue:43388|issue:45059", - "issue:44514|issue:44545", "issue:43873|issue:45704", + "issue:44514|issue:44545", "issue:42490|issue:43329", "issue:41720|issue:43746", "issue:43421|issue:43927", - "issue:33666|issue:35707", "issue:44898|issue:45072", "issue:45759|issue:45859", "issue:44451|issue:44991", + "issue:33666|issue:35707", "issue:43531|issue:44589", "issue:45588|issue:45759", "issue:44368|issue:45357", - "issue:44062|issue:44451", "issue:44987|issue:45042", + "issue:44062|issue:44451", "issue:39692|issue:44610", "issue:45704|issue:45923", "issue:43421|issue:43653", - "issue:43381|issue:43844", "issue:45663|issue:45923", "issue:42886|issue:44843", - "issue:44918|issue:44936", - "issue:45704|issue:45859", - "issue:34634|issue:41720", - "issue:43421|issue:44186", - "issue:43381|issue:45704", - "issue:43525|issue:43531", - "issue:45081|issue:45356", - "issue:43540|issue:46294", - "issue:39692|issue:43873" + "issue:43381|issue:43844" ], - "prepared_review_unit_hash": "6c71dab0bba49a38a5841e3a158114bb99eb18667c386446b0e37541a3cbdfd6", + "prepared_review_unit_hash": "c2f4914fdf8e57da1fb6d65ae8e138aaac61444de01d214565ded4cf5e9cd076", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36896, - "estimated_input_tokens": 9224, - "estimated_eval_tokens": 18704 + "soft_pair_count": 29, + "serialized_chars": 36188, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Only one strong duplicate pair stands out: the two Qwen2_5_VLProcessor.apply_chat_template padding=False issues. The rest are mostly unrelated bugs across different models/subsystems and should not be merged as duplicates.", - "confidence": 0.92, - "canonical_issue_reason": "issue:44545 is the cleanest representative of the exact Qwen2_5_VLProcessor batched-input/padding=False crash and has slightly more linkage, making it the better canonical issue.", + "summary": "This cluster is mostly heterogeneous, with one clear issue duplicate pair around Qwen2_5_VLProcessor batching; the rest are unrelated model/loading/tokenizer/training bugs and should not be merged together.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 44514 is the cleanest canonical: it is the earlier, more explicit report of the exact same Qwen2_5_VLProcessor.apply_chat_template batched-input/padding=False crash as 44545.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44545 is the best overall issue in this cluster because it most precisely describes the shared bug in the only true duplicate pair.", + "best_issue_reason": "44514 is the best representative issue because it precisely states the bug and has an exact duplicate in 44545; the remaining items are largely unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Different models and failure modes: CPU offload device mismatch vs unpacked packed weights during accelerate loading." + }, + { + "left": "issue:44530", + "right": "issue:46291", + "accept": false, + "reason": "Unrelated: Qwen3.5 PagedAttentionCache crash vs kernels import/version requirement in evaluate." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Both mention tokenization, but one is a runtime special-token post-processor bug and the other is a broad version-regression report." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Different code paths and symptoms: Qwen3Moe FP8 config failure vs Llava Next load segfault." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen configs, but one is a sliding-window issue and the other is missing text_config unwrapping for composite multimodal configs." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Completely different subsystems: model offload/device mismatch vs tokenizer special-token registration." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo fix and a docs cleanup are not the same underlying bug." + }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "Different failures in different trainer paths: token counting state vs progressive generation with inputs_embeds/past_key_values." + "reason": "TrainerState token counting and progressive generation with past_key_values are unrelated issues." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "Different subsystems and symptoms: distributed metric gathering label handling vs SAM3 text/box behavior." - }, - { - "left": "issue:44514", - "right": "issue:44545", - "accept": true, - "reason": "Same concrete bug: Qwen2_5_VLProcessor.apply_chat_template crashes on batched input when padding=False." + "reason": "Different areas: metrics gathering tuple handling vs SAM3 text/box behavior." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Quantization/offloading mismatch is unrelated to a T5 RMSNorm memory leak." + "reason": "Quantization/offloading behavior is unrelated to the T5 apex RMSNorm memory leak." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Exact same Qwen2_5_VLProcessor.apply_chat_template batched-input crash when padding=False; clearly the same bug." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "Local-path slash import warning is unrelated to a multimodal token-counting video-branch bug." + "reason": "Local-path slash import warning is unrelated to a multimodal token-counting video-branch NameError." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "Qwen3 auto device-map CUDA assert is unrelated to GraniteSpeech PEFT local checkpoint loading." + "reason": "Different failures: auto device mapping cudaErrorAssert vs PEFT adapter checkpoint loading." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Runtime special-token post-processor update bug is unrelated to DiaConfig losing custom token IDs on save/load." - }, - { - "left": "issue:33666", - "right": "issue:35707", - "accept": false, - "reason": "Multi-GPU training for Qwen2-VL is unrelated to generation with inputs_embeds and past_key_values." + "reason": "Both are tokenizer/config related, but one is runtime post-processor refresh and the other is save/load token-ID loss." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Perceiver non-default resolution failure is unrelated to SwitchTransformers/TimmWrapperModel dtype mismatch." + "reason": "Image resolution handling and bfloat16 dtype mismatches are different bugs." }, { "left": "issue:45759", "right": "issue:45859", "accept": false, - "reason": "Composite Qwen config unwrapping is unrelated to Qwen3_5MoE rotary embedding CPU offload." + "reason": "Composite-config unwrapping and CPU-offload rotary embedding compatibility are separate Qwen issues." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Loading a specific model fails for different tokenizer/config reasons; not the same bug." + "reason": "Both are tokenizer load failures, but they affect different models and likely different root causes." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL is unrelated to inputs_embeds/past_key_values generation behavior." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to the Float8 storage lookup error." + "reason": "Sliding-window support and missing Float8 storage are unrelated." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Flash-attention sink handling bug is unrelated to Qwen 3.5/3.6 multimodal config unwrapping." + "reason": "Flash-attention sink-less crash is unrelated to multimodal text_config unwrapping." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "Config warning about tie_word_embeddings is unrelated to incorrect visual encoder keys in save_pretrained." + "reason": "A warning about tie_word_embeddings is not the same as incorrect visual encoder keys in save_pretrained." }, { - "left": "issue:44062", - "right": "issue:44451", + "left": "issue:44987", + "right": "issue:45042", "accept": false, - "reason": "AddedToken special-argument conflict is unrelated to loading a specific pretrained model." + "reason": "Loading a specific model failing in v5.1.0 and PIL processors wrongly requiring torchvision are different bugs." }, { - "left": "issue:44987", - "right": "issue:45042", + "left": "issue:44062", + "right": "issue:44451", "accept": false, - "reason": "Tokenizer/model loading regression is unrelated to PIL image processors requiring torchvision." + "reason": "AddedToken special-argument collision and ScandiBERT loading failure are not the same code-path." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "SigLIP2 docs errors are unrelated to OmDet-Turbo processor/model image-size mismatch." + "reason": "Both mention processor/model mismatches, but they concern different models and distinct preprocessing errors." }, { "left": "issue:45704", "right": "issue:45923", "accept": false, - "reason": "Apex RMSNorm memory leak is unrelated to missing supports_gradient_checkpointing on a trust_remote_code model." + "reason": "A memory leak in T5 RMSNorm and a missing supports_gradient_checkpointing flag are unrelated." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Tokenizer post-processor update bug is unrelated to BigBirdTokenizer mask-token registration/empty decode issue." - }, - { - "left": "issue:43381", - "right": "issue:43844", - "accept": false, - "reason": "Gradient checkpointing eval-mode restriction is unrelated to DeepSpeed ZeRO-3 gradient growth." + "reason": "Special-token post-processor refresh and BigBirdTokenizer mask-token registration are different tokenizer bugs." }, { "left": "issue:45663", "right": "issue:45923", "accept": false, - "reason": "Gemma4 FSDP2 shared_kv_states bug is unrelated to Nemotron-3-Nano-Omni gradient-checkpointing flag omission." + "reason": "Gemma4 FSDP2 KeyError and a trust_remote_code capability flag issue are unrelated." }, { "left": "issue:42886", "right": "issue:44843", "accept": false, - "reason": "Offline cache tokenizer loading failure is unrelated to mistral regex patch calling model_info unconditionally." - }, - { - "left": "issue:44918", - "right": "issue:44936", - "accept": false, - "reason": "Qwen3.5 SFT unpacking issue is unrelated to trainer.evaluate failing after trainer.train." - }, - { - "left": "issue:45704", - "right": "issue:45859", - "accept": false, - "reason": "RMSNorm memory leak in T5 is unrelated to Qwen3_5MoE CPU offload incompatibility." - }, - { - "left": "issue:34634", - "right": "issue:41720", - "accept": false, - "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping are different model-specific bugs." - }, - { - "left": "issue:43421", - "right": "issue:44186", - "accept": false, - "reason": "Tokenizer backend post-processor update bug is unrelated to LayoutLMv2 NER/batched padding crashes." + "reason": "Both involve HF_HUB_OFFLINE, but one is a general cache-load failure and the other is a specific model_info() call in _patch_mistral_regex." }, { "left": "issue:43381", - "right": "issue:45704", - "accept": false, - "reason": "Gradient checkpointing eval-mode restriction is unrelated to T5 RMSNorm memory leak." - }, - { - "left": "issue:43525", - "right": "issue:43531", - "accept": false, - "reason": "Missing pad_token_id on Llama4Config is unrelated to Qwen3-MoE sliding_window behavior." - }, - { - "left": "issue:45081", - "right": "issue:45356", - "accept": false, - "reason": "Mistral regex crash on tokenizer loading is related to tokenizer patching but not the same as the Kimi-K2.5 codec/regression report." - }, - { - "left": "issue:43540", - "right": "issue:46294", - "accept": false, - "reason": "Qwen3OmniMoe video-input ValueError and Qwen3.5-9B video token mismatch are different video-processing failures." - }, - { - "left": "issue:39692", - "right": "issue:43873", + "right": "issue:43844", "accept": false, - "reason": "SigLIP2 doc example issues are unrelated to quantization/offloading behavior." + "reason": "Gradient checkpointing in eval mode and DeepSpeed ZeRO-3 gradient inflation are separate training bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only clearly duplicate pair is issue:44514 / issue:44545, and the rest of the soft-edge rejections are consistent with the issue titles and descriptions. Canonical/best-issue selection is also supported by the slightly higher linkage on issue:44545." + "feedback": "The summary is grounded in the packet: 44514/44545 are an exact title match and a credible duplicate pair, and the remaining verdicts are conservative rejections of clearly different issues. I don\u2019t see any overstatement of evidence." }, "evaluator_used": true, "retried": false, @@ -4837,71 +4783,80 @@ "component_index": 1, "component_count": 18, "review_unit_index": 15, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:30064", + "issue:34634", "issue:36010", + "issue:39692", + "issue:41720", "issue:42915", "issue:43295", - "issue:43335", + "issue:43381", "issue:43388", "issue:43421", + "issue:43525", "issue:43531", "issue:43540", "issue:43550", "issue:43596", "issue:43618", - "issue:43643", "issue:43653", "issue:43697", "issue:43716", "issue:43720", "issue:43746", - "issue:43756", "issue:43782", "issue:43819", "issue:43873", - "issue:43950", "issue:43994", "issue:44008", - "issue:44062", "issue:44077", "issue:44186", "issue:44220", - "issue:44488", "issue:44625", "issue:44661", "issue:44671", - "issue:44811", - "issue:44843", - "issue:44877", "issue:44898", + "issue:44918", + "issue:44936", "issue:45072", "issue:45081", "issue:45183", "issue:45356", "issue:45381", "issue:45479", + "issue:45704", "issue:45834", + "issue:45859", "issue:45907", - "issue:45987", "issue:46032", - "issue:46050" + "issue:46050", + "issue:46294" ], "soft_pairs": [ + "issue:44918|issue:44936", + "issue:45704|issue:45859", + "issue:34634|issue:41720", + "issue:43421|issue:44186", + "issue:43381|issue:45704", + "issue:43525|issue:43531", + "issue:45081|issue:45356", + "issue:43540|issue:46294", + "issue:39692|issue:43873", "issue:44625|issue:45479", "issue:43782|issue:45381", - "issue:45356|issue:45907", "issue:43994|issue:44671", - "issue:43746|issue:46050", + "issue:45356|issue:45907", "issue:43720|issue:43819", "issue:30064|issue:36010", + "issue:43746|issue:46050", "issue:44077|issue:44625", "issue:43596|issue:44220", "issue:43653|issue:43720", @@ -4916,231 +4871,222 @@ "issue:45183|issue:45479", "issue:43388|issue:46032", "issue:44186|issue:44898", - "issue:43335|issue:43756", - "issue:43716|issue:44008", - "issue:44062|issue:44488", - "issue:43653|issue:43819", - "issue:43531|issue:43643", - "issue:44843|issue:45081", - "issue:43950|issue:45987", - "issue:43643|issue:44877", - "issue:43421|issue:44811", - "issue:43540|issue:45381" + "issue:43716|issue:44008" ], - "prepared_review_unit_hash": "60e1449be85798848ae9b983ef463237b7af30b778dbd919d2b741d7984466a2", + "prepared_review_unit_hash": "37c8d9ec912e7225b32bebddde86cfaf385cf1490f1ada9fdb521d205fdd9c27", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 37453, - "estimated_input_tokens": 9364, - "estimated_eval_tokens": 18984 + "serialized_chars": 37250, + "estimated_input_tokens": 9313, + "estimated_eval_tokens": 18882 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly heterogeneous: the soft-similarity pairs span different models, APIs, and failure modes, so there are no strong duplicate merges here. I would keep the cluster anchored on one concrete, well-documented bug report rather than merging across these pairs.", + "summary": "The cluster is highly heterogeneous and does not contain any clear duplicate pair; most items are unrelated bug reports across different models, tokenizers, trainers, and quantization/offload paths. Best representative issue is the broad, active quantization/offloading report.", "confidence": 0.91, - "canonical_issue_reason": "issue:46032 is the strongest representative in this set: it has a clear, concrete code-path failure, active discussion, and inbound references, making it the best anchor for the cluster. The other issues are largely orthogonal or model-specific.", + "canonical_issue_reason": "issue:43873 is the most central and broadly phrased report, with the highest discussion and reference activity in this set, so it is the best cluster anchor despite the cluster not being a true duplicate group.", "canonical_pr_reason": null, - "best_issue_reason": "issue:46032 is the most actionable and clearly reproduced bug here, with the strongest signal that it represents a real underlying defect worth deduplicating against if a matching report appears.", + "best_issue_reason": "issue:43873 is the strongest representative issue because it is active, widely discussed, and covers a general runtime behavior problem rather than a narrow model-specific edge case.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Both mention trainer-related failures, but one is about Qwen3.5 input embeddings unpacking and the other is about evaluate-after-train behavior; different bugs and code paths." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "T5 Apex RMSNorm memory leak and Qwen3_5MoE CPU offload incompatibility are unrelated model/runtime issues." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice preset handling and Qwen3 auto device mapping CUDA asserts are unrelated subsystems and failure modes." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "One is about TokenizersBackend not refreshing post-processing after runtime special-token changes; the other is a LayoutLMv2Tokenizer crash on NER padding/truncation." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing in eval mode and a T5 RMSNorm memory leak are distinct issues with no shared concrete code path." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are different configuration bugs." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both involve tokenizer regex/codec handling, but the reports target different models and different concrete failures; not the same bug." + }, + { + "left": "issue:43540", + "right": "issue:46294", + "accept": false, + "reason": "Both are video-input issues, but one is a Qwen3OmniMoe ValueError and the other is a Qwen3.5 chat-template token/feature mismatch; different failure points." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 documentation example errors and quantization/offloading behavior are unrelated." + }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Both involve labels/classification, but one is a config propagation bug and the other is a loss-function regression across sequence-classification models; different underlying defects." + "reason": "Qwen3.5 num_labels propagation and the zero-loss single-label-classification bug are different configuration problems across different model families." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Different models and different failure modes: a Qwen3VL load/error path versus a video-input vision_position_ids bug in Qwen2.5-VL." - }, - { - "left": "issue:45356", - "right": "issue:45907", - "accept": false, - "reason": "Completely unrelated topics: tokenizer regression for Kimi-K2.5 versus hub API forwarding of revision in list_repo_files." + "reason": "Qwen3VL weight_only loading failure and Qwen2.5-VL video vision_position_ids mismatch are different multimodal bugs." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Both are wrong-output reports, but they concern different models and likely different root causes; too broad to treat as the same bug." + "reason": "Different models and different symptoms: SigLIP2 nonsensical outputs vs CamemBERT masked-LM prediction regression." }, { - "left": "issue:43746", - "right": "issue:46050", + "left": "issue:45356", + "right": "issue:45907", "accept": false, - "reason": "Both are load/save related, but one is PEFT adapter loading and the other is quantized model persistence; different code paths and symptoms." + "reason": "Kimi tokenizer regression/warning and list_repo_files revision forwarding are unrelated." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "Different model families and failures: packed-weight loading versus DAC latent conversion / missing STE behavior." + "reason": "BitNet packed-weight loading and DAC from_latents/STE mismatch are separate model implementation issues." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "No meaningful overlap: image processor segmentation-map handling versus a GenerationMixin import error." + "reason": "Image segmentation-map processing and a GenerationMixin import error are entirely unrelated." + }, + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "PEFT adapter checkpoint loading and sinq quantized save/load breakage are different persistence/loading bugs." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "One is about patchtsmixer post_init policy, the other about num_labels propagation; unrelated implementation bugs." + "reason": "Optional post_init policy for patchtsmixer and Qwen3.5 num_labels propagation are unrelated." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "Different subsystems entirely: DeepSpeed/BertModel initialization versus audio feature extraction." + "reason": "DeepSpeed ZeRO3/BertModel initialization and _torch_extract_fbank_features are unrelated paths." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "Tokenizer special-token registration bug versus BitNet packed-weight unpacking; not the same underlying issue." + "reason": "BigBirdTokenizer special-token registration and BitNet packed-weight loading are unrelated tokenizer vs model-loading issues." }, { "left": "issue:42915", "right": "issue:43746", "accept": false, - "reason": "Different models and components: Qwen3Moe FP8 configuration versus GraniteSpeech PEFT checkpoint loading." + "reason": "Qwen3Moe FP8 config failure and GraniteSpeech PEFT checkpoint loading are different model-specific problems." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Both are multimodal, but one is a Qwen3OmniMoe video-processing ValueError and the other is a Gemma3n variable-name collision; not duplicates." + "reason": "Qwen3OmniMoe video-input processing and Gemma3n forward variable collision are unrelated multimodal bugs." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio fbank extraction and add-new-model-like / TOKENIZER_MAPPING_NAMES logic are unrelated." + "reason": "Audio feature extraction and add-new-model-like/tokenizer-mapping logic are different code paths." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "One is a CLIPOutput field omission, the other is RTDetrV2 behavioral drift in v5; different bug classes." + "reason": "CLIPOutput attentions assignment and RTDetrV2 output differences in v5 are different regression reports." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Different dtype/compile problems in different models and execution paths; too broad to merge." + "reason": "Bamba torch.compile/SDPA failure and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." }, { "left": "issue:43746", "right": "issue:43873", "accept": false, - "reason": "Checkpoint loading with PEFT adapters is distinct from offloading/quantization behavior." + "reason": "PEFT adapter checkpoint loading and quantization/offloading behavior do not describe the same underlying bug." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Processor/tokenizer regression and long OCR index error are different model-specific failures." + "reason": "Processor.tokenizer regression and Kosmos2.5 OCR index errors are different model/input-processing issues." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "torch.compile/SDPA failure versus DAC.from_latents mismatch; unrelated code paths." + "reason": "Different failure modes: compiled SDPA on Bamba vs DAC latent reconstruction mismatch." }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "One is input validation/error-message logic, the other is a zero-loss regression; not the same defect." + "reason": "Validation error messaging for input_ids/inputs_embeds and degenerate zero loss are separate classification issues." }, { "left": "issue:43388", "right": "issue:46032", "accept": false, - "reason": "Metric-gathering label truncation and Mamba2 cache correctness are unrelated training/runtime bugs." + "reason": "gather_for_metrics label truncation and Mamba2Mixer use_cache correctness are unrelated trainer vs model logic bugs." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Tokenizer crash on NER padding/truncation versus Perceiver image-classification resolution handling; different subsystems." - }, - { - "left": "issue:43335", - "right": "issue:43756", - "accept": false, - "reason": "SwitchTransformers sparse-layer creation and Smollm3 RoPE-layer retention are separate architecture/config issues." + "reason": "LayoutLMv2Tokenizer batching crash and Perceiver non-default resolution interpolation failure are different model/tokenizer issues." }, { "left": "issue:43716", "right": "issue:44008", "accept": false, - "reason": "Different failures: dtype mismatch between image preprocessor/model versus an audio_mel_mask attribute collision." - }, - { - "left": "issue:44062", - "right": "issue:44488", - "accept": false, - "reason": "AddedToken keyword conflict is unrelated to loading a specific tokenizer/model checkpoint." - }, - { - "left": "issue:43653", - "right": "issue:43819", - "accept": false, - "reason": "Tokenizer special-token registration and DAC latent/forward mismatch are different domains and code paths." - }, - { - "left": "issue:43531", - "right": "issue:43643", - "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and trust_remote_code AutoConfig field loss are unrelated." - }, - { - "left": "issue:44843", - "right": "issue:45081", - "accept": false, - "reason": "Both mention _patch_mistral_regex, but the failures are different: unconditional model_info offline breakage versus backend_tokenizer AttributeError when fix_mistral_regex=True." - }, - { - "left": "issue:43950", - "right": "issue:45987", - "accept": false, - "reason": "Non-persistent buffer corruption on from_pretrained is unrelated to StaticCache.get_seq_length returning the wrong type." - }, - { - "left": "issue:43643", - "right": "issue:44877", - "accept": false, - "reason": "One is missing fields with trust_remote_code; the other is strict config blocking granite_speech loading. Similar area, different bug." - }, - { - "left": "issue:43421", - "right": "issue:44811", - "accept": false, - "reason": "Tokenizers post-processor refresh and Whisper batch_decode skip_special_tokens handling are different tokenizer/processor issues." - }, - { - "left": "issue:43540", - "right": "issue:45381", - "accept": false, - "reason": "Different Qwen video/multimodal bugs with distinct symptoms and likely different fixes." + "reason": "Mistral-3 image-preprocessor dtype mismatch and Gemma3n variable-name collision are unrelated bugs." } ] }, @@ -5156,296 +5102,274 @@ "component_index": 1, "component_count": 18, "review_unit_index": 16, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ - "issue:28218", - "issue:29159", "issue:30064", "issue:34634", "issue:36010", "issue:36331", "issue:39692", - "issue:42175", "issue:43322", - "issue:43404", - "issue:43452", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", "issue:43577", "issue:43582", "issue:43606", - "issue:43720", + "issue:43643", + "issue:43653", + "issue:43756", "issue:43782", "issue:43818", + "issue:43819", "issue:43825", - "issue:43827", - "issue:43906", + "issue:43950", "issue:43994", + "issue:44062", "issue:44186", "issue:44442", "issue:44448", "issue:44479", "issue:44485", + "issue:44488", "issue:44509", "issue:44561", - "issue:44610", "issue:44671", - "issue:44805", + "issue:44811", "issue:44821", - "issue:44857", - "issue:44936", + "issue:44843", + "issue:44877", "issue:44977", - "issue:44991", "issue:45020", "issue:45072", "issue:45081", "issue:45084", - "issue:45406", + "issue:45381", "issue:45584", "issue:45685", - "issue:45701", "issue:45834", "issue:45987", - "issue:46192", - "issue:46209" + "issue:46192" ], "soft_pairs": [ + "issue:43335|issue:43756", + "issue:44062|issue:44488", + "issue:43653|issue:43819", + "issue:43531|issue:43643", + "issue:43950|issue:45987", + "issue:44843|issue:45081", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:43540|issue:45381", "issue:44448|issue:44671", "issue:30064|issue:36331", "issue:43782|issue:44977", "issue:43577|issue:43818", "issue:39692|issue:45834", "issue:45584|issue:45834", - "issue:43322|issue:45685", "issue:44821|issue:45084", + "issue:43322|issue:45685", "issue:43606|issue:45072", "issue:44479|issue:45834", "issue:43825|issue:43994", "issue:44186|issue:44442", "issue:34634|issue:36010", "issue:44485|issue:44509", - "issue:45987|issue:46192", "issue:44561|issue:45020", - "issue:28218|issue:29159", - "issue:43577|issue:43582", - "issue:44805|issue:44936", - "issue:44610|issue:45072", - "issue:43720|issue:45072", - "issue:43452|issue:44991", - "issue:43825|issue:43827", - "issue:43582|issue:44857", - "issue:43404|issue:43782", - "issue:45081|issue:45406", - "issue:43906|issue:46209", - "issue:42175|issue:45081", - "issue:44671|issue:45701" + "issue:45987|issue:46192", + "issue:43577|issue:43582" ], - "prepared_review_unit_hash": "043c74d4b979f660fe2ed2c46ac891204510c233e12c5691e3d08f7505008e9a", + "prepared_review_unit_hash": "7478ce8b898c320bdf3c2613aa948ac94e1b35ee7188f0cd7f937fe3cab345e7", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36406, - "estimated_input_tokens": 9102, - "estimated_eval_tokens": 18460 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35067, + "estimated_input_tokens": 8767, + "estimated_eval_tokens": 17790 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly a loose set of regression reports sharing broad themes like tokenization, v5 behavior changes, and model-loading issues, but they do not form a strong duplicate cluster. I found no soft edge that clearly meets the bar for the same concrete bug/change.", - "confidence": 0.77, - "canonical_issue_reason": "issue:45701 is the broadest and most central report here, with the highest inbound reference count and a title that can serve as an umbrella for tokenizer-version regressions.", + "summary": "The set is mostly a collection of unrelated issue reports; the soft-similarity pairs are largely false positives across different models, tokenizer behaviors, or API regressions. The closest thematic cluster is the remote_code/config-loading regressions, for which the broadest representative is issue #45020.", + "confidence": 0.4, + "canonical_issue_reason": "#45020 is the broadest umbrella report in the only clear thematic cluster (remote_code-related breakages), so it is the best representative issue title for triage.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the best representative issue in this set because it is broad, well-referenced, and closest to the recurring tokenizer/version-regression theme.", + "best_issue_reason": "#45020 best captures the shared remote_code regression theme while remaining broad enough to represent adjacent config-loading breakages without being overly narrow.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44448", - "right": "issue:44671", - "accept": false, - "reason": "Both are version-related output regressions, but they affect different models and different code paths; too broad to be the same bug." - }, - { - "left": "issue:30064", - "right": "issue:36331", - "accept": false, - "reason": "Image segmentation-map processing and trainer compute_loss signature errors are unrelated." - }, - { - "left": "issue:43782", - "right": "issue:44977", - "accept": false, - "reason": "Different models, different failure modes, and different subsystems; no shared concrete bug." - }, - { - "left": "issue:43577", - "right": "issue:43818", + "left": "issue:43335", + "right": "issue:43756", "accept": false, - "reason": "One is a dtype-loading issue in BLIP2, the other is a missing temporal-attention/weight-sharing problem in Video-LLaVA." + "reason": "Different bugs: sparse-layer construction in SwitchTransformersConfig vs Smollm3 RoPE-layer dropping; no shared concrete code path." }, { - "left": "issue:39692", - "right": "issue:45834", + "left": "issue:44062", + "right": "issue:44488", "accept": false, - "reason": "Doc-example errors for SigLIP2 and long-input OCR index errors in Kosmos2.5 are not the same underlying problem." + "reason": "One is an AddedToken argument duplication error; the other is a model load failure for cjvt/sleng-bert. Same tokenizer area, but different root causes." }, { - "left": "issue:45584", - "right": "issue:45834", + "left": "issue:43653", + "right": "issue:43819", "accept": false, - "reason": "Whisper empty-transcription generation and Kosmos2.5 OCR indexing are unrelated." + "reason": "BigBird special-token decoding bug vs DAC latent/STE mismatch; unrelated behavior and fix surface." }, { - "left": "issue:43322", - "right": "issue:45685", + "left": "issue:43531", + "right": "issue:43643", "accept": false, - "reason": "Llava Next segfault and an MPS histogram dtype error in moe are different bugs." + "reason": "Qwen3-MoE sliding-window handling and remote_code config-field loss are different problems in different subsystems." }, { - "left": "issue:44821", - "right": "issue:45084", + "left": "issue:43950", + "right": "issue:45987", "accept": false, - "reason": "AutoImageProcessor URL loading and template-compilation failure are unrelated." + "reason": "Both are regressions, but one corrupts non-persistent buffers in from_pretrained and the other returns the wrong type from StaticCache.get_seq_length()." }, { - "left": "issue:43606", - "right": "issue:45072", + "left": "issue:44843", + "right": "issue:45081", "accept": false, - "reason": "Both mention runtime mismatches, but they involve different models and different failure causes; not mergeable into one fix." + "reason": "Both involve _patch_mistral_regex, but one is an offline hub lookup issue and the other is an AttributeError on tokenizer object shape; not the same bug." }, { - "left": "issue:44479", - "right": "issue:45834", + "left": "issue:43643", + "right": "issue:44877", "accept": false, - "reason": "Different model families and different regression types; only loosely similar because both are input-processing bugs." + "reason": "Both touch config loading, but one returns incomplete AutoConfig data while the other rejects strict granite_speech loading; distinct failures." }, { - "left": "issue:43825", - "right": "issue:43994", + "left": "issue:43421", + "right": "issue:44811", "accept": false, - "reason": "One is an error-message/docs issue around removed translation tasks, the other is a model output regression; not the same bug." + "reason": "Runtime special-token/post-processor updates and Whisper batch_decode skip_special_tokens handling are different code paths." }, { - "left": "issue:44186", - "right": "issue:44442", + "left": "issue:43540", + "right": "issue:45381", "accept": false, - "reason": "Both are tokenizer-loading/usage issues, but they concern different tokenizers and different failure modes." + "reason": "Both are video-input bugs, but they affect different Qwen model families and have different symptoms/root causes." }, { - "left": "issue:34634", - "right": "issue:36010", + "left": "issue:44448", + "right": "issue:44671", "accept": false, - "reason": "BarkProcessor voice_preset behavior and a GenerationMixin import error are unrelated." + "reason": "Pegasus v4/v5 output mismatch and CamemBERT masked-LM regressions are separate model-specific issues." }, { - "left": "issue:44485", - "right": "issue:44509", + "left": "issue:30064", + "right": "issue:36331", "accept": false, - "reason": "RoPE implementation discussion and docs still mentioning removed pipeline tasks do not share a concrete code-path bug." + "reason": "Void segmentation-map processing and CustomTrainer.compute_loss signature changes are unrelated." }, { - "left": "issue:45987", - "right": "issue:46192", + "left": "issue:43782", + "right": "issue:44977", "accept": false, - "reason": "StaticCache return type and text_kwargs/return_tensors handling are separate API bugs." + "reason": "Qwen3VL weight_only loading failure and Qwen3.5 flash-attention generation issues are different concrete bugs." }, { - "left": "issue:44561", - "right": "issue:45020", + "left": "issue:43577", + "right": "issue:43818", "accept": false, - "reason": "Both relate to remote_code breakage in v5, but 45020 is a broad umbrella and 44561 is a specific missing-function regression; not clearly the same defect." + "reason": "Blip2 dtype propagation and Video-LLaVA tower initialization/weight-sharing are not the same underlying defect." }, { - "left": "issue:28218", - "right": "issue:29159", + "left": "issue:39692", + "right": "issue:45834", "accept": false, - "reason": "Both involve tokenizer behavior, but one is a specific added-token spacing bug and the other is a broad slow/fast inconsistency report." + "reason": "SigLIP2 docs/example errors and Kosmos2.5 long-OCR index errors are unrelated." }, { - "left": "issue:43577", - "right": "issue:43582", + "left": "issue:45584", + "right": "issue:45834", "accept": false, - "reason": "BLIP2 dtype mismatch and AppleSilicon caching_allocator_warmup TypeError are unrelated." + "reason": "Whisper empty-transcription generation and Kosmos2.5 OCR indexing are different model-specific failures." }, { - "left": "issue:44805", - "right": "issue:44936", + "left": "issue:44821", + "right": "issue:45084", "accept": false, - "reason": "Mask shape IndexError and trainer.evaluate() failing after training are different issues." + "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." }, { - "left": "issue:44610", - "right": "issue:45072", + "left": "issue:43322", + "right": "issue:45685", "accept": false, - "reason": "Processor image-size mismatch and bfloat16 dtype mismatch are different code paths." + "reason": "Llava Next load segfault and MPS histogram_mps integer support error are different bugs." }, { - "left": "issue:43720", + "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading and dtype mismatch in inference are separate bugs." + "reason": "Both are CI/device-dtype regressions, but they affect different mechanisms and models; not a single fixable bug." }, { - "left": "issue:43452", - "right": "issue:44991", + "left": "issue:44479", + "right": "issue:45834", "accept": false, - "reason": "Both are loading failures, but one is about gguf_file handling in from_pretrained and the other is tokenizer loading for a specific model under v5." + "reason": "Qwen video-input regression and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:43825", - "right": "issue:43827", + "right": "issue:43994", "accept": false, - "reason": "Both touch pipeline v5 removals, but one is an error message and the other is stale docs; they would not plausibly merge into one PR." + "reason": "One is a stale pipeline error message/docs issue; the other is incorrect inference output for SigLIP2." }, { - "left": "issue:43582", - "right": "issue:44857", + "left": "issue:44186", + "right": "issue:44442", "accept": false, - "reason": "AppleSilicon warmup TypeError and CUDA AMP float16 crash are unrelated hardware/runtime issues." + "reason": "LayoutLMv2 NER/padding crash and AutoTokenizer loading FastSpeech2ConformerTokenizer are distinct tokenizer issues." }, { - "left": "issue:43404", - "right": "issue:43782", + "left": "issue:34634", + "right": "issue:36010", "accept": false, - "reason": "Mistral3 weight tying and Qwen3VL weight_only loading are different model-specific regressions." + "reason": "BarkProcessor voice_preset handling and GenerationMixin import failure are unrelated." }, { - "left": "issue:45081", - "right": "issue:45406", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "A Mistral tokenizer regex patch crash and a Gemma4Processor _tokenizer attribute error are not the same bug." + "reason": "GLM-5 RoPE implementation discussion and docs mentioning removed pipeline tasks are not the same bug or change." }, { - "left": "issue:43906", - "right": "issue:46209", + "left": "issue:44561", + "right": "issue:45020", "accept": false, - "reason": "An isolated reproduction of an older issue and an FP8/B200 inference problem are unrelated." + "reason": "Both mention remote_code breakage, but #44561 is a specific is_torch_fx_available regression while #45020 is a broader umbrella report." }, { - "left": "issue:42175", - "right": "issue:45081", + "left": "issue:45987", + "right": "issue:46192", "accept": false, - "reason": "Backend installation packaging and Mistral tokenizer regex handling are different areas entirely." + "reason": "Both are API regressions around tokenizer/cache inputs, but they affect different parameters and code paths." }, { - "left": "issue:44671", - "right": "issue:45701", + "left": "issue:43577", + "right": "issue:43582", "accept": false, - "reason": "CamemBERT masked-LM output drift and a general tokenization-change report are too different in scope and mechanism." + "reason": "Blip2 dtype propagation and Apple Silicon caching_allocator_warmup TypeError are unrelated." } ] }, @@ -5461,31 +5385,26 @@ "component_index": 1, "component_count": 18, "review_unit_index": 17, - "review_unit_count": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ - "issue:34634", - "issue:36010", - "issue:36331", - "issue:38175", - "issue:39692", - "issue:43257", + "issue:28218", + "issue:29159", + "issue:42175", "issue:43262", "issue:43329", - "issue:43454", + "issue:43404", + "issue:43452", "issue:43526", - "issue:43531", "issue:43550", - "issue:43577", + "issue:43582", "issue:43638", - "issue:43643", "issue:43644", - "issue:43645", "issue:43650", "issue:43653", "issue:43697", @@ -5493,278 +5412,572 @@ "issue:43742", "issue:43746", "issue:43749", + "issue:43782", "issue:43819", - "issue:43854", + "issue:43825", + "issue:43827", "issue:43906", - "issue:43927", "issue:44060", - "issue:44291", "issue:44368", - "issue:44554", "issue:44589", "issue:44610", + "issue:44671", + "issue:44805", "issue:44811", + "issue:44857", "issue:44912", "issue:44936", - "issue:44977", + "issue:44991", "issue:45003", "issue:45020", "issue:45042", + "issue:45072", + "issue:45081", "issue:45084", - "issue:45459", + "issue:45406", "issue:45538", "issue:45600", - "issue:45759", - "issue:45803", + "issue:45701", + "issue:46209", "issue:46285" ], "soft_pairs": [ - "issue:43262|issue:43819", - "issue:45003|issue:46285", - "issue:43526|issue:43697", - "issue:43653|issue:44912", - "issue:44060|issue:44368", - "issue:43650|issue:43906", - "issue:43742|issue:45020", - "issue:45084|issue:45538", + "issue:28218|issue:29159", + "issue:44610|issue:45072", + "issue:44805|issue:44936", + "issue:43720|issue:45072", + "issue:43452|issue:44991", + "issue:43825|issue:43827", + "issue:43582|issue:44857", + "issue:43404|issue:43782", + "issue:45081|issue:45406", + "issue:42175|issue:45081", + "issue:43906|issue:46209", + "issue:44671|issue:45701", + "issue:43262|issue:43819", + "issue:45003|issue:46285", + "issue:43526|issue:43697", + "issue:43653|issue:44912", + "issue:44060|issue:44368", + "issue:43650|issue:43906", + "issue:43742|issue:45020", + "issue:45084|issue:45538", "issue:43329|issue:45600", "issue:43746|issue:44811", - "issue:43644|issue:43749", "issue:44589|issue:45042", + "issue:43644|issue:43749", "issue:43638|issue:44936", - "issue:43550|issue:44912", - "issue:43819|issue:43927", - "issue:34634|issue:36331", - "issue:43854|issue:44977", - "issue:39692|issue:44912", - "issue:38175|issue:44610", - "issue:36010|issue:43645", - "issue:43720|issue:44610", - "issue:45459|issue:45803", - "issue:43454|issue:43577", - "issue:43526|issue:44554", - "issue:36010|issue:36331", - "issue:43262|issue:44811", - "issue:43749|issue:44291", - "issue:43531|issue:45042", - "issue:43257|issue:43329", - "issue:43643|issue:45759" + "issue:43550|issue:44912" ], - "prepared_review_unit_hash": "515588f8868a93dd25def96dd2acdb501da8f8e76a40d1add9fe9fae24d78bcb", + "prepared_review_unit_hash": "ca3302152f2befd319661c03425339072a01ebcea43316ffd1689a8c0648c9d8", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 37019, - "estimated_input_tokens": 9255, - "estimated_eval_tokens": 18766 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35118, + "estimated_input_tokens": 8780, + "estimated_eval_tokens": 17816 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a heterogeneous mix of unrelated bugs; none of the proposed soft pairs looks like the same concrete underlying issue, so all soft edges should be rejected.", - "confidence": 0.94, - "canonical_issue_reason": "Issue 45020 is the broadest and most representative loading-regression report in the set, but the cluster is too mixed to treat any pair as a true duplicate group.", + "summary": "The items are mostly unrelated one-off issues; only one soft edge looks plausibly duplicate-level from titles alone. The rest appear to be distinct bugs affecting different models, loaders, or runtime paths.", + "confidence": 0.58, + "canonical_issue_reason": "issue:45020 is the best high-signal, broadly scoped regression report in this set; it is concrete enough to be actionable and broad enough to represent a wider breakage class.", "canonical_pr_reason": null, - "best_issue_reason": "45020 is the best cluster anchor because it is the most general current regression report; the others are narrow, model-specific edge cases rather than duplicates of it.", + "best_issue_reason": "issue:45020 has the clearest user-facing regression framing and the broadest applicability among these unrelated issues, so it is the strongest canonical candidate.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer spacing/inconsistency regression around added tokens; 29159 is the broader formulation of the same bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Different subsystems and failure modes: image size mismatch vs bfloat16 dtype mismatch." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "An indexing shape error during masking is unrelated to evaluate-after-train behavior." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading in BitNet is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading, but the concrete failure modes and affected code paths differ." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "One is an incorrect runtime error message, the other is stale docs; related topic, not the same bug." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon allocator TypeError and CUDA AMP loss crash are separate issues." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Different model families and distinct loading/tie-weight problems." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Different attributes, different components, and different model/processor paths." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend packaging mismatch is unrelated to Mistral regex patching." + }, + { + "left": "issue:43906", + "right": "issue:46209", + "accept": false, + "reason": "A reproduction of one earlier issue is not the same as an FP8 inference failure." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "Generic tokenization changes are too broad to be the same as CamemBERT masked-LM prediction regressions." + }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Both are audio-related, but one is chat-template sampling-rate handling and the other is a DAC latent/STE correctness bug; different code paths." + "reason": "Audio sampling-rate defaulting and DAC latent reconstruction are unrelated." }, { "left": "issue:45003", "right": "issue:46285", "accept": false, - "reason": "Both involve modeling internals, but one is unsafe sys.modules access and the other is CLIP text-model structure changes; not the same bug." + "reason": "Unsafe sys.modules access is a different problem from CLIP text model structure inconsistency." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "BEiT label reduction and RTDetrV2 output drift are separate vision-model issues with no shared concrete failure mode." + "reason": "Label-reduction bug in BEIT preprocessing is unrelated to RTDetrV2 output drift." }, { "left": "issue:43653", "right": "issue:44912", "accept": false, - "reason": "Tokenizer special-token registration is unrelated to MXFP4 quantization loading behavior." + "reason": "Tokenizer special-token registration and MXFP4 quantization fallback are unrelated." }, { "left": "issue:44060", "right": "issue:44368", "accept": false, - "reason": "Both mention tied-weights warnings, but they concern different models and different underlying warnings, so they are not duplicates." + "reason": "Both mention tied-weight warnings, but the models and concrete failure descriptions differ enough that this is not clearly the same bug." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "A vague placeholder issue is unrelated to an isolated reproduction of another bug." + "reason": "Placeholder issue text is unrelated to a technical reproduction report." }, { "left": "issue:43742", "right": "issue:45020", "accept": false, - "reason": "A specific MobileLLM loading KeyError is not the same concrete issue as the broader remote_code regression." + "reason": "MobileLLM loading key errors are not the same as broad remote_code breakage." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "These are unrelated: template-node compilation versus tokenizer max length defaults." + "reason": "Template compilation errors and tokenizer max-length configuration are different issues." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "One is a missing video-token-count implementation path; the other is stale auto-mapping config references." + "reason": "Multimodal token counting bug and auto_mappings CI breakage do not share the same underlying defect." }, { "left": "issue:43746", "right": "issue:44811", "accept": false, - "reason": "PEFT local-checkpoint loading and Whisper batch decoding are unrelated code paths." + "reason": "Checkpoint loading with PEFT adapters is unrelated to Whisper batch_decode skipping special tokens." }, { - "left": "issue:43644", - "right": "issue:43749", + "left": "issue:44589", + "right": "issue:45042", "accept": false, - "reason": "Non-persistent buffer junk and FSDP CPU RAM-efficient loading are both loading-related, but not the same bug or fix." + "reason": "Float8 storage lookup failure and torchvision dependency regression are separate." }, { - "left": "issue:44589", - "right": "issue:45042", + "left": "issue:43644", + "right": "issue:43749", "accept": false, - "reason": "Float8 storage lookup failure is unrelated to PIL image processor torchvision requirements." + "reason": "Non-persistent buffer junk filling and FSDP CPU RAM efficient loading are different loading bugs." }, { "left": "issue:43638", "right": "issue:44936", "accept": false, - "reason": "Zero3/non-pretrained-Bert index errors and train-then-evaluate failure are different trainer/runtime problems." + "reason": "DeepSpeed ZeRO3 index error is unrelated to trainer.evaluate failing after train." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "torch.compile/SDPA failures are unrelated to MXFP4 quantization fallback behavior." + "reason": "Torch.compile/SDPA failure and MXFP4 quantization fallback are unrelated model execution paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted soft edge (28218/29159) is plausibly duplicate-level from the titles, while the other pairs are reasonably rejected as distinct bugs. Canonical issue choice is also defensible within this mixed set." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 18, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:29159", + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:42490", + "issue:42915", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43645", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44977", + "issue:45042", + "issue:45356", + "issue:45372", + "issue:45459", + "issue:45701", + "issue:45759", + "issue:45803", + "issue:45859", + "issue:46326" + ], + "soft_pairs": [ + "issue:45372|issue:46326", + "issue:43819|issue:43927", + "issue:34634|issue:36331", + "issue:43854|issue:44977", + "issue:39692|issue:44912", + "issue:36010|issue:43645", + "issue:38175|issue:44610", + "issue:43720|issue:44610", + "issue:45459|issue:45803", + "issue:43454|issue:43577", + "issue:43526|issue:44554", + "issue:36010|issue:36331", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43257|issue:43329", + "issue:43643|issue:45759", + "issue:42490|issue:43257", + "issue:43329|issue:43450", + "issue:43606|issue:45859", + "issue:34567|issue:40990", + "issue:44568|issue:45356", + "issue:29159|issue:34567", + "issue:43329|issue:44479", + "issue:42915|issue:43742", + "issue:43257|issue:43931", + "issue:44291|issue:45042", + "issue:43452|issue:43582", + "issue:43927|issue:44912", + "issue:44849|issue:45701" + ], + "prepared_review_unit_hash": "3faa9713077b24b91377f6b3c3c6190280ef2ec493207d3510e866d96488eeb4", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37021, + "estimated_input_tokens": 9256, + "estimated_eval_tokens": 18768 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated. The only strong soft edge is the Qwen video regression pair, with 44479 as the broad umbrella report and 43329 as a narrower report on the same video-token counting path. No PRs were provided.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 44479 is the broadest and most representative report in the cluster for the Qwen video-input regression; 43329 is a narrower related report focused on the same video-token counting path.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the best global issue candidate because it captures the shared user-facing Qwen video regression across multiple VL/MoE variants and serves as the clearest umbrella report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45372", + "right": "issue:46326", + "accept": false, + "reason": "Both mention mistral_common/tokenizer behavior, but they describe different failures and code paths: Gemma 4 processor loading import error vs continue_final_message handling." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "DAC latent reconstruction mismatch and DiaConfig token-ID persistence are distinct model bugs." + "reason": "Different models and bugs: DAC from_latents/STE mismatch versus DiaConfig save/load token ID loss." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "BarkProcessor voice_preset and CustomTrainer.compute_loss signature mismatch are unrelated." + "reason": "Unrelated subsystems: BarkProcessor voice_preset versus Trainer compute_loss signature compatibility." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "These are different model-specific generation/loading regressions, not one shared code-path bug." + "reason": "Both are model-loading/generation problems, but they affect different models and concrete code paths." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "SigLIP2 doc/example errors are unrelated to git-oss MXFP4 quantization loading." + "reason": "SigLIP2 doc-example errors are unrelated to GPT-OSS MXFP4 quantization fallback." }, { - "left": "issue:38175", - "right": "issue:44610", + "left": "issue:36010", + "right": "issue:43645", "accept": false, - "reason": "Unexpected zero probabilities and OmDet-Turbo resolution mismatch are separate vision-model issues." + "reason": "GenerationMixin import break and Jupyter custom-model initialization are distinct bugs." }, { - "left": "issue:36010", - "right": "issue:43645", + "left": "issue:38175", + "right": "issue:44610", "accept": false, - "reason": "GenerationMixin import breakage is not the same as the Jupyter custom-model initialization regression." + "reason": "Different image-model failures: zero probabilities in SigLIP2 versus wrong processor output size in OmDet-Turbo." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "BitNet packed-weight loading and OmDet-Turbo image-size mismatch are unrelated." + "reason": "Packed-weight loading for BitNet is unrelated to OmDet-Turbo input-shape mismatch." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve broad exception handling, but they target different components and different failure modes." + "reason": "Both involve error handling, but they affect different code paths and different failure modes." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Weight tying garbage-generation and Blip2 dtype handling are different model-loading bugs." + "reason": "AyaVision lm_head tying and BLIP2 dtype propagation are separate model-loading bugs." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "BEiT label reduction and MPS attention correctness are unrelated issues." + "reason": "Beit label reduction and MPS attention correctness are unrelated issues." }, { "left": "issue:36010", "right": "issue:36331", "accept": false, - "reason": "Importing GenerationMixin and compute_loss keyword-argument incompatibility are separate API breakages." - }, - { - "left": "issue:43262", - "right": "issue:44811", - "accept": false, - "reason": "Audio chat-template sampling rate and Whisper batch_decode skip_special_tokens are different processor behaviors." + "reason": "GenerationMixin import break and custom compute_loss signature incompatibility are different failures." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "FSDP CPU RAM-efficient loading and init_empty_weights _is_hf_initialized are related to low-memory loading, but not the same concrete bug." + "reason": "Both touch loading, but FSDP CPU RAM efficient loading and init_empty_weights/_is_hf_initialized are different failure modes." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior is unrelated to PIL backend torchvision dependency requirements." + "reason": "Qwen3-MoE sliding-window behavior is unrelated to the PIL backend torchvision requirement regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate defaults and Whisper batch_decode special-token handling are different processor bugs." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "MoE weight conversion with accelerate/deepspeed and multimodal token counting video-path bugs are unrelated." + "reason": "Qwen3 MOE weight conversion under accelerate+deepspeed is unrelated to the multimodal token-counting video branch bug." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "Both touch config/model loading, but one is missing fields from trust_remote_code and the other is text_config unwrapping for composite Qwen configs; not the same fix." + "reason": "Both involve config loading, but missing fields from trust_remote_code and unwrapping text_config for composite Qwen configs are different problems." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash import warning and Qwen3 MOE weight conversion are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both are video-related, but one is an undefined-helper bug in multimodal token counting and the other is a batched processor shape issue." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both mention CPU offload, but they affect different models and different code paths." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token-count tracking and GPT-OSS perplexity are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they concern different models and different behaviors." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer fast/slow inconsistency and TrainerState num_input_tokens_seen are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "Same underlying Qwen video-input regression in the multimodal token/video path; 43329 isolates the undefined helper issue, while 44479 reports the broader regression across Qwen VL/MoE variants." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config and MobileLLM loading key errors are different model-loading bugs." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MOE weight conversion and Qwen3-VL weight-shape mismatch are separate loading failures." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to the PIL backend torchvision dependency change." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file loading errors and Apple Silicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token ID persistence and GPT-OSS MXFP4 fallback are different bugs." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-states behavior and a generic tokenization-version-change report are not the same concrete bug." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, + "evaluator_result": { + "accept": false, + "feedback": "The soft-edge verdicts are mostly conservative, but the overall rationale slightly overstates the evidence: the packet supports 44479 as the broad Qwen video-regression issue and 43329 as a narrower related report, but it does not explicitly establish an \"accepted duplicate pair\" in the source data. Safer wording would avoid claiming duplicate-status beyond what the packet shows." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5772,332 +5985,315 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 18, - "review_unit_count": 50, + "review_unit_index": 19, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:24643", "issue:29159", "issue:33357", "issue:34567", + "issue:36331", "issue:38175", - "issue:40990", "issue:41720", - "issue:42490", "issue:42915", "issue:43257", "issue:43317", - "issue:43329", - "issue:43450", - "issue:43452", + "issue:43404", + "issue:43493", "issue:43540", "issue:43577", - "issue:43582", - "issue:43606", + "issue:43646", "issue:43696", "issue:43697", "issue:43742", - "issue:43927", - "issue:43931", + "issue:43749", + "issue:43756", + "issue:43906", + "issue:43994", "issue:44062", "issue:44291", "issue:44479", "issue:44560", "issue:44568", "issue:44737", + "issue:44756", + "issue:44792", "issue:44821", - "issue:44849", "issue:44898", - "issue:44912", + "issue:44913", + "issue:44964", "issue:44987", "issue:44991", - "issue:45042", "issue:45072", + "issue:45081", "issue:45137", - "issue:45356", "issue:45357", "issue:45381", "issue:45405", "issue:45488", "issue:45538", "issue:45588", - "issue:45701", - "issue:45859", - "issue:45907" + "issue:45907", + "issue:45987", + "issue:46121" ], "soft_pairs": [ - "issue:42490|issue:43257", - "issue:43329|issue:43450", - "issue:43606|issue:45859", - "issue:34567|issue:40990", - "issue:44568|issue:45356", - "issue:29159|issue:34567", - "issue:43329|issue:44479", - "issue:42915|issue:43742", - "issue:43257|issue:43931", - "issue:44849|issue:45701", - "issue:44291|issue:45042", - "issue:43452|issue:43582", - "issue:43927|issue:44912", "issue:43697|issue:45357", - "issue:44568|issue:45488", "issue:41720|issue:43540", "issue:42915|issue:44821", - "issue:33357|issue:34567", + "issue:44568|issue:45488", "issue:42915|issue:45538", + "issue:33357|issue:34567", "issue:44987|issue:45538", + "issue:43317|issue:45538", "issue:44479|issue:45381", "issue:43540|issue:44479", - "issue:43317|issue:45538", "issue:43540|issue:44560", + "issue:24643|issue:29159", "issue:45137|issue:45405", "issue:44987|issue:45907", - "issue:24643|issue:29159", "issue:43742|issue:44291", "issue:43577|issue:45072", "issue:38175|issue:44898", "issue:44062|issue:44991", + "issue:44737|issue:45588", "issue:43257|issue:43696", - "issue:44737|issue:45588" + "issue:43404|issue:45987", + "issue:34567|issue:36331", + "issue:43646|issue:43749", + "issue:44062|issue:45081", + "issue:44913|issue:46121", + "issue:43493|issue:43994", + "issue:43257|issue:43756", + "issue:43749|issue:44756", + "issue:44792|issue:44964", + "issue:43906|issue:45381", + "issue:44291|issue:44821" ], - "prepared_review_unit_hash": "4e58f44ef3ce4f591246d3add0b5af86ebb988e17545e1beb8bb3cfd80cfcbd3", + "prepared_review_unit_hash": "c35c5b6f31c52ec82edbeeeba79ab9f76b4472e55a820c858e4dbe9ac1fb6021", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37720, - "estimated_input_tokens": 9430, - "estimated_eval_tokens": 19116 + "soft_pair_count": 31, + "serialized_chars": 37136, + "estimated_input_tokens": 9284, + "estimated_eval_tokens": 18824 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These issues are mostly unrelated; the soft-similarity links do not rise to duplicate-level matches. I\u2019d keep one concrete tokenizer regression as the best representative issue, but no PR is present.", - "confidence": 0.89, - "canonical_issue_reason": "issue:45488 is the clearest standalone report: a specific tokenizer regression with concrete impact on DeepSeek V3/R1-style models. It is more actionable than the vaguer tokenization reports in the set.", + "summary": "This cluster is mostly a mix of unrelated transformer/model-loading regressions. I only see two true duplicate-style pairs: the SigLIP2 implementation issue and the Qwen video-input regression pair.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44479 is the broadest, most representative bug report here: it describes a concrete video-input regression across several Qwen variants and can subsume the closer duplicate-style report in this set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45488 is the best issue to anchor this cluster because it is specific, reproducible, and describes a real user-facing regression rather than a broad symptom.", + "best_issue_reason": "issue:44479 is the strongest issue candidate because it is specific, user-facing, and broad enough to serve as the representative issue for the video-input subcluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42490", - "right": "issue:43257", - "accept": false, - "reason": "Both involve loading, but one is a path/import warning and the other is Qwen3 MoE weight conversion with accelerate+deepspeed; different failures and code paths." - }, - { - "left": "issue:43329", - "right": "issue:43450", + "left": "issue:43697", + "right": "issue:45357", "accept": false, - "reason": "Both are video/multimodal related, but one is an undefined-helper bug in video token counting and the other is a batched-shape bug in video processors; not the same defect." + "reason": "Different bugs: one is a training/runtime failure with DeepSpeed, the other is a save_pretrained key regression for Qwen3.5 multimodal models." }, { - "left": "issue:43606", - "right": "issue:45859", + "left": "issue:41720", + "right": "issue:43540", "accept": false, - "reason": "Both mention CPU offload, but they affect different models and different modules; no evidence they are the same concrete bug." + "reason": "Different model families and failures: CUDA device-mapping assert on Qwen3 vs. video-input ValueError on Qwen3OmniMoe." }, { - "left": "issue:34567", - "right": "issue:40990", + "left": "issue:42915", + "right": "issue:44821", "accept": false, - "reason": "TrainerState token counting not updating is unrelated to GPT-OSS perplexity behavior." + "reason": "Unrelated: Qwen3Moe FP8 loading failure vs. AutoImageProcessor URL loading problem." }, { "left": "issue:44568", - "right": "issue:45356", - "accept": false, - "reason": "Both are tokenizer regressions, but they describe different model-specific issues and different tokenizer behaviors." - }, - { - "left": "issue:29159", - "right": "issue:34567", - "accept": false, - "reason": "Tokenizer consistency versus TrainerState token counting are unrelated areas." - }, - { - "left": "issue:43329", - "right": "issue:44479", + "right": "issue:45488", "accept": false, - "reason": "The latter is a broad video-input regression across Qwen VL families; the former is a specific missing-undefined-helper bug. They may be in the same area, but not clearly the same underlying defect." + "reason": "Both are tokenizer bugs, but the concrete failures differ: mDeBERTa special-token handling vs. LlamaTokenizer overwriting ByteLevel pre-tokenization." }, { "left": "issue:42915", - "right": "issue:43742", - "accept": false, - "reason": "Different model-loading errors: FineGrainedFP8Config for Qwen3 MoE versus a key error on MobileLLM-125M." - }, - { - "left": "issue:43257", - "right": "issue:43931", + "right": "issue:45538", "accept": false, - "reason": "Both are model loading problems, but one is MOE weight conversion with deepspeed while the other is a Qwen3-VL shape mismatch; different root causes." + "reason": "Unrelated issues: Qwen3Moe FP8 config failure vs. CLIPTokenizer model_max_length behavior." }, { - "left": "issue:44849", - "right": "issue:45701", + "left": "issue:33357", + "right": "issue:34567", "accept": false, - "reason": "Qwen3.5 hidden-state output bug is unrelated to the generic tokenization-change report." + "reason": "No shared bug path: MacOS bus error on a CLIP model vs. TrainerState token-count tracking not updating." }, { - "left": "issue:44291", - "right": "issue:45042", + "left": "issue:44987", + "right": "issue:45538", "accept": false, - "reason": "Unexpected init_empty_weights argument and PIL image-processor torchvision dependency are unrelated." + "reason": "Different problems: model loading regression for physical-intelligence/fast vs. tokenizer max_length default for CLIPTokenizer." }, { - "left": "issue:43452", - "right": "issue:43582", + "left": "issue:43317", + "right": "issue:45538", "accept": false, - "reason": "GGUF loading failures and Apple Silicon caching_allocator_warmup TypeError are unrelated." + "reason": "Different failure modes: device_map/offload load error vs. tokenizer max_length semantics." }, { - "left": "issue:43927", - "right": "issue:44912", - "accept": false, - "reason": "DiaConfig save/load token IDs and MXFP4 quantization fallback are different bugs." + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same underlying video-input regression in Qwen multimodal code: 45381 is a specific manifestation of the broader v5.3.0 video-input bug described in 44479." }, { - "left": "issue:43697", - "right": "issue:45357", + "left": "issue:43540", + "right": "issue:44479", "accept": false, - "reason": "RTDetrV2 output changes and Qwen3.5 save_pretrained visual-key corruption are different code paths." + "reason": "Both involve video processing, but the model families and concrete error paths are different enough that this is not clearly the same bug." }, { - "left": "issue:44568", - "right": "issue:45488", + "left": "issue:24643", + "right": "issue:29159", "accept": false, - "reason": "Both are tokenizer regressions, but one is about add_special_tokens/BOS-EOS behavior and the other is LlamaTokenizer overriding tokenizer.json pre-tokenizer settings; different concrete bugs." + "reason": "Unrelated: DeepSpeed training weight-shape error vs. tokenizer slow/fast inconsistency." }, { - "left": "issue:41720", - "right": "issue:43540", + "left": "issue:45137", + "right": "issue:45405", "accept": false, - "reason": "Auto device-mapping CUDA assert and Qwen3OmniMoe video ValueError are unrelated." + "reason": "Completely unrelated: DeepSpeed ZeRO3 deque error vs. version-bump issue for MIN_PEFT_VERSION." }, { - "left": "issue:42915", - "right": "issue:44821", + "left": "issue:44987", + "right": "issue:45907", "accept": false, - "reason": "Qwen3 MoE FP8 loading and AutoImageProcessor-from-URL are different failures." + "reason": "No common bug path: model loading regression vs. hub API revision-forwarding issue." }, { - "left": "issue:33357", - "right": "issue:34567", + "left": "issue:43742", + "right": "issue:44291", "accept": false, - "reason": "MacOS bus error with CLIP and TrainerState token counting are unrelated." + "reason": "Both are loading-time errors, but they are different code paths and failure causes: MobileLLM key error vs. init_empty_weights unexpected argument." }, { - "left": "issue:42915", - "right": "issue:45538", + "left": "issue:43577", + "right": "issue:45072", "accept": false, - "reason": "Qwen3 MoE FP8 load failure is unrelated to CLIPTokenizer's max-length bug." + "reason": "Different dtype issues in different models; not the same concrete bug." }, { - "left": "issue:44987", - "right": "issue:45538", + "left": "issue:38175", + "right": "issue:44898", "accept": false, - "reason": "Loading physical-intelligence/fast and CLIPTokenizer model_max_length are unrelated." + "reason": "Different models and symptoms: SigLIP2 zero probabilities vs. Perceiver non-default-resolution failure." }, { - "left": "issue:44479", - "right": "issue:45381", + "left": "issue:44062", + "right": "issue:44991", "accept": false, - "reason": "Both concern video input in Qwen VL models, but they report different regressions and symptoms; not enough to treat as the same bug." + "reason": "Tokenizer loading bugs, but one is an AddedToken argument collision and the other is a model-specific tokenizer load failure." }, { - "left": "issue:43540", - "right": "issue:44479", + "left": "issue:44737", + "right": "issue:45588", "accept": false, - "reason": "Both are video-related, but one is a Qwen3OmniMoe processing error and the other is a broader v5.3.0 regression across multiple VL families; different concrete problems." + "reason": "Unrelated: XLNet CPU allocation bug vs. flash-attention crash on sink-less models." }, { - "left": "issue:43317", - "right": "issue:45538", + "left": "issue:43257", + "right": "issue:43696", "accept": false, - "reason": "Dequantized model offload failure and CLIPTokenizer max-length bug are unrelated." + "reason": "Different issues: Qwen3 MoE weight conversion with accelerate/deepspeed vs. GPT-oss-20b OOM." }, { - "left": "issue:43540", - "right": "issue:44560", + "left": "issue:43404", + "right": "issue:45987", "accept": false, - "reason": "Both involve video inputs, but they affect different models and describe different failures (ValueError vs StopIteration)." + "reason": "Different code paths: lm_head tying bug vs. StaticCache sequence-length return type bug." }, { - "left": "issue:45137", - "right": "issue:45405", + "left": "issue:34567", + "right": "issue:36331", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error and a PEFT version bump are unrelated." + "reason": "Both are Trainer-related, but one is a state counter update bug and the other is a breaking API signature change." }, { - "left": "issue:44987", - "right": "issue:45907", + "left": "issue:43646", + "right": "issue:43749", "accept": false, - "reason": "Model loading regression and list_repo_files not forwarding revision are unrelated." + "reason": "Unrelated: custom model initialization breakage vs. FSDP CPU RAM efficient loading regression." }, { - "left": "issue:24643", - "right": "issue:29159", + "left": "issue:44062", + "right": "issue:45081", "accept": false, - "reason": "DeepSpeed training weight shape error and tokenizer slow/fast inconsistency are unrelated." + "reason": "Different tokenizer bugs: AddedToken keyword collision vs. Mistral regex patch crashing on backend_tokenizer access." }, { - "left": "issue:43742", - "right": "issue:44291", + "left": "issue:44913", + "right": "issue:46121", "accept": false, - "reason": "MobileLLM key error and init_empty_weights argument handling are different loading bugs." + "reason": "Both involve RoPE/config handling, but one is silent reload fallback and the other is a validation TypeError with JSON-loaded lists." }, { - "left": "issue:43577", - "right": "issue:45072", + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same underlying SigLIP2 implementation discrepancy: 43994 is the user-facing symptom of the model behaving incorrectly compared with the reference implementation." + }, + { + "left": "issue:43257", + "right": "issue:43756", "accept": false, - "reason": "Both mention dtype issues, but they affect different architectures and code paths; not the same bug." + "reason": "Different Qwen3-related issues: MoE weight conversion failure vs. Smollm3 RoPE-layer mismatch." }, { - "left": "issue:38175", - "right": "issue:44898", + "left": "issue:43749", + "right": "issue:44756", "accept": false, - "reason": "SIGLIP zero probabilities and Perceiver non-default-resolution failure are different vision-model issues." + "reason": "Both mention loading/memory, but one is an FSDP loading regression and the other is a Strix Halo mmap/OOM issue." }, { - "left": "issue:44062", - "right": "issue:44991", + "left": "issue:44792", + "right": "issue:44964", "accept": false, - "reason": "AddedToken keyword collision and est-roberta tokenizer loading failure are not the same defect." + "reason": "Different multimodal failures: a janus image-generation test failure vs. Phi-4-multimodal model loading failure." }, { - "left": "issue:43257", - "right": "issue:43696", + "left": "issue:43906", + "right": "issue:45381", "accept": false, - "reason": "Qwen3 MoE weight conversion and GPT-OSS out-of-memory are unrelated." + "reason": "Cannot confirm same bug from the titles alone; 43906 is only a reproduction of another issue, while 45381 is a specific qwen2.5-vl video-input regression." }, { - "left": "issue:44737", - "right": "issue:45588", + "left": "issue:44291", + "right": "issue:44821", "accept": false, - "reason": "XLNet CPU placement bug and flash_attention s_aux=None crash are unrelated." + "reason": "Different loading failures: init_empty_weights argument mismatch vs. AutoImageProcessor URL loading." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 44479 is a broader Qwen video-input regression report, and the two accepted pairs (43493/43994 and 44479/45381) are conservatively framed as duplicate-style matches. The many rejected pairs are also appropriately cautious and mostly correspond to clearly different model families or bug classes." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -6105,292 +6301,281 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 19, - "review_unit_count": 50, + "review_unit_index": 20, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ + "issue:24643", "issue:28282", "issue:29127", - "issue:34567", "issue:34689", "issue:36010", - "issue:36331", + "issue:41762", "issue:42175", - "issue:43257", - "issue:43404", "issue:43452", - "issue:43493", "issue:43526", "issue:43531", + "issue:43577", "issue:43582", "issue:43643", - "issue:43646", "issue:43697", + "issue:43720", "issue:43742", - "issue:43749", "issue:43756", + "issue:43819", "issue:43824", "issue:43906", - "issue:43994", - "issue:44062", - "issue:44291", + "issue:44466", "issue:44488", + "issue:44514", "issue:44589", "issue:44625", - "issue:44756", - "issue:44792", + "issue:44811", "issue:44821", + "issue:44843", "issue:44877", - "issue:44913", - "issue:44964", + "issue:44898", + "issue:44936", "issue:44977", + "issue:45005", "issue:45042", "issue:45081", "issue:45216", "issue:45325", "issue:45357", + "issue:45372", "issue:45375", "issue:45381", "issue:45405", "issue:45479", "issue:45600", "issue:45920", - "issue:45987", - "issue:46121" + "issue:46170", + "issue:46202" ], "soft_pairs": [ - "issue:43404|issue:45987", - "issue:34567|issue:36331", - "issue:43646|issue:43749", - "issue:44062|issue:45081", - "issue:44913|issue:46121", - "issue:43906|issue:45381", - "issue:43493|issue:43994", - "issue:43749|issue:44756", - "issue:43257|issue:43756", - "issue:44792|issue:44964", - "issue:44291|issue:44821", - "issue:28282|issue:34689", "issue:36010|issue:42175", + "issue:28282|issue:34689", "issue:42175|issue:43824", "issue:45042|issue:45081", - "issue:45357|issue:45920", "issue:43452|issue:44488", + "issue:45357|issue:45920", "issue:43742|issue:44589", "issue:45405|issue:45600", "issue:28282|issue:29127", - "issue:43643|issue:45375", "issue:43526|issue:45479", - "issue:43756|issue:45325", + "issue:43643|issue:45375", "issue:43531|issue:44821", "issue:44625|issue:44877", + "issue:43756|issue:45325", "issue:43697|issue:45216", - "issue:43582|issue:44977" + "issue:43582|issue:44977", + "issue:43720|issue:44898", + "issue:44514|issue:45381", + "issue:43452|issue:43577", + "issue:24643|issue:29127", + "issue:41762|issue:44936", + "issue:44466|issue:45005", + "issue:43452|issue:44843", + "issue:45372|issue:46170", + "issue:43819|issue:44811", + "issue:43906|issue:46202" ], - "prepared_review_unit_hash": "686b7a32efa7d16ad8e92f75474cc1478af555c4641c4f9e5540a0659eb49b95", + "prepared_review_unit_hash": "8d47a178185e1fef8384ebe72b81b24de1581df6eca2674a5430768c61d425a7", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 36070, - "estimated_input_tokens": 9018, - "estimated_eval_tokens": 18292 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35404, + "estimated_input_tokens": 8851, + "estimated_eval_tokens": 17958 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated Transformers issues across loading, configs, trainers, tokenizers, and multimodal models. The SigLIP2 pair is only adjacent/possibly related, not a confirmed duplicate; the rest should remain separate.", - "confidence": 0.74, - "canonical_issue_reason": "No single canonical issue cleanly represents the cluster because the items are largely unrelated. If one must be chosen, issue 43493 is the broadest technical report and the most plausible anchor, but it does not unify the whole set.", + "summary": "The cluster is highly mixed: the soft-similar pairs mostly share broad themes like loading, config, tokenizer, or serialization, but they are not the same underlying bug/change. I would not merge any of the candidate pairs.", + "confidence": 0.94, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43493 is the best representative issue for the cluster only in the limited sense that it is the most detailed substantive report among the adjacent SigLIP2 items; it should not be read as a true cluster-wide duplicate anchor.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43404", - "right": "issue:45987", + "left": "issue:36010", + "right": "issue:42175", "accept": false, - "reason": "Different bugs: Mistral lm_head tying vs StaticCache sequence-length return type. Same area, not the same defect." + "reason": "Different problems: missing GenerationMixin import vs packaging/backends missing TensorFlow in a torch install." }, { - "left": "issue:34567", - "right": "issue:36331", + "left": "issue:28282", + "right": "issue:34689", "accept": false, - "reason": "Both touch trainer behavior, but one is token counting and the other is a new compute_loss kwarg. Different code paths." + "reason": "One is PyTorch not installed; the other is a model-loading regression for Llama 3.2 Vision in 4.46.2." }, { - "left": "issue:43646", - "right": "issue:43749", + "left": "issue:42175", + "right": "issue:43824", "accept": false, - "reason": "One is a Transformers 5 custom model init regression; the other is FSDP CPU RAM efficient loading. Too different to merge." + "reason": "Backend/package omission vs Qwen2_5_VL import failure; unrelated failure paths." }, { - "left": "issue:44062", + "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "Different tokenizer-related failures: AddedToken argument handling vs mistral regex patching/backend access." + "reason": "Torchvision dependency regression in image processors vs a Mistral regex patch AttributeError." }, { - "left": "issue:44913", - "right": "issue:46121", + "left": "issue:43452", + "right": "issue:44488", "accept": false, - "reason": "Both involve RoPE config/validation, but one is silent reload persistence and the other is a TypeError in rope dict conversion. Not the same bug." + "reason": "Both involve loading, but one is gguf_file handling and the other is a specific model load failure; not the same bug." }, { - "left": "issue:43906", - "right": "issue:45381", + "left": "issue:45357", + "right": "issue:45920", "accept": false, - "reason": "Isolated reproduction of an old issue versus a Qwen2.5-VL video position-id regression. Different models and symptoms." + "reason": "Save_pretrained key regression vs tokenizer token-ID regression; different code paths." }, { - "left": "issue:43493", - "right": "issue:43994", + "left": "issue:43742", + "right": "issue:44589", "accept": false, - "reason": "These are SigLIP2-adjacent but not clearly the same bug: one reports a JAX/HF implementation discrepancy, the other nonsensical AutoModel/pipeline outputs. Related, but unconfirmed duplicate." + "reason": "KeyError on one model load vs missing Float8 storage type; unrelated runtime failures." }, { - "left": "issue:43749", - "right": "issue:44756", + "left": "issue:45405", + "right": "issue:45600", "accept": false, - "reason": "Both concern memory/loading, but one is an FSDP loading regression and the other is a Strix Halo mmap OOM workaround. Different fixes." + "reason": "PEFT version pin issue vs stale auto_mappings references; different causes." }, { - "left": "issue:43257", - "right": "issue:43756", + "left": "issue:28282", + "right": "issue:29127", "accept": false, - "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed is unrelated to Smollm3 RoPE layer dropping." + "reason": "Missing PyTorch import and LayoutLMv3 box-validation messaging are unrelated." }, { - "left": "issue:44792", - "right": "issue:44964", + "left": "issue:43526", + "right": "issue:45479", "accept": false, - "reason": "Different multimodal model issues: Janus image-generation test failure vs Phi-4 multimodal model loading failure." + "reason": "BeitImageProcessorFast label reduction bug vs sequence-classification zero-loss regression." }, { - "left": "issue:44291", - "right": "issue:44821", + "left": "issue:43643", + "right": "issue:45375", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized argument handling is unrelated to AutoImageProcessor URL loading." + "reason": "Both config-related, but one is generic remote-code config field loss and the other is a specific Qwen3_5MoeVision strict-field drop." }, { - "left": "issue:28282", - "right": "issue:34689", + "left": "issue:43531", + "right": "issue:44821", "accept": false, - "reason": "PyTorch-not-found ImportError versus a specific Llama 3.2 vision loading regression. Not the same defect." + "reason": "Sliding-window bug in Qwen3-MoE vs AutoImageProcessor URL loading; unrelated." }, { - "left": "issue:36010", - "right": "issue:42175", + "left": "issue:44625", + "right": "issue:44877", "accept": false, - "reason": "GenerationMixin import failure and missing TensorFlow backend in a torch install are unrelated packaging/import problems." + "reason": "num_labels propagation bug vs strict config rejection for granite_speech; different underlying issues." }, { - "left": "issue:42175", - "right": "issue:43824", + "left": "issue:43756", + "right": "issue:45325", "accept": false, - "reason": "Missing TensorFlow backend versus missing Qwen2_5_VL symbol. Different import/export issues." + "reason": "Different Qwen/Smollm rope-position bugs with different models and mechanics." }, { - "left": "issue:45042", - "right": "issue:45081", + "left": "issue:43697", + "right": "issue:45216", "accept": false, - "reason": "PIL image processors wrongly requiring torchvision is unrelated to Mistral regex patch crashes." + "reason": "RTDetrV2 output drift in v5 vs Qwen3.5 save_pretrained regression; not the same bug." }, { - "left": "issue:45357", - "right": "issue:45920", + "left": "issue:43582", + "right": "issue:44977", "accept": false, - "reason": "Qwen3.5 save_pretrained checkpoint key regression is unrelated to AutoTokenizer producing wrong token IDs across multiple models." + "reason": "AppleSilicon allocator TypeError vs Qwen3.5 flash-attention generation issue; unrelated." }, { - "left": "issue:43452", - "right": "issue:44488", + "left": "issue:43720", + "right": "issue:44898", "accept": false, - "reason": "gguf_file loading breakage is a different root cause from the cjvt/sleng-bert load failure." + "reason": "BitNet packed-weight unpacking bug vs Perceiver resolution failure; different code paths." }, { - "left": "issue:43742", - "right": "issue:44589", + "left": "issue:44514", + "right": "issue:45381", "accept": false, - "reason": "MobileLLM-125M key error and missing Float8 storage are distinct loading/runtime failures." + "reason": "Both Qwen2.5-VL, but one is chat-template batching/padding and the other is wrong video vision_position_ids." }, { - "left": "issue:45405", - "right": "issue:45600", + "left": "issue:43452", + "right": "issue:43577", "accept": false, - "reason": "PEFT version bump and auto_mappings referencing removed configs are unrelated maintenance issues." + "reason": "gguf_file loading regression vs BLIP2 dtype handling; unrelated." }, { - "left": "issue:28282", + "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "PyTorch missing ImportError and LayoutLMv3 box validation messaging are unrelated." - }, - { - "left": "issue:43643", - "right": "issue:45375", - "accept": false, - "reason": "trust_remote_code missing fields is a general config-return issue; Qwen3_5MoeVisionConfig missing deepstack_visual_indexes is a specific schema omission." + "reason": "DeepSpeed training weight-shape runtime error vs LayoutLMv3 error-message clarity; not duplicates." }, { - "left": "issue:43526", - "right": "issue:45479", + "left": "issue:41762", + "right": "issue:44936", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and single-label classification zero-loss regression are unrelated." + "reason": "Gemma3 ZeRO-3 loading failure vs trainer.evaluate() after train; different subsystems." }, { - "left": "issue:43756", - "right": "issue:45325", + "left": "issue:44466", + "right": "issue:45005", "accept": false, - "reason": "Both involve RoPE, but they affect different models and different calculations (layer dropping vs position-id scaling)." + "reason": "Both mention tied weights, but one is device-dependent serialization and the other is translation-model weight handling; too broad to merge." }, { - "left": "issue:43531", - "right": "issue:44821", + "left": "issue:43452", + "right": "issue:44843", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior is unrelated to AutoImageProcessor URL loading." + "reason": "gguf_file loading regression vs offline mistral regex patch calling model_info(); different bugs." }, { - "left": "issue:44625", - "right": "issue:44877", + "left": "issue:45372", + "right": "issue:46170", "accept": false, - "reason": "Num-label propagation bug and strict config blocking granite_speech loading are different configuration issues." + "reason": "Gemma 4 processor import dependency issue vs Windows ROCm torch.distributed dependency problem." }, { - "left": "issue:43697", - "right": "issue:45216", + "left": "issue:43819", + "right": "issue:44811", "accept": false, - "reason": "RTDetrV2 output differences in v5 and Qwen3.5 save_pretrained checkpoint corruption are separate regressions." + "reason": "DAC.from_latents mismatch vs Whisper batch_decode skip_special_tokens handling; unrelated." }, { - "left": "issue:43582", - "right": "issue:44977", + "left": "issue:43906", + "right": "issue:46202", "accept": false, - "reason": "Apple Silicon caching_allocator_warmup TypeError and Qwen3.5 flash-attention generation failure are unrelated." + "reason": "A reproduction of a prior issue vs a Gemma pipeline roundtrip failure; no evidence they are the same bug." } ] - }, - "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but it overstates one soft-edge pair: issue 43493 vs 43994 is marked deterministic_accept=false in the packet, so calling it the same underlying bug is too strong without more evidence. Please keep that verdict conservative (e.g. 'possibly related' or 'adjacent but unconfirmed') and avoid elevating the pair to accepted." - }, - "evaluator_used": true, - "retried": true, + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -6399,35 +6584,36 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 20, - "review_unit_count": 50, + "review_unit_index": 21, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ - "issue:24643", - "issue:29127", + "issue:28282", "issue:29159", "issue:30064", + "issue:32090", "issue:33357", "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", "issue:38175", "issue:41720", - "issue:41762", "issue:43295", - "issue:43452", + "issue:43504", "issue:43531", "issue:43550", "issue:43577", + "issue:43643", "issue:43653", "issue:43697", "issue:43720", "issue:43742", - "issue:43819", - "issue:43906", "issue:43927", "issue:44361", "issue:44442", @@ -6436,38 +6622,27 @@ "issue:44484", "issue:44493", "issue:44514", + "issue:44561", "issue:44568", + "issue:44610", "issue:44704", "issue:44743", - "issue:44811", "issue:44843", - "issue:44898", "issue:44936", "issue:44977", "issue:44991", - "issue:45005", "issue:45290", "issue:45356", - "issue:45372", - "issue:45381", + "issue:45491", "issue:45542", + "issue:45588", "issue:45823", + "issue:46002", "issue:46050", - "issue:46170", "issue:46178", - "issue:46202" + "issue:46209" ], "soft_pairs": [ - "issue:43720|issue:44898", - "issue:44514|issue:45381", - "issue:24643|issue:29127", - "issue:41762|issue:44936", - "issue:43452|issue:43577", - "issue:44466|issue:45005", - "issue:43906|issue:46202", - "issue:45372|issue:46170", - "issue:43452|issue:44843", - "issue:43819|issue:44811", "issue:43295|issue:45356", "issue:30064|issue:33666", "issue:44936|issue:45823", @@ -6475,235 +6650,259 @@ "issue:43653|issue:44361", "issue:44361|issue:44442", "issue:38175|issue:43295", - "issue:44514|issue:45290", "issue:45542|issue:46178", - "issue:43653|issue:44568", + "issue:44514|issue:45290", "issue:43577|issue:43697", + "issue:43653|issue:44568", "issue:44493|issue:46050", - "issue:29159|issue:33357", "issue:44843|issue:44991", + "issue:29159|issue:33357", "issue:44464|issue:44743", "issue:43653|issue:43927", - "issue:41720|issue:43906", "issue:43531|issue:43742", - "issue:43550|issue:43927", "issue:44464|issue:44977", - "issue:43550|issue:44361" + "issue:43550|issue:43927", + "issue:43643|issue:44561", + "issue:44977|issue:46209", + "issue:43550|issue:44361", + "issue:43577|issue:45588", + "issue:32090|issue:34567", + "issue:28282|issue:35141", + "issue:45491|issue:46002", + "issue:32090|issue:33666", + "issue:44466|issue:46050", + "issue:43504|issue:43720", + "issue:43504|issue:43550", + "issue:41720|issue:44464", + "issue:43504|issue:44610", + "issue:33666|issue:36010" ], - "prepared_review_unit_hash": "f7c42ba2f36d82ed2d43516914f8b848bbb4656ab991e142654151986afa6179", + "prepared_review_unit_hash": "0d89c5d3a6a230273a45e4f358014289db71bbdb8d622f6872cba127d43e9f6e", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37237, - "estimated_input_tokens": 9310, - "estimated_eval_tokens": 18876 + "soft_pair_count": 33, + "serialized_chars": 37777, + "estimated_input_tokens": 9445, + "estimated_eval_tokens": 19146 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: the issues share broad Transformers/tokenizer/model-loading themes, but the soft pairs describe different concrete bugs and code paths. I would not merge any of the proposed soft edges; no PRs are present.", - "confidence": 0.74, - "canonical_issue_reason": "If a single issue must stand in for the cluster, issue:44843 is the best representative because it is a broad framework-level loading regression (AutoTokenizer/_patch_mistral_regex/offline mode) rather than a model-specific edge case.", + "summary": "The cluster is heterogeneous: most items are distinct bugs spanning tokenizer loading/behavior, training, generation, model loading, and backend availability. I do not see any soft pair that is the same underlying issue, so none should be merged as duplicates.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 43653 is the closest anchor because the cluster\u2019s soft links skew toward tokenizer-related failures, and it has inbound references; however, this is not a strong canonical due to the overall mix of unrelated bugs.", "canonical_pr_reason": null, - "best_issue_reason": "Issue:44843 is the most suitable global representative because it concerns a central loading path with wider impact across models and environments, while most other issues are narrower model-specific failures.", + "best_issue_reason": "43653 is the most representative issue among these because it sits near the most repeated theme in the set (tokenizer behavior/load regressions), but the cluster is too diverse for a true duplicate hub.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43720", - "right": "issue:44898", + "left": "issue:43295", + "right": "issue:45356", "accept": false, - "reason": "Different failures in different code paths: BitNet accelerate loading/unpacking vs Perceiver image classification with interpolation." + "reason": "Both are tokenizer/regression reports, but they describe different failures and code paths (processor.tokenizer/images handling vs codec/fix_mistral_regex behavior)." }, { - "left": "issue:44514", - "right": "issue:45381", + "left": "issue:30064", + "right": "issue:33666", "accept": false, - "reason": "Both are Qwen2.5-VL related, but one is chat-template batching/padding and the other is video vision_position_ids; not the same bug." + "reason": "Different subsystems and symptoms: image processor void-segmentation handling vs multi-GPU training for Qwen2-VL." }, { - "left": "issue:24643", - "right": "issue:29127", + "left": "issue:44936", + "right": "issue:45823", "accept": false, - "reason": "Unrelated errors: DeepSpeed training weight shape vs LayoutLMv3 box-content validation/message clarity." + "reason": "Unrelated problems: trainer state after train/evaluate vs device-map forward mismatch in Gemma4 PLE." }, { - "left": "issue:41762", - "right": "issue:44936", + "left": "issue:44484", + "right": "issue:44704", "accept": false, - "reason": "Different paths and symptoms: Gemma3 ZeRO-3 loading failure vs trainer.evaluate() breaking after train()." + "reason": "One is about default shard size in save_pretrained; the other is AutoProcessor not forwarding kwargs to cached_file." }, { - "left": "issue:43452", - "right": "issue:43577", + "left": "issue:43653", + "right": "issue:44361", "accept": false, - "reason": "Tokenizer/AutoModel gguf_file loading breakage is unrelated to Blip2 dtype remaining float32 on load." + "reason": "Both are tokenizer bugs, but they affect different tokenizers and different failure modes (special-token registration vs AttributeError on tasks)." }, { - "left": "issue:44466", - "right": "issue:45005", + "left": "issue:44361", + "right": "issue:44442", "accept": false, - "reason": "Both mention tied weights, but one is device-dependent serialization and the other is translation-model behavior; too broad to treat as the same bug." + "reason": "Both involve tokenizers, but one is an AttributeError in MLukeTokenizer and the other is AutoTokenizer failing to load a specific tokenizer class." }, { - "left": "issue:43906", - "right": "issue:46202", + "left": "issue:38175", + "right": "issue:43295", "accept": false, - "reason": "Different reproductions: issue 38071 replay vs Gemma pipeline roundtrip failure on a specific token." + "reason": "Different model/runtime issues: zero probabilities in SigLIP2 vs custom processor/tokenizer regression." }, { - "left": "issue:45372", - "right": "issue:46170", + "left": "issue:45542", + "right": "issue:46178", "accept": false, - "reason": "Unrelated import/dependency failures: mistral_common ReasoningEffort for Gemma 4 vs Windows/ROCm torch.distributed issues." + "reason": "Both concern optional backend detection, but they target different backends and different error conditions; not the same bug." }, { - "left": "issue:43452", - "right": "issue:44843", + "left": "issue:44514", + "right": "issue:45290", "accept": false, - "reason": "Both affect model loading, but gguf_file handling and offline model_info() calls are distinct failure modes." + "reason": "Both crash in apply_chat_template, but the triggers are different (batched padding=False vs assistant tool-call messages without content)." }, { - "left": "issue:43819", - "right": "issue:44811", + "left": "issue:43577", + "right": "issue:43697", "accept": false, - "reason": "DAC latents/STE mismatch is unrelated to Whisper batch_decode skipping special tokens." + "reason": "Distinct issues: dtype propagation when loading BLIP2 vs output differences in RTDetrV2 under Transformers v5." }, { - "left": "issue:43295", - "right": "issue:45356", + "left": "issue:43653", + "right": "issue:44568", "accept": false, - "reason": "Different regressions in processor/tokenizer behavior: processor.tokenizer access vs Kimi-K2.5 codec/regex warning handling." + "reason": "Both are special-token related, but one is BigBirdTokenizer mask-token registration and the other is mdeberta BOS/EOS insertion behavior." }, { - "left": "issue:30064", - "right": "issue:33666", + "left": "issue:44493", + "right": "issue:46050", "accept": false, - "reason": "Void segmentation maps in image processing vs Qwen2-VL multi-GPU training are unrelated." + "reason": "Different serialization/loading problems: unexpected position-id keys vs quantized sinq model breakage after save/load." }, { - "left": "issue:44936", - "right": "issue:45823", + "left": "issue:44843", + "right": "issue:44991", "accept": false, - "reason": "Trainer state after training vs Gemma4 PLE device mismatch during forward are different bugs." + "reason": "Both are tokenizer load regressions, but one is offline model_info patching and the other is a specific tokenizer failing on a particular model." }, { - "left": "issue:44484", - "right": "issue:44704", + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Slow-vs-fast tokenizer inconsistency is not the same as the MacOS bus error with a community CLIP model." + }, + { + "left": "issue:44464", + "right": "issue:44743", "accept": false, - "reason": "Shard-size configuration question is unrelated to AutoProcessor kwargs not reaching cached_file." + "reason": "Both mention generation/cache, but one is chunked generation with compiled forward and the other is recurrent-state reset in a specific modular Qwen3.5 implementation." }, { "left": "issue:43653", - "right": "issue:44361", + "right": "issue:43927", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug is unrelated to MLukeTokenizer attribute errors." + "reason": "Different bugs: BigBirdTokenizer special-token registration vs DiaConfig losing custom token IDs on save/load." }, { - "left": "issue:44361", - "right": "issue:44442", + "left": "issue:43531", + "right": "issue:43742", "accept": false, - "reason": "Different tokenizer failures: MLukeTokenizer task handling vs AutoTokenizer loading FastSpeech2ConformerTokenizer." + "reason": "Distinct issues: Qwen3-MoE sliding_window behavior vs key error loading MobileLLM-125M." }, { - "left": "issue:38175", - "right": "issue:43295", + "left": "issue:44464", + "right": "issue:44977", "accept": false, - "reason": "Siglip2 zero probabilities are unrelated to the processor.tokenizer regression in v4.57.5." + "reason": "Both affect generation, but they concern different models and different mechanisms (compiled forward chunking vs flash-attention behavior)." }, { - "left": "issue:44514", - "right": "issue:45290", + "left": "issue:43550", + "right": "issue:43927", "accept": false, - "reason": "Same API surface, but different crash triggers: batched padding=False vs assistant tool-call messages without content." + "reason": "Different failure classes: torch.compile/SDPA on Bamba vs configuration token-ID loss on save/load." }, { - "left": "issue:45542", - "right": "issue:46178", + "left": "issue:43643", + "right": "issue:44561", "accept": false, - "reason": "Different backend registration problems: missing TensorFlow backend vs offending tensorflow_text backend mapping." + "reason": "Both involve trust_remote_code-ish compatibility, but one is missing fields in AutoConfig and the other is removal of is_torch_fx_available." }, { - "left": "issue:43653", - "right": "issue:44568", + "left": "issue:44977", + "right": "issue:46209", + "accept": false, + "reason": "Unrelated model/runtime issues: Qwen3.5 flash-attention generation vs FP8 inference failing on B200." + }, + { + "left": "issue:43550", + "right": "issue:44361", "accept": false, - "reason": "Different tokenizer bugs affecting different models and token types." + "reason": "Different problems: Bamba torch.compile + SDPA vs MLukeTokenizer task AttributeError." }, { "left": "issue:43577", - "right": "issue:43697", + "right": "issue:45588", "accept": false, - "reason": "Blip2 dtype persistence and RTDetrV2 output drift are unrelated." + "reason": "Both are model/runtime edge cases, but one is BLIP2 dtype loading and the other is flash_attention.py crashing on s_aux=None." }, { - "left": "issue:44493", - "right": "issue:46050", + "left": "issue:32090", + "right": "issue:34567", "accept": false, - "reason": "Position-id key warnings and sinq quantization save/load breakage are different serialization/compatibility issues." + "reason": "Trainer broadcast NoneType error and TrainerState token counter not updating are different trainer bugs." }, { - "left": "issue:29159", - "right": "issue:33357", + "left": "issue:28282", + "right": "issue:35141", "accept": false, - "reason": "Slow-vs-fast tokenizer inconsistency is unrelated to the MacOS CLIP bus error." + "reason": "ImportError for missing PyTorch and embedding reinitialization after resizing are unrelated." }, { - "left": "issue:44843", - "right": "issue:44991", + "left": "issue:45491", + "right": "issue:46002", "accept": false, - "reason": "Both are tokenizer-loading regressions, but one is offline model_info() patching and the other is a specific model tokenizer load failure." + "reason": "Both mention NaNs, but one is a GPU sliding-window attention issue and the other is NaNs in classification heads after checkout/init." }, { - "left": "issue:44464", - "right": "issue:44743", + "left": "issue:32090", + "right": "issue:33666", "accept": false, - "reason": "Chunked generation with compiled forward is a different problem from recurrent states being reset with cache and seq_len>1." + "reason": "Different areas: trainer GPU broadcast error vs Qwen2-VL multi-GPU training discussion." }, { - "left": "issue:43653", - "right": "issue:43927", + "left": "issue:44466", + "right": "issue:46050", "accept": false, - "reason": "BigBirdTokenizer special token registration and DiaConfig custom token ID persistence are unrelated." + "reason": "Different serialization/regression topics: lm_head.weight serialization vs sinq quantized save/load breakage." }, { - "left": "issue:41720", - "right": "issue:43906", + "left": "issue:43504", + "right": "issue:43720", "accept": false, - "reason": "Qwen3 auto device mapping cudaErrorAssert is unrelated to an isolated reproduction of issue 38071." + "reason": "Both are loading-related, but one is a legacy field in Beit semantic segmentation and the other is BitNet packed-weight unpacking during accelerate loading." }, { - "left": "issue:43531", - "right": "issue:43742", + "left": "issue:43504", + "right": "issue:43550", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and MobileLLM key errors are different code paths." + "reason": "Distinct bugs in different models and stacks: Beit preset loading vs Bamba torch.compile with SDPA." }, { - "left": "issue:43550", - "right": "issue:43927", + "left": "issue:41720", + "right": "issue:44464", "accept": false, - "reason": "torch.compile SDPA failure in Bamba-9B-v2 is unrelated to DiaConfig save/load token ID loss." + "reason": "Qwen3 auto device-map cudaErrorAssert and chunked generation compiled-forward inconsistency are different failure paths." }, { - "left": "issue:44464", - "right": "issue:44977", + "left": "issue:43504", + "right": "issue:44610", "accept": false, - "reason": "Different generation regressions: compiled-forward chunking vs flash-attention behavior in Qwen3.5." + "reason": "Different model-loading vs preprocessing issues: Beit legacy field vs OmDet-Turbo processor output size mismatch." }, { - "left": "issue:43550", - "right": "issue:44361", + "left": "issue:33666", + "right": "issue:36010", "accept": false, - "reason": "Compilation/SDPA failure and tokenizer AttributeError are not the same underlying bug." + "reason": "Qwen2-VL multi-GPU training and GenerationMixin import failure are unrelated." } ] }, @@ -6718,304 +6917,290 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 21, - "review_unit_count": 50, + "review_unit_index": 22, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28282", "issue:32090", "issue:33357", "issue:33666", - "issue:34567", - "issue:35141", - "issue:36010", "issue:36331", "issue:39692", - "issue:41720", "issue:43262", "issue:43295", "issue:43452", "issue:43493", - "issue:43504", "issue:43525", - "issue:43550", + "issue:43540", "issue:43572", "issue:43577", "issue:43606", - "issue:43643", "issue:43688", "issue:43720", "issue:43742", + "issue:43749", "issue:43756", "issue:43825", "issue:43927", "issue:43994", "issue:44361", "issue:44451", - "issue:44464", - "issue:44466", - "issue:44561", - "issue:44610", + "issue:44479", + "issue:44488", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44625", "issue:44821", + "issue:44843", "issue:44849", "issue:44913", + "issue:44964", "issue:44977", + "issue:45200", + "issue:45229", "issue:45357", + "issue:45405", "issue:45440", - "issue:45491", - "issue:45588", + "issue:45812", "issue:45823", - "issue:46002", "issue:46050", "issue:46192", - "issue:46209" + "issue:46209", + "issue:46285" ], "soft_pairs": [ - "issue:44977|issue:46209", - "issue:43643|issue:44561", - "issue:32090|issue:34567", - "issue:43577|issue:45588", - "issue:28282|issue:35141", - "issue:45491|issue:46002", - "issue:32090|issue:33666", - "issue:43504|issue:43550", - "issue:43504|issue:43720", - "issue:44466|issue:46050", - "issue:43504|issue:44610", - "issue:41720|issue:44464", - "issue:33666|issue:36010", "issue:43688|issue:45440", "issue:43742|issue:44821", "issue:45823|issue:46050", "issue:28282|issue:32090", - "issue:28282|issue:33357", "issue:43262|issue:43295", + "issue:28282|issue:33357", "issue:43720|issue:43927", - "issue:44849|issue:46209", - "issue:43606|issue:43927", "issue:43994|issue:46192", "issue:43452|issue:44451", + "issue:43606|issue:43927", + "issue:44849|issue:46209", "issue:33666|issue:36331", - "issue:43756|issue:44913", - "issue:43720|issue:44361", "issue:43525|issue:43572", + "issue:43720|issue:44361", + "issue:43756|issue:44913", "issue:43493|issue:43825", + "issue:39692|issue:43493", + "issue:44964|issue:45405", + "issue:44479|issue:44625", + "issue:43577|issue:44554", "issue:44849|issue:45357", - "issue:39692|issue:43493" + "issue:43688|issue:43749", + "issue:44568|issue:45812", + "issue:43540|issue:44977", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:39692|issue:43295", + "issue:44493|issue:46285" ], - "prepared_review_unit_hash": "847c0d6dc4362ab8e392a7078022c42ee3bec7f7679e3105330f40260afe4b68", + "prepared_review_unit_hash": "81544dd06dbaefe6c2923c5eeaac12567e9c9795a9aeef68fd95d9fec1d903bd", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 31, - "serialized_chars": 36554, - "estimated_input_tokens": 9139, - "estimated_eval_tokens": 18534 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36165, + "estimated_input_tokens": 9042, + "estimated_eval_tokens": 18340 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of unrelated issue reports that only share superficial regression/loading/model keywords. I don\u2019t see any soft pair that looks like the same underlying bug or change, and there are no PRs in the set.", - "confidence": 0.96, - "canonical_issue_reason": "Issue 44561 is the broadest, clearest representative of the cluster\u2019s overall v5/trust_remote_code regression theme, but it is still not a duplicate hub for the other reports.", + "summary": "This cluster is heterogeneous: most items are unrelated model/config/tokenizer regressions rather than duplicates. No soft edge looks like the same underlying bug, so all candidate merges are rejected. If forced to pick a representative issue, the broad tokenizer regression in Granite is the strongest single example.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45812 is the broadest, clearest user-facing regression in the set: a silent AutoTokenizer token-ID bug affecting all Granite models, making it the best representative issue.", "canonical_pr_reason": null, - "best_issue_reason": "44561 is the most general and actionable issue in the set, with a concrete compatibility regression and a clearer scope than the other mostly model-specific reports.", + "best_issue_reason": "issue:45812 has the strongest cluster-wide signal because it describes a general, high-impact tokenizer regression rather than a narrow model-specific edge case.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44977", - "right": "issue:46209", - "accept": false, - "reason": "Different bugs: Qwen3.5 flash-attention generation failure vs FP8 inference failure on B200." - }, - { - "left": "issue:43643", - "right": "issue:44561", + "left": "issue:43688", + "right": "issue:45440", "accept": false, - "reason": "Both touch trust_remote_code, but one is missing config fields and the other is removal of a helper breaking models; not the same code-path bug." + "reason": "Both are MoE-related, but they describe different failures and code paths: aux-loss normalization vs model implementation divergence." }, { - "left": "issue:32090", - "right": "issue:34567", + "left": "issue:43742", + "right": "issue:44821", "accept": false, - "reason": "Unrelated Trainer distributed broadcast TypeError vs TrainerState token-count tracking bug." + "reason": "A model load KeyError for MobileLLM is unrelated to loading AutoImageProcessor from a URL." }, { - "left": "issue:43577", - "right": "issue:45588", + "left": "issue:45823", + "right": "issue:46050", "accept": false, - "reason": "Different subsystems: Blip2 dtype propagation vs flash_attention handling of s_aux=None." + "reason": "Gemma4 device-mapping forward mismatch and sinq save/load quantization breakage are different bugs." }, { "left": "issue:28282", - "right": "issue:35141", + "right": "issue:32090", "accept": false, - "reason": "Missing PyTorch import and embedding reinitialization are unrelated failures." + "reason": "ImportError for missing PyTorch and a Trainer GPU broadcast NoneType TypeError are unrelated." }, { - "left": "issue:45491", - "right": "issue:46002", + "left": "issue:43262", + "right": "issue:43295", "accept": false, - "reason": "Both mention NaNs, but one is Gemma3 sliding-window attention and the other is classification-head init/checkpointing." + "reason": "Audio chat-template sampling-rate handling and multimodal processor/tokenizer regression are different code paths." }, { - "left": "issue:32090", - "right": "issue:33666", + "left": "issue:28282", + "right": "issue:33357", "accept": false, - "reason": "Distributed broadcast type error is not the same as multi-GPU training behavior for Qwen2-VL." + "reason": "Missing PyTorch import error is unrelated to the MacOS CLIP bus error regression." }, { - "left": "issue:43504", - "right": "issue:43550", + "left": "issue:43720", + "right": "issue:43927", "accept": false, - "reason": "One is a legacy-field load bug in Beit; the other is a torch.compile/SDPA failure in Bamba." + "reason": "BitNet packed-weight loading and DiaConfig token-ID persistence are different failures." }, { - "left": "issue:43504", - "right": "issue:43720", + "left": "issue:43994", + "right": "issue:46192", "accept": false, - "reason": "Both are loading issues, but the concrete causes differ: legacy preset field vs unpacking packed BitNet weights." + "reason": "SigLIP2 wrong results and ignored return_tensors in text_kwargs are unrelated tokenizer/pipeline behaviors." }, { - "left": "issue:44466", - "right": "issue:46050", + "left": "issue:43452", + "right": "issue:44451", "accept": false, - "reason": "Both concern save/load behavior, but one is tied-weight serialization and the other is sinq quantization persistence." + "reason": "Both involve loading models, but one is gguf handling for tokenizer/causal LM and the other is a specific model load failure." }, { - "left": "issue:43504", - "right": "issue:44610", + "left": "issue:43606", + "right": "issue:43927", "accept": false, - "reason": "Model preset loading bug vs processor/model input-size mismatch; different layers of the stack." + "reason": "CPU offload device mismatch is unrelated to config token-ID loss on save/load." }, { - "left": "issue:41720", - "right": "issue:44464", + "left": "issue:44849", + "right": "issue:46209", "accept": false, - "reason": "CUDA assert under auto device mapping is unrelated to inconsistent chunked generation with compiled forward." + "reason": "Qwen3.5 hidden-state output bug and FP8 B200 inference failure are different issues." }, { "left": "issue:33666", - "right": "issue:36010", - "accept": false, - "reason": "Multi-GPU training issue and GenerationMixin import failure are different problems." - }, - { - "left": "issue:43688", - "right": "issue:45440", + "right": "issue:36331", "accept": false, - "reason": "Both involve MoE models, but one is auxiliary-loss normalization and the other is a native-vs-remote implementation divergence." + "reason": "Multi-GPU training for Qwen2-VL and a custom Trainer signature error are not the same bug." }, { - "left": "issue:43742", - "right": "issue:44821", + "left": "issue:43525", + "right": "issue:43572", "accept": false, - "reason": "Key error loading MobileLLM-125M is unrelated to loading AutoImageProcessor from a URL." + "reason": "Both mention missing pad-token config fields, but they affect different model configs and different attributes." }, { - "left": "issue:45823", - "right": "issue:46050", + "left": "issue:43720", + "right": "issue:44361", "accept": false, - "reason": "Device mismatch with device_map=\"auto\" is not the same as quantized save/load breakage." + "reason": "Packed-weight unpacking during accelerate loading is unrelated to MLukeTokenizer AttributeError on tasks." }, { - "left": "issue:28282", - "right": "issue:32090", + "left": "issue:43756", + "right": "issue:44913", "accept": false, - "reason": "ImportError for PyTorch and GPU broadcast TypeError are unrelated." + "reason": "Smollm3 RoPE-layer omission and GPTNeoX rotary_pct reload regression are separate positional-encoding bugs." }, { - "left": "issue:28282", - "right": "issue:33357", + "left": "issue:43493", + "right": "issue:43825", "accept": false, - "reason": "PyTorch import missing vs Mac bus error in CLIP are different failure modes and code paths." + "reason": "SigLIP2 implementation discrepancy and a misleading pipeline translation error message are unrelated." }, { - "left": "issue:43262", - "right": "issue:43295", + "left": "issue:39692", + "right": "issue:43493", "accept": false, - "reason": "Audio chat-template sampling-rate default bug and processor.tokenizer/image-passing regression are separate issues." + "reason": "Documentation/example mistakes are not the same as the SigLIP2 HF-vs-JAX implementation divergence." }, { - "left": "issue:43720", - "right": "issue:43927", + "left": "issue:44964", + "right": "issue:45405", "accept": false, - "reason": "BitNet loading with packed weights and DiaConfig custom-token-ID loss are unrelated save/load bugs." + "reason": "A model load regression and an unreleased PEFT version bump are unrelated." }, { - "left": "issue:44849", - "right": "issue:46209", + "left": "issue:44479", + "right": "issue:44625", "accept": false, - "reason": "Qwen3.5 hidden-states bug is unrelated to FP8 inference failure on B200." + "reason": "Video-input regression across Qwen variants and num_labels propagation in Qwen3.5 are different problems." }, { - "left": "issue:43606", - "right": "issue:43927", + "left": "issue:43577", + "right": "issue:44554", "accept": false, - "reason": "CPU-offload device mismatch and config token-ID loss do not share the same underlying bug." + "reason": "BLIP2 dtype propagation and an MPS attention correctness issue are unrelated." }, { - "left": "issue:43994", - "right": "issue:46192", + "left": "issue:44849", + "right": "issue:45357", "accept": false, - "reason": "SigLIP2 inference correctness issues are unrelated to return_tensors being ignored when text_kwargs is passed." + "reason": "Output_hidden_states behavior and incorrect save_pretrained visual encoder keys are different regressions." }, { - "left": "issue:43452", - "right": "issue:44451", + "left": "issue:43688", + "right": "issue:43749", "accept": false, - "reason": "GGUF-related tokenizer/model loading breakage is not the same as ScandiBERT loading failure." + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are different training/runtime issues." }, { - "left": "issue:33666", - "right": "issue:36331", + "left": "issue:44568", + "right": "issue:45812", "accept": false, - "reason": "Qwen2-VL multi-GPU training and CustomTrainer.compute_loss signature mismatch are different Trainer problems." + "reason": "Both are tokenizer regressions, but one is special-token insertion for mDeBERTa and the other is wrong token IDs for Granite; different code paths." }, { - "left": "issue:43756", - "right": "issue:44913", + "left": "issue:43540", + "right": "issue:44977", "accept": false, - "reason": "Smollm3 RoPE-layer behavior and GPTNeoXConfig reload of rotary_pct are related only thematically, not as the same bug." + "reason": "Video processing in Qwen3OmniMoe and flash-attention generation in Qwen3.5 are not the same bug." }, { - "left": "issue:43720", - "right": "issue:44361", + "left": "issue:45200", + "right": "issue:45229", "accept": false, - "reason": "BitNet model loading and MLukeTokenizer task AttributeError are unrelated." + "reason": "Text-only mm_token_type_ids behavior and Gemma4 multi-GPU inference OOM are unrelated." }, { - "left": "issue:43525", - "right": "issue:43572", + "left": "issue:44488", + "right": "issue:44843", "accept": false, - "reason": "Similar symptom class, but different configs and missing fields: Llama4 pad_token_id vs StableLm pad_token_idx." + "reason": "A model failing to load and an offline-mode tokenizer regex bug are different causes." }, { - "left": "issue:43493", - "right": "issue:43825", + "left": "issue:39692", + "right": "issue:43295", "accept": false, - "reason": "SigLIP2 implementation discrepancy and pipeline translation-task messaging are unrelated." + "reason": "A doc-example mismatch/quantization issue is unrelated to a processor.tokenizer API regression." }, { - "left": "issue:39692", - "right": "issue:43493", + "left": "issue:44493", + "right": "issue:46285", "accept": false, - "reason": "Documentation-example errors are not the same underlying bug as the SigLIP2 implementation discrepancy." + "reason": "Unexpected position-id keys and CLIP text-model structural inconsistency are different model-structure regressions." } ] }, @@ -7030,304 +7215,296 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 22, - "review_unit_count": 50, + "review_unit_index": 23, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ + "issue:29159", + "issue:29942", + "issue:30333", + "issue:32090", "issue:33357", "issue:33666", - "issue:39692", "issue:43257", "issue:43278", - "issue:43295", "issue:43299", "issue:43334", "issue:43493", "issue:43504", - "issue:43540", "issue:43572", "issue:43575", - "issue:43577", "issue:43606", "issue:43646", "issue:43653", "issue:43688", - "issue:43749", "issue:43756", "issue:43824", "issue:43844", + "issue:43873", "issue:43927", + "issue:43994", "issue:44112", "issue:44291", "issue:44361", + "issue:44423", + "issue:44464", "issue:44466", - "issue:44479", - "issue:44488", "issue:44493", - "issue:44554", - "issue:44568", "issue:44589", "issue:44625", - "issue:44843", + "issue:44734", + "issue:44792", "issue:44964", - "issue:44977", "issue:45083", - "issue:45200", "issue:45229", "issue:45405", "issue:45520", + "issue:45584", + "issue:45588", "issue:45701", "issue:45704", "issue:45759", - "issue:45812", "issue:45823", - "issue:46285" + "issue:46050" ], "soft_pairs": [ - "issue:44964|issue:45405", - "issue:44479|issue:44625", - "issue:43577|issue:44554", - "issue:43688|issue:43749", - "issue:44568|issue:45812", - "issue:43540|issue:44977", - "issue:45200|issue:45229", - "issue:44488|issue:44843", - "issue:39692|issue:43295", "issue:43688|issue:45704", - "issue:44493|issue:46285", "issue:43756|issue:45083", "issue:43493|issue:43844", - "issue:43334|issue:43572", - "issue:43646|issue:44466", - "issue:45229|issue:45823", - "issue:33357|issue:33666", - "issue:43334|issue:45759", - "issue:43824|issue:44589", - "issue:43927|issue:44361", - "issue:43278|issue:43844", - "issue:43504|issue:43606", - "issue:44589|issue:45520", - "issue:44625|issue:45759", - "issue:43257|issue:43299", - "issue:43572|issue:44291", - "issue:43575|issue:45405", - "issue:43688|issue:45701", - "issue:43606|issue:44112", - "issue:43504|issue:43653" - ], - "prepared_review_unit_hash": "23323ac74f7c20ee6c7c4ef873357eb1972a8ee9d2e77effe6d23bad4ffe9ca4", - "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 - }, - "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36905, - "estimated_input_tokens": 9227, - "estimated_eval_tokens": 18710 - }, - "overflow_policy": "truncate_then_skip", - "trimmed": false, - "aggressively_trimmed": false, - "split": true, - "analyst_result": { - "summary": "This cluster is not a duplicate set; it mixes many unrelated model-loading, tokenizer, config, dtype, and training/runtime regressions across different model families. None of the soft edges look like the same underlying bug/change, so all should be rejected.", - "confidence": 0.94, - "canonical_issue_reason": "If a single issue must represent the cluster, issue 43646 is the broadest umbrella ('Transformers 5.0.0 breaks custom model initialization'), but it still does not actually duplicate most of the others.", - "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the most generic version-wide regression in the set and best serves as an approximate umbrella, though the cluster is too heterogeneous for a true canonical duplicate.", - "best_pr_reason": null, - "soft_edge_verdicts": [ - { - "left": "issue:44964", - "right": "issue:45405", - "accept": false, - "reason": "Different problems: Phi-4 multimodal loading regression vs an unreleased PEFT version bump." - }, - { - "left": "issue:44479", - "right": "issue:44625", - "accept": false, - "reason": "One is a video-input regression in Qwen VL models; the other is num_labels propagation in Qwen3.5 config plumbing." - }, - { - "left": "issue:43577", - "right": "issue:44554", - "accept": false, - "reason": "Blip2 dtype-casting bug is unrelated to the MPS attention correctness issue." - }, - { - "left": "issue:43688", - "right": "issue:43749", - "accept": false, - "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are different code paths and failure modes." - }, - { - "left": "issue:44568", - "right": "issue:45812", - "accept": false, - "reason": "Both involve tokenization, but one is BOS/EOS insertion for mdeberta while the other is Granite token ID regression; not the same bug." - }, - { - "left": "issue:43540", - "right": "issue:44977", - "accept": false, - "reason": "Qwen3Omni video input processing is unrelated to Qwen3.5 flash-attention generation behavior." - }, - { - "left": "issue:45200", - "right": "issue:45229", - "accept": false, - "reason": "Gemma4 token-type defaults for fine-tuning vs multi-GPU inference OOM are distinct issues." - }, - { - "left": "issue:44488", - "right": "issue:44843", - "accept": false, - "reason": "Model load failure for a specific repo is not the same as the offline model_info call regression." - }, - { - "left": "issue:39692", - "right": "issue:43295", - "accept": false, - "reason": "Documentation/example mistakes are not the same as a runtime processor.tokenizer API regression." - }, + "issue:43334|issue:43572", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:33357|issue:33666", + "issue:43334|issue:45759", + "issue:43927|issue:44361", + "issue:43824|issue:44589", + "issue:44589|issue:45520", + "issue:43504|issue:43606", + "issue:43278|issue:43844", + "issue:44625|issue:45759", + "issue:43257|issue:43299", + "issue:43572|issue:44291", + "issue:43575|issue:45405", + "issue:43504|issue:43653", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:43688|issue:45701", + "issue:45588|issue:46050", + "issue:44464|issue:45584", + "issue:43994|issue:44493", + "issue:44423|issue:44734", + "issue:29942|issue:30333", + "issue:43844|issue:44964", + "issue:43688|issue:43873", + "issue:29159|issue:32090" + ], + "prepared_review_unit_hash": "8e7e893484b0630698639ee4c0ea1b00902dd45428ac31fabeccf0361fd07890", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35897, + "estimated_input_tokens": 8975, + "estimated_eval_tokens": 18206 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly superficial topical matches across unrelated bugs, model families, or code paths. None look like the same underlying defect, so no duplicate merge is justified. The broadest representative issue is the tokenizer-regression report (45701), but it is not a true canonical duplicate for the rest.", + "confidence": 0.8, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the broadest and most reusable report in the set because it describes a general tokenizer-version regression, but it still does not match the other reports closely enough to serve as a true canonical duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Different model-specific bugs: auxiliary loss normalization vs T5 apex RMSNorm memory leak." - }, - { - "left": "issue:44493", - "right": "issue:46285", - "accept": false, - "reason": "Unexpected position-id keys during loading is unrelated to CLIP text-model attribute structure changes." + "reason": "Different bugs: auxiliary-loss normalization in MoE models vs a T5/apex RMSNorm memory leak." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "Smollm3 RoPE-layer dropping and qwen3_omni_moe feature-length helper behavior are unrelated." + "reason": "Unrelated failures: RoPE-layer dropping in Smollm3 vs a feature-extraction length helper issue in qwen3_omni_moe." }, { "left": "issue:43493", "right": "issue:43844", "accept": false, - "reason": "HF-vs-JAX SigLIP2 discrepancy is not the same as the ZeRO-3 gradient blow-up bug." + "reason": "Both are model-quality regressions, but one is SigLIP2 implementation mismatch and the other is ZeRO-3 gradient blowup; not the same code-path problem." }, { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Both mention missing token IDs, but they affect different configs/models and different fields." + "reason": "Both mention missing config fields after the 5.0 update, but they affect different models and different attributes (`pad_token_id` vs `pad_token_idx`)." }, { "left": "issue:43646", "right": "issue:44466", "accept": false, - "reason": "Custom model initialization breakage is separate from device-dependent lm_head serialization." + "reason": "Custom model initialization breakage is not the same issue as device-dependent `lm_head.weight` serialization." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "OOM in Gemma4 inference and PLE device mismatch during forward are different failures." + "reason": "Same model family, but one is multi-GPU OOM and the other is a device-mismatch forward bug; different underlying failures." }, { "left": "issue:33357", "right": "issue:33666", "accept": false, - "reason": "MacOS CLIP bus error and Qwen2-VL multi-GPU training are unrelated." + "reason": "Completely different subsystems and symptoms: MacOS CLIP bus error vs Qwen2-VL multi-GPU training." }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Missing pad_token_id in Qwen3-VL config is not the same as failing to unwrap text_config for composite multimodal configs." + "reason": "Both involve Qwen multimodal configs, but one is a missing config attribute while the other is `from_config` not unwrapping `text_config`; not the same concrete bug." }, { - "left": "issue:43824", - "right": "issue:44589", + "left": "issue:43927", + "right": "issue:44361", "accept": false, - "reason": "ImportError for a missing Qwen2.5-VL class and a float8 storage lookup error are unrelated." + "reason": "Different tokenizer/config failures: lost custom token IDs after save/load vs a tokenizer AttributeError on tasks." }, { - "left": "issue:43927", - "right": "issue:44361", + "left": "issue:43824", + "right": "issue:44589", "accept": false, - "reason": "Config save/load losing token IDs is a different bug from MLukeTokenizer AttributeError on tasks." + "reason": "ImportError for a missing Qwen2.5-VL class is unrelated to the Float8 storage type error." }, { - "left": "issue:43278", - "right": "issue:43844", + "left": "issue:44589", + "right": "issue:45520", "accept": false, - "reason": "Embedding dtype mismatch at eval time is unrelated to the ZeRO-3 gradient increase issue." + "reason": "Different failure modes: missing Float8 storage registration vs `flash_attn` KeyError on Python 3.13." }, { "left": "issue:43504", "right": "issue:43606", "accept": false, - "reason": "Legacy config field loading and CPU-offload device mismatch are different classes of bugs." + "reason": "Legacy-field loading issue for BEiT is unrelated to the Bark CPU-offload device mismatch." }, { - "left": "issue:44589", - "right": "issue:45520", + "left": "issue:43278", + "right": "issue:43844", "accept": false, - "reason": "Float8 storage resolution and flash_attn import key errors are different backend/import issues." + "reason": "Embedding dtype drift in evaluate is unrelated to the ZeRO-3 gradient anomaly." }, { "left": "issue:44625", "right": "issue:45759", "accept": false, - "reason": "Num_labels propagation and text_config unwrapping are related to config plumbing but not the same concrete failure." + "reason": "Both are Qwen3.5 config issues, but one is `num_labels` propagation and the other is `from_config` text-config unwrapping; too different to merge." }, { "left": "issue:43257", "right": "issue:43299", "accept": false, - "reason": "Accelerate+DeepSpeed weight conversion bug is distinct from the Qwen3VL MOE loading regression." + "reason": "Both mention Qwen3 MoE loading, but one is accelerate+deepspeed weight conversion and the other is a dev-version load failure; not the same bug." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "StableLm pad_token_idx loss and unexpected _is_hf_initialized argument are unrelated v5 regressions." + "reason": "Both are 5.0 compatibility regressions, but one is a missing config field and the other is an unexpected `_is_hf_initialized` argument." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "Tensor-parallel OOM for Qwen2-57B is unrelated to the PEFT version pin issue." + "reason": "CUDA OOM during tensor-parallel load is unrelated to an unmet PEFT version pin." }, { - "left": "issue:43688", - "right": "issue:45701", + "left": "issue:43504", + "right": "issue:43653", "accept": false, - "reason": "Auxiliary loss normalization and tokenization changes are entirely different issues." + "reason": "Different tokenizer issues: BEiT legacy-field loading vs BigBird mask token registration/empty decode." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "Bark CPU-offload device mismatch and GraniteSpeech stale-device CI test are not the same bug." + "reason": "Different device-related problems: CPU offload mismatch vs a stale CI override test." }, { - "left": "issue:43504", - "right": "issue:43653", + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to the PEFT version bump." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "MoE auxiliary-loss normalization is unrelated to a general tokenizer-version regression." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "Flash-attention sink handling error is unrelated to quantized save/load breakage." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to Whisper empty-transcription handling after token alignment." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 inference corruption and unexpected position-id keys are different problems." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve crashes, but one is a multimodal `.to` type error and the other is KV-cache indexing; different code paths." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention test failures are unrelated to MLflow reporting after training failure." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Different model/runtime issues: ZeRO-3 gradient instability vs failure to load Phi-4 multimodal." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to quantization offloading behavior." + }, + { + "left": "issue:29159", + "right": "issue:32090", "accept": false, - "reason": "Beit legacy-field loading failure and BigBirdTokenizer special-token decoding are unrelated." + "reason": "Tokenizer slow/fast inconsistency is unrelated to the Trainer `_gpu_broadcast_one` NoneType error." } ] }, @@ -7342,21 +7519,17 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 23, - "review_unit_count": 50, + "review_unit_index": 24, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:15354", "issue:28218", - "issue:29159", - "issue:29942", - "issue:30333", - "issue:32090", "issue:33357", "issue:34567", "issue:38175", @@ -7367,272 +7540,278 @@ "issue:43450", "issue:43493", "issue:43540", - "issue:43688", + "issue:43550", + "issue:43572", + "issue:43575", "issue:43701", "issue:43844", "issue:43873", - "issue:43994", + "issue:43950", + "issue:43957", "issue:44186", - "issue:44423", - "issue:44464", - "issue:44493", + "issue:44466", "issue:44521", "issue:44554", "issue:44610", - "issue:44734", - "issue:44792", "issue:44849", - "issue:44964", + "issue:44898", + "issue:44987", "issue:45072", "issue:45084", + "issue:45127", "issue:45198", "issue:45200", "issue:45290", + "issue:45325", "issue:45356", - "issue:45405", + "issue:45381", "issue:45406", + "issue:45412", "issue:45446", "issue:45520", - "issue:45584", - "issue:45588", "issue:45823", "issue:46050", "issue:46121", - "issue:46192" + "issue:46178", + "issue:46192", + "issue:46209", + "issue:46285" ], "soft_pairs": [ - "issue:44792|issue:45405", - "issue:44423|issue:44734", - "issue:44464|issue:45584", - "issue:45588|issue:46050", - "issue:43994|issue:44493", - "issue:29942|issue:30333", - "issue:43844|issue:44964", - "issue:43688|issue:43873", "issue:28218|issue:34567", - "issue:29159|issue:32090", - "issue:44521|issue:45290", "issue:44554|issue:45446", - "issue:15354|issue:38175", "issue:45084|issue:45520", + "issue:15354|issue:38175", "issue:43540|issue:45200", + "issue:44521|issue:45290", "issue:43873|issue:46050", "issue:45200|issue:45823", "issue:43278|issue:43701", "issue:45072|issue:45198", - "issue:43232|issue:44849", "issue:44186|issue:46192", "issue:45406|issue:46121", + "issue:43232|issue:44849", "issue:45823|issue:46192", - "issue:28218|issue:33357", "issue:43493|issue:43701", + "issue:28218|issue:33357", "issue:43295|issue:43450", "issue:43295|issue:44610", "issue:39692|issue:46192", - "issue:44554|issue:45356" + "issue:44554|issue:45356", + "issue:45381|issue:46209", + "issue:43572|issue:44987", + "issue:43295|issue:43873", + "issue:44898|issue:45412", + "issue:43572|issue:43957", + "issue:43950|issue:46285", + "issue:44466|issue:45127", + "issue:43550|issue:43844", + "issue:45200|issue:45325", + "issue:45520|issue:46178", + "issue:43450|issue:43575" ], - "prepared_review_unit_hash": "4bf8acf3a280ad2f015ec76a65e7cd1e509dac145b5e189b1a3949375bbf94e1", + "prepared_review_unit_hash": "81ee6c8b1bc6940f69eae6c21e064ec08f667cb1b78697bcf55d2ef27384f72f", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36481, - "estimated_input_tokens": 9121, - "estimated_eval_tokens": 18498 + "soft_pair_count": 31, + "serialized_chars": 37226, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No convincing duplicates here: the issues span unrelated areas (tokenizers, generation, serving, quantization, training, and multimodal processors). The soft-similarity pairs mostly share a subsystem label, not the same underlying bug or change.", - "confidence": 0.91, - "canonical_issue_reason": "issue:44521 is the most representative current bug report in this set: open, reproducible, and a concrete multimodal template regression with user-visible impact.", - "canonical_pr_reason": null, - "best_issue_reason": "issue:44521 is the best single issue to anchor on because it is specific, actionable, and actively reported; among these unrelated issues it reads like the clearest candidate for triage attention.", - "best_pr_reason": null, + "summary": "This cluster is a grab-bag of unrelated Transformers bugs and regressions across tokenization, chat templates, multimodal processors, generation, loading/serialization, quantization, and device/dtype handling. None of the soft pairs look like the same underlying bug/change, so no soft edge should be merged.", + "confidence": 0.97, + "canonical_issue_reason": "No single issue is a safe canonical because the items span many unrelated failure modes rather than one duplicate thread.", + "canonical_pr_reason": "No pull requests are present in the provided items, so there is no PR canonical to choose.", + "best_issue_reason": "No issue clearly subsumes the others; the set is too heterogeneous for a global best issue.", + "best_pr_reason": "No pull requests are present in the provided items, so there is no PR candidate to select.", "soft_edge_verdicts": [ { - "left": "issue:44792", - "right": "issue:45405", + "left": "issue:28218", + "right": "issue:34567", "accept": false, - "reason": "Different problems: a janus test failure vs. a PEFT version constraint/release issue." + "reason": "Tokenizer spacing bug vs TrainerState token-count update regression; different subsystems and symptoms." }, { - "left": "issue:44423", - "right": "issue:44734", + "left": "issue:44554", + "right": "issue:45446", "accept": false, - "reason": "Both involve serve/generation crashes, but the failing code paths and symptoms differ (continuous batching multimodal crash vs KV-cache continuation indexing bug)." + "reason": "MPS attention correctness issue vs PyTorch version-check import bug; unrelated code paths." }, { - "left": "issue:44464", - "right": "issue:45584", + "left": "issue:45084", + "right": "issue:45520", "accept": false, - "reason": "Both are generation-related, but one is compiled-forward inconsistency and the other is Whisper empty-transcription handling after token alignment." + "reason": "Template-node compile error vs flash_attn backend lookup failure; not the same defect." }, { - "left": "issue:45588", - "right": "issue:46050", + "left": "issue:15354", + "right": "issue:38175", "accept": false, - "reason": "Flash-attention sinkless-model crash is unrelated to sinq save/load corruption after quantization." + "reason": "torch.jit.script GeneratorExp limitation vs SigLIP2 probability anomaly; unrelated." }, { - "left": "issue:43994", - "right": "issue:44493", + "left": "issue:43540", + "right": "issue:45200", "accept": false, - "reason": "SigLIP2 bad outputs vs a position-id key warning; different symptoms and likely different root causes." + "reason": "Video-input processing ValueError vs Gemma4 multimodal token-id defaulting; different model paths." }, { - "left": "issue:29942", - "right": "issue:30333", + "left": "issue:44521", + "right": "issue:45290", "accept": false, - "reason": "Flash Attention 2 test failures are unrelated to MLFlow reporting after training failure." + "reason": "Both touch chat templates, but one is all-zero assistant masks and the other is tool-call crash; different bugs." }, { - "left": "issue:43844", - "right": "issue:44964", + "left": "issue:43873", + "right": "issue:46050", "accept": false, - "reason": "ZeRO-3 gradient inflation is unrelated to loading a multimodal Phi-4 model." + "reason": "Quantization/offloading behavior vs sinq save/load corruption; different lifecycle stages." }, { - "left": "issue:43688", - "right": "issue:43873", + "left": "issue:45200", + "right": "issue:45823", "accept": false, - "reason": "Aux-loss normalization and quantization/offloading are different bugs in different training/runtime paths." + "reason": "Gemma4 mm_token_type_ids handling vs device_map auto forward device mismatch; unrelated." }, { - "left": "issue:28218", - "right": "issue:34567", + "left": "issue:43278", + "right": "issue:43701", "accept": false, - "reason": "Tokenizer spacing behavior is unrelated to TrainerState token counting." + "reason": "BF16-to-FP32 evaluation dtype drift vs resume checkpoint key mismatch; no shared root cause." }, { - "left": "issue:29159", - "right": "issue:32090", + "left": "issue:45072", + "right": "issue:45198", "accept": false, - "reason": "Tokenizer slow/fast inconsistency is unrelated to a Trainer GPU broadcast NoneType error." + "reason": "bfloat16 inference dtype mismatch vs Wav2Vec2 save_pretrained/tokenization failure; different problems." }, { - "left": "issue:44521", - "right": "issue:45290", + "left": "issue:44186", + "right": "issue:46192", "accept": false, - "reason": "Both touch apply_chat_template, but one is wrong assistant masks for multimodal inputs and the other is a crash on tool-call messages with empty content." + "reason": "LayoutLMv2 NER/padding crash vs return_tensors precedence bug; separate tokenizer issues." }, { - "left": "issue:44554", - "right": "issue:45446", + "left": "issue:45406", + "right": "issue:46121", "accept": false, - "reason": "MPS attention correctness issue and a flex_attention version-check bug are separate code paths." + "reason": "Gemma4Processor missing _tokenizer vs rope-param dict conversion type error; unrelated." }, { - "left": "issue:15354", - "right": "issue:38175", + "left": "issue:43232", + "right": "issue:44849", "accept": false, - "reason": "JIT scripting/export failure for ViT is unrelated to SigLIP2 zero-probability outputs." + "reason": "Generation kwargs update after sync_gpus vs Qwen3.5 hidden-states bug; different code paths." }, { - "left": "issue:45084", - "right": "issue:45520", + "left": "issue:45823", + "right": "issue:46192", "accept": false, - "reason": "Template-node compilation error and flash_attn import KeyError are unrelated failures." + "reason": "Device_map auto forward mismatch vs return_tensors being ignored; not the same bug." }, { - "left": "issue:43540", - "right": "issue:45200", + "left": "issue:43493", + "right": "issue:43701", "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe is unrelated to Gemma4 text-only fine-tuning token-type defaults." + "reason": "SigLIP2 HF-vs-JAX discrepancy vs resume_from_checkpoint key mismatch; unrelated." }, { - "left": "issue:43873", - "right": "issue:46050", + "left": "issue:28218", + "right": "issue:33357", "accept": false, - "reason": "Quantization offloading behavior and sinq save/load breakage are not the same bug." + "reason": "Tokenizer extra-space bug vs MacOS bus error in CLIP model loading; different failure modes." }, { - "left": "issue:45200", - "right": "issue:45823", + "left": "issue:43295", + "right": "issue:43450", "accept": false, - "reason": "Missing mm_token_type_ids defaults and Gemma4 PLE device mismatch during forward are distinct issues." + "reason": "processor.tokenizer regression vs batched video shape bug; different multimodal paths." }, { - "left": "issue:43278", - "right": "issue:43701", + "left": "issue:43295", + "right": "issue:44610", "accept": false, - "reason": "Embedding dtype drift in eval is unrelated to checkpoint key mismatch on resume." + "reason": "processor.tokenizer regression vs OmDet processor/model size mismatch; unrelated." }, - { - "left": "issue:45072", - "right": "issue:45198", + { + "left": "issue:39692", + "right": "issue:46192", "accept": false, - "reason": "bfloat16 dtype mismatches in inference and Wav2Vec2 save/tokenization failures are unrelated." + "reason": "Documentation example errors vs tokenizer kwargs handling regression; not the same defect." }, { - "left": "issue:43232", - "right": "issue:44849", + "left": "issue:44554", + "right": "issue:45356", "accept": false, - "reason": "Generation kwarg update after sync_gpus is unrelated to an output_hidden_states bug in Qwen3.5." + "reason": "Attention correctness on MPS vs Kimi-K2.5 tokenizer regression; unrelated." }, { - "left": "issue:44186", - "right": "issue:46192", + "left": "issue:45381", + "right": "issue:46209", "accept": false, - "reason": "LayoutLMv2 tokenization crashes on NER/batched padding are unrelated to return_tensors being ignored when text_kwargs is passed." + "reason": "Qwen2.5-VL video position-id bug vs FP8 inference failure on B200; separate issues." }, { - "left": "issue:45406", - "right": "issue:46121", + "left": "issue:43572", + "right": "issue:44987", "accept": false, - "reason": "Gemma4Processor missing _tokenizer in serve is unrelated to RoPE validation rejecting a JSON-loaded list." + "reason": "StableLmConfig missing pad_token_idx vs model-loading regression on v5.1.0; different root causes." }, { - "left": "issue:45823", - "right": "issue:46192", + "left": "issue:43950", + "right": "issue:46285", "accept": false, - "reason": "Gemma4 PLE device placement and return_tensors handling are different bugs." + "reason": "from_pretrained buffer corruption vs CLIP text-model structure inconsistency; not the same bug." }, { - "left": "issue:28218", - "right": "issue:33357", + "left": "issue:44898", + "right": "issue:45412", "accept": false, - "reason": "Tokenizer added-space bug is unrelated to a MacOS bus error with CLIP." + "reason": "Perceiver resize/interpolation failure vs RT-DETR memory leak; unrelated." }, { - "left": "issue:43493", - "right": "issue:43701", + "left": "issue:44466", + "right": "issue:45127", "accept": false, - "reason": "SigLIP2 implementation discrepancy is unrelated to resume checkpoint key mismatch." + "reason": "lm_head serialization inconsistency vs LoRA merge collapse with extended vocab; different bugs despite tied-weights theme." }, { - "left": "issue:43295", - "right": "issue:43450", + "left": "issue:43550", + "right": "issue:43844", "accept": false, - "reason": "Processor/tokenizer regression is not the same as batched video shape handling." + "reason": "torch.compile/SDPA failure vs ZeRO-3 gradient explosion; unrelated training/runtime issues." }, { - "left": "issue:43295", - "right": "issue:44610", + "left": "issue:45200", + "right": "issue:45325", "accept": false, - "reason": "Custom processor/tokenizer regression and OmDet-Turbo image-size mismatch are different model-specific bugs." + "reason": "Gemma4 multimodal token-id defaulting vs Qwen2.5-VL rope scaling bug; different models and code paths." }, { - "left": "issue:39692", - "right": "issue:46192", + "left": "issue:45520", + "right": "issue:46178", "accept": false, - "reason": "SigLIP2 doc/example errors are unrelated to return_tensors being ignored with text_kwargs." + "reason": "flash_attn import KeyError vs tensorflow_text backend mapping error; unrelated import machinery." }, { - "left": "issue:44554", - "right": "issue:45356", + "left": "issue:43450", + "right": "issue:43575", "accept": false, - "reason": "MPS attention correctness and Kimi-K2.5 tokenizer codec/regression issues do not share the same code path." + "reason": "Batched video shape bug vs OOM while loading a 57B model; no shared underlying defect." } ] }, @@ -7647,14 +7826,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 24, - "review_unit_count": 50, + "review_unit_index": 25, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:37428", "issue:38175", @@ -7665,291 +7844,277 @@ "issue:43278", "issue:43295", "issue:43334", + "issue:43335", "issue:43450", "issue:43493", "issue:43525", "issue:43526", "issue:43550", - "issue:43572", - "issue:43575", + "issue:43606", "issue:43653", "issue:43696", + "issue:43819", "issue:43824", - "issue:43844", + "issue:43827", "issue:43856", - "issue:43873", - "issue:43950", + "issue:43901", "issue:43957", "issue:43975", "issue:44112", + "issue:44206", "issue:44442", - "issue:44466", "issue:44514", "issue:44521", "issue:44561", - "issue:44898", - "issue:44987", - "issue:45127", + "issue:44610", + "issue:44857", + "issue:45083", "issue:45198", - "issue:45200", - "issue:45325", - "issue:45381", + "issue:45290", "issue:45412", "issue:45520", + "issue:45584", + "issue:45593", "issue:45759", "issue:46170", - "issue:46178", "issue:46192", "issue:46209", "issue:46234", - "issue:46285" + "issue:46285", + "issue:46326" ], "soft_pairs": [ - "issue:45381|issue:46209", - "issue:43295|issue:43873", - "issue:43572|issue:44987", - "issue:44898|issue:45412", - "issue:43950|issue:46285", - "issue:43572|issue:43957", - "issue:43550|issue:43844", - "issue:44466|issue:45127", - "issue:45200|issue:45325", - "issue:43450|issue:43575", - "issue:45520|issue:46178", "issue:43334|issue:43525", "issue:37428|issue:43957", "issue:42490|issue:43696", "issue:43824|issue:43975", "issue:43278|issue:43856", + "issue:45290|issue:46326", "issue:43526|issue:46192", "issue:38175|issue:43493", "issue:43653|issue:44112", "issue:42915|issue:43824", - "issue:44442|issue:45198", "issue:43295|issue:43493", + "issue:44442|issue:45198", "issue:38175|issue:45412", + "issue:37428|issue:43824", "issue:43262|issue:43450", "issue:44514|issue:44521", - "issue:37428|issue:43824", "issue:45520|issue:46170", "issue:45759|issue:46285", + "issue:44561|issue:46234", "issue:41720|issue:46209", - "issue:44561|issue:46234" + "issue:44610|issue:44857", + "issue:43819|issue:44112", + "issue:43827|issue:43901", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:44857|issue:45593", + "issue:43335|issue:43550", + "issue:43606|issue:45083" ], - "prepared_review_unit_hash": "f64c2b3d7b39f048de2e04fe73e63c9cfe16a7cc95ad95b1c0f5b94652cfd4aa", + "prepared_review_unit_hash": "591a66c154855ed8ee23c0f0a5edbfc40ce71846430645312506af0bc7c99f40", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36449, - "estimated_input_tokens": 9113, - "estimated_eval_tokens": 18482 + "soft_pair_count": 28, + "serialized_chars": 35718, + "estimated_input_tokens": 8930, + "estimated_eval_tokens": 18116 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly noisy and spans unrelated Transformers regressions. The only soft edge that looks like a true duplicate is the pair of pad_token_id AttributeErrors in different config classes; the rest are distinct bugs affecting different models, modalities, or code paths.", - "confidence": 0.37, - "canonical_issue_reason": "issue:43334 is the clearest representative of the shared regression: a load-time AttributeError caused by missing pad_token_id on model/config objects. It is more general than the Llama4-specific report and best captures the underlying config API breakage.", + "summary": "Most pairs are different bugs, not true duplicates. The only strong duplicate candidates are the multimodal pad_token_id AttributeErrors and the SigLIP2 implementation-mismatch reports.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43493 is the broader root-cause report for the SigLIP2 HF-vs-JAX discrepancy; issue:38175 reads like a specific symptom of that same model behavior.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43334 is the best global issue because it describes a concrete, reproducible regression in a widely shared config access path and is broad enough to cover the closely related Llama4 report.", + "best_issue_reason": "issue:44521 is open, actively discussed, has the most inbound references, and is a clean user-facing bug report suitable as a cluster anchor.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:45381", - "right": "issue:46209", - "accept": false, - "reason": "Different bugs: one is wrong vision_position_ids for Qwen2.5-VL video/still image handling, the other is FP8 inference failure on B200 GPUs." - }, - { - "left": "issue:43295", - "right": "issue:43873", - "accept": false, - "reason": "Unrelated symptoms and code paths: processor.tokenizer regression vs quantization/offloading behavior." - }, - { - "left": "issue:43572", - "right": "issue:44987", - "accept": false, - "reason": "Both are load failures, but they point to different root causes and different models; not the same bug." - }, - { - "left": "issue:44898", - "right": "issue:45412", - "accept": false, - "reason": "Perceiver positional-encoding failure and RT-DETR memory release issue are unrelated." - }, - { - "left": "issue:43950", - "right": "issue:46285", - "accept": false, - "reason": "Both involve model structure/loading changes in v5, but the specific defects differ: non-persistent buffer corruption vs CLIP text_model structure mismatch." - }, - { - "left": "issue:43572", - "right": "issue:43957", - "accept": false, - "reason": "Different classes of regressions: missing pad_token_idx in a config vs meta-device loading breakage." - }, - { - "left": "issue:43550", - "right": "issue:43844", - "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to DeepSpeed ZeRO-3 gradient growth." - }, - { - "left": "issue:44466", - "right": "issue:45127", - "accept": false, - "reason": "Both mention tied weights/serialization-adjacent behavior, but one is inconsistent lm_head.weight saving and the other is post-LoRA model collapse with extended vocab." - }, - { - "left": "issue:45200", - "right": "issue:45325", - "accept": false, - "reason": "Both are Qwen2.5-VL multimodal issues, but one is missing mm_token_type_ids defaults while the other is incorrect rope/temporal position scaling." - }, - { - "left": "issue:43450", - "right": "issue:43575", - "accept": false, - "reason": "Video processor batch-shape bug and Qwen2-57B tensor-parallel OOM are unrelated." - }, - { - "left": "issue:45520", - "right": "issue:46178", - "accept": false, - "reason": "Different import/backend issues: flash_attn lookup on Python 3.13 vs tensorflow_text backend mapping." - }, { "left": "issue:43334", "right": "issue:43525", "accept": true, - "reason": "Same underlying load-time regression: both configs lack pad_token_id and crash when Transformers code expects that attribute." + "reason": "Both report the same pad_token_id AttributeError in multimodal config handling; likely the same regression across model configs." }, { "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Both are loading/import issues, but one is a missing helper import and the other is meta-device model loading breakage." + "reason": "Different failures: a missing flash-attention import symbol vs meta-device loading breakage for some models." }, { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Trailing-slash local path warning and GPT-oss CUDA OOM are unrelated." + "reason": "Path-trailing-slash import warning and CUDA OOM are unrelated." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "ImportError for Qwen2_5_VL class and DeepSeek detokenization bug are different defects." + "reason": "One is a missing Qwen2_5_VL export; the other is a detokenization regression." }, { "left": "issue:43278", "right": "issue:43856", "accept": false, - "reason": "Training/eval dtype drift is unrelated to Qwen3 MoE memory inefficiency." + "reason": "Different symptoms and code paths: eval dtype drift vs MoE training memory usage." + }, + { + "left": "issue:45290", + "right": "issue:46326", + "accept": false, + "reason": "Both involve chat templates, but the concrete bugs differ: tool-call/no-content crash vs mistral_common continue_final_message behavior." }, { "left": "issue:43526", "right": "issue:46192", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug and return_tensors being ignored are distinct processor issues." + "reason": "Unrelated processor bugs: Beit reduce_labels shape/selection vs return_tensors being ignored with text_kwargs." }, { "left": "issue:38175", "right": "issue:43493", - "accept": false, - "reason": "SigLIP2 zero-probabilities and HF-vs-JAX discrepancy are related to the same model family but not the same concrete bug." + "accept": true, + "reason": "Same SigLIP2 implementation mismatch; the zero-probability symptom fits the broader HF-vs-JAX discrepancy report." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "BigBirdTokenizer special-token registration and GraniteSpeech CI test staleness are unrelated." + "reason": "Tokenizer special-token registration bug vs a stale CI device-override test." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Qwen3Moe FP8 failure and Qwen2_5_VL import error are different model-specific issues." + "reason": "Different models and failures: FineGrainedFP8Config issue vs Qwen2_5_VL import error." }, { - "left": "issue:44442", - "right": "issue:45198", + "left": "issue:43295", + "right": "issue:43493", "accept": false, - "reason": "Tokenizer load failure and Wav2Vec2 save_pretrained/tokenization failure are separate bugs." + "reason": "Processor.tokenizer regression and SigLIP2 numeric mismatch are different bugs." }, { - "left": "issue:43295", - "right": "issue:43493", + "left": "issue:44442", + "right": "issue:45198", "accept": false, - "reason": "Processor.tokenizer regression and SigLIP2 implementation discrepancy do not share the same failing code path." + "reason": "Tokenizer loading failure and save_pretrained/tokenization failure are related only by tokenizer scope, not the same bug." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 probability issue and RT-DETR memory cleanup bug are unrelated." + "reason": "SigLIP2 probability issue and RT-DETR memory release issue are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols and different model families." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio chat-template sampling-rate defaulting and video batch-shape handling are different processor bugs." + "reason": "Audio sampling-rate defaulting and batched video shape handling are different processor bugs." }, { "left": "issue:44514", "right": "issue:44521", "accept": false, - "reason": "Both involve Qwen2.5-VL apply_chat_template, but one is a batched-input crash and the other is incorrect assistant_masks output; not clearly the same bug." - }, - { - "left": "issue:37428", - "right": "issue:43824", - "accept": false, - "reason": "Different import errors for different symbols and root causes." + "reason": "Both touch apply_chat_template, but one is a padding=False crash and the other is all-zero assistant masks; not the same concrete failure." }, { "left": "issue:45520", "right": "issue:46170", "accept": false, - "reason": "flash_attn import lookup on Python 3.13 and Windows ROCm torch.distributed dependency issues are unrelated." + "reason": "flash_attn import KeyError on Python 3.13 is unrelated to Windows ROCm torch.distributed dependency issues." }, { "left": "issue:45759", "right": "issue:46285", "accept": false, - "reason": "Composite Qwen multimodal config unwrapping and CLIP text_model structure mismatch are different regressions." + "reason": "Both concern composite/text model structure, but they are different API regressions with different affected classes." + }, + { + "left": "issue:44561", + "right": "issue:46234", + "accept": false, + "reason": "Different missing helper symbols affecting different remote-code/model paths." }, { "left": "issue:41720", "right": "issue:46209", "accept": false, - "reason": "Qwen3 auto-device-map cudaErrorAssert and FP8 inference failure on B200 are separate hardware/runtime problems." + "reason": "Both are Qwen hardware/runtime failures, but one is auto device mapping on A800 and the other is FP8 inference on B200; different bugs." }, { - "left": "issue:44561", - "right": "issue:46234", + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor output size mismatch and AMP/CUDA loss crash are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "A forward-vs-from_latents mismatch is unrelated to a GraniteSpeech CI test issue." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs issues, but they target different pipelines and different deprecations." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "Different model/helper bugs with no shared code-path evidence." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center arg in an extractor is unrelated to Whisper empty-transcription generation." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Float16 AMP crash and missing auxiliary losses are different D-FINE/LwDetr issues." + }, + { + "left": "issue:43335", + "right": "issue:43550", "accept": false, - "reason": "Removal of is_torch_fx_available and missing is_falcon_mamba_ssm_available are different API compatibility issues." + "reason": "SwitchTransformers sparse-layer construction and Bamba torch.compile SDPA failures are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "Device-mismatch CPU offload bug and qwen3_omni_moe helper-length bug are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative overall. The only accepted soft edge is well supported by the titles: both issues are load-time `pad_token_id` AttributeErrors on config objects, so treating them as the same regression is reasonable. The remaining pairings are phrased cautiously as distinct bugs and do not overstate evidence from the packet." + "feedback": "The summary is well grounded in the packet: 44521 has the strongest inbound-reference/activity profile, and the duplicate calls are conservative. The only accepted soft edges are plausibly the same bug class (pad_token_id config errors and the SigLIP2 discrepancy/symptom pair), while the rest are appropriately rejected as different failures." }, "evaluator_used": true, "retried": false, @@ -7961,14 +8126,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 25, - "review_unit_count": 50, + "review_unit_index": 26, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28218", "issue:29942", @@ -7976,6 +8141,7 @@ "issue:35141", "issue:37428", "issue:39692", + "issue:42490", "issue:43278", "issue:43335", "issue:43388", @@ -7989,16 +8155,15 @@ "issue:43720", "issue:43819", "issue:43825", - "issue:43827", - "issue:43901", + "issue:43854", "issue:43931", "issue:44112", "issue:44206", "issue:44351", "issue:44448", "issue:44493", - "issue:44610", "issue:44743", + "issue:44779", "issue:44792", "issue:44855", "issue:44857", @@ -8012,7 +8177,6 @@ "issue:45459", "issue:45478", "issue:45563", - "issue:45584", "issue:45588", "issue:45593", "issue:45823", @@ -8020,286 +8184,251 @@ "issue:46234" ], "soft_pairs": [ - "issue:44610|issue:44857", - "issue:43819|issue:44112", - "issue:43827|issue:43901", - "issue:43819|issue:45083", - "issue:44206|issue:45584", - "issue:43335|issue:43550", - "issue:44857|issue:45593", - "issue:43606|issue:45083", "issue:44792|issue:45563", - "issue:44448|issue:44743", "issue:37428|issue:43425", "issue:45200|issue:45588", + "issue:44448|issue:44743", "issue:45127|issue:45245", "issue:43611|issue:43931", - "issue:45290|issue:45381", "issue:43335|issue:43653", - "issue:44855|issue:45083", - "issue:43550|issue:44112", + "issue:45290|issue:45381", "issue:43819|issue:44493", + "issue:44855|issue:45083", "issue:44206|issue:45823", + "issue:43550|issue:44112", "issue:29942|issue:32090", "issue:43335|issue:43504", - "issue:45588|issue:45859", "issue:37428|issue:44351", + "issue:45588|issue:45859", "issue:43278|issue:43825", "issue:45459|issue:46234", "issue:39692|issue:43526", "issue:43388|issue:43526", - "issue:43335|issue:45083", "issue:45310|issue:45478", + "issue:43335|issue:45083", "issue:39692|issue:44493", "issue:28218|issue:35141", "issue:43720|issue:44112", "issue:43335|issue:44112", - "issue:43335|issue:45593" + "issue:44448|issue:44779", + "issue:43335|issue:45593", + "issue:42490|issue:43854", + "issue:43606|issue:44857" ], - "prepared_review_unit_hash": "69d334598dab42e01d4d761aa92dcac72e5f2eb07f232bf8feaf7f09ccc220b6", + "prepared_review_unit_hash": "558d53173a98bbc6bbe6b0440b053514a1b8d9b328e934f0dc8469851b2fd02b", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 35, - "serialized_chars": 38417, - "estimated_input_tokens": 9605, - "estimated_eval_tokens": 19466 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36338, + "estimated_input_tokens": 9085, + "estimated_eval_tokens": 18426 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous; the only clear duplicate pair is the repeated Qwen3.5 MoE `from_pretrained` regression report. All other soft pairs are related only at a broad subsystem level and should stay separate.", - "confidence": 0.74, - "canonical_issue_reason": "issue:45310 is the best canonical issue because it is the earlier, fuller report of the Qwen3.5 MoE `from_pretrained` regression, and issue:45478 appears to be the later duplicate of the same bug.", + "summary": "The cluster is mostly a grab-bag of unrelated Transformers issues; only one soft pair looks like a true duplicate: the Qwen3.5 Moe from_pretrained regression reported twice with the same title and nearly identical scope.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45310 is the better canonical issue because it is the earlier report of the exact same Qwen3.5 Moe from_pretrained failure; issue:45478 reads like a later duplicate.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45310 is the strongest representative issue in the cluster: it has the same concrete failure mode as issue:45478, clearer scope, and is the earlier tracking report. The rest of the cluster is too mixed to use as a single thematic representative.", + "best_issue_reason": "issue:45310 is the strongest representative item in the cluster because it is a concrete, narrowly-scoped regression report and the only clear duplicate anchor here.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44610", - "right": "issue:44857", - "accept": false, - "reason": "Both are vision/detection runtime bugs, but they affect different models and different code paths; not the same underlying defect." - }, - { - "left": "issue:43819", - "right": "issue:44112", - "accept": false, - "reason": "One is a DAC decoding/STE mismatch, the other is a GraniteSpeech CI device-override test failure; no shared bug identity." - }, - { - "left": "issue:43827", - "right": "issue:43901", - "accept": false, - "reason": "Both are docs-related, but they describe different pipeline API/documentation mismatches and are not the same change or bug." - }, - { - "left": "issue:43819", - "right": "issue:45083", - "accept": false, - "reason": "Unrelated model internals: DAC latent reconstruction vs. qwen3_omni_moe feature-length helper behavior." - }, - { - "left": "issue:44206", - "right": "issue:45584", - "accept": false, - "reason": "Both are audio-related, but one is an audio feature extractor arg crash and the other is Whisper generation on empty transcription; different failures." - }, - { - "left": "issue:43335", - "right": "issue:43550", - "accept": false, - "reason": "Different models and different failure modes: SwitchTransformers config construction vs. Bamba torch.compile/SDPA issue." - }, - { - "left": "issue:44857", - "right": "issue:45593", - "accept": false, - "reason": "Both involve detection models, but the bugs are distinct (AMP crash vs. missing auxiliary losses)." - }, - { - "left": "issue:43606", - "right": "issue:45083", - "accept": false, - "reason": "Device-mismatch CPU offload issue in Bark is unrelated to qwen3_omni_moe helper behavior." - }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "A janus test failure and a stale generate() warning are different issues." - }, - { - "left": "issue:44448", - "right": "issue:44743", - "accept": false, - "reason": "Pegasus output regression and Qwen3 recurrent-state reset are different model-specific bugs." + "reason": "Different bugs: a Janus generate_images test failure vs a stale warning in paged generate() for num_return_sequences." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "A missing import symbol and a Torch 2.10 compatibility report are related only broadly to versioning, not the same defect." + "reason": "ImportError for a missing flash-attention helper is not the same issue as generic Torch 2.10 incompatibility." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Different code paths: Gemma4 token-type defaults vs. flash_attention sink-less model crash." + "reason": "Gemma4 token-type-id behavior and a flash_attention.py s_aux=None crash are unrelated code paths." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output drift and Qwen3 recurrent-state reset are different model behaviors." }, { "left": "issue:45127", "right": "issue:45245", "accept": false, - "reason": "LoRA merge collapse with tied embeddings is unrelated to the 2^24 category limit error." + "reason": "LoRA merging with extended vocab is unrelated to the 2^24 category-count runtime limit." }, { "left": "issue:43611", "right": "issue:43931", "accept": false, - "reason": "Base-model-prefix loading breakage and Qwen3-VL shape mismatch are distinct model-loading failures." - }, - { - "left": "issue:45290", - "right": "issue:45381", - "accept": false, - "reason": "Chat template tool-call handling and Qwen2.5-VL video position IDs are different bugs." + "reason": "Base_model_prefix loading regression and Qwen3-VL weight-shape mismatch are different load failures." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and BigBirdTokenizer special-token registration are unrelated." + "reason": "SwitchTransformers sparse-layer config bug and BigBirdTokenizer special-token registration are unrelated." }, { - "left": "issue:44855", - "right": "issue:45083", + "left": "issue:45290", + "right": "issue:45381", "accept": false, - "reason": "Python 3.13 import/torchscript parsing error is unrelated to qwen3_omni_moe feature-length output behavior." + "reason": "Chat-template tool-call handling and qwen2.5-vl vision_position_ids are separate bugs." }, { - "left": "issue:43550", - "right": "issue:44112", + "left": "issue:43819", + "right": "issue:44493", "accept": false, - "reason": "Different subsystems and failures: compile/SDPA vs. CI stale device override test." + "reason": "DAC.from_latents/STE mismatch is not the same underlying problem as unexpected position-id keys." }, { - "left": "issue:43819", - "right": "issue:44493", + "left": "issue:44855", + "right": "issue:45083", "accept": false, - "reason": "DAC latent reconstruction and unexpected position-id keys are not the same bug." + "reason": "Python 3.13 IndentationError on import is unrelated to qwen3_omni_moe feature-extractor helper behavior." }, { "left": "issue:44206", "right": "issue:45823", "accept": false, - "reason": "Both are device-related, but they hit different models and different mechanisms; not mergeable as one fix." + "reason": "Unsupported center argument in LasrFeatureExtractor and Gemma4 PLE device mismatch are different failures." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba-9B-v2 is unrelated to a stale GraniteSpeech device-override test." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` TypeError are unrelated." + "reason": "Flash Attention 2 test failures and a Trainer _gpu_broadcast_one NoneType error are different subsystems and symptoms." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "SwitchTransformers config construction and Beit pretrained preset loading are different model-loading issues." + "reason": "SwitchTransformers config creates sparse layers; Beit semantic-segmentation preset loading is a legacy-field issue." }, { - "left": "issue:45588", - "right": "issue:45859", + "left": "issue:37428", + "right": "issue:44351", "accept": false, - "reason": "Both involve CPU/offload context, but the failing code paths are different (flash_attention sink-less handling vs. rotary embedding)." + "reason": "Missing _flash_supports_window_size import and missing HybridCache import are both import errors but for different symbols and paths." }, { - "left": "issue:37428", - "right": "issue:44351", + "left": "issue:45588", + "right": "issue:45859", "accept": false, - "reason": "Missing import symbols in different modules are not the same underlying issue." + "reason": "flash_attention.py s_aux=None crash is not the same bug as Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype drift in evaluation and an error-message mismatch about pipeline support are unrelated." + "reason": "Embedding dtype drift during evaluate and a stale pipeline translation warning are unrelated." }, { "left": "issue:45459", "right": "issue:46234", "accept": false, - "reason": "Tokenizer error handling with missing protobuf and a missing import_utils helper are separate API issues." + "reason": "Protobuf-related tokenizer error masking and a missing import_utils availability flag are different issues." }, { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "SigLIP2 docs errors and BeitImageProcessorFast label reduction are different topics." + "reason": "SigLIP2 documentation errors are unrelated to BeitImageProcessorFast reducing labels incorrectly." }, { "left": "issue:43388", "right": "issue:43526", "accept": false, - "reason": "Both touch label handling, but one is metric gathering on tuple labels and the other is Beit fast processor reduction; not the same bug." - }, - { - "left": "issue:43335", - "right": "issue:45083", - "accept": false, - "reason": "SwitchTransformers sparse-layer config and qwen3_omni_moe feature-length helper behavior are unrelated." + "reason": "gather_for_metrics dropping tuple-label elements and BeitImageProcessorFast.reduce_labels are separate bugs." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "These are duplicate reports of the same Qwen3.5 MoE `from_pretrained` failure under transformers>=5.4.0." + "reason": "Same underlying bug: both report transformers>=5.4.0 / Qwen3.5 Moe from_pretrained failure with essentially identical scope and wording." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and a qwen3_omni_moe helper function issue are unrelated." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 documentation example issues and unexpected position-id key warnings are unrelated." + "reason": "SigLIP2 docs example problems do not match the unexpected position-id key regression." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added token and post-init reinitialization of output embeddings are different bugs." + "reason": "Tokenizer adds an extra space after added token and output embedding reinitialization are different model/tokenizer behaviors." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet accelerate-loading unpacking bug and GraniteSpeech CI device override failure are unrelated." + "reason": "BitNet packed-weight unpacking during accelerate loading and a GraniteSpeech stale test are unrelated." }, { "left": "issue:43335", "right": "issue:44112", "accept": false, - "reason": "SwitchTransformers sparse-layer config and a CI stale device override test do not share the same bug." + "reason": "SwitchTransformers sparse-layer config bug and GraniteSpeech stale device-override test are not the same change or failure." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output differences across versions and Deepseek tokenizer regressions are different model-specific issues." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers config creation and D-FINE auxiliary-loss behavior are unrelated model-specific issues." + "reason": "SwitchTransformers config bug and D-FINE auxiliary-loss handling are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Local-path slash import warning and GLM-4.7-Flash unit-test loading failure are distinct loading problems." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch for bark-small and float16 AMP crash in LwDetrImageLoss are different bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The canonicalization is well grounded in the packet: 45310 and 45478 have the same title and appear to be duplicate Qwen3.5 MoE from_pretrained reports, with 45310 slightly earlier. The summary stays conservative about the rest of the cluster being heterogeneous, and the soft-edge verdicts generally reject only broad topical similarity rather than asserting duplicate identity." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, issue:45310 / issue:45478, is strongly supported by identical titles and near-identical scope, while the rest of the verdicts appropriately avoid overclaiming." }, "evaluator_used": true, "retried": false, @@ -8311,14 +8440,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 26, - "review_unit_count": 50, + "review_unit_index": 27, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:25251", "issue:29127", @@ -8326,6 +8455,8 @@ "issue:32090", "issue:34689", "issue:35141", + "issue:36010", + "issue:37428", "issue:38175", "issue:40444", "issue:42490", @@ -8335,12 +8466,10 @@ "issue:43526", "issue:43550", "issue:43575", - "issue:43606", "issue:43611", "issue:43653", "issue:43701", "issue:43746", - "issue:43854", "issue:43927", "issue:44360", "issue:44448", @@ -8370,14 +8499,11 @@ "issue:46285" ], "soft_pairs": [ - "issue:44448|issue:44779", - "issue:42490|issue:43854", - "issue:43606|issue:44857", "issue:45920|issue:46192", "issue:44360|issue:44561", "issue:38175|issue:44493", - "issue:44977|issue:45229", "issue:44857|issue:45072", + "issue:44977|issue:45229", "issue:44448|issue:44977", "issue:34689|issue:35141", "issue:43701|issue:45083", @@ -8390,239 +8516,228 @@ "issue:44561|issue:44779", "issue:44977|issue:45563", "issue:44857|issue:45588", - "issue:43746|issue:46209", - "issue:44568|issue:45491", "issue:43412|issue:45588", + "issue:43746|issue:46209", "issue:45372|issue:45588", + "issue:44568|issue:45491", "issue:43278|issue:43381", - "issue:45198|issue:45803", "issue:45588|issue:45823", "issue:43611|issue:46285", + "issue:45198|issue:45803", "issue:44448|issue:44466", "issue:45245|issue:45563", + "issue:36010|issue:37428", "issue:25251|issue:32090", "issue:43653|issue:44743" ], - "prepared_review_unit_hash": "dcfebee9fe332132c88ca179358d6d98a2439e4ed0bf5806e257ec047ed923b1", + "prepared_review_unit_hash": "bf02d94f5e77dece11ace7a70a6fec8f1070742d1546af4c621f5cb9572a9ebf", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37506, - "estimated_input_tokens": 9377, - "estimated_eval_tokens": 19010 + "soft_pair_count": 30, + "serialized_chars": 36946, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are largely unrelated, spanning tokenizer regressions, model-loading/saving issues, device/dtype mismatches, export failures, and model-specific runtime bugs. None of the soft pairs look like the same underlying bug or change, so all soft edges should be rejected.", - "confidence": 0.97, - "canonical_issue_reason": "Issue 45920 is the best representative because it is the broadest, most explicit v5 tokenizer regression umbrella and covers multiple affected models, making it the strongest canonical issue for a tokenizer-bug cluster.", + "summary": "The set is mostly a collection of unrelated issue reports; the soft-pair similarities are mostly broad subsystem or version-regression overlap rather than the same concrete bug. No PRs are present. I would anchor the cluster on the broad tokenizer regression issue.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45920 is the broadest and most representative concrete bug report here: an open, reproducible tokenizer regression affecting multiple named models, with clear impact and discussion.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45920 is the strongest standalone issue: it is specific enough to be actionable, but broad enough to subsume related tokenizer reports across several models.", + "best_issue_reason": "issue:45920 is the best single issue to represent the cluster because it is specific enough to be actionable yet broad enough to capture the main user-facing regression pattern in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44448", - "right": "issue:44779", - "accept": false, - "reason": "Both are v5 output regressions, but one is Pegasus output drift and the other is a DeepSeek tokenizer error; different code paths and symptoms." - }, - { - "left": "issue:42490", - "right": "issue:43854", - "accept": false, - "reason": "One is a local-path import warning with trailing slash, the other is a model-loading failure for GLM-4.7; not the same defect." - }, - { - "left": "issue:43606", - "right": "issue:44857", - "accept": false, - "reason": "CPU offload device mismatch in bark-small is unrelated to an AMP float16 crash in LwDetrImageLoss." - }, { "left": "issue:45920", "right": "issue:46192", "accept": false, - "reason": "Tokenizer wrong IDs across multiple models is different from return_tensors being ignored when text_kwargs is passed." + "reason": "Different bugs: wrong token IDs from AutoTokenizer vs return_tensors being ignored when text_kwargs is passed." }, { "left": "issue:44360", "right": "issue:44561", "accept": false, - "reason": "DSA indexer ReLU discussion has no overlap with the removal of is_torch_fx_available breaking trust_remote_code models." + "reason": "Unrelated failures: DSA indexer/ReLU discussion vs v5 trust_remote_code import break from removed helper." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Siglip2 zero probabilities and unexpected position-id keys are different model-specific inference bugs." + "reason": "Different symptoms and code paths: zero probabilities in SigLIP2 vs unexpected position-id key warnings." }, { - "left": "issue:44977", - "right": "issue:45229", + "left": "issue:44857", + "right": "issue:45072", "accept": false, - "reason": "Qwen3.5 flash-attention generation failure and Gemma4 multi-GPU OOM are unrelated failures." + "reason": "One is an AMP loss crash; the other is a bfloat16 dtype mismatch during inference." }, { - "left": "issue:44857", - "right": "issue:45072", + "left": "issue:44977", + "right": "issue:45229", "accept": false, - "reason": "Both mention dtype-related problems, but one is an AMP crash in a loss module and the other is a bfloat16 mismatch in different models." + "reason": "Flash-attention generation bug vs multi-GPU CUDA OOM; not the same underlying issue." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Pegasus v4/v5 output differences and Qwen3.5 flash-attention failures affect different models and code paths." + "reason": "Pegasus v4/v5 output regression is distinct from Qwen3.5 flash-attention generation failure." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Model loading breakage for Llama 3.2 vision is unrelated to output embeddings being reinitialized after resize when weights are untied." + "reason": "Model loading failure for Llama 3.2 vision is not the same as post_init reinitializing lm_head after resize." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch and qwen3_omni_moe feature-length helper behavior are distinct issues." + "reason": "Checkpoint key mismatch and qwen3_omni_moe length helper behavior are different problems." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Trainer _gpu_broadcast_one NoneType failure are unrelated." + "reason": "LayoutLMv3 error-message clarity issue is unrelated to Trainer broadcasting NoneType errors." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is not the same underlying bug as a qwen3_omni_moe output-length helper issue." + "reason": "torch.compile/SDPA bug in Bamba is not the same as the qwen3_omni_moe feature-length helper bug." }, { "left": "issue:43927", "right": "issue:45698", "accept": false, - "reason": "Both involve save/load behavior, but one loses custom token IDs and the other loads the wrong custom module; different metadata paths." + "reason": "Both involve save/load behavior, but one loses custom token IDs and the other loads the wrong custom module." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "IterableDataset with multiple images per prompt and BeitImageProcessorFast reduce_labels are different preprocessing bugs." + "reason": "Multi-image IterableDataset finetuning failure is unrelated to BeitImageProcessorFast reduce_labels returning one label." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Flash Attention 2 test failures are unrelated to embedding reinitialization during post_init." + "reason": "Flash Attention 2 test failures and embedding reinitialization after resize are separate regressions." }, { "left": "issue:42490", "right": "issue:43575", "accept": false, - "reason": "Trailing-slash local-model warning is unrelated to Qwen2-57B TP out-of-memory." + "reason": "Trailing-slash local model import warning is unrelated to tensor-parallel OOM on Qwen2-57B." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "A missing helper in v5 trust_remote_code support is not the same bug as DeepSeek tokenizer regression." + "reason": "Removed is_torch_fx_available import break is distinct from DeepSeek tokenizer regression." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Flash-attention generation failure and a stale warning for num_return_sequences are different generate-path issues." + "reason": "Flash-attention generation malfunction is not the same as a stale warning about num_return_sequences." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "Float16 AMP crash in LwDetrImageLoss and flash_attention.py crashing on s_aux=None are separate defects." + "reason": "LwDetrImageLoss AMP crash and flash_attention.py s_aux=None crash are different code paths." }, { - "left": "issue:43746", - "right": "issue:46209", + "left": "issue:43412", + "right": "issue:45588", "accept": false, - "reason": "PEFT checkpoint loading for GraniteSpeech and FP8 inference failure on B200 are unrelated." + "reason": "Gemma3n executorch export issues are unrelated to flash_attention integration null-handling." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:43746", + "right": "issue:46209", "accept": false, - "reason": "Tokenizer add_special_tokens behavior and Gemma3 NaN embeddings with sliding-window attention are not the same bug." + "reason": "PEFT checkpoint loading failure and FP8 inference failure on B200 are unrelated." }, { - "left": "issue:43412", + "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Executorch export guard/support issues are unrelated to flash_attention.py AttributeError on sink-less models." + "reason": "ReasoningEffort import break affects processor loading, not flash_attention None handling." }, { - "left": "issue:45372", - "right": "issue:45588", + "left": "issue:44568", + "right": "issue:45491", "accept": false, - "reason": "Gemma4 processor import failure and flash_attention.py s_aux=None crash are different failures." + "reason": "Tokenizer add_special_tokens regression is unrelated to Gemma3 NaN embeddings with mixed-length batching." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "Embedding dtype drift in eval and gradient checkpointing being unusable in eval mode are distinct." - }, - { - "left": "issue:45198", - "right": "issue:45803", - "accept": false, - "reason": "Wav2Vec2 save/tokenization failure and Fuyu bare-except swallowing errors are unrelated." + "reason": "Embedding dtype drift between train/eval is not the same as gradient checkpointing being disallowed in eval mode." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different runtime bugs." + "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different forward-pass bugs." }, { "left": "issue:43611", "right": "issue:46285", "accept": false, - "reason": "base_model_prefix loading breakage and CLIPTextModel structural inconsistency are both v5 model-structure issues but not the same underlying defect." + "reason": "base_model_prefix load break in v5 is unrelated to CLIP text-model structure inconsistency." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure is distinct from FuyuBatchFeature's bare-except bug." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Pegasus v4/v5 output mismatch and lm_head.weight serialization varying by device are separate regression classes." + "reason": "Both are v4/v5 regressions, but one is generation output drift and the other is lm_head.weight serialization inconsistency." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Category-cardinality limit error and stale generate warning are unrelated." + "reason": "Category-cardinality runtime error is unrelated to a stale generate() warning." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Both are import errors, but they concern different removed symbols and different loading paths." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Pipeline top_k nesting change and Trainer _gpu_broadcast_one NoneType error affect different subsystems and code paths." + "reason": "Pipeline top_k nesting behavior is unrelated to Trainer GPU broadcast of NoneType." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBirdTokenizer special-token decoding issue and qwen3_5 recurrent-state reset bug are unrelated." + "reason": "BigBirdTokenizer special-token registration bug is unrelated to Qwen3.5 recurrent-state reset in cache mode." } ] }, @@ -8637,14 +8752,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 27, - "review_unit_count": 50, + "review_unit_index": 28, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:10000", "issue:15354", @@ -8654,8 +8769,6 @@ "issue:32090", "issue:33357", "issue:34567", - "issue:36010", - "issue:37428", "issue:39692", "issue:41720", "issue:42490", @@ -8664,12 +8777,14 @@ "issue:43065", "issue:43066", "issue:43278", + "issue:43329", "issue:43381", "issue:43421", "issue:43575", "issue:43611", "issue:43653", "issue:43701", + "issue:43756", "issue:43873", "issue:43976", "issue:43994", @@ -8696,238 +8811,252 @@ "issue:46121" ], "soft_pairs": [ - "issue:36010|issue:37428", "issue:43065|issue:45412", "issue:45459|issue:45712", "issue:43611|issue:46121", "issue:44186|issue:45198", - "issue:44361|issue:45198", "issue:29127|issue:34567", "issue:33357|issue:39692", "issue:44871|issue:44977", + "issue:44361|issue:45198", "issue:45372|issue:45459", "issue:44206|issue:44479", "issue:42915|issue:42994", "issue:43994|issue:45412", "issue:29942|issue:30064", "issue:43976|issue:45440", - "issue:43278|issue:43575", "issue:43066|issue:44462", + "issue:43278|issue:43575", "issue:44265|issue:45198", "issue:10000|issue:15354", "issue:42490|issue:43873", "issue:43873|issue:45229", "issue:43065|issue:43994", - "issue:44734|issue:45406", "issue:43381|issue:43701", "issue:43421|issue:45491", + "issue:44734|issue:45406", "issue:43653|issue:44442", "issue:44610|issue:45412", "issue:41720|issue:45229", - "issue:32090|issue:33357" + "issue:32090|issue:33357", + "issue:43756|issue:45440", + "issue:45372|issue:45406", + "issue:43278|issue:43329" ], - "prepared_review_unit_hash": "129375939ff4ce0b3e72ee0d2e5ebe18320f88e0a1b45157669aa27c3144aec0", + "prepared_review_unit_hash": "c47ca10260b59cadf38a181aa1a96b1b657366f5ceceb4648311229e46acad23", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36454, - "estimated_input_tokens": 9114, - "estimated_eval_tokens": 18484 + "soft_pair_count": 31, + "serialized_chars": 37103, + "estimated_input_tokens": 9276, + "estimated_eval_tokens": 18808 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a real duplicate set: it mixes unrelated issues across tokenizers, generation, training, serving, quantization, and model-specific regressions. All soft edges look like false positives.", - "confidence": 0.99, - "canonical_issue_reason": "No safe canonical issue: the items span many unrelated code paths and would not collapse into one duplicate cluster.", + "summary": "This cluster is mostly a set of unrelated Transformers bugs that only share broad subsystem vocabulary (tokenizers, processors, quantization, serving). I found no true duplicate/merge-worthy soft edges; the best triage anchor is the broad open quantization/offloading report.", + "confidence": 0.44, + "canonical_issue_reason": "issue:43873 is the broadest, most reusable issue here: it is open, generic, and already has discussion/references around quantization/offloading failures, making it the best place to consolidate adjacent reports.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a good global representative; the cluster is too heterogeneous to use one issue as the canonical target.", + "best_issue_reason": "issue:43873 is the strongest global canonical candidate because it is the most general active bug report in the set and most suitable as a triage sink for related quantization/offloading complaints.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:36010", - "right": "issue:37428", - "accept": false, - "reason": "Different import failures in different modules: GenerationMixin vs flash-attention utility." - }, { "left": "issue:43065", "right": "issue:45412", "accept": false, - "reason": "Sam3PixelDecoder dummy layer vs RT-DETR memory leak; unrelated bugs." + "reason": "Dummy Sam3PixelDecoder Conv2d and RT-DETR memory retention are unrelated bugs in different model paths." }, { "left": "issue:45459", "right": "issue:45712", "accept": false, - "reason": "Tokenizer error masking with missing protobuf vs leftover dummy classes; no shared bug." + "reason": "Hidden tokenizer errors from missing protobuf and leftover dummy classes are different issues with different fixes." }, { "left": "issue:43611", "right": "issue:46121", "accept": false, - "reason": "base_model_prefix loading regression vs rope validation TypeError; different code paths." + "reason": "base_model_prefix loading regression and rope-params JSON list handling are unrelated code paths." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2 NER/padding crash vs Wav2Vec2 save/tokenization failure; different tokenizer behavior." - }, - { - "left": "issue:44361", - "right": "issue:45198", - "accept": false, - "reason": "MLukeTokenizer AttributeError is unrelated to Wav2Vec2 tokenization/save_pretrained issues." + "reason": "LayoutLMv2 NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer bugs." }, { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error messaging vs TrainerState token counter update; unrelated training/model issues." + "reason": "A LayoutLMv3 error-message clarity issue is not the same as TrainerState token accounting." }, { "left": "issue:33357", "right": "issue:39692", "accept": false, - "reason": "MacOS CLIP bus error vs SigLIP2 documentation/example errors; different failure modes." + "reason": "MacOS CLIP bus error and SigLIP2 doc example errors are separate model-specific problems." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma-3 eos_token mismatch vs Qwen3.5 flash-attention generation bug; different model/config paths." + "reason": "Gemma eos-token mismatch and Qwen3.5 flash-attention generation failure are distinct symptoms and fixes." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLuke tokenizer attribute errors and Wav2Vec2 save/tokenization failure are not the same underlying bug." }, { "left": "issue:45372", "right": "issue:45459", "accept": false, - "reason": "Gemma4 processor import dependency issue vs protobuf decode-error handling; unrelated." + "reason": "Gemma4 processor import failure and tokenizer protobuf error masking are different failure points." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "LasrFeatureExtractor crash vs video-input regression for Qwen VL models; not the same bug." + "reason": "Unsupported center argument in LasrFeatureExtractor and Qwen VL video-input regression are unrelated." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "Qwen3Moe FP8 config failure vs quantized model saving failure; separate quantization problems." + "reason": "FineGrainedFP8Config failure and quantized-model saving failure are separate quantization bugs." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 bad outputs vs RT-DETR memory leak; unrelated subsystems." + "reason": "SigLIP2 nonsensical outputs and RT-DETR memory leak do not share the same code path." }, { "left": "issue:29942", "right": "issue:30064", "accept": false, - "reason": "Flash Attention 2 test failures vs void segmentation-map processing; different regressions." + "reason": "Flash Attention 2 test failures and void segmentation-map processing are unrelated." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version compatibility issue vs DeepseekV3MoE divergence; unrelated." + "reason": "Python version incompatibility and DeepseekV3MoE divergence are different classes of bugs." }, { - "left": "issue:43278", - "right": "issue:43575", + "left": "issue:43066", + "right": "issue:44462", "accept": false, - "reason": "Embedding dtype drift vs tensor-parallel OOM; different bugs." + "reason": "Wrong tokenizer decoder type in v5 and ignoring tokenizer.json are both tokenizer-related but not the same defect." }, { - "left": "issue:43066", - "right": "issue:44462", + "left": "issue:43278", + "right": "issue:43575", "accept": false, - "reason": "Tokenizer decoder type regression vs AutoTokenizer ignoring tokenizer.json; both tokenizer-related but distinct." + "reason": "Embedding dtype drift during eval and Qwen2 tensor-parallel OOM are unrelated." }, { "left": "issue:44265", "right": "issue:45198", "accept": false, - "reason": "torch.export/torch_compilable_check failure vs Wav2Vec2 tokenization/save failure; unrelated." + "reason": "torch.export failures via torch_compilable_check and Wav2Vec2 save/tokenization issues are different." }, { "left": "issue:10000", "right": "issue:15354", "accept": false, - "reason": "DistilBertModel issue vs GeneratorExp unsupported in torch.jit.script; unrelated model/export bugs." + "reason": "German DistilBertModel issue and GeneratorExp/JIT export failure are unrelated legacy bugs." }, { "left": "issue:42490", "right": "issue:43873", "accept": false, - "reason": "Trailing-slash local model warning vs quantization offloading regression; different behavior." + "reason": "Path-with-slash import warning and quantization/offloading malfunction are not the same bug." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Offloading-with-quantization problem vs multi-GPU CUDA OOM; both memory-related but not the same bug." + "reason": "Offloading/quantization behavior and Gemma4 multi-GPU OOM are distinct resource-management problems." }, { "left": "issue:43065", "right": "issue:43994", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder vs SigLIP2 inference issues; unrelated." - }, - { - "left": "issue:44734", - "right": "issue:45406", - "accept": false, - "reason": "KV-cache continuation indexing crash vs Gemma4Processor missing _tokenizer; different code paths." + "reason": "Sam3 pixel decoder dummy Conv2d and SigLIP2 output corruption are unrelated model issues." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Eval-mode checkpointing restriction vs resume_from_checkpoint key mismatch; unrelated training-state bugs." + "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch are different trainer behaviors." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token update feature vs Gemma3 NaN embeddings; not the same issue." + "reason": "Runtime special-token post-processing and Gemma3 mixed-length NaNs are not the same underlying bug." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation indexing in serve and Gemma4Processor missing _tokenizer are different serve failures." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer special-token registration vs AutoTokenizer loading FastSpeech2ConformerTokenizer; distinct tokenizer problems." + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer failing to load a tokenizer class are separate tokenizer issues." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor image size mismatch and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "A800 cudaErrorAssert with auto device mapping and Gemma4 OOM are different hardware/runtime failures." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer NoneType broadcast error and MacOS CLIP bus error are unrelated." }, { - "left": "issue:44610", - "right": "issue:45412", + "left": "issue:43756", + "right": "issue:45440", "accept": false, - "reason": "Processor/model size mismatch vs RT-DETR memory leak; unrelated." + "reason": "Smollm3 RoPE layer mismatch and DeepseekV3MoE divergence are different model-implementation discrepancies." }, { - "left": "issue:41720", - "right": "issue:45229", + "left": "issue:45372", + "right": "issue:45406", "accept": false, - "reason": "Qwen3 auto device-mapping assert vs Gemma4 multi-GPU OOM; different hardware/runtime failures." + "reason": "Both involve Gemma4, but one is an import-time processor-loading failure and the other is a missing attribute in transformers serve; not the same concrete bug." }, { - "left": "issue:32090", - "right": "issue:33357", + "left": "issue:43278", + "right": "issue:43329", "accept": false, - "reason": "Trainer NoneType broadcast error vs MacOS bus error with CLIP; unrelated issues." + "reason": "BF16/FP32 eval dtype drift and multimodal video-token counting are unrelated." } ] }, @@ -8942,26 +9071,28 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 28, - "review_unit_count": 50, + "review_unit_index": 29, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ + "issue:28218", "issue:29127", "issue:29942", + "issue:32090", + "issue:33290", "issue:33357", + "issue:34567", "issue:35141", "issue:36010", "issue:38175", "issue:42490", "issue:42915", "issue:43262", - "issue:43278", - "issue:43329", "issue:43334", "issue:43381", "issue:43452", @@ -8971,7 +9102,6 @@ "issue:43646", "issue:43701", "issue:43723", - "issue:43756", "issue:43761", "issue:43824", "issue:43931", @@ -8982,17 +9112,16 @@ "issue:44279", "issue:44387", "issue:44442", + "issue:44464", "issue:44554", "issue:44743", "issue:44811", "issue:44857", "issue:44977", "issue:45072", - "issue:45103", "issue:45245", - "issue:45372", - "issue:45406", "issue:45440", + "issue:45491", "issue:45584", "issue:45588", "issue:45593", @@ -9001,15 +9130,11 @@ "issue:45907" ], "soft_pairs": [ - "issue:43756|issue:45440", - "issue:43278|issue:43329", - "issue:45372|issue:45406", - "issue:43526|issue:45834", "issue:29942|issue:36010", + "issue:43526|issue:45834", "issue:43723|issue:44554", "issue:43761|issue:45859", "issue:45440|issue:45593", - "issue:45103|issue:45372", "issue:43526|issue:44186", "issue:43575|issue:43701", "issue:44977|issue:45245", @@ -9020,205 +9145,202 @@ "issue:43824|issue:44279", "issue:44442|issue:45072", "issue:43646|issue:44077", - "issue:29127|issue:35141", "issue:42915|issue:43931", - "issue:44743|issue:44811", + "issue:29127|issue:35141", "issue:43262|issue:44206", + "issue:44743|issue:44811", "issue:43452|issue:45588", "issue:44977|issue:45584", "issue:33357|issue:38175", - "issue:44062|issue:45907" + "issue:44062|issue:45907", + "issue:28218|issue:32090", + "issue:44464|issue:45491", + "issue:33290|issue:34567" ], - "prepared_review_unit_hash": "5333ce7461c1b4c300bab98dbbc8e4dfb096c96200dd817c37afd48ddcb11c9d", + "prepared_review_unit_hash": "e73a8f4603d3da70477ce9bfbaab800618f25f718258b698f010c05ad32a1e36", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 27, - "serialized_chars": 35862, - "estimated_input_tokens": 8966, - "estimated_eval_tokens": 18188 + "soft_pair_count": 26, + "serialized_chars": 35352, + "estimated_input_tokens": 8838, + "estimated_eval_tokens": 17932 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated Transformers bug reports across different models, APIs, and regressions. None of the soft pairs looks like the same underlying bug or change, so all soft edges are rejected.", - "confidence": 0.94, - "canonical_issue_reason": "No single issue is a clear canonical for this cluster; the set is heterogeneous and does not collapse to one underlying defect.", + "summary": "This cluster is a broad mix of unrelated Transformers issues spanning tokenizers, model loading, training, quantization, attention, and hardware/backend-specific regressions. I don\u2019t see any soft pair that is the same underlying bug or a plausible single merged fix, so all candidate links should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: the items do not form one duplicate family and cover many unrelated code paths, so there is no single issue that meaningfully represents the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "No global best issue stands out because the items span unrelated failures across different components and models.", + "best_issue_reason": "No single issue is a good global representative because the cluster is not a coherent duplicate set; selecting one would be arbitrary.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43756", - "right": "issue:45440", - "accept": false, - "reason": "Different model families and different bugs: RoPE-layer handling vs DeepSeekV3MoE divergence from remote implementation." - }, - { - "left": "issue:43278", - "right": "issue:43329", - "accept": false, - "reason": "One is an embedding dtype regression during eval; the other is an undefined-variable bug in multimodal token counting." - }, - { - "left": "issue:45372", - "right": "issue:45406", + "left": "issue:29942", + "right": "issue:36010", "accept": false, - "reason": "Both touch Gemma 4 loading, but one is a missing dependency import and the other is a processor attribute crash; not the same bug." + "reason": "Flash Attention 2 test failures and a GenerationMixin import error are unrelated failures in different subsystems." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "Different processors and failures: BEiT label reduction vs Kosmos2.5 OCR long-input indexing." - }, - { - "left": "issue:29942", - "right": "issue:36010", - "accept": false, - "reason": "Unrelated issues: Flash Attention 2 test failures vs GenerationMixin import breakage." + "reason": "BEiT label reduction and Kosmos2.5 OCR long-input indexing are different vision preprocessor bugs." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are unrelated code paths." + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are not the same code-path problem." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "Different models and subsystems: CLIPVision hidden-state regression vs Qwen rotary embedding CPU-offload incompatibility." + "reason": "CLIP hidden_states regression and Qwen3_Moe rotary embedding CPU offload incompatibility are unrelated." }, { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "Different bugs in different models: DeepSeekV3MoE divergence vs D-FINE auxiliary-loss handling." - }, - { - "left": "issue:45103", - "right": "issue:45372", - "accept": false, - "reason": "Auto-docstring annotation handling and Gemma 4 dependency import failure are unrelated." + "reason": "DeepSeekV3 divergence and D-FINE auxiliary-loss behavior are distinct model-specific issues." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "Both are tokenizer/processor bugs, but they affect different models and distinct failure modes." + "reason": "BEiT image processor label reduction and LayoutLMv2 tokenizer crashes are different tokenizer/processor bugs." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "OOM during tensor-parallel model load is unrelated to resume-from-checkpoint key mismatch." + "reason": "TP OOM on Qwen2-57B loading and resume_from_checkpoint key mismatch are unrelated training/loading issues." }, { "left": "issue:44977", "right": "issue:45245", "accept": false, - "reason": "Flash-attention generation failure and category-count overflow are unrelated issues." + "reason": "Qwen3.5 flash-attention generation bug and category-count limit errors are unrelated failures." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "Different components and bugs: BEiT processor label reduction vs LwDetrImageLoss AMP crash." + "reason": "These affect different components: BEiT image processing versus LwDetrImageLoss AMP behavior." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both mention memory pressure, but one is tp load OOM and the other is int4 reserved-memory growth; not the same defect." + "reason": "Both mention OOM, but one is TP model loading and the other is int4 quantization memory growth; not the same bug." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Local-path import warnings and gradient-checkpointing eval-mode behavior do not share an underlying bug." + "reason": "Path-trailing-slash import warning and gradient-checkpointing eval-mode restriction are unrelated." }, { "left": "issue:43334", "right": "issue:43531", "accept": false, - "reason": "Different Qwen variants and different errors: missing pad_token_id vs sliding_window behavior." + "reason": "Qwen3-VL pad_token_id loading failure and Qwen3-MoE sliding_window behavior are different model/config regressions." }, { "left": "issue:43824", "right": "issue:44279", "accept": false, - "reason": "An import error for a specific VL model is unrelated to a general dependency issue with transformers." + "reason": "A missing Qwen2.5-VL import and a generic dependency issue are not the same concrete bug." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are unrelated." + "reason": "Tokenizer loading failure and dtype mismatch in inference are unrelated problems." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "The first is a broad Transformers 5 initialization regression; the second is a specific patchtsmixer post_init policy issue." - }, - { - "left": "issue:29127", - "right": "issue:35141", - "accept": false, - "reason": "LayoutLMv3 error messaging and token-embedding reinitialization are unrelated." + "reason": "General v5 custom model init breakage and a patchtsmixer-specific post_init restriction are not the same underlying issue." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Different models and failures: FineGrainedFP8Config support vs Qwen3-VL weight-shape mismatch." + "reason": "FineGrainedFP8 config failure and Qwen3-VL weight-shape mismatch are different model-loading errors." }, { - "left": "issue:44743", - "right": "issue:44811", + "left": "issue:29127", + "right": "issue:35141", "accept": false, - "reason": "Qwen recurrent-state caching and Whisper batch_decode skip_special_tokens are unrelated subsystems." + "reason": "LayoutLMv3 error-message clarity and embedding reinitialization after resize are unrelated." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Both are audio-preprocessing related, but one is apply_chat_template sampling-rate defaulting and the other is an unsupported center-arg crash." + "reason": "Audio chat-template sample-rate defaulting and unsupported center argument in feature extraction are different audio-preprocessing bugs." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset and Whisper batch_decode skip_special_tokens handling are separate generation/decoder issues." }, { "left": "issue:43452", "right": "issue:45588", "accept": false, - "reason": "GGUF loading breakage for tokenizer/model APIs is unrelated to a flash-attention crash on sink-less models." + "reason": "gguf_file loading breakage and flash_attention s_aux=None crashes are unrelated loader versus attention failures." }, { "left": "issue:44977", "right": "issue:45584", "accept": false, - "reason": "Both are generation failures, but they involve different models and different code paths." + "reason": "Qwen3.5 flash-attention generation and Whisper empty-transcription failure do not share a concrete code path." }, { "left": "issue:33357", "right": "issue:38175", "accept": false, - "reason": "Different CLIP/SigLIP models and distinct symptoms: MacOS bus error vs zero probabilities." + "reason": "MacOS bus error on CLIP and SigLIP2 zero-probability outputs are distinct model/runtime issues." }, { "left": "issue:44062", "right": "issue:45907", "accept": false, - "reason": "AddedToken special-argument duplication and list_repo_files revision forwarding are unrelated bugs." + "reason": "AddedToken special-arg duplication and list_repo_files missing revision forwarding are unrelated API bugs." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer added-space behavior and Trainer _gpu_broadcast_one NoneType handling are entirely different subsystems." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward and Gemma3 NaNs under mixed-length sliding-window attention are not the same bug." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor+DeepSpeed OOM and TrainerState token counter not updating are unrelated training issues." } ] }, @@ -9233,23 +9355,24 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 29, - "review_unit_count": 50, + "review_unit_index": 30, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ - "issue:28218", + "issue:29127", "issue:32090", "issue:33290", - "issue:34567", + "issue:33357", "issue:34689", "issue:36010", "issue:42175", "issue:42907", + "issue:43295", "issue:43316", "issue:43381", "issue:43493", @@ -9260,6 +9383,7 @@ "issue:43650", "issue:43720", "issue:43761", + "issue:43825", "issue:43827", "issue:43873", "issue:43931", @@ -9267,7 +9391,6 @@ "issue:44188", "issue:44190", "issue:44442", - "issue:44464", "issue:44479", "issue:44496", "issue:44568", @@ -9277,23 +9400,20 @@ "issue:44898", "issue:44913", "issue:44964", + "issue:44987", "issue:45137", "issue:45216", "issue:45290", "issue:45440", "issue:45479", - "issue:45491", "issue:45698", "issue:45759", "issue:45803", + "issue:46178", "issue:46202", - "issue:46209", "issue:46234" ], "soft_pairs": [ - "issue:28218|issue:32090", - "issue:44464|issue:45491", - "issue:33290|issue:34567", "issue:44442|issue:44898", "issue:43381|issue:43873", "issue:44964|issue:45440", @@ -9301,228 +9421,224 @@ "issue:34689|issue:43611", "issue:32090|issue:33290", "issue:43720|issue:44442", - "issue:44479|issue:45290", "issue:43931|issue:45216", "issue:34689|issue:36010", + "issue:44479|issue:45290", "issue:44442|issue:45803", - "issue:43550|issue:44743", "issue:43493|issue:43827", + "issue:43550|issue:44743", "issue:42907|issue:45698", "issue:42175|issue:46234", "issue:43873|issue:44871", "issue:43643|issue:44913", "issue:43761|issue:44188", "issue:43316|issue:45759", - "issue:45290|issue:46209", - "issue:33290|issue:34689", "issue:44190|issue:44496", "issue:44568|issue:45479", + "issue:33290|issue:34689", "issue:44077|issue:44479", "issue:44855|issue:45137", - "issue:43650|issue:46202" + "issue:44987|issue:46178", + "issue:43650|issue:46202", + "issue:29127|issue:33357", + "issue:43295|issue:43825" ], - "prepared_review_unit_hash": "791e08a582ef2b611b2bd7469a92c4b6104f140f69d32d6c4d8491c375290867", + "prepared_review_unit_hash": "728b2135f416f1f26e576ba38eee0ddaa0ad87264a51d4181d16674fc79bd736", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 29, - "serialized_chars": 36053, - "estimated_input_tokens": 9014, - "estimated_eval_tokens": 18284 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36423, + "estimated_input_tokens": 9106, + "estimated_eval_tokens": 18468 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are mostly unrelated Transformers issues that were linked only by loose textual similarity. No soft edge looks like the same underlying bug/change, so none should be merged as duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "If a representative issue is needed, issue 45698 is the broadest and most active loading/saving report here, with multiple references and discussion around from_pretrained/save_pretrained behavior.", + "summary": "These items are mostly thematically similar Transformers bugs, but the soft-edge pairs do not describe the same underlying defect or change. I would not merge any of the proposed pairs as duplicates, and there are no PRs in this cluster.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45698 is the strongest standalone triage candidate because it is open, has higher discussion/inbound refs, and concerns a general model-loading regression rather than a model-specific edge case.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:28218", - "right": "issue:32090", - "accept": false, - "reason": "Tokenizer added-token spacing is unrelated to Trainer's _gpu_broadcast_one NoneType error." - }, - { - "left": "issue:44464", - "right": "issue:45491", - "accept": false, - "reason": "Chunked generation with compiled forward is a different failure mode from Gemma3 mixed-length NaN embeddings." - }, - { - "left": "issue:33290", - "right": "issue:34567", - "accept": false, - "reason": "Deepspeed Adafactor OOM and num_input_tokens_seen not updating are distinct trainer/optimizer bugs." - }, { "left": "issue:44442", "right": "issue:44898", "accept": false, - "reason": "Tokenizer loading failure and Perceiver image-classification resolution failure are unrelated code paths." + "reason": "Different failures in different model paths: tokenizer loading vs Perceiver image classification at non-default resolution." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing eval-mode behavior does not match quantization offloading issues." + "reason": "Both are training/runtime issues, but one is gradient checkpointing in eval mode and the other is quantization offloading behavior." }, { "left": "issue:44964", "right": "issue:45440", "accept": false, - "reason": "Phi-4 multimodal loading regression and DeepseekV3MoE implementation divergence are different model-specific bugs." + "reason": "Different multimodal model bugs with different symptoms and code paths: Phi-4-VL loading vs DeepSeekV3MoE implementation divergence." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Gemma3TextConfig API mismatch is not the same as Llama4Config missing pad_token_id." + "reason": "Both are config API mismatches, but they concern different models and different missing fields." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Llama 3.2 Vision loading failure and base_model_prefix loading regression are separate model-loading problems." + "reason": "Both involve model loading regressions, but the affected mechanisms and breakages are unrelated." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer GPU broadcast type error and Adafactor/deepspeed OOM are different training failures." + "reason": "Trainer broadcast TypeError and DeepSpeed AdaFactor OOM are unrelated failures." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "BitNet packed-weight loading bug is unrelated to FastSpeech2ConformerTokenizer auto-loading." - }, - { - "left": "issue:44479", - "right": "issue:45290", - "accept": false, - "reason": "Video-input regression for Qwen variants is not the same as chat-template crashes on tool-call assistant messages." + "reason": "Accelerate packed-weight loading bug vs tokenizer class loading bug; no shared underlying defect." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and Qwen3.5 save_pretrained regression are different load/save failures." + "reason": "One is a weight-shape mismatch on load, the other is a save_pretrained regression for Qwen3.5 checkpoints." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Llama 3.2 Vision loading and GenerationMixin import failure are unrelated import/config issues." + "reason": "Both are loading/import regressions, but one is a specific model load breakage and the other is a GenerationMixin import-path issue." }, { - "left": "issue:44442", - "right": "issue:45803", + "left": "issue:44479", + "right": "issue:45290", "accept": false, - "reason": "Tokenizer loading and Fuyu batch tensor conversion error are different subsystems and symptoms." + "reason": "Both touch multimodal/chat workflows, but one is a video-input regression and the other is a chat template crash on tool-call messages." }, { - "left": "issue:43550", - "right": "issue:44743", + "left": "issue:44442", + "right": "issue:45803", "accept": false, - "reason": "Bamba torch.compile/SDPA failure is unrelated to Qwen3.5 recurrent-state cache reset." + "reason": "Tokenizer loading failure and Fuyu tensor conversion error are unrelated." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "SigLIP2 implementation divergence is not the same as docs still referencing removed pipeline()." + "reason": "SigLIP2 implementation mismatch vs documentation lag after pipeline removals are different issues." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and recurrent-state reset in Qwen3.5 are distinct code-path bugs." }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "Dequantized save failure for Ministral/Devstral is unrelated to wrong custom-module loading after save_pretrained." + "reason": "Both are save/load related, but one is dequantized model saving and the other is custom-module resolution after save_pretrained." }, { "left": "issue:42175", "right": "issue:46234", "accept": false, - "reason": "TensorFlow missing from a torch extra install and a missing import_utils symbol are different packaging/API issues." + "reason": "Backend packaging gap for TensorFlow in a torch install is unrelated to a missing import_utils symbol." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Quantization offloading behavior is unrelated to Gemma-3 eos_token_id config inconsistency." + "reason": "Quantization offloading behavior and Gemma EOS token config inconsistency do not share the same root cause." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "trust_remote_code missing fields and GPTNeoX rotary_pct reload fallback are different config-loading bugs." + "reason": "Both involve config persistence, but one is trust_remote_code returning missing fields and the other is GPTNeoX rotary_pct not surviving reload." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "CLIPVision hidden_states regression is unrelated to attention kernel divergence under torch.compile." + "reason": "Hidden-states output regression in CLIPVisionModel vs attention-kernel divergence under torch.compile are different bugs." }, { "left": "issue:43316", "right": "issue:45759", "accept": false, - "reason": "Gemma3TextConfig API discrepancy and Qwen multimodal text_config unwrapping are different config-shape issues." - }, - { - "left": "issue:45290", - "right": "issue:46209", - "accept": false, - "reason": "Chat template tool-call crash and FP8 inference failure on B200 are unrelated failure modes." - }, - { - "left": "issue:33290", - "right": "issue:34689", - "accept": false, - "reason": "Deepspeed Adafactor OOM and Llama 3.2 Vision loading error are not the same bug." + "reason": "Gemma3TextConfig API discrepancy and AutoModelForCausalLM text_config unwrapping are related only broadly to config handling, not the same defect." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Local dataset loading in a training script and unrecognized model/config.json errors are unrelated." + "reason": "Local dataset loading in a training script and unrecognized-model config.json loading failure are unrelated." }, { "left": "issue:44568", "right": "issue:45479", "accept": false, - "reason": "mDeBERTa special-token regression and sequence-classification zero-loss bug affect different model/task paths." + "reason": "Tokenizer special-token insertion bug and sequence-classification zero-loss bug are completely separate." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "AdaFactor/deepspeed OOM and Llama 3.2 Vision model loading regression are unrelated." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "patchtsmixer post_init policy and Qwen video-input regression are unrelated model-specific changes." + "reason": "PatchTSMixer post_init validation and Qwen video-input regression are different model-specific issues." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "TorchScript import IndentationError and DeepSpeed ZeRO3 deque error are completely different runtime failures." + "reason": "Python 3.13 TorchScript parsing error and DeepSpeed ZeRO3 deque IndexError are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:46178", + "accept": false, + "reason": "Loading a specific model repo and missing tensorflow_text backend mapping are different failure modes." }, { "left": "issue:43650", "right": "issue:46202", "accept": false, - "reason": "Vague data request and Gemma pipeline roundtrip failure on \u2581 are not the same issue." + "reason": "Placeholder 'ADD THE DATA' issue is not the same as a Gemma pipeline roundtrip failure." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and CLIP bus error on macOS are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression and pipeline translation messaging bug are separate v5 regressions." } ] }, @@ -9537,20 +9653,18 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 30, - "review_unit_count": 50, + "review_unit_index": 31, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:25251", "issue:28282", - "issue:29127", "issue:33290", - "issue:33357", "issue:35141", "issue:41950", "issue:42617", @@ -9574,253 +9688,248 @@ "issue:43716", "issue:43742", "issue:43761", - "issue:43825", + "issue:44077", "issue:44162", "issue:44479", "issue:44496", "issue:44514", + "issue:44534", "issue:44617", "issue:44792", "issue:44871", "issue:44877", "issue:44913", - "issue:44987", "issue:45127", "issue:45200", + "issue:45542", "issue:45584", "issue:45656", "issue:45698", "issue:45803", "issue:46050", "issue:46170", - "issue:46178" + "issue:46178", + "issue:46234" ], "soft_pairs": [ - "issue:29127|issue:33357", - "issue:44987|issue:46178", - "issue:43295|issue:43825", "issue:25251|issue:28282", - "issue:43550|issue:43701", "issue:42617|issue:43575", + "issue:43550|issue:43701", "issue:43606|issue:43701", "issue:43540|issue:44514", "issue:33290|issue:35141", "issue:43575|issue:43742", - "issue:33290|issue:45656", "issue:43316|issue:43716", - "issue:43404|issue:43441", - "issue:44162|issue:44792", + "issue:33290|issue:45656", "issue:44871|issue:45584", + "issue:43404|issue:43441", "issue:43316|issue:44877", "issue:43295|issue:44871", + "issue:44162|issue:44792", "issue:45803|issue:46170", "issue:43065|issue:44617", "issue:41950|issue:43475", - "issue:43646|issue:44913", "issue:44871|issue:46050", + "issue:43646|issue:44913", "issue:45127|issue:45200", "issue:43452|issue:44496", "issue:43761|issue:44479", "issue:43232|issue:43388", "issue:43504|issue:45698", - "issue:43572|issue:46178" + "issue:43572|issue:46178", + "issue:44077|issue:44534", + "issue:45542|issue:46234" ], - "prepared_review_unit_hash": "5d794f083919246a7b75a049651a1ea19c157032cb0e5b0acd97c52bcd2cb97f", + "prepared_review_unit_hash": "8ef1263ceaa76643d6ed4fb3d6d68319ed4923c15d7fe29be6639918a9aba4e0", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 28, - "serialized_chars": 36078, - "estimated_input_tokens": 9020, - "estimated_eval_tokens": 18296 + "soft_pair_count": 27, + "serialized_chars": 35731, + "estimated_input_tokens": 8933, + "estimated_eval_tokens": 18122 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: the items cover unrelated pipeline, model-loading, config, OOM, and runtime errors. None of the soft edges look like true duplicates or the same fix path, so all should be rejected.", - "confidence": 0.97, - "canonical_issue_reason": "No single issue captures the cluster; the items span unrelated regressions, configuration mismatches, loading failures, and memory/runtime bugs.", + "summary": "The cluster is highly heterogeneous: the paired issues mostly share only broad subsystem keywords (loading, config, generation, multimodal, deepspeed) but not the same underlying bug or fix path. I would not merge any soft-edge pair as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": "No single canonical issue fits the cluster well; the soft pairs span unrelated bugs and regressions rather than one underlying problem.", "canonical_pr_reason": null, - "best_issue_reason": "No issue is a strong global representative because this is not a coherent duplicate set and the reports do not share one underlying code path.", + "best_issue_reason": "issue:45698 is the most broadly impactful and discussion-rich issue in the set, so it is the best representative issue overall, even though it is not a duplicate anchor for the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:29127", - "right": "issue:33357", - "accept": false, - "reason": "Different bugs: LayoutLMv3 box-content validation/error clarity vs a MacOS CLIP bus error." - }, - { - "left": "issue:44987", - "right": "issue:46178", - "accept": false, - "reason": "Both involve loading/backend problems, but one is a model load regression in transformers>=5.1 while the other is a missing BACKENDS_MAPPING entry for tensorflow_text." - }, - { - "left": "issue:43295", - "right": "issue:43825", - "accept": false, - "reason": "Both are regressions around processors/pipelines, but one is custom code accessing processor.tokenizer with images and the other is an incorrect translation-task error message." - }, { "left": "issue:25251", "right": "issue:28282", "accept": false, - "reason": "Unrelated: pipeline top_k output nesting vs AutoModel ImportError because PyTorch is missing." + "reason": "Different problems: pipeline top_k output shape vs missing PyTorch import for AutoModel." }, { - "left": "issue:43550", - "right": "issue:43701", + "left": "issue:42617", + "right": "issue:43575", "accept": false, - "reason": "Different failure modes: torch.compile/SDPA on Bamba vs resume_from_checkpoint key mismatch." + "reason": "Both mention failures/OOM, but one is a script runtime problem and the other is model loading OOM with tensor parallelism." }, { - "left": "issue:42617", - "right": "issue:43575", + "left": "issue:43550", + "right": "issue:43701", "accept": false, - "reason": "Both mention OOM-ish symptoms, but one is running 3d_parallel.py and the other is tensor-parallel loading of a large Qwen model; not the same underlying bug." + "reason": "Unrelated: torch.compile/SDPA failure in Bamba vs resume_from_checkpoint key mismatch." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "CPU offload device mismatch vs checkpoint key mismatch are separate code paths and failures." + "reason": "Different code paths: CPU offload device mismatch vs checkpoint key mismatch on resume." }, { "left": "issue:43540", "right": "issue:44514", "accept": false, - "reason": "Qwen3OmniMoe video-input ValueError and Qwen2_5_VL batched chat-template crash are different APIs and bugs." + "reason": "Both touch multimodal processing, but one is Qwen3OmniMoe video input handling and the other is batched chat template padding behavior." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "Deepspeed/Adafactor OOM is unrelated to embedding reinitialization after resizing token embeddings." + "reason": "Deepspeed Adafactor OOM is unrelated to embedding reinitialization after resize." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Large-model tensor-parallel OOM vs MobileLLM loading KeyError; different root causes." - }, - { - "left": "issue:33290", - "right": "issue:45656", - "accept": false, - "reason": "OOM with Adafactor/DeepSpeed is not the same as optimizer.step being called twice under DeepSpeed." - }, - { - "left": "issue:43316", - "right": "issue:43716", - "accept": false, - "reason": "Gemma3TextConfig API discrepancy and Mistral-3 image preprocessor dtype mismatch are distinct issues." + "reason": "Model-parallel OOM on Qwen2-57B is not the same as a KeyError when loading MobileLLM." }, { - "left": "issue:43404", - "right": "issue:43441", + "left": "issue:43316", + "right": "issue:43716", "accept": false, - "reason": "lm_head weight tying bug in Mistral3ForConditionalGeneration is unrelated to a FlashAttention failure in Ministral-3." + "reason": "Config API discrepancy and image preprocessor dtype mismatch are distinct issues." }, { - "left": "issue:44162", - "right": "issue:44792", + "left": "issue:33290", + "right": "issue:45656", "accept": false, - "reason": "ESM2 breakage and a janus image-generation test failure do not share the same code path." + "reason": "Both involve deepspeed, but one is OOM and the other is duplicate optimizer stepping." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma-3 eos_token_id inconsistency and Whisper empty-transcription failure after align_special_tokens are different bugs." + "reason": "Token/eos configuration mismatch vs Whisper empty-transcription failure after token alignment are different bugs." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but one is tied weights in Mistral3ForConditionalGeneration and the other is FlashAttention in Ministral-3." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "Config API discrepancy for Gemma3TextConfig is not the same as strict config loading failing for granite_speech." + "reason": "Both are config-related, but one is an API discrepancy and the other is strict config loading rejection." }, { "left": "issue:43295", "right": "issue:44871", "accept": false, - "reason": "Custom processor/tokenizer regression is unrelated to Gemma-3 eos_token_id mismatch." + "reason": "Processor/tokenizer regression vs eos_token_id inconsistency are separate regressions." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 workflow breakage and Janus test failure are unrelated models and failure modes." }, { "left": "issue:45803", "right": "issue:46170", "accept": false, - "reason": "Bare except swallowing exceptions in Fuyu conversion is unrelated to the Windows ROCm torch.distributed import problem." + "reason": "Bare except in tensor conversion is unrelated to Windows ROCm distributed import issues." }, { "left": "issue:43065", "right": "issue:44617", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video CUDA OOM are different issues." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video OOM are not the same bug." }, { "left": "issue:41950", "right": "issue:43475", "accept": false, - "reason": "Video-classification pipeline processor selection bug and missing fpn_position_embeddings on Sam3VisionEncoderOutput are not the same defect." + "reason": "Image-processor lookup in a video-classification pipeline is unrelated to missing fpn_position_embeddings on Sam3VisionEncoderOutput." }, { - "left": "issue:43646", - "right": "issue:44913", + "left": "issue:44871", + "right": "issue:46050", "accept": false, - "reason": "Custom model initialization breakage in Transformers 5.0 is separate from GPTNeoXConfig rotary_pct reload behavior." + "reason": "eos_token_id inconsistency is not the same as quantized save/load breakage." }, { - "left": "issue:44871", - "right": "issue:46050", + "left": "issue:43646", + "right": "issue:44913", "accept": false, - "reason": "Gemma-3 eos_token_id mismatch is unrelated to quantized-model save/load corruption." + "reason": "Broad custom-init regression and GPTNeoX rotary_pct reload bug are different code paths." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge collapse with tied embeddings and missing mm_token_type_ids default are different model-behavior bugs." + "reason": "LoRA merge collapse with extended vocab is unrelated to Gemma 4 mm_token_type_ids defaults." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "gguf_file handling for tokenizer/model loading and an unrecognized model_type error are separate from-pretrained/config issues." + "reason": "Both concern model loading, but gguf_file handling and missing model_type in config.json are distinct failures." }, { "left": "issue:43761", "right": "issue:44479", "accept": false, - "reason": "CLIPVisionModel hidden_states regression and Qwen video-input regression affect different models and code paths." + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are different models and outputs." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs update after sync_gpus and gather_for_metrics dropping tuple labels are unrelated training/eval issues." + "reason": "Generation kwarg sync behavior is unrelated to gather_for_metrics dropping label elements." }, { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "Legacy field preventing Beit semantic-segmentation load is not the same as loading the wrong custom module after save_pretrained." + "reason": "Both involve pretrained/save loading, but one is a legacy-field preset load failure and the other is wrong custom-module resolution after save/load." }, { "left": "issue:43572", "right": "issue:46178", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig and tensorflow_text backend mapping are entirely different failures." + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to tensorflow_text backend mapping errors." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Optional post_init policy in patchtsmixer is unrelated to non-persistent buffer initialization in v5." + }, + { + "left": "issue:45542", + "right": "issue:46234", + "accept": false, + "reason": "TensorBoard/TensorFlow backend mismatch and missing is_falcon_mamba_ssm_available are unrelated import-utility issues." } ] }, @@ -9835,14 +9944,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 31, - "review_unit_count": 50, + "review_unit_index": 32, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:35141", "issue:41720", @@ -9883,7 +9992,6 @@ "issue:45245", "issue:45357", "issue:45381", - "issue:45542", "issue:45584", "issue:45588", "issue:45600", @@ -9894,10 +10002,8 @@ "issue:46234" ], "soft_pairs": [ - "issue:44077|issue:44534", - "issue:45542|issue:46234", - "issue:43673|issue:44743", "issue:43761|issue:44242", + "issue:43673|issue:44743", "issue:44792|issue:44977", "issue:44617|issue:45584", "issue:44534|issue:44913", @@ -9917,229 +10023,217 @@ "issue:43550|issue:44190", "issue:45632|issue:46234", "issue:44077|issue:44877", - "issue:43540|issue:44734", "issue:45127|issue:45357", + "issue:43540|issue:44734", "issue:44462|issue:45907", "issue:44521|issue:45381", - "issue:43335|issue:44190", "issue:44737|issue:45803", + "issue:43335|issue:44190", "issue:44112|issue:45600", "issue:43116|issue:44190" ], - "prepared_review_unit_hash": "8d6ecdda8c4c7205dee5268cfeca29e4f07d389538a56efe6ffb0681650afeff", + "prepared_review_unit_hash": "72edd59a7953e5afd95b8e1c8185a4bec6e04e480f30df00f34cb68d57cfeb20", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 37102, - "estimated_input_tokens": 9276, - "estimated_eval_tokens": 18808 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35930, + "estimated_input_tokens": 8983, + "estimated_eval_tokens": 18222 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous; the only clear duplicate-style theme is the Transformers v5 non-persistent-buffer initialization regression, but none of the provided soft edges are exact enough to merge. No PRs are present.", - "confidence": 0.74, - "canonical_issue_reason": "Issue 44534 is the cleanest umbrella for the one substantive bug theme in this set: v5 fills non-persistent buffers with junk. Its wording is broader and more representative than the narrower version-specific report.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues. The only obvious thematic overlap is a small v5 regression subgroup around non-persistent buffers being initialized with junk; the rest are separate bugs spanning model loading, multimodal/video, generation, config reloads, CI, and docs.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 44534 is the best representative issue overall because it most clearly captures the recurring buffer-initialization regression and is the most general title among the relevant items.", + "best_issue_reason": "issue:44534 is the broadest representative of the repeated v5 non-persistent-buffer regression theme, but it does not cover the cluster as a whole.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44077", - "right": "issue:44534", - "accept": false, - "reason": "Different bugs: optional post_init enforcement in PatchTSTMixer vs non-persistent buffer initialization junk in v5." - }, - { - "left": "issue:45542", - "right": "issue:46234", + "left": "issue:43761", + "right": "issue:44242", "accept": false, - "reason": "Unrelated: TensorBoard/TensorFlow backend detection vs a missing import_utils symbol." + "reason": "Different failures: CLIPVision hidden_states regression vs MoE load-balancing loss omission." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Both involve cache/state behavior, but the concrete failures differ: missing generation cache in chunked prefill vs recurrent states resetting in modular_qwen3_5." - }, - { - "left": "issue:43761", - "right": "issue:44242", - "accept": false, - "reason": "Different model paths and failures: CLIPVisionModel hidden_states handling vs missing load-balancing loss when router logits are disabled." + "reason": "Both involve cache/state, but one is missing GenerationMixin cache in chunked prefill and the other resets recurrent states in Qwen3.5." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "Different symptoms and code paths: Janus image generation test failure vs Qwen3.5 flash-attention generation behavior." + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are different code paths." }, { "left": "issue:44617", "right": "issue:45584", "accept": false, - "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription failure after align_special_tokens." + "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription generation after token alignment." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "The buffer-junk regression is unrelated to GPTNeoX rotary_pct resetting on reload." + "reason": "Generic v5 buffer-junk regression vs GPTNeoX rotary_pct reload default bug." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in the example script is unrelated to loading a specific multimodal model checkpoint." + "reason": "Local dataset loading script issue vs model loading failure for Phi-4 multimodal." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "Different problems: a Janus generation test failure vs stale auto_mappings references to removed configs." + "reason": "Janus generate-images test failure vs stale auto_mappings CI breakage; unrelated." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Both are Qwen-related regressions, but one is a video-input regression and the other is KV-cache continuation tensor indexing in serve." + "reason": "Video-input regression across Qwen variants vs serve KV-cache continuation indexing bug." }, { "left": "issue:43827", "right": "issue:43994", "accept": false, - "reason": "Docs still referencing removed pipeline() APIs is not the same as nonsensical AutoModel/pipeline outputs for siglip2." + "reason": "Docs still referencing pipeline() vs SigLIP model/pipeline producing wrong outputs." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 import parsing failure in DebertaV2Model is unrelated to flash_attention crashing on s_aux=None." + "reason": "Python 3.13 JIT parsing problem vs flash_attention AttributeError on sink-less models." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "CUDA assert during Qwen3 auto device mapping is unrelated to the categories upper-bound error." + "reason": "cudaErrorAssert during Qwen3 auto device mapping is unrelated to the 2^24 category limit error." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "A dummy Conv2d in Sam3PixelDecoder is not the same as processor/model input-size mismatch in OmDet-Turbo." + "reason": "Dummy Conv2d in Sam3PixelDecoder vs processor/model input-resolution mismatch." }, { "left": "issue:43931", "right": "issue:44060", "accept": false, - "reason": "Weight-shape mismatch while loading Qwen3-VL is a different failure from an incorrect tied-weights warning in Qwen3-Next." + "reason": "Qwen3-VL weight-shape mismatch vs incorrect tied-weights warning in Qwen3-Next." }, { "left": "issue:45803", "right": "issue:45987", "accept": false, - "reason": "Bare except swallowing errors in FuyuBatchFeature is unrelated to StaticCache.get_seq_length returning the wrong type." + "reason": "Bare except swallowing errors vs StaticCache.get_seq_length() contract mismatch." }, { "left": "issue:35141", "right": "issue:42490", "accept": false, - "reason": "Token-embedding resize reinit in post_init and local-path trailing-slash import warnings are unrelated issues." + "reason": "Embedding resize/reinit bug vs import warning for local paths ending with slash." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "Both mention model/config state, but one is the v5 buffer-junk regression and the other is rotary_pct not persisting on reload." + "reason": "Shared theme is only broad v5 regression; buffer junk initialization is not the same as rotary_pct reset on reload." }, { "left": "issue:43976", "right": "issue:44855", "accept": false, - "reason": "A version support mismatch for Python 3.9+ vs 3.10+ is not the same as a specific IndentationError on Python 3.13." + "reason": "Python version support issue vs IndentationError from @torch.jit.script comment parsing." }, { "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "Sparse-layer construction in SwitchTransformersConfig and a DebertaV2 import parsing error are unrelated." + "reason": "Sparse-layer creation bug and JIT parsing failure are unrelated." }, { "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to local dataset loading in the example script." + "reason": "Bamba torch.compile SDPA failure vs local dataset loading example issue." }, { "left": "issue:45632", "right": "issue:46234", "accept": false, - "reason": "Cache-path collisions for trust_remote_code local models are unrelated to the missing import_utils export." + "reason": "Cache-path collision for trust_remote_code models vs missing import_utils symbol." }, { "left": "issue:44077", "right": "issue:44877", "accept": false, - "reason": "PatchTSTMixer post_init allowance and granite_speech strict-config loading are different configuration issues." + "reason": "Optional post_init policy issue vs strict config rejecting granite_speech config." }, { - "left": "issue:43540", - "right": "issue:44734", + "left": "issue:45127", + "right": "issue:45357", "accept": false, - "reason": "Video-input processing in Qwen3OmniMoe is unrelated to serve-side KV-cache continuation indexing." + "reason": "Both touch Qwen models, but LoRA/extended-vocab collapse and incorrect visual-encoder save keys are different bugs." }, { - "left": "issue:45127", - "right": "issue:45357", + "left": "issue:43540", + "right": "issue:44734", "accept": false, - "reason": "LoRA merge collapse with extended vocab and incorrect visual encoder keys on save_pretrained are different bugs." + "reason": "Video-input processing ValueError in Qwen3OmniMoe vs serve KV-cache tensor indexing bug." }, { "left": "issue:44462", "right": "issue:45907", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json is unrelated to list_repo_files failing to forward revision." + "reason": "AutoTokenizer ignoring tokenizer.json vs list_repo_files not forwarding revision." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "All-zero assistant masks in multimodal chat templates and wrong vision_position_ids in Qwen2.5-VL are related only at a very broad level, not the same bug." + "reason": "assistant_masks all-zero in multimodal templates vs wrong video vision_position_ids; related area but not the same bug." }, { - "left": "issue:43335", - "right": "issue:44190", + "left": "issue:44737", + "right": "issue:45803", "accept": false, - "reason": "SwitchTransformers sparse-layer config and local dataset loading in an example script are unrelated." + "reason": "XLNet CPU device placement bug vs broad exception swallowing in FuyuBatchFeature." }, { - "left": "issue:44737", - "right": "issue:45803", + "left": "issue:43335", + "right": "issue:44190", "accept": false, - "reason": "CPU-side relative positional encoding and a bare except in FuyuBatchFeature are unrelated code paths." + "reason": "SwitchTransformers sparse-layer construction bug vs local dataset loading failure." }, { "left": "issue:44112", "right": "issue:45600", "accept": false, - "reason": "A stale GraniteSpeech device-override test and removed Sam3LiteText auto_mappings references are different CI issues." + "reason": "GraniteSpeech CI stale device override vs auto_mappings referencing removed configs." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Multi-label classification returning empty results and local dataset loading failure are unrelated example-script bugs." + "reason": "Multi-label classification example returns empty results; unrelated to local dataset loading." } ] }, @@ -10154,14 +10248,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 32, - "review_unit_count": 50, + "review_unit_index": 33, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36246", "issue:38175", @@ -10220,9 +10314,9 @@ "issue:45245|issue:45584", "issue:44464|issue:45563", "issue:43650|issue:44220", - "issue:44186|issue:44734", "issue:36246|issue:41628", "issue:43404|issue:45216", + "issue:44186|issue:44734", "issue:44246|issue:45003", "issue:44683|issue:45446", "issue:38175|issue:43065", @@ -10233,8 +10327,8 @@ "issue:44112|issue:44964", "issue:45563|issue:45584", "issue:36246|issue:38617", - "issue:44734|issue:45632", "issue:44561|issue:45632", + "issue:44734|issue:45632", "issue:42907|issue:43441", "issue:43531|issue:45600", "issue:43526|issue:43901", @@ -10243,214 +10337,214 @@ "issue:44496|issue:45042", "issue:43388|issue:43688" ], - "prepared_review_unit_hash": "335dd5967cd6e7cfcf2f5dbbad405dfb430a249719b285e68098d093cab9c79a", + "prepared_review_unit_hash": "8dd9f465f46c44a9566c123e8956156a5f96c6dbdaff4c2c30dbda3824126d63", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36137, - "estimated_input_tokens": 9035, - "estimated_eval_tokens": 18326 + "serialized_chars": 36130, + "estimated_input_tokens": 9033, + "estimated_eval_tokens": 18322 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose topical grouping of mostly unrelated Transformers issues. The soft pairs share broad themes like imports, multimodal configs, or generation, but none look like the same underlying bug/change closely enough to dedupe.", - "confidence": 0.9, - "canonical_issue_reason": "No single issue cleanly represents the cluster: the items span distinct models, subsystems, and failure modes rather than one shared defect.", - "canonical_pr_reason": "No pull requests are present in the cluster.", - "best_issue_reason": "No global best issue stands out because the soft matches are mostly thematic rather than true duplicates; any one issue would misrepresent the rest.", - "best_pr_reason": "No pull requests are present in the cluster.", + "summary": "This cluster is highly heterogeneous: it mixes import regressions, model-loading/config issues, generation bugs, training/eval bugs, and docs/perf reports. There is no clear duplicate stack across the whole set, so only a weak representative issue can be chosen.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 41628 is the broadest, cleanest user-facing regression report among the set: a straightforward top-level import failure with clear impact. It is not a true canonical for all items here, but it is the best single representative of the import-regression subset.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 41628 is the most triage-worthy representative because it is a concrete, broadly understandable import breakage and has the strongest chance of being actionable as a standalone bug report.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:46082", "right": "issue:46121", "accept": false, - "reason": "Both concern config validation, but one is about Llama head_dim checks and the other about JSON-loaded rope ignore_keys type handling; different code paths and bugs." + "reason": "Different failure surfaces: LlamaConfig head_dim validation vs rope-parameter dict conversion TypeError. Not the same bug or code path." }, { "left": "issue:43479", "right": "issue:45375", "accept": false, - "reason": "Both are multimodal config issues, but they affect different configs and different missing-field behavior; not the same defect." + "reason": "Different models and different config-field bugs: Phi4Multimodal default init vs Qwen3.5 MoE vision field dropping." }, { "left": "issue:44938", "right": "issue:45542", "accept": false, - "reason": "A Python 3.14 import/load failure is unrelated to a tensorboard-without-TF backend error." + "reason": "One is a Python 3.14 import/load failure; the other is a backend dependency issue with tensorboard-only installs. Distinct root causes." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Gemma token embedding resizing and Whisper empty-transcription generation are different model behaviors and failure modes." + "reason": "Gemma4 token-embedding resizing bug vs Whisper empty-transcription generation failure. Unrelated code paths." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "Processor/tokenizer regression is unrelated to Gemma4 resize_token_embeddings not updating tied embeddings." + "reason": "Processor/tokenizer regression and embedding-resize bug are different model behaviors and fixes." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "Category-count limits and Whisper empty transcription are unrelated bugs." + "reason": "Category-count limit error is unrelated to Whisper empty transcription handling." }, { "left": "issue:44464", "right": "issue:45563", "accept": false, - "reason": "Chunked generation with compiled forward is a different path from a stale warning in paged generate()." + "reason": "Compiled-forward chunked-generation inconsistency vs stale warning about num_return_sequences. Different generation bugs." }, { "left": "issue:43650", "right": "issue:44220", "accept": false, - "reason": "A vague request issue and an audio feature extraction bug are not the same underlying problem." - }, - { - "left": "issue:44186", - "right": "issue:44734", - "accept": false, - "reason": "LayoutLMv2 tokenizer crashes and server KV-cache continuation indexing failures are separate code paths." + "reason": "No meaningful overlap: placeholder/nonspecific issue title vs fbank feature extraction bug." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and likely different export surfaces." + "reason": "Both are import errors, but they are for different symbols and different underlying breakages." }, { "left": "issue:43404", "right": "issue:45216", "accept": false, - "reason": "A tied-weight bug in Mistral3 is unrelated to Qwen3.5 save_pretrained checkpoint corruption." + "reason": "Weight-tying bug in Mistral3 generation is separate from Qwen3.5 save_pretrained checkpoint regression." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/truncation crash vs serve KV-cache tensor indexing crash; unrelated components." }, { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Import-time slowness and unsafe sys.modules access are related at a broad level, but not the same concrete bug." + "reason": "Import performance regression is not the same as unsafe sys.modules access, even if both concern import internals." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Both touch flex_attention versioning, but one is a compiled runtime failure and the other is a bad version check for an import." + "reason": "Both mention flex_attention, but one is a compiled flex_attention failure on torch 2.9+ while the other is a version-check/import-path bug for AuxRequest." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "Siglip2 zero probabilities and a dummy Conv2d in Sam3PixelDecoder are unrelated model bugs." + "reason": "Different models and symptoms: SigLIP2 zero probabilities vs Sam3PixelDecoder dummy Conv2d." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "A missing image_utils import and a Qwen3.5-35B chat crash do not share the same failure mode." + "reason": "Missing image_utils import and Qwen3.5-35B chat crash are unrelated bugs." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "trust_remote_code returning missing fields is not the same as config parsing failing for an unrecognized model." + "reason": "Both are config/load related, but one is trust_remote_code missing fields and the other is an unrecognized model missing model_type. Different concrete problems." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Both are model loading issues, but they affect different models with different symptoms and likely different fixes." + "reason": "Different models and repro contexts: unit-test loading of GLM-4.7-Flash vs latest-transformers load failure for Phi-4 multimodal." }, { "left": "issue:44964", "right": "issue:45600", "accept": false, - "reason": "Phi-4 multimodal loading and stale auto_mappings entries for removed configs are different problems." + "reason": "Phi-4 multimodal load regression and Sam3LiteText auto_mappings breakage are unrelated." }, { "left": "issue:44112", "right": "issue:44964", "accept": false, - "reason": "A GraniteSpeech CI device-override test failure is unrelated to Phi-4 multimodal loading." + "reason": "CI stale device-override test in GraniteSpeech is not the same issue as model loading failure for Phi-4 multimodal." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "A stale warning in paged generate() is not the same as Whisper generation failing on empty transcription." + "reason": "A stale warning on paged generate() is different from Whisper failing on empty transcription after align_special_tokens." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Both are import errors, but they point to different missing names in different modules." + "reason": "Both are import errors, but they concern different missing symbols and likely different version skew." }, { - "left": "issue:44734", + "left": "issue:44561", "right": "issue:45632", "accept": false, - "reason": "Server KV-cache tensor indexing and trust_remote_code cache-path collisions are unrelated." + "reason": "Removal of is_torch_fx_available breaking trust_remote_code models is unrelated to a local cache-path collision." }, { - "left": "issue:44561", + "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "A removed helper breaking trust_remote_code models is a different issue from local cache path collisions." + "reason": "Serve KV-cache indexing crash and trust_remote_code cache-path collision are distinct bugs." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Ministral save/dequantization failure and Ministral-3 FlashAttention runtime failure are different bugs." + "reason": "Saving dequantized Ministral/Devstral models and FlashAttention inference failure are different code paths and symptoms." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and stale auto_mappings references are unrelated." + "reason": "Qwen3-MoE sliding-window behavior and Sam3LiteText auto_mappings cleanup are unrelated." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "BeitImageProcessorFast label reduction and outdated docs for return_all_scores are unrelated." + "reason": "BeitImageProcessorFast label reduction bug is unrelated to TextClassificationPipeline docs mismatch." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "These are different embedding-resize regressions in different models and components." + "reason": "Different regression targets: processor/tokenizer access vs token embedding resize propagation." }, { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both mention flash attention, but one is a model-specific failure and the other is an AttributeError when s_aux is None." + "reason": "Both touch flash_attention, but one is a Ministral-3 v5 RC failure and the other is an s_aux=None crash for sink-less models; not clearly the same fix." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "Unrecognized model loading and PIL image processors requiring torchvision are distinct issues." + "reason": "Unrecognized model config and PIL-backend torchvision requirement are separate loading/dependency issues." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "A metric gathering edge case and an auxiliary-loss normalization bug are different training/evaluation problems." + "reason": "gather_for_metrics batch truncation and auxiliary-loss normalization are different training/eval bugs." } ] }, @@ -10465,14 +10559,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 33, - "review_unit_count": 50, + "review_unit_index": 34, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:32090", "issue:35141", @@ -10503,10 +10597,10 @@ "issue:44368", "issue:44496", "issue:44617", - "issue:44683", "issue:44779", "issue:44933", "issue:45020", + "issue:45103", "issue:45200", "issue:45216", "issue:45278", @@ -10514,7 +10608,6 @@ "issue:45357", "issue:45372", "issue:45405", - "issue:45542", "issue:45584", "issue:45593", "issue:45759", @@ -10524,245 +10617,245 @@ "issue:46234" ], "soft_pairs": [ - "issue:43673|issue:44336", "issue:41950|issue:44016", "issue:44075|issue:44368", - "issue:43299|issue:45216", + "issue:43673|issue:44336", "issue:42175|issue:44279", - "issue:43381|issue:45593", + "issue:43299|issue:45216", "issue:43901|issue:44496", + "issue:43381|issue:45593", "issue:44016|issue:44220", "issue:44496|issue:45759", - "issue:43650|issue:46209", "issue:45372|issue:46234", "issue:45335|issue:45584", + "issue:43650|issue:46209", "issue:32090|issue:35141", "issue:43479|issue:43525", + "issue:45103|issue:45372", "issue:44242|issue:45200", "issue:43577|issue:45216", - "issue:43299|issue:45357", "issue:38175|issue:44617", + "issue:43299|issue:45357", + "issue:44279|issue:45405", + "issue:44351|issue:45278", "issue:43824|issue:44933", "issue:44779|issue:45812", - "issue:44279|issue:45405", "issue:39692|issue:43901", - "issue:44351|issue:45278", "issue:41950|issue:45020", - "issue:43295|issue:44779", "issue:44016|issue:44062", + "issue:43295|issue:44779", "issue:41950|issue:45823", "issue:43299|issue:43854", - "issue:43976|issue:45405", - "issue:44683|issue:45542" + "issue:43976|issue:45405" ], - "prepared_review_unit_hash": "0f8e4b15bdbc06f7e53724bbc9c89c9c75d4afa410c4b031343a65bedf2e7c9d", + "prepared_review_unit_hash": "6eacf922bb673c02b42c37a9ff430248edb9f6d259e613aa67be7c88015beb7d", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36648, - "estimated_input_tokens": 9162, - "estimated_eval_tokens": 18580 + "serialized_chars": 36144, + "estimated_input_tokens": 9036, + "estimated_eval_tokens": 18328 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a true duplicate set: the items cover many unrelated bugs, regressions, import errors, and docs issues. The soft pairings mostly reflect broad topical similarity (tokenizers, configs, imports, multimodal models) rather than the same underlying fix, so they should stay separate.", - "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue; these items span distinct bugs/regressions/docs/import failures, so collapsing them would be misleading.", + "summary": "This is a loose similarity cluster of mostly unrelated Transformers issues: model-loading regressions, tokenizer/config bugs, import failures, docs problems, and a few pipeline/model-specific reports. The soft pairs do not look like true duplicates; issue 45020 is the closest umbrella representative, but it still does not subsume the rest of the set.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 45020 is the broadest and most representative regression report in the cluster, covering the general theme of recent Transformers versions breaking model loading/remote-code workflows.", "canonical_pr_reason": null, - "best_issue_reason": "No issue in this set is a good global canonical because the group is heterogeneous and the apparent links are mostly superficial.", + "best_issue_reason": "Issue 45020 is the best global issue representative because it is the broadest umbrella regression in the set, though the cluster remains too heterogeneous for a true duplicate canonical.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43673", - "right": "issue:44336", - "accept": false, - "reason": "Chunked-prefill cache behavior and ANSI terminal coloring are unrelated subsystems." - }, { "left": "issue:41950", "right": "issue:44016", "accept": false, - "reason": "Video-classification processor lookup and a notebook syntax error are not the same bug." + "reason": "Video-classification processor lookup is unrelated to a notebook syntax error; different subsystems and failure modes." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "SGD argument handling and a tie_word_embeddings warning in Qwen fine-tuning are different problems." + "reason": "SGD optimizer args being ignored is unrelated to a Qwen LoRA warning about tie_word_embeddings." }, { - "left": "issue:43299", - "right": "issue:45216", + "left": "issue:43673", + "right": "issue:44336", "accept": false, - "reason": "Qwen3VL loading failure and Qwen3.5 save_pretrained checkpoint corruption are different code paths." + "reason": "Chunked-prefill cache handling and ANSI output in loading_report are unrelated." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Missing TensorFlow in a torch extra and a generic dependency issue are too broad and not the same fix." + "reason": "Missing TensorFlow backend on install and a generic dependency issue are not the same bug." }, { - "left": "issue:43381", - "right": "issue:45593", + "left": "issue:43299", + "right": "issue:45216", "accept": false, - "reason": "Gradient checkpointing in eval mode and D-FINE auxiliary-loss handling are unrelated." + "reason": "Both are regression reports, but one is model loading and the other is save_pretrained checkpoint serialization for different Qwen multimodal paths." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "TextClassificationPipeline docs and an unrecognized model/config loading error are unrelated." + "reason": "A docs mismatch for return_all_scores is unrelated to an unrecognized model/config error." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode and D-FINE denoising losses are unrelated training behaviors." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "Notebook syntax and _torch_extract_fbank_features() behavior are different issues." + "reason": "Notebook syntax error and audio fbank feature extraction issue are different problems." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Unrecognized model loading and composite Qwen config unwrapping are separate model/config bugs." - }, - { - "left": "issue:43650", - "right": "issue:46209", - "accept": false, - "reason": "A generic placeholder issue and FP8 inference on B200 have no shared underlying change." + "reason": "Unrecognized-model/config loading and AutoModel text_config unwrapping are both config-related, but they affect different code paths and model classes." }, { "left": "issue:45372", "right": "issue:46234", "accept": false, - "reason": "Different missing imports in different modules; same broad theme, but not the same bug." + "reason": "Gemma4 processor import failure and missing falcon_mamba availability helper are unrelated import/export issues." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "T5Gemma embedding resize and Whisper empty transcription handling are unrelated." + "reason": "Token embedding resizing for T5Gemma is unrelated to Whisper generation on empty transcription." + }, + { + "left": "issue:43650", + "right": "issue:46209", + "accept": false, + "reason": "A placeholder data request and an FP8 inference failure on B200 are unrelated." }, { "left": "issue:32090", "right": "issue:35141", "accept": false, - "reason": "Trainer GPU broadcast NoneType error and embedding reinit after resize/tie_word_embedding=False do not describe the same failure." + "reason": "Trainer GPU broadcast TypeError is unrelated to post_init reinitializing output embeddings after resize_token_embeddings." }, { "left": "issue:43479", "right": "issue:43525", "accept": false, - "reason": "Different config classes with different missing/default fields; not one defect." + "reason": "Phi4Multimodal default config initialization and Llama4 missing pad_token_id are separate config bugs." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation handling is unrelated to the Gemma4 processor import error." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "MoE load-balancing loss gating and Gemma 4 mm_token_type_ids defaults are distinct behaviors." + "reason": "MoE load-balancing loss and Gemma4 mm_token_type_ids defaults do not describe the same bug." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "BLIP2 dtype propagation and Qwen3.5 save_pretrained key serialization are unrelated." + "reason": "BLIP2 dtype loading and Qwen3.5 save_pretrained serialization are different multimodal issues." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated model/runtime failures." }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Qwen3VL loading and Qwen3.5 visual-encoder save_pretrained bugs are different regressions." + "reason": "Both mention Qwen multimodal regressions, but one is model loading and the other is incorrect visual-encoder keys on save; different concrete code paths." }, { - "left": "issue:38175", - "right": "issue:44617", + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A transformers dependency issue is unrelated to an unreleased MIN_PEFT_VERSION bump." + }, + { + "left": "issue:44351", + "right": "issue:45278", "accept": false, - "reason": "SigLIP2 zero-probability outputs and Sam3Video OOM are unrelated." + "reason": "HybridCache import failure and broad import errors after upgrade are related in theme only, not the same underlying defect." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Missing exported model class vs nonexistent image_utils import are different import failures." + "reason": "Different missing-import reports from different modules; no shared concrete bug." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Deepseek tokenizer regression and Granite tokenizer regression are model-specific and not the same patch." - }, - { - "left": "issue:44279", - "right": "issue:45405", - "accept": false, - "reason": "Generic dependency trouble and an unreleased PEFT minimum version are unrelated." + "reason": "Deepseek tokenization regression and Granite token-id regression are separate tokenizer bugs." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "Broken SigLIP2 docs example and stale TextClassificationPipeline docs are separate documentation issues." - }, - { - "left": "issue:44351", - "right": "issue:45278", - "accept": false, - "reason": "A specific HybridCache import miss and a broad import-regression report are too unspecific to merge." + "reason": "SigLIP2 doc example errors and TextClassificationPipeline docs mismatch are both documentation issues but not the same one." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Video pipeline processor lookup and remote_code model breakage are different failure modes." + "reason": "Video-classification processor lookup and remote_code breakages are both regressions, but they hit different pipelines and failure modes." }, { - "left": "issue:43295", - "right": "issue:44779", + "left": "issue:44016", + "right": "issue:44062", "accept": false, - "reason": "Processor.tokenizer/images regression and Deepseek tokenization errors are distinct tokenizer bugs." + "reason": "Notebook syntax error and AddedToken keyword duplication are unrelated." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:43295", + "right": "issue:44779", "accept": false, - "reason": "Notebook syntax error and AddedToken special-argument conflict are unrelated." + "reason": "Custom processor/tokenizer regression and Deepseek tokenizer regression are different code paths and models." }, { "left": "issue:41950", "right": "issue:45823", "accept": false, - "reason": "Image-processor lookup in video classification and Gemma4 device placement are different bugs." + "reason": "Video-classification processor lookup and Gemma4 device mismatch are unrelated." }, { "left": "issue:43299", "right": "issue:43854", "accept": false, - "reason": "Qwen3VL loading breakage and GLM-4.7-Flash unit-test loading failure are unrelated model issues." + "reason": "Qwen3VL loading failure and GLM-4.7 unit-test loading failure are unrelated model-specific regressions." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Python-version support and PEFT minimum-version pinning are unrelated dependency problems." - }, - { - "left": "issue:44683", - "right": "issue:45542", - "accept": false, - "reason": "Torch flex_attention compilation and TensorFlow/tensorboard backend detection are unrelated." + "reason": "Python-version compatibility breakage and an unreleased PEFT minimum version bump are different dependency problems." } ] }, @@ -10777,17 +10870,18 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 34, - "review_unit_count": 50, + "review_unit_index": 35, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:42994", "issue:43065", + "issue:43262", "issue:43317", "issue:43441", "issue:43450", @@ -10835,6 +10929,7 @@ "issue:46132" ], "soft_pairs": [ + "issue:44683|issue:45542", "issue:43650|issue:46132", "issue:44462|issue:45081", "issue:43976|issue:44987", @@ -10842,238 +10937,251 @@ "issue:43976|issue:44279", "issue:43450|issue:44279", "issue:45081|issue:45907", - "issue:44521|issue:45325", "issue:44466|issue:45276", + "issue:44521|issue:45325", "issue:43441|issue:45834", "issue:42994|issue:43317", - "issue:43653|issue:45593", "issue:45600|issue:45712", + "issue:43653|issue:45593", "issue:44623|issue:44749", - "issue:44623|issue:45397", "issue:43065|issue:44898", + "issue:44623|issue:45397", "issue:44261|issue:44263", "issue:44361|issue:45593", "issue:44671|issue:44779", - "issue:44016|issue:45823", "issue:43441|issue:44683", - "issue:43723|issue:44162", + "issue:44016|issue:45823", "issue:43901|issue:43994", - "issue:44297|issue:45397", - "issue:43525|issue:43881", + "issue:43723|issue:44162", "issue:43450|issue:44617", + "issue:43525|issue:43881", + "issue:44297|issue:45397", "issue:43901|issue:44246", "issue:43525|issue:43643", "issue:43784|issue:45542", - "issue:44016|issue:44291" + "issue:44016|issue:44291", + "issue:43262|issue:44521" ], - "prepared_review_unit_hash": "5620ea6855bfa79c5cab3185d15daaceabdf6310635dc4a615e570d1d39f600a", + "prepared_review_unit_hash": "e027b1f16ceb83ee00e6e9e16730b7177a9830c128c8f247001e9fbe08df0018", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 35943, - "estimated_input_tokens": 8986, - "estimated_eval_tokens": 18228 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37170, + "estimated_input_tokens": 9293, + "estimated_eval_tokens": 18842 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a heterogeneous cluster of mostly unrelated closed issues across tokenizer loading/saving, model-specific regressions, multimodal preprocessing, config/serialization bugs, and CI/docs noise. None of the soft pairs look like true duplicates of the same concrete bug or change.", - "confidence": 0.94, - "canonical_issue_reason": "No single canonical issue for the full cluster; the only plausible anchor is issue 44462, but the rest of the items span too many unrelated failure modes to treat as duplicates of it.", + "summary": "This cluster is not a duplicate set; it mixes many unrelated Transformers v5 regressions across tokenizers, model loading, processors, attention kernels, docs, and CI. None of the soft edges look like the same underlying bug/change.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the cluster is heterogeneous. If forced, #44462 is the closest representative because it covers a broad tokenizer-loading regression, which is the nearest shared theme among several items.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44462 is the broadest tokenizer-loading report in the set and the closest thing to a representative issue, but it still does not cover the cluster as a whole.", + "best_issue_reason": "#44462 is the most representative issue in the cluster because it is a broad, user-facing tokenizer-loading regression; the other issues are mostly narrower, model-specific, or unrelated failures.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on new torch vs TensorBoard/TensorFlow backend setup; unrelated subsystems and failure modes." + }, { "left": "issue:43650", "right": "issue:46132", "accept": false, - "reason": "Placeholder/low-signal issue vs an AttentionInterface.register behavior change; unrelated artifacts." + "reason": "A placeholder issue title vs behavior change in AttentionInterface.register; no shared bug path." }, { "left": "issue:44462", "right": "issue:45081", "accept": false, - "reason": "Both involve tokenizers, but one is AutoTokenizer ignoring tokenizer.json while the other is a Mistral regex patch crash; different code paths and bugs." + "reason": "Both touch tokenizers, but one is AutoTokenizer loading ignoring tokenizer.json and the other is a Mistral regex-patch crash; different code paths." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "Python version compatibility problem vs a model loading failure; no concrete shared bug." + "reason": "Python version support breakage vs loading a specific repo/model; too different to be duplicates." }, { "left": "issue:44297", "right": "issue:44462", "accept": false, - "reason": "Tokenizer save_pretrained class metadata mismatch vs AutoTokenizer ignoring tokenizer.json; adjacent area, but distinct failures." + "reason": "Tokenizer save_pretrained writes the wrong tokenizer_class, while this is AutoTokenizer loading the repo file; save vs load bugs." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Version-support issue vs vague dependency issue; not the same underlying bug." + "reason": "A Python compatibility issue vs an unspecified dependency problem; not the same underlying defect." }, { "left": "issue:43450", "right": "issue:44279", "accept": false, - "reason": "Video processor batch-shape bug vs dependency issue; unrelated." + "reason": "Video processor batch-shape bug vs generic dependency issue; no overlap in concrete code path." }, { "left": "issue:45081", "right": "issue:45907", "accept": false, - "reason": "Mistral tokenizer regex crash vs list_repo_files revision forwarding; completely different functionality." + "reason": "Mistral tokenizer regex patch crash vs list_repo_files not forwarding revision; completely different functionality." }, { - "left": "issue:44521", - "right": "issue:45325", + "left": "issue:44466", + "right": "issue:45276", "accept": false, - "reason": "Both multimodal, but assistant mask generation and temporal rope index scaling are different code paths." + "reason": "Serialization of tied lm_head weights vs resize_token_embeddings not updating Gemma4 embeddings; different model logic." }, { - "left": "issue:44466", - "right": "issue:45276", + "left": "issue:44521", + "right": "issue:45325", "accept": false, - "reason": "Both touch embeddings/weights, but serialization of lm_head.weight and resize_token_embeddings updating modules are different bugs." + "reason": "assistant_masks generation bug vs Qwen2.5-VL rope index scaling; both multimodal, but distinct internals and symptoms." }, { "left": "issue:43441", "right": "issue:45834", "accept": false, - "reason": "FlashAttention loading failure vs OCR long-input index error; unrelated model-specific issues." + "reason": "FlashAttention failure in Ministral vs OCR index error in Kosmos2.5; unrelated model-specific issues." }, { "left": "issue:42994", "right": "issue:43317", "accept": false, - "reason": "Quantized saving vs dequantized/offload loading; same broad area, but not the same concrete defect." - }, - { - "left": "issue:43653", - "right": "issue:45593", - "accept": false, - "reason": "Tokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; unrelated." + "reason": "Quantized save failure vs dequantized model load with gpu/cpu offload; both involve quantization, but different stages and bugs." }, { "left": "issue:45600", "right": "issue:45712", "accept": false, - "reason": "Both are repo hygiene/auto-generated-file issues, but they affect different files and failures." + "reason": "auto_mappings.py stale config references vs leftover dummy classes in dummy_pt_objects.py; both repo hygiene/CI, but not the same issue." }, { - "left": "issue:44623", - "right": "issue:44749", + "left": "issue:43653", + "right": "issue:45593", "accept": false, - "reason": "Missing files in processor.save_pretrained vs performance regression during data filtering; unrelated." + "reason": "BigBirdTokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; unrelated areas." }, { "left": "issue:44623", - "right": "issue:45397", + "right": "issue:44749", "accept": false, - "reason": "Processor save bug vs Gemma4 zero3 loading bug; different code paths." + "reason": "processor.save_pretrained missing files vs slow filtering after upgrade; different symptoms and code paths." }, { "left": "issue:43065", "right": "issue:44898", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder vs Perceiver interpolation failure; different models and errors." + "reason": "Dummy Conv2d in Sam3PixelDecoder vs Perceiver non-default resolution failure; both vision-related but not the same bug." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files from processor.save_pretrained vs Gemma-4 zero3 from_pretrained; unrelated failures." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "Missing rms_norm_eps causing precision drift vs torch.split return-value handling; unrelated math bugs." + "reason": "MLA q_a_layernorm missing config.rms_norm_eps vs torch.split return values in GlmMoeDsaIndexer; different model components." }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "MLukeTokenizer AttributeError vs D-FINE auxiliary-loss issue; no shared underlying defect." + "reason": "MLukeTokenizer AttributeError vs D-FINE auxiliary-loss issue; unrelated subsystems." }, { "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Both are v5 regressions, but one is CamemBERT masked-LM output corruption and the other is Deepseek tokenizer output corruption; not the same bug." - }, - { - "left": "issue:44016", - "right": "issue:45823", - "accept": false, - "reason": "Notebook syntax error vs Gemma4 device mismatch; unrelated." + "reason": "CamemBERT masked LM prediction regression vs Deepseek tokenizer regression; both output-quality bugs, but different models and code paths." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "FlashAttention model failure vs compiled flex_attention failure on torch>=2.9; different implementations and causes." + "reason": "Model-specific FlashAttention failure vs compiled flex_attention failing on torch>=2.9; one is a model issue, the other a kernel/runtime compatibility issue." }, { - "left": "issue:43723", - "right": "issue:44162", + "left": "issue:44016", + "right": "issue:45823", "accept": false, - "reason": "Tokenizer loading regression vs ESM2 broken; both loading-related, but not the same failure mode." + "reason": "Notebook syntax error vs Gemma4 PLE device mismatch; completely different bug types." }, { "left": "issue:43901", "right": "issue:43994", "accept": false, - "reason": "Docs mismatch for return_all_scores vs bad model outputs in pipeline; different problem class." + "reason": "Documentation mismatch for return_all_scores vs nonsensical model outputs; not the same underlying problem." }, { - "left": "issue:44297", - "right": "issue:45397", + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer loading regression vs ESM2 breakage; both are v5 regressions, but they affect different model families and mechanisms." + }, + { + "left": "issue:43450", + "right": "issue:44617", "accept": false, - "reason": "Tokenizer serialization metadata bug vs Gemma4 zero3 loading bug; unrelated." + "reason": "Incorrect batched video processor shape vs Sam3Video CUDA OOM; one is a shape bug, the other is memory usage." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Missing pad_token_id in Llama4Config vs glm-4v-9b loading failure; different model/config issues." + "reason": "Missing pad_token_id on Llama4Config vs glm-4v-9b loading failure; both config/loading-related but not the same concrete defect." }, { - "left": "issue:43450", - "right": "issue:44617", + "left": "issue:44297", + "right": "issue:45397", "accept": false, - "reason": "Incorrect batched video processor shape vs CUDA OOM in Sam3Video; not the same bug." + "reason": "Tokenizer serialization mismatch vs Gemma-4 zero3 loading; unrelated bugs." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Documentation mismatch vs intermittent import slowness; unrelated." + "reason": "Docs inconsistency vs import-time slowness; different problem classes." }, { "left": "issue:43525", "right": "issue:43643", "accept": false, - "reason": "Specific missing config field vs trust_remote_code returning incomplete config fields; related theme, but not the same concrete issue." + "reason": "Both involve config fields during loading, but one is a missing pad_token_id attribute and the other is trust_remote_code dropping fields; different root causes." }, { "left": "issue:43784", "right": "issue:45542", "accept": false, - "reason": "Sentence-transformers import NameError vs missing TensorFlow backend handling; different optional-dependency paths." + "reason": "Import NameError for sentence-transformers vs TensorBoard/TensorFlow backend error; unrelated dependency/import issues." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error vs init_empty_weights TypeError from unexpected argument; unrelated." + "reason": "Notebook syntax error vs init_empty_weights TypeError from unexpected argument; different failure modes." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Audio chat_template default sampling rate bug vs multimodal assistant_masks all-zero bug; both processor-related but not the same issue." } ] }, @@ -11088,14 +11196,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 35, - "review_unit_count": 50, + "review_unit_index": 36, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:16998", "issue:22355", @@ -11125,7 +11233,6 @@ "issue:44373", "issue:44485", "issue:44496", - "issue:44521", "issue:44561", "issue:44589", "issue:44749", @@ -11139,252 +11246,261 @@ "issue:45250", "issue:45292", "issue:45362", + "issue:45375", "issue:45397", "issue:45412", "issue:45593", + "issue:45759", "issue:46123", "issue:46132" ], "soft_pairs": [ "issue:44188|issue:44336", - "issue:43262|issue:44521", "issue:41628|issue:43976", "issue:44589|issue:45362", "issue:43673|issue:43761", "issue:16998|issue:22355", - "issue:44336|issue:44373", "issue:42491|issue:43299", + "issue:44336|issue:44373", "issue:44246|issue:44496", - "issue:44295|issue:45397", "issue:44242|issue:45593", - "issue:44336|issue:44485", + "issue:44295|issue:45397", "issue:44246|issue:44871", "issue:43824|issue:43976", + "issue:44336|issue:44485", "issue:41950|issue:44220", "issue:43976|issue:44964", - "issue:42886|issue:46132", "issue:36246|issue:42757", + "issue:42886|issue:46132", "issue:36246|issue:44351", - "issue:44779|issue:45292", "issue:44242|issue:44857", + "issue:44779|issue:45292", "issue:45081|issue:45362", + "issue:43352|issue:45250", "issue:43673|issue:44561", "issue:44295|issue:44749", - "issue:43352|issue:45250", "issue:44162|issue:45200", "issue:43901|issue:45003", "issue:43526|issue:45003", "issue:44496|issue:45003", - "issue:45412|issue:46123" + "issue:45412|issue:46123", + "issue:45375|issue:45759", + "issue:43262|issue:44246" ], - "prepared_review_unit_hash": "780239c227bd63f1c777810292e1030f9b2a859a733a5cc6a83f8459de6eecd2", + "prepared_review_unit_hash": "41776cb8f16087de9584fa1991849cb91c297a32158f40ab994160b10936d276", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 30, - "serialized_chars": 36013, - "estimated_input_tokens": 9004, - "estimated_eval_tokens": 18264 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36938, + "estimated_input_tokens": 9235, + "estimated_eval_tokens": 18726 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is heterogeneous, with mostly unrelated regression/import/model-loading issues that only loosely share Transformers-v5 breakage themes. None of the soft pairs looks like the same underlying bug or change.", - "confidence": 0.42, - "canonical_issue_reason": "Issue 44561 is the broadest core v5 regression here: a low-level API removal that breaks trust_remote_code models and best matches the cluster\u2019s general breakage/import theme.", + "summary": "The set is mostly a grab bag of unrelated Transformers regressions and import/config bugs. I don\u2019t see any soft pair that clearly describes the same concrete bug or change, so no merges are warranted.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 41950 is the clearest, most user-facing concrete bug in the set: it names a specific pipeline misbehavior, has active discussion and inbound references, and is more actionable than the more ambiguous import/config reports.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44561 is the best representative issue because it is a concrete, high-impact v5 compatibility regression affecting a wide class of models, making it the most central exemplar in this set.", + "best_issue_reason": "Issue 41950 is the strongest standalone issue candidate because it describes a specific failing code path with direct user impact and enough context to triage independently.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention-kernel divergence on torch.compile is unrelated to ANSI escape codes in loading_report." - }, - { - "left": "issue:43262", - "right": "issue:44521", - "accept": false, - "reason": "Audio apply_chat_template sampling-rate default bug is a different code path from multimodal assistant_mask generation." + "reason": "Different subsystems and symptoms: attention-kernel divergence under torch.compile vs ANSI color output in loading_report." }, { "left": "issue:41628", "right": "issue:43976", "accept": false, - "reason": "Missing AutoImageProcessor import and Python-version incompatibility are different failures with different causes." + "reason": "Both are import/version problems, but one is a missing symbol and the other is a Python-version compatibility regression; not the same bug." }, { "left": "issue:44589", "right": "issue:45362", "accept": false, - "reason": "Float8 storage lookup error is unrelated to Qwen3.5 chat crashes." + "reason": "Float8 storage import failure and a Qwen3.5 chat crash are different failure modes and code paths." }, { "left": "issue:43673", "right": "issue:43761", "accept": false, - "reason": "Chunked-prefill cache handling and CLIPVisionModel hidden_states regression are distinct bugs in different subsystems." + "reason": "Both mention v5 regressions, but one is missing GenerationMixin cache during chunked prefill and the other is CLIPVisionModel hidden_states behavior." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "A model_max_length question for DeBERTa-V3 is unrelated to a missing transformers.onnx module import." - }, - { - "left": "issue:44336", - "right": "issue:44373", - "accept": false, - "reason": "Loading-report ANSI codes and a wrong docstring for position_ids are not the same bug." + "reason": "Unrelated issues: DeBERTa model_max_length handling vs missing transformers.onnx module." }, { "left": "issue:42491", "right": "issue:43299", "accept": false, - "reason": "Both concern Qwen MoE loading, but they target different model generations and different failure modes." + "reason": "Same broad Qwen/MoE area, but one is LoRA compatibility across hf4.x/hf5.x and the other is multimodal model loading; not clearly the same bug." }, { - "left": "issue:44246", - "right": "issue:44496", + "left": "issue:44336", + "right": "issue:44373", "accept": false, - "reason": "Import latency sometimes and unrecognized model config are unrelated." + "reason": "ANSI code emission and a position_ids docstring typo are unrelated." }, { - "left": "issue:44295", - "right": "issue:45397", + "left": "issue:44246", + "right": "issue:44496", "accept": false, - "reason": "Buffer access on position_ids is unrelated to Gemma-4 zero3 from_pretrained behavior." + "reason": "Import-time slowness is unrelated to unrecognized-model loading for a specific checkpoint." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Missing load-balancing loss and missing auxiliary losses are different model-specific training bugs." + "reason": "Both concern missing losses, but they are different losses in different model families and different conditions." }, { - "left": "issue:44336", - "right": "issue:44485", + "left": "issue:44295", + "right": "issue:45397", "accept": false, - "reason": "ANSI code output and GLM-5 RoPE implementation are unrelated." + "reason": "A position_ids buffer access error is not the same as a Gemma-4 ZeRO3 from_pretrained failure." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Import-time slowness is unrelated to Gemma eos_token_id configuration mismatch." + "reason": "Import slowness and eos_token_id config mismatch are unrelated." }, { "left": "issue:43824", "right": "issue:43976", "accept": false, - "reason": "Qwen2_5_VL symbol export/import failure is not the same as the Python 3.9+/3.10+ compatibility issue." + "reason": "A missing Qwen2_5_VL export and a Python compatibility issue are different problems." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading-report ANSI formatting has nothing to do with GLM-5 RoPE implementation." }, { "left": "issue:41950", "right": "issue:44220", "accept": false, - "reason": "Video-classification pipeline image-processor lookup and _torch_extract_fbank_features are different pipeline/audio bugs." + "reason": "Both touch pipelines/utilities, but one is video-classification using image processors and the other is audio feature extraction; different code paths." }, { "left": "issue:43976", "right": "issue:44964", "accept": false, - "reason": "Interpreter-version incompatibility and Phi-4 multimodal loading failure are different problems." + "reason": "A Python version support bug is not the same as failing to load a specific multimodal model." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportError reports, but they concern different missing symbols from different packages." }, { "left": "issue:42886", "right": "issue:46132", "accept": false, - "reason": "Offline tokenizer cache loading and AttentionInterface.register behavior change are unrelated." + "reason": "Tokenizer cache/offline loading and AttentionInterface.register behavior are unrelated." }, { "left": "issue:36246", - "right": "issue:42757", + "right": "issue:44351", "accept": false, - "reason": "Missing Qwen2_5_VL image processor export is unrelated to missing is_offline_mode from huggingface_hub." + "reason": "Different missing imports: Qwen2_5_VLImageProcessor vs HybridCache." }, { - "left": "issue:36246", - "right": "issue:44351", + "left": "issue:44242", + "right": "issue:44857", "accept": false, - "reason": "These are separate import errors for different symbols and different packages." + "reason": "Missing MoE load-balancing loss and an AMP/CUDA crash in a detection loss are different issues." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Tokenizer correctness regression and resize_token_embeddings/output_embeddings mismatch are different bugs." + "reason": "Tokenizer correctness regression and resize_token_embeddings not updating output embeddings are not the same bug." }, { - "left": "issue:44242", - "right": "issue:44857", + "left": "issue:45081", + "right": "issue:45362", "accept": false, - "reason": "Training loss omission in D-FINE and LwDetrImageLoss AMP crash are distinct issues." + "reason": "A Mistral regex patch crash and a Qwen3.5 chat crash are different model/path failures." }, { - "left": "issue:45081", - "right": "issue:45362", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "Mistral tokenizer regex patch crash and Qwen3.5 chat crash are different model/tokenizer paths." + "reason": "The second title is too broad to establish the same concrete bug; one is a specific model lacking FA2 support." }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Both are v5 regressions, but one is GenerationMixin chunked_prefill cache handling and the other is trust_remote_code import breakage." + "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available break different code paths." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Position_ids buffer access and slowed filtering after upgrade are not the same bug." - }, - { - "left": "issue:43352", - "right": "issue:45250", - "accept": false, - "reason": "Unsupported Flash Attention 2.0 on Nemotron and a generic Flash Attention 2.0 topic are not the same concrete issue." + "reason": "A buffer access error and a Chinese-reported slowdown after upgrade are not the same underlying defect." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaults are unrelated." + "reason": "ESM2 breakage and Gemma-4 mm_token_type_ids defaulting are unrelated." }, { "left": "issue:43901", "right": "issue:45003", "accept": false, - "reason": "A doc/behavior mismatch for return_all_scores is unrelated to unsafe sys.modules access." + "reason": "A docs mismatch for return_all_scores is unrelated to unsafe sys.modules access." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "BeitImageProcessorFast reduce_labels and modeling_utils sys.modules access are different code paths." + "reason": "reduce_labels behavior in BeitImageProcessorFast is unrelated to sys.modules access in modeling_utils." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized model config and unsafe sys.modules access are separate failure modes." + "reason": "An unrecognized model config and unsafe sys.modules access are different load-time problems." }, { "left": "issue:45412", "right": "issue:46123", "accept": false, - "reason": "RT-DETR memory lifecycle and MaskGenerationPipeline final-batch dropping are unrelated." + "reason": "RT-DETR memory release and MaskGenerationPipeline partial-batch dropping are unrelated." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is a missing field being dropped by strict validation and the other is text_config unwrapping in from_config." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting is unrelated to import-time slowness." } ] }, @@ -11399,21 +11515,20 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 36, - "review_unit_count": 50, + "review_unit_index": 37, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36246", "issue:42886", "issue:43065", "issue:43232", "issue:43257", - "issue:43262", "issue:43408", "issue:43475", "issue:43540", @@ -11424,12 +11539,13 @@ "issue:44060", "issue:44077", "issue:44162", - "issue:44246", + "issue:44297", "issue:44336", "issue:44368", "issue:44466", "issue:44479", "issue:44483", + "issue:44623", "issue:44734", "issue:44877", "issue:44977", @@ -11451,35 +11567,32 @@ "issue:45600", "issue:45656", "issue:45701", - "issue:45759", "issue:45987", "issue:46082", "issue:46170", "issue:46202" ], "soft_pairs": [ - "issue:45375|issue:45759", "issue:43257|issue:45137", - "issue:43262|issue:44246", "issue:45292|issue:45584", "issue:36246|issue:43596", "issue:45292|issue:45701", "issue:44877|issue:45375", "issue:45561|issue:45563", + "issue:43065|issue:43408", "issue:43232|issue:44336", "issue:44987|issue:45459", - "issue:43065|issue:43408", "issue:45987|issue:46082", "issue:44995|issue:45200", "issue:44479|issue:46170", - "issue:43475|issue:43540", "issue:44466|issue:45335", + "issue:43475|issue:43540", "issue:45397|issue:45656", "issue:44483|issue:46202", - "issue:43653|issue:44162", "issue:45137|issue:45600", - "issue:44368|issue:44977", + "issue:43653|issue:44162", "issue:44995|issue:45588", + "issue:44368|issue:44977", "issue:44368|issue:45563", "issue:44877|issue:46170", "issue:43931|issue:44368", @@ -11487,216 +11600,211 @@ "issue:44060|issue:44077", "issue:45003|issue:45561", "issue:43673|issue:44734", - "issue:45584|issue:46170" + "issue:45584|issue:46170", + "issue:44297|issue:44623" ], - "prepared_review_unit_hash": "f430359dbdc9297e182268b3f051454994a77a0724ab4ff504954da9be15e7bf", + "prepared_review_unit_hash": "fefb0de649b01f84a68f22ba3d037bfe80c27ebf880cf103da8a5a60fecfa085", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36796, - "estimated_input_tokens": 9199, - "estimated_eval_tokens": 18654 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35873, + "estimated_input_tokens": 8969, + "estimated_eval_tokens": 18194 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous: it spans unrelated bugs in configs, generation, tokenizers, DeepSpeed, and testing infrastructure. None of the soft pairs look like the same underlying bug/change, so I reject all of them.", - "confidence": 0.86, - "canonical_issue_reason": "issue:45701 is the broadest open, user-facing regression in the set and is the most plausible umbrella tracker; the rest are narrower environment/model-specific reports.", + "summary": "This cluster is heterogeneous: most items are unrelated bugs across different models, configs, and code paths. The soft pairs share only broad subsystem similarity (tokenization, generation, DeepSpeed, save/load, vision/video), not the same underlying defect.", + "confidence": 0.96, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the best representative issue here because it is open, has multiple inbound references, and is less model-specific than the other reports.", + "best_issue_reason": "No single issue is a strong canonical representative; the cluster spans distinct regressions and model families rather than one duplicate bug.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:45375", - "right": "issue:45759", - "accept": false, - "reason": "Both touch Qwen multimodal config handling, but one is a missing config field and the other is a from_config text_config unwrap bug; different failure points." - }, { "left": "issue:43257", "right": "issue:45137", "accept": false, - "reason": "Both mention DeepSpeed, but one is Qwen3 MoE weight conversion under accelerate+deepspeed and the other is a ZeRO3 empty-deque IndexError in BertModel init." - }, - { - "left": "issue:43262", - "right": "issue:44246", - "accept": false, - "reason": "Audio processor sampling-rate defaults and slow import behavior are unrelated bugs in different code paths." + "reason": "Different failures: Qwen3 MOE weight conversion vs DeepSpeed ZeRO3 deque underflow." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "resize_token_embeddings/output_embeddings mismatch and Whisper empty transcription after align_special_tokens are distinct bugs." + "reason": "Resize-embeddings bug vs Whisper empty-transcription generation failure." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "A missing Qwen2.5 VL image processor import and a DeepSpeed/BertModel IndexError are unrelated." + "reason": "ImportError for Qwen2.5 VL image processor is unrelated to BertModel/ZeRO3 index error." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "Embedding resize behavior and version-dependent tokenization changes are separate issues, not the same concrete bug." + "reason": "Embedding resize issue is not the same as a version-dependent tokenization change." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Strict granite_speech config loading and a Qwen3.5 multimodal config field omission are different model/config problems." + "reason": "Both involve config loading, but they target different models and different field-handling failures." }, { "left": "issue:45561", "right": "issue:45563", "accept": false, - "reason": "A pytest-xdist race on captured_info.txt and a stale num_return_sequences warning in paged generate are unrelated testing/generation issues." + "reason": "pytest-xdist file race and a stale generation warning are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Different SAM3 problems: pixel decoder implementation vs tracker/video config warning." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs updating after sync_gpus and ANSI codes emitted by loading_report are unrelated subsystems." + "reason": "Generation kwargs syncing bug is unrelated to ANSI output in loading_report." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model loading failure for physical-intelligence/fast and tokenizer errors hidden by protobuf import handling are different bugs." - }, - { - "left": "issue:43065", - "right": "issue:43408", - "accept": false, - "reason": "Both are SAM3-related, but one is a dummy Conv2d in pixel decoder and the other is a wrong sam3_video vs sam3_tracker config warning." + "reason": "Model loading failure and tokenizer error masking are different bugs." }, { "left": "issue:45987", "right": "issue:46082", "accept": false, - "reason": "StaticCache.get_seq_length returning a tensor and LlamaConfig head_dim validation are different API/validation issues." + "reason": "Cache length return type bug vs LlamaConfig head_dim validation are unrelated." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "A stale indexer cache on second forward and Gemma4 mm_token_type_ids defaults are unrelated model bugs." + "reason": "Stale indexer cache on second forward pass is unrelated to missing mm_token_type_ids defaults." }, { "left": "issue:44479", "right": "issue:46170", "accept": false, - "reason": "A v5.3 video regression in Qwen VL models and a Windows/ROCm torch.distributed import failure are unrelated." + "reason": "Video-input regression and Windows ROCm import failure are separate code paths." }, { - "left": "issue:43475", - "right": "issue:43540", + "left": "issue:44466", + "right": "issue:45335", "accept": false, - "reason": "One is a SAM 3 video encoder attribute error; the other is a Qwen3OmniMoe video-input ValueError." + "reason": "Serialization of tied weights is different from resize_token_embeddings not updating decoder embeddings." }, { - "left": "issue:44466", - "right": "issue:45335", + "left": "issue:43475", + "right": "issue:43540", "accept": false, - "reason": "Both concern embedding/weight updates, but one is serialization of tied weights and the other is resize_token_embeddings not updating decoder.embed_tokens." + "reason": "SAM3 video encoder output attribute bug vs Qwen3OmniMoe video processing ValueError." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Both involve DeepSpeed, but one is gemma-4 zero3 from_pretrained and the other is optimizer.step being called twice." + "reason": "Gemma-4 ZeRO3 loading issue and double optimizer step under DeepSpeed are different defects." }, { "left": "issue:44483", "right": "issue:46202", "accept": false, - "reason": "A /v1/chat/completions request rejection and a Gemma pipeline roundtrip issue on \u2581 are different surfaces and failures." - }, - { - "left": "issue:43653", - "right": "issue:44162", - "accept": false, - "reason": "A BigBirdTokenizer special-token registration bug and a broken ESM2 model are unrelated." + "reason": "Chat/completions request handling failure is unrelated to Gemma pipeline roundtrip tokenization." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "A ZeRO3 deque IndexError and removed Sam3LiteText config references are unrelated." + "reason": "ZeRO3 deque underflow and auto_mappings stale config references are unrelated." }, { - "left": "issue:44368", - "right": "issue:44977", + "left": "issue:43653", + "right": "issue:44162", "accept": false, - "reason": "A tie_word_embeddings warning during LoRA fine-tuning and a flash-attention generation failure are not the same bug." + "reason": "BigBirdTokenizer special-token registration bug is unrelated to ESM2 breakage." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "A stale indexer cache on second forward and an AttributeError on s_aux=None in flash_attention are different code paths." + "reason": "Stale forward-pass cache bug is unrelated to flash_attention crashing on s_aux=None." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Tie-word-embeddings warning in fine-tuning is not the same as flash-attention generation failure." }, { "left": "issue:44368", "right": "issue:45563", "accept": false, - "reason": "Both are warnings, but one is about tied weights and the other is a stale generate warning for num_return_sequences." + "reason": "These are different warnings in different paths with no shared bug mechanism." }, { "left": "issue:44877", "right": "issue:46170", "accept": false, - "reason": "Strict config loading for granite_speech and a Windows/ROCm import dependency issue are unrelated." + "reason": "Strict config loading and Windows ROCm import/type errors are unrelated." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and a Qwen3.5 tied-weights warning are different model/version issues." + "reason": "Qwen3-VL weight-shape mismatch is unrelated to tie-word-embeddings warnings." }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU CUDA OOM are unrelated." + "reason": "Offline cache tokenizer loading and Gemma4 multi-GPU OOM are not the same issue." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "A Qwen3-Next tied-weights warning and a patchtsmixer post_init policy issue are different config/validation bugs." + "reason": "Incorrect tied-weights warning in Qwen3-Next is unrelated to patchtsmixer post_init policy." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "Unsafe sys.modules access in modeling_utils and a pytest-xdist file race are unrelated." + "reason": "sys.modules access bug and xdist captured_info.txt race are different problems." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both involve generation/cache behavior, but one is missing GenerationMixin cache in chunked_prefill and the other is wrong tensor indexing in serve KV-cache continuation." + "reason": "Missing GenerationMixin cache in v5.0.0 and wrong tensor indexing in serve are distinct generation bugs." }, { "left": "issue:45584", "right": "issue:46170", "accept": false, - "reason": "Whisper empty transcription after align_special_tokens and a Windows/ROCm import failure are unrelated." + "reason": "Whisper empty-transcription failure is unrelated to Windows ROCm torch.distributed import errors." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch and processor save_pretrained missing files are related but not the same bug." } ] }, @@ -11711,17 +11819,18 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 37, - "review_unit_count": 50, + "review_unit_index": 38, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28282", "issue:30990", + "issue:36010", "issue:41628", "issue:42371", "issue:42673", @@ -11741,7 +11850,6 @@ "issue:44162", "issue:44188", "issue:44222", - "issue:44297", "issue:44351", "issue:44361", "issue:44623", @@ -11770,7 +11878,6 @@ "issue:46202" ], "soft_pairs": [ - "issue:44297|issue:44623", "issue:44869|issue:45356", "issue:44361|issue:44749", "issue:43646|issue:44162", @@ -11784,8 +11891,8 @@ "issue:42994|issue:43482", "issue:44038|issue:44623", "issue:43475|issue:45381", - "issue:28282|issue:30990", "issue:43475|issue:43643", + "issue:28282|issue:30990", "issue:42371|issue:45092", "issue:43232|issue:43673", "issue:41628|issue:44933", @@ -11801,231 +11908,250 @@ "issue:44964|issue:45137", "issue:44222|issue:45310", "issue:42994|issue:43824", - "issue:44038|issue:45310" + "issue:44038|issue:45310", + "issue:36010|issue:41628" ], - "prepared_review_unit_hash": "e4e21da679a6e02570e425400a4817216e8b0fc3423f82012f73c01d4147fabd", + "prepared_review_unit_hash": "b38eac144f80188613c43cefefebdbd559394e44d9ffba0c130e12b908b28c63", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37108, - "estimated_input_tokens": 9277, - "estimated_eval_tokens": 18810 + "serialized_chars": 37089, + "estimated_input_tokens": 9273, + "estimated_eval_tokens": 18802 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a mix of unrelated Transformers regression reports. The only clear duplicate pairs are the two identical Qwen3ForCausalLM VRAM-leak reports and the two identical Qwen3.5-MoE from_pretrained error reports; the rest are similar only at a broad subsystem/version level and should not be merged.", + "summary": "This cluster is noisy and mostly spans distinct Transformer regressions and model-specific issues. The only clear duplicate pair is the Qwen3ForCausalLM VRAM leak report; most other soft-similar pairs are related only at the subsystem/theme level, not the same underlying bug.", "confidence": 0.84, - "canonical_issue_reason": "issue:42673 is the strongest canonical issue candidate because it is a concrete, well-described bug report with an exact duplicate follow-up (issue:43704) and enough context to anchor that subcluster.", + "canonical_issue_reason": "issue:42673 is the best canonical issue because issue:43704 appears to be an exact duplicate with the same title, and 42673 has higher discussion activity in the packet (10 vs 1).", "canonical_pr_reason": null, - "best_issue_reason": "issue:42673 is the best issue to keep as the representative duplicate anchor: it has a precise title, a specific code-path symptom, and a later exact duplicate with the same title.", + "best_issue_reason": "issue:42673 is the best overall issue candidate because it matches issue:43704 exactly by title and has more discussion activity, making it the clearest representative of that bug in the visible set.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44297", - "right": "issue:44623", - "accept": false, - "reason": "Tokenizer save metadata mismatch vs missing files on processor save; different failure modes and likely different code paths." - }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper word timestamp decode crash vs Kimi-K2.5 tokenizer codec regression; unrelated model/tokenizer bugs." + "reason": "Different bugs: Whisper timestamp decoding crash vs Kimi tokenizer regression/codec handling." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "MLukeTokenizer task AttributeError and a broad upgrade slowdown report are not the same underlying defect." + "reason": "Different code paths: MLukeTokenizer task AttributeError vs a performance slowdown after upgrade." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Custom model init breakage under v5 vs ESM2 being broken; both are v5-era regressions but not the same bug." + "reason": "Both are broad breakages, but they describe different affected models and failure modes; not the same concrete bug." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Performance slowdown after upgrade vs optimizer stepping twice with deepspeed are different runtime issues." + "reason": "Unrelated symptoms: data filtering slowdown vs DeepSpeed optimizer stepping twice." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "Processor save_pretrained file omission and double optimizer step with deepspeed do not share a concrete code path." + "reason": "Different subsystems and failures: processor.save_pretrained file omission vs DeepSpeed optimizer double-step." }, { "left": "issue:44871", "right": "issue:46132", "accept": false, - "reason": "Gemma eos_token_id config inconsistency vs AttentionInterface.register behavior change are unrelated." + "reason": "Different features: Gemma eos token config mismatch vs AttentionInterface.register behavior change." }, { "left": "issue:43701", "right": "issue:44749", "accept": false, - "reason": "resume_from_checkpoint key mismatch is not the same as a filtering slowdown regression." + "reason": "Checkpoint key mismatch is not the same bug as the reported preprocessing slowdown." }, { "left": "issue:43673", "right": "issue:43827", "accept": false, - "reason": "Generation cache missing during chunked_prefill vs docs still referencing removed pipeline APIs; no shared bug." + "reason": "Generation cache bug vs documentation still referencing removed pipeline APIs." }, { "left": "issue:44188", "right": "issue:46202", "accept": false, - "reason": "torch.compile attention-kernel divergence is unrelated to Gemma pipeline roundtrip/tokenization issues." + "reason": "Different failures: torch.compile attention-kernel divergence vs Gemma pipeline roundtrip/tokenization issue." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "Generic bug report vs gemma-4 zero3 from_pretrained failure; not enough evidence of the same issue." + "reason": "One is a placeholder bug report, the other is a specific gemma-4 zero3 from_pretrained failure." }, { "left": "issue:42994", "right": "issue:43482", "accept": false, - "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are distinct save/load problems." + "reason": "Quantized model saving failure is not the same as GGUF loading failure." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe v5 bug and missing processor save files are different model/component failures." + "reason": "Different bugs: Qwen3-VL-Moe/v5 compatibility vs missing files on processor.save_pretrained." }, { "left": "issue:43475", "right": "issue:45381", "accept": false, - "reason": "SAM 3 Video missing fpn_position_embeddings and qwen2.5-vl video position-id regression are separate multimodal issues." + "reason": "Different model families and failures: SAM 3 video attribute error vs Qwen2.5-VL video position-id bug." }, { - "left": "issue:28282", - "right": "issue:30990", + "left": "issue:43475", + "right": "issue:43643", "accept": false, - "reason": "PyTorch ImportError for AutoModel and Sentence Transformers loading hang are unrelated symptoms." + "reason": "SAM 3 vision encoder attribute error is unrelated to trust_remote_code field loss in AutoConfig." }, { - "left": "issue:43475", - "right": "issue:43643", + "left": "issue:28282", + "right": "issue:30990", "accept": false, - "reason": "SAM 3 Video attribute error and AutoConfig trust_remote_code missing fields are different bugs." + "reason": "ImportError for missing PyTorch is not the same as a loading hang in Sentence Transformers." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 settings guidance and old InternVL2 meta-init incompatibility are unrelated." + "reason": "TF32 API settings change and remote-code/meta-init incompatibility are unrelated." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Generation kwargs update after sync_gpus and missing generation cache in chunked_prefill are different generation-path issues." + "reason": "Both are generation-related, but they affect different code paths and reported failures." }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "Cannot import AutoImageProcessor vs non-existent image_utils import; both are import errors but for different symbols." + "reason": "Both are import issues, but for different symbols and modules; not a clear duplicate." }, { "left": "issue:45375", "right": "issue:45478", "accept": false, - "reason": "Missing deepstack_visual_indexes being dropped and Qwen3.5-MoE from_pretrained error are related to the same model family but not the same concrete defect." + "reason": "Both mention Qwen3.5 Moe, but one is a missing config field being dropped and the other is a generic from_pretrained error; too different to merge." }, { "left": "issue:43475", "right": "issue:44661", "accept": false, - "reason": "SAM 3 Video attribute error and add-new-model-like tokenizer mapping failure are unrelated." + "reason": "SAM 3 vision encoder issue is unrelated to tokenizer-mapping logic in add-new-model-like." }, { "left": "issue:42994", "right": "issue:43525", "accept": false, - "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are different model/config regressions." + "reason": "Quantized model saving failure is not the same as Llama4Config missing pad_token_id." }, { "left": "issue:46077", "right": "issue:46123", "accept": false, - "reason": "Gemma4 attention-mask construction bug and MaskGenerationPipeline final-batch dropping bug are distinct pipeline/masking issues." + "reason": "Different attention/masking bugs: Gemma4 causal-mask construction vs pipeline final-batch result dropping." }, { "left": "issue:45310", "right": "issue:45375", "accept": false, - "reason": "Qwen3.5-MoE from_pretrained error and missing deepstack_visual_indexes are both Qwen issues but not the same failure mode." + "reason": "Same model family, but different concrete failures: from_pretrained loading error vs missing deepstack_visual_indexes field." }, { "left": "issue:45081", "right": "issue:45103", "accept": false, - "reason": "Mistral tokenizer regex patch crash and auto_docstring annotation crash are unrelated AttributeErrors." + "reason": "Tokenizer regex patch crash and auto-docstring future-annotations crash are unrelated." }, { "left": "issue:45406", "right": "issue:46202", "accept": false, - "reason": "Gemma4Processor missing _tokenizer in serve and Gemma pipeline roundtrip failure are different code paths." + "reason": "Gemma4Processor missing _tokenizer is a different bug from Gemma pipeline roundtrip token handling." }, { "left": "issue:42673", "right": "issue:43704", "accept": true, - "reason": "Identical title and same reported symptom: Qwen3ForCausalLM leaking VRAM in multiple dataloader threads." + "reason": "Exact duplicate bug report: same Qwen3ForCausalLM VRAM leak in multiple dataloader threads, with identical title and matching symptom." }, { "left": "issue:41628", "right": "issue:44351", "accept": false, - "reason": "Importing AutoImageProcessor and importing HybridCache are separate missing-symbol reports." + "reason": "Different missing imports: AutoImageProcessor vs HybridCache." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Phi-4-multimodal load failure and DeepSpeed ZeRO3 deque IndexError are unrelated." + "reason": "Model loading failure for Phi-4 multimodal and DeepSpeed ZeRO3 deque underflow are unrelated." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "FP8 save_pretrained on moe models and Qwen3.5-MoE from_pretrained error are different operations and failures." + "reason": "Save-pretrained FP8 moe bug and Qwen3.5 Moe from_pretrained loading bug are different operations and failures." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Qwen3-VL-Moe v5 bug and Qwen3.5-MoE from_pretrained error are model-family neighbors, not the same concrete bug." + "reason": "Both involve Qwen MoE models, but they are different regressions/version contexts and not the same concrete code-path bug." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer patch crash and auto-docstring annotation handling failure do not share the same underlying defect." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4 processor initialization failure is not the same as the Gemma pipeline roundtrip issue." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact duplicate bug report: same Qwen3ForCausalLM VRAM leak in multiple dataloader threads, with identical title and matching symptom." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different import errors involving different APIs and model classes." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The representative anchor choice is well grounded: issue:42673 has an exact duplicate in issue:43704 with the same title and symptom. The soft-edge decisions are appropriately conservative overall, and the summary stays within what the packet supports by separating the clearly duplicated reports from merely adjacent v5/model-family regressions." + "accept": false, + "feedback": "The overall choice of issue:42673 is plausible, but the justification overstates the packet. There are no inbound references for either 42673 or 43704, so phrases like \"well-supported by discussion and references\" / \"richer discussion/inbound-reference trail\" are not grounded. Please keep the canonical/best-issue rationale limited to what is visible in the packet (identical titles and higher discussion activity on 42673)." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -12034,21 +12160,19 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 38, - "review_unit_count": 50, + "review_unit_index": 39, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:30333", "issue:30990", "issue:33290", "issue:35141", - "issue:36010", - "issue:41628", "issue:42175", "issue:42222", "issue:42831", @@ -12084,23 +12208,24 @@ "issue:45200", "issue:45310", "issue:45356", + "issue:45405", "issue:45561", "issue:45600", "issue:45656", "issue:45712", "issue:45812", "issue:46123", - "issue:46231" + "issue:46231", + "issue:46326" ], "soft_pairs": [ - "issue:36010|issue:41628", "issue:42831|issue:44222", "issue:42175|issue:45712", "issue:44496|issue:45561", "issue:43377|issue:44242", "issue:45561|issue:45600", - "issue:42898|issue:44568", "issue:43901|issue:45561", + "issue:42898|issue:44568", "issue:43232|issue:44792", "issue:30990|issue:35141", "issue:43278|issue:45137", @@ -12108,223 +12233,225 @@ "issue:43065|issue:46123", "issue:44623|issue:45310", "issue:30333|issue:33290", - "issue:44188|issue:44373", "issue:43232|issue:44188", + "issue:44188|issue:44373", "issue:42898|issue:45812", "issue:43784|issue:43824", "issue:43723|issue:44568", - "issue:43874|issue:45092", "issue:42898|issue:45356", "issue:42898|issue:44779", "issue:44734|issue:45103", "issue:44016|issue:46231", + "issue:43874|issue:45092", "issue:44075|issue:46231", + "issue:43723|issue:46326", "issue:44060|issue:45125", + "issue:42898|issue:44448", "issue:44295|issue:45656", - "issue:42898|issue:44448" + "issue:45405|issue:45712" ], - "prepared_review_unit_hash": "5aaef5330c8fb3b718b892773ab3997f21753c12ba441fb47a5a5fbb1b579dad", + "prepared_review_unit_hash": "4375470e0a3c0de8a8caa708b96879329048659232a9d9ba249e99dc0650a6bd", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36485, - "estimated_input_tokens": 9122, - "estimated_eval_tokens": 18500 + "soft_pair_count": 30, + "serialized_chars": 36784, + "estimated_input_tokens": 9196, + "estimated_eval_tokens": 18648 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of unrelated issues. There is a small tokenizer-v5 regression subtheme, but none of the soft pairs look like the same underlying bug/change closely enough to merge as duplicates.", - "confidence": 0.82, - "canonical_issue_reason": "Issue 42898 is the best representative of the only visible subfamily here: a concrete Transformers v5 tokenizer regression with broad user impact. It is still not a duplicate of the others, but it is the most central anchor for the tokenizer-behavior cluster.", + "summary": "This cluster is a loose collection of unrelated Transformers issues, with only superficial overlap around tokenizers, v5 regressions, multimodal models, DeepSpeed, and packaging/import problems. None of the soft-edge pairs look like true duplicates or the same underlying fix.", + "confidence": 0.95, + "canonical_issue_reason": "issue:42898 is a clear, high-signal regression report with a well-defined tokenizer behavior change in v5, making it a good representative anchor for the cluster\u2019s tokenizer-regression subset.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 42898 is the strongest global representative because it is a specific, user-facing regression with a clear repro scope and it sits near several other tokenizer-v5 complaints. Even so, the overall cluster is not a true duplicate set.", + "best_issue_reason": "issue:42898 is the strongest representative issue: it is concrete, versioned, user-visible, and narrowly scoped enough to summarize a common failure mode seen elsewhere in the cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:36010", - "right": "issue:41628", - "accept": false, - "reason": "Both are import errors, but for different missing symbols and different code paths; not the same bug." - }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "FP8 is the only overlap; one is an accuracy regression and the other is a save_pretrained/MoE serialization issue." + "reason": "Both mention FP8, but one is an accuracy regression and the other is a save_pretrained/MoE serialization issue; different bug classes." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "One is an extras/backend packaging complaint, the other is leftover dummy-class cleanup and repo-check leakage." + "reason": "Both are backend/import packaging problems, but one is missing TensorFlow under the torch extra and the other is stale dummy classes leaking without torch; not the same defect." }, { "left": "issue:44496", "right": "issue:45561", "accept": false, - "reason": "Unrecognized-model config failure and pytest-xdist file-race are unrelated." + "reason": "Unrecognized model config loading and pytest-xdist file races are unrelated." }, { "left": "issue:43377", "right": "issue:44242", "accept": false, - "reason": "Different bugs: batched-vs-single encoder output mismatch versus missing load-balancing loss when router logits are off." + "reason": "MIMI padding-mask batch consistency and MoE load-balancing loss gating are different model behaviors and code paths." }, { "left": "issue:45561", "right": "issue:45600", "accept": false, - "reason": "A test-worker race on a captured file is not the same as stale auto_mappings references breaking CI." + "reason": "A test-worker race on captured_info.txt is unrelated to auto_mappings referencing removed configs." }, { - "left": "issue:42898", - "right": "issue:44568", + "left": "issue:43901", + "right": "issue:45561", "accept": false, - "reason": "Both are tokenizer v5 regressions, but one is clean-up spacing behavior and the other is add_special_tokens/BOS-EOS handling." + "reason": "Documentation mismatch for TextClassificationPipeline does not share the same bug as the xdist file race." }, { - "left": "issue:43901", - "right": "issue:45561", + "left": "issue:42898", + "right": "issue:44568", "accept": false, - "reason": "Docs mismatch for a pipeline option and a pytest-xdist race are unrelated." + "reason": "Both are tokenizer v5 regressions, but one is clean-up spacing behavior and the other is special-token insertion; different underlying fixes." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation kwargs after sync_gpus and a janus image-generation test failure do not share the same failure mode." + "reason": "Generation kwarg sync logic and a Janus image-generation test failure are not the same issue." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Loading gets stuck and output embeddings being reinitialized are different issues." + "reason": "Sentence-Transformers loading hangs and token-embedding reinitialization in post_init are unrelated." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "BF16-to-FP32 dtype drift in evaluation is unrelated to the DeepSpeed ZeRO3 deque error." + "reason": "BF16-to-FP32 dtype drift in evaluation is unrelated to DeepSpeed ZeRO3 deque underflow." }, { "left": "issue:42222", "right": "issue:45200", "accept": false, - "reason": "Different model families and different multimodal bugs; not the same change." + "reason": "Broken vitpose models and Gemma 4 mm_token_type_ids defaults affect different model families and code paths." }, { "left": "issue:43065", "right": "issue:46123", "accept": false, - "reason": "Dummy placeholder layer cleanup and final-batch is_last handling in a pipeline are unrelated." + "reason": "A dummy Conv2d placeholder in Sam3PixelDecoder is unrelated to MaskGenerationPipeline partial-batch handling." }, { "left": "issue:44623", "right": "issue:45310", "accept": false, - "reason": "Processor save_pretrained file emission and Qwen3.5 from_pretrained incompatibility are different concrete bugs." + "reason": "Missing processor files on save and Qwen3.5 MoE from_pretrained failures are different serialization/loading problems." }, { "left": "issue:30333", "right": "issue:33290", "accept": false, - "reason": "MLflow reporting on failed training and a Deepspeed AdaFactor OOM are unrelated." + "reason": "MLflow reporting on failed training jobs and Adafactor OOM in DeepSpeed are unrelated." }, { - "left": "issue:44188", - "right": "issue:44373", + "left": "issue:43232", + "right": "issue:44188", "accept": false, - "reason": "torch.compile attention branching and a docstring typo about position_ids are not the same issue." + "reason": "Both involve generation/attention internals, but one is kwarg update after sync_gpus and the other is bidirectional-skip branching under torch.compile; not the same bug." }, { - "left": "issue:43232", - "right": "issue:44188", + "left": "issue:44188", + "right": "issue:44373", "accept": false, - "reason": "Both mention generation/attention internals, but the concrete code-path problems are different." + "reason": "Attention-kernel divergence under compile is unrelated to a position_ids docstring issue." }, { "left": "issue:42898", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but one concerns clean_up_tokenization_spaces while the other is wrong token IDs for Granite models." + "reason": "Both are tokenizer regressions, but one concerns cleanup spacing and the other wrong Granite token IDs; distinct root causes." }, { "left": "issue:43784", "right": "issue:43824", "accept": false, - "reason": "Different import failures for different symbols and packages." + "reason": "A missing nn import in sentence-transformers and a missing Qwen2_5_VL class import are separate import errors." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Tokenizer loading regression and add_special_tokens BOS/EOS regression are separate behaviors." - }, - { - "left": "issue:43874", - "right": "issue:45092", - "accept": false, - "reason": "A missing image-patch helper and a remote-code meta-init incompatibility are different model-specific issues." + "reason": "Tokenizer loading in v5 and missing BOS/EOS on add_special_tokens are different failure modes." }, { "left": "issue:42898", "right": "issue:45356", "accept": false, - "reason": "Both are v5 tokenizer regressions, but the reported failures and affected code paths differ." + "reason": "Both are tokenizer regressions, but Kimi codec handling/warning behavior is not the same as clean_up_tokenization_spaces changes." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both involve tokenizers, but one is clean-up spacing while the other is Deepseek codec handling and tokenizer output correctness." + "reason": "Deepseek tokenization output corruption and cleanup spacing behavior are different tokenizer bugs." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Serving KV-cache indexing and auto_docstring future-annotations crashes are unrelated." + "reason": "Serve-time KV-cache continuation indexing and auto_docstring annotation handling are unrelated." }, { "left": "issue:44016", "right": "issue:46231", "accept": false, - "reason": "Notebook syntax error and a docs parameter-name mismatch are not the same bug." + "reason": "A syntax error in a notebook and a docstring parameter-name mismatch are different documentation issues." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing get_number_of_image_patches in GLM46V and meta-init incompatibility for InternVL2 are different multimodal issues." }, { "left": "issue:44075", "right": "issue:46231", "accept": false, - "reason": "Optimizer args being ignored is unrelated to a documentation typo." + "reason": "SGD arguments being ignored is a runtime optimizer bug, not a documentation typo." + }, + { + "left": "issue:43723", + "right": "issue:46326", + "accept": false, + "reason": "Tokenizer loading failures and continue_final_message behavior for mistral_common tokenizers are not the same underlying problem." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "Incorrect tied-weights warning and missing tensor-parallel plan are different Qwen3-related problems." + "reason": "Wrong tied-weights warning and missing tensor-parallel plan for Qwen3.5 MoE are separate Qwen model bugs." }, { "left": "issue:44295", "right": "issue:45656", "accept": false, - "reason": "Position_ids buffer access error and duplicate optimizer-step behavior with DeepSpeed are different code paths." + "reason": "Reading position_ids after buffer registration and double optimizer.step under DeepSpeed are different execution bugs." }, { - "left": "issue:42898", - "right": "issue:44448", + "left": "issue:45405", + "right": "issue:45712", "accept": false, - "reason": "Both are v5 output regressions, but one is tokenizer clean-up behavior and the other is a Pegasus model output change." + "reason": "A PyPI version pin problem and leftover dummy classes in dummy_pt_objects.py are unrelated maintenance issues." } ] }, @@ -12339,14 +12466,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 39, - "review_unit_count": 50, + "review_unit_index": 40, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28282", "issue:30333", @@ -12374,6 +12501,7 @@ "issue:44297", "issue:44373", "issue:44448", + "issue:44483", "issue:44484", "issue:44485", "issue:44623", @@ -12387,7 +12515,7 @@ "issue:45245", "issue:45310", "issue:45381", - "issue:45405", + "issue:45406", "issue:45656", "issue:45712", "issue:45834", @@ -12397,7 +12525,6 @@ "issue:46305" ], "soft_pairs": [ - "issue:45405|issue:45712", "issue:44448|issue:46132", "issue:42175|issue:44933", "issue:44222|issue:44297", @@ -12411,245 +12538,246 @@ "issue:45245|issue:46132", "issue:44190|issue:46082", "issue:30333|issue:36331", - "issue:43479|issue:44869", "issue:45071|issue:46082", - "issue:28282|issue:30333", + "issue:43479|issue:44869", "issue:30333|issue:35141", + "issue:28282|issue:30333", "issue:43475|issue:46305", "issue:44297|issue:45310", "issue:41628|issue:42757", "issue:44206|issue:45103", "issue:43723|issue:44977", "issue:45381|issue:46305", - "issue:44263|issue:45092", "issue:43873|issue:44945", "issue:43122|issue:46209", "issue:43232|issue:45834", "issue:44222|issue:44484", - "issue:44373|issue:44485", + "issue:44263|issue:45092", "issue:44295|issue:44623", - "issue:43479|issue:43644" + "issue:43479|issue:43644", + "issue:44373|issue:44485", + "issue:44483|issue:45406" ], - "prepared_review_unit_hash": "8f9966680d80a4967b710fedc9da9d76504152b2b9ef99baecff34ec4285a7f9", + "prepared_review_unit_hash": "0936a506bdf9d219fe04926b43daad73ce9d77d403d1c94bead725286161ec15", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 36455, - "estimated_input_tokens": 9114, - "estimated_eval_tokens": 18484 + "serialized_chars": 37061, + "estimated_input_tokens": 9266, + "estimated_eval_tokens": 18788 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous; the soft-similarity pairs mostly share broad vocabulary (imports, save_pretrained, config, generation) but not the same concrete bug or code path. I would not merge any of the candidate pairs.", - "confidence": 0.74, - "canonical_issue_reason": "issue:44297 is the clearest, most self-contained bug report in the set: it has a specific failing path (`tokenizer.save_pretrained`) and an actionable symptom (`tokenizer_class` mismatch). The rest of the cluster is too mixed to serve as a stronger canonical anchor.", + "summary": "This cluster is a loose grab-bag of unrelated Transformers issues; the soft pairs do not look like duplicate bug reports or the same fixable change, so all suggested merges should be rejected.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 44483 is the clearest high-severity user-facing regression in this set and the best single anchor, though the cluster is still heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44297 is the best representative issue overall because it is concrete, reproducible, and narrowly scoped, even though it is not a duplicate of the neighboring save_pretrained-related reports.", + "best_issue_reason": "Issue 44483 is concrete, impactful, and well-scoped compared with the rest, which span unrelated imports, configs, serialization, training, and model-specific regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:45405", - "right": "issue:45712", - "accept": false, - "reason": "Different problems: PEFT version pinning vs leftover dummy classes/import leakage." - }, { "left": "issue:44448", "right": "issue:46132", "accept": false, - "reason": "Different code paths: Pegasus output drift vs AttentionInterface registration behavior." + "reason": "Different problems: Pegasus output drift vs AttentionInterface.register changing a function wrapper's behavior." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Both mention imports/backends, but one is an installation/backend packaging issue and the other is a missing import from `image_utils`." + "reason": "Missing TensorFlow backend and a nonexistent image_utils import are separate import-path failures." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "Both touch `save_pretrained`, but one is FP8 MoE serialization and the other is tokenizer metadata mismatch." + "reason": "FP8 save_pretrained on MoE models and tokenizer_config tokenizer_class mismatch are unrelated save_pretrained bugs." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Unrelated import failures: `image_utils` symbol missing vs dummy PT objects leaking into the package API." + "reason": "One is a bad import from image_utils; the other is leftover dummy PT classes leaking into dir(transformers)." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "A Python version compatibility regression is not the same underlying bug as a missing import from `image_utils`." + "reason": "Python version/backend compatibility is not the same bug as an invalid image_utils import symbol." }, { "left": "issue:43479", "right": "issue:44079", "accept": false, - "reason": "Both involve object initialization/None handling, but in different classes and with different failure modes." + "reason": "Phi4MultimodalConfig default initialization and ModelOutput key assignment are different code paths and symptoms." }, { "left": "issue:44297", "right": "issue:45656", "accept": false, - "reason": "Tokenizer config serialization and double optimizer stepping are unrelated." + "reason": "Tokenizer save metadata and DeepSpeed optimizer-step behavior are unrelated." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Both mention `save_pretrained`, but one is FP8 MoE model saving and the other is processor file output completeness." + "reason": "FP8 MoE save_pretrained and processor.save_pretrained missing files are both save-related but not the same defect." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "MLFlow reporting on failed training and model-loading breakage are unrelated bugs." + "reason": "MLflow reporting on failed training jobs and a model-loading regression are distinct issues." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "FP8 accuracy vs missing processor files are different issues." + "reason": "FineGrainedFP8 accuracy and processor.save_pretrained file emission are different failures." }, { "left": "issue:45245", "right": "issue:46132", "accept": false, - "reason": "Category-cardinality limits and attention registration semantics do not share the same bug." + "reason": "Category limit overflow and AttentionInterface.register behavior have no shared underlying bug." }, { "left": "issue:44190", "right": "issue:46082", "accept": false, - "reason": "Dataset loading in a training example and `LlamaConfig` validation are unrelated." + "reason": "Local dataset loading in an example script is unrelated to LlamaConfig head_dim validation." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "Failed MLFlow reporting and a changed `compute_loss` signature are different trainer bugs." - }, - { - "left": "issue:43479", - "right": "issue:44869", - "accept": false, - "reason": "Config default initialization and Whisper timestamp decoding are unrelated." + "reason": "MLflow job status handling and CustomTrainer.compute_loss signature breakage are separate training issues." }, { "left": "issue:45071", "right": "issue:46082", "accept": false, - "reason": "Generic `PretrainedConfig` type-checking regression vs `LlamaConfig` head_dim validation are not the same issue." + "reason": "PretrainedConfig type-checking regression is not the same as LlamaConfig head_dim rejection." }, { - "left": "issue:28282", - "right": "issue:30333", + "left": "issue:43479", + "right": "issue:44869", "accept": false, - "reason": "Importing `AutoModel` without PyTorch and MLFlow run-state reporting are unrelated." + "reason": "Multimodal config defaults and Whisper word-timestamp decoding are unrelated model-specific bugs." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "Training-job reporting and embedding reinitialization after resizing are different bugs." + "reason": "Failed-job MLflow reporting and output embedding reinitialization after resize are different problems." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "A missing PyTorch import and MLflow reporting on failed jobs do not share a code path." }, { "left": "issue:43475", "right": "issue:46305", "accept": false, - "reason": "SAM3 missing attribute and Moonshine off-by-one masking are unrelated model bugs." + "reason": "SAM 3 Video missing attribute and Moonshine streaming mask off-by-one are different video-model bugs." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer config mismatch and Qwen3.5 MoE `from_pretrained` failure are different failures." + "reason": "Tokenizer class metadata mismatch and Qwen3.5 MoE from_pretrained failure are unrelated." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Two import errors, but from different packages and causes; not the same underlying bug." + "reason": "Both are import errors, but they involve different missing symbols and different dependency breakages." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Feature extractor argument regression and auto-docstring annotation crash are unrelated." + "reason": "Unsupported feature extractor arg and auto_docstring future-annotations crash are separate failures." }, { "left": "issue:43723", "right": "issue:44977", "accept": false, - "reason": "Tokenizer loading regression and flash-attention generation failure are unrelated." + "reason": "Tokenizer loading regression in v5 and Qwen3.5 flash-attention generation failure are unrelated." }, { "left": "issue:45381", "right": "issue:46305", "accept": false, - "reason": "Both involve position-related logic, but one is vision token IDs and the other is a sliding-window mask off-by-one." - }, - { - "left": "issue:44263", - "right": "issue:45092", - "accept": false, - "reason": "A `torch.split` indexing bug and meta-initialization incompatibility are unrelated." + "reason": "Wrong vision_position_ids and sliding_window_mask_function off-by-one affect different model components." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Quantization offloading and pipeline-parallel output corruption are different runtime issues." + "reason": "Quantization/offloading behavior and pipeline-parallel output correctness are not the same bug." }, { "left": "issue:43122", "right": "issue:46209", "accept": false, - "reason": "Tokenization differences across versions and FP8 inference failure on B200 are unrelated." + "reason": "Tokenization changes across versions and FP8 inference on B200 are unrelated regressions." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation kwargs syncing and long-OCR index errors are different bugs." + "reason": "Generation kwargs handling after sync_gpus and long-OCR index errors have no common root cause." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "Both are about `save_pretrained`, but one is FP8 MoE saving and the other is shard-size defaults." + "reason": "FP8 MoE save_pretrained and max_shard_size defaults are different save_pretrained concerns." }, { - "left": "issue:44373", - "right": "issue:44485", + "left": "issue:44263", + "right": "issue:45092", "accept": false, - "reason": "A docstring typo and GLM-5 RoPE implementation are not the same bug." + "reason": "torch.split return handling in a MoE indexer and meta-init incompatibility for old checkpoints are unrelated." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Position buffer access and missing processor save files are unrelated." + "reason": "position_ids buffer access and processor.save_pretrained missing files are different serialization bugs." }, { "left": "issue:43479", "right": "issue:43644", "accept": false, - "reason": "Config defaulting and non-persistent buffer corruption are different initialization bugs." + "reason": "Incorrect multimodal config defaults and junk non-persistent buffers are not the same initialization issue." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A docstring mistake for position_ids is unrelated to GLM-5 RoPE implementation behavior." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat-completions request rejection and Gemma4Processor missing _tokenizer are separate API failures." } ] }, @@ -12664,14 +12792,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 40, - "review_unit_count": 50, + "review_unit_index": 41, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:22355", "issue:28282", @@ -12687,6 +12815,7 @@ "issue:42994", "issue:43066", "issue:43479", + "issue:43550", "issue:43576", "issue:43644", "issue:43646", @@ -12702,7 +12831,6 @@ "issue:44368", "issue:44373", "issue:44464", - "issue:44483", "issue:44514", "issue:44568", "issue:44704", @@ -12715,31 +12843,30 @@ "issue:45278", "issue:45310", "issue:45357", - "issue:45406", "issue:45753", "issue:46002", "issue:46050", "issue:46082", + "issue:46132", "issue:46305" ], "soft_pairs": [ - "issue:44483|issue:45406", "issue:43761|issue:46082", "issue:43723|issue:44871", + "issue:30990|issue:38175", "issue:45092|issue:45357", - "issue:44263|issue:44360", "issue:42907|issue:46050", - "issue:30990|issue:38175", - "issue:44261|issue:45092", "issue:44514|issue:45103", + "issue:44263|issue:44360", "issue:43644|issue:46305", "issue:44829|issue:46002", + "issue:44261|issue:45092", "issue:43479|issue:44913", "issue:42831|issue:45310", "issue:22355|issue:28282", - "issue:44263|issue:44373", "issue:41628|issue:43824", "issue:42831|issue:44038", + "issue:44263|issue:44373", "issue:39401|issue:44568", "issue:42886|issue:42994", "issue:44368|issue:46305", @@ -12747,207 +12874,208 @@ "issue:44945|issue:45753", "issue:42757|issue:45278", "issue:44464|issue:46082", - "issue:44117|issue:44704", "issue:43576|issue:43784", "issue:43646|issue:46002", + "issue:44117|issue:44704", + "issue:43550|issue:46132", "issue:42371|issue:44263" ], - "prepared_review_unit_hash": "91e1274808db7601c54fa7b397f371ce5f380cf9eb01a4cbb84b4a6fa445a2ba", + "prepared_review_unit_hash": "c5d50060078d00a46e989e335b8ee7c1ccc4dfed829f52192e26fc28351b21a3", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 35914, - "estimated_input_tokens": 8979, - "estimated_eval_tokens": 18214 + "serialized_chars": 35858, + "estimated_input_tokens": 8965, + "estimated_eval_tokens": 18186 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is a loose collection of unrelated Transformers regression/import/tokenizer issues. I did not find any soft pair that clearly describes the same underlying bug or change, so all soft edges should be rejected.", - "confidence": 0.87, - "canonical_issue_reason": "issue:45278 is the broadest, most representative regression report in the set: it captures multiple import failures after a Transformers upgrade, matching the overall import/regression theme better than the narrower single-class bugs.", + "summary": "This cluster is mostly a loose collection of Transformers v5 regressions and import/runtime bugs, not a tight duplicate set. The best single anchor is the broad upgrade/import-regression report.", + "confidence": 0.31, + "canonical_issue_reason": "issue:45278 is the broadest umbrella here: it captures the common v5 upgrade/import breakage pattern better than the many narrow model- or tokenizer-specific bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best anchor issue because it is clearly framed as a version-regression affecting imports in general, making it the most useful representative for this mixed cluster.", + "best_issue_reason": "issue:45278 is the best cluster anchor because it summarizes the recurring \u201cafter upgrade, imports break\u201d theme without overfitting to one specific symbol or model.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:44483", - "right": "issue:45406", - "accept": false, - "reason": "Different code paths: one is API request handling for chat completions, the other is a processor import/attribute failure in Gemma4." - }, { "left": "issue:43761", "right": "issue:46082", "accept": false, - "reason": "Unrelated bugs: CLIPVisionModel hidden_states regression versus LlamaConfig validation of head_dim." + "reason": "Different failures: CLIPVisionModel hidden_states regression vs LlamaConfig head_dim validation. Not the same code path." }, { "left": "issue:43723", "right": "issue:44871", "accept": false, - "reason": "Both involve model loading/config, but one is a tokenizer loading regression and the other is an eos_token_id inconsistency." + "reason": "Tokenizer loading regression vs eos_token_id config inconsistency. Related area, but distinct bugs." }, { - "left": "issue:45092", - "right": "issue:45357", + "left": "issue:30990", + "right": "issue:38175", "accept": false, - "reason": "Both mention Qwen3.5/vision, but one is meta initialization incompatibility and the other is incorrect save_pretrained visual encoder keys." + "reason": "Sentence Transformers loading hang and siglip2 zero-probability output are unrelated failures." }, { - "left": "issue:44263", - "right": "issue:44360", + "left": "issue:45092", + "right": "issue:45357", "accept": false, - "reason": "Different model internals: a torch.split return-value issue versus a missing ReLU in the DSA indexer." + "reason": "Remote-code/meta-init incompatibility vs incorrect visual encoder keys on save_pretrained. Different concrete bugs." }, { "left": "issue:42907", "right": "issue:46050", "accept": false, - "reason": "Both concern quantized model persistence, but they describe different quantization methods and different failure modes." - }, - { - "left": "issue:30990", - "right": "issue:38175", - "accept": false, - "reason": "Different symptoms and models: loading hangs in Sentence Transformers versus zero probabilities in a SigLIP2 model." + "reason": "Both involve quantized saving/loading, but one is dequantized Ministrals/Devstrals save failure and the other is sinq round-trip breakage; not the same bug." }, { - "left": "issue:44261", - "right": "issue:45092", + "left": "issue:44514", + "right": "issue:45103", "accept": false, - "reason": "Different underlying problems: an RMS norm epsilon precision issue versus an InternVL2 meta-init compatibility problem." + "reason": "Batched apply_chat_template crash and auto_docstring annotation crash are unrelated code paths." }, { - "left": "issue:44514", - "right": "issue:45103", + "left": "issue:44263", + "right": "issue:44360", "accept": false, - "reason": "Completely different layers: processor chat-template batching versus auto-docstring processing under future annotations." + "reason": "Both mention the DSA indexer, but one is torch.split return handling and the other is a missing ReLU. Different defects." }, { "left": "issue:43644", "right": "issue:46305", "accept": false, - "reason": "Both are runtime correctness bugs, but one is about non-persistent buffers and the other is a sliding-window mask off-by-one." + "reason": "Non-persistent buffer junk and sliding_window_mask off-by-one are separate logic issues." }, { "left": "issue:44829", "right": "issue:46002", "accept": false, - "reason": "Both affect training stability, but the reported causes are different: flash_attention_3 degeneration versus checkout/init NaNs." + "reason": "Degenerate training with FA3 and NaNs in classification heads after checkout/init are different symptoms with different likely causes." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA layernorm precision issue vs remote-code checkpoint/meta-init incompatibility are unrelated." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Different config bugs in different classes: Phi4Multimodal default init versus GPTNeoX rotary_pct not persisting on reload." + "reason": "Phi4MultimodalConfig default subconfig initialization and GPTNeoXConfig rotary_pct reload are distinct configuration bugs." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "Different issues: FineGrainedFP8 accuracy versus a Qwen3.5-Moe from_pretrained error." + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 Moe from_pretrained error do not describe the same underlying problem." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "Both are import errors, but one is a missing transformers.onnx module and the other is a missing PyTorch dependency." - }, - { - "left": "issue:44263", - "right": "issue:44373", - "accept": false, - "reason": "One is a runtime tensor-splitting bug; the other is just a docstring problem." + "reason": "Missing transformers.onnx module and missing PyTorch for AutoModel are different import/runtime dependency issues." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are missing-symbol import errors, but they concern different exported classes and no shared concrete failure mode is shown." + "reason": "Both are import errors, but they concern different missing symbols and model families." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "Different regressions: FP8 accuracy issue versus Qwen3-VL-Moe bug in v5." + "reason": "Different bugs: FP8 accuracy regression vs Qwen3-VL-Moe transform/load failure." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "torch.split handling in GlmMoeDsaIndexer and a wrong docstring for position_ids are unrelated." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer-related, but offset_mapping and special-token insertion are distinct behaviors." + "reason": "Wrong offset_mapping and missing BOS/EOS addition are both tokenizer bugs, but not the same concrete defect." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline tokenizer cache loading and quantized model saving are separate failure modes." + "reason": "Offline cache loading and quantized model saving are separate failures." }, { "left": "issue:44368", "right": "issue:46305", "accept": false, - "reason": "A config warning about tie_word_embeddings is unrelated to the Moonshine streaming mask off-by-one." + "reason": "A tie_word_embeddings warning and a sliding_window_mask off-by-one bug are unrelated." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Both involve tokenizers, but one is offline cache loading and the other is decoder type selection in v5." + "reason": "Offline tokenizer cache loading and wrong decoder type are different tokenizer-related regressions." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Different application-level failures: pipeline parallelism output corruption versus an infinite loop on a specific image in Qwen3_5." + "reason": "Pipeline parallelism output corruption and an infinite-loop multimodal prompt are different failure modes." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "Both are import-related, but one is a specific huggingface_hub symbol missing and the other is a broad post-upgrade import breakage report." + "reason": "Both are import-related regressions, but one is a specific huggingface_hub symbol and the other is a broad post-upgrade import breakage report." }, { "left": "issue:44464", "right": "issue:46082", "accept": false, - "reason": "Chunked generation with compiled forward is unrelated to LlamaConfig head_dim validation." - }, - { - "left": "issue:44117", - "right": "issue:44704", - "accept": false, - "reason": "Different loader paths: tokenizer mapping returning None versus AutoProcessor not forwarding kwargs to cached_file." + "reason": "Chunked generation with compiled forward and LlamaConfig head_dim validation are unrelated." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "Different breakages: a CLI/environment command regression versus an import-time NameError in sentence-transformers integration." + "reason": "Broken transformers env CLI and a sentence-transformers NameError are separate import/CLI regressions." }, { "left": "issue:43646", "right": "issue:46002", "accept": false, - "reason": "One concerns non-persistent buffer initialization; the other concerns NaNs in classification heads at checkout/init." + "reason": "Non-persistent buffer junk and NaNs in classification heads are not the same bug." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor not forwarding kwargs to cached_file are different from_pretrained/processor issues." + }, + { + "left": "issue:43550", + "right": "issue:46132", + "accept": false, + "reason": "Bamba SDPA torch.compile failure and AttentionInterface.register behavior change are distinct attention-stack bugs." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 API settings and a DSA indexer ReLU bug are entirely unrelated." + "reason": "TF32 API warning and DSA indexer torch.split behavior are unrelated." } ] }, @@ -12962,14 +13090,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 41, - "review_unit_count": 50, + "review_unit_index": 42, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28218", "issue:30990", @@ -12984,19 +13112,17 @@ "issue:43408", "issue:43452", "issue:43475", - "issue:43550", "issue:43723", "issue:43756", "issue:43784", - "issue:43824", "issue:43937", "issue:44038", "issue:44060", "issue:44222", "issue:44261", + "issue:44279", "issue:44295", "issue:44297", - "issue:44351", "issue:44360", "issue:44373", "issue:44442", @@ -13018,10 +13144,10 @@ "issue:45478", "issue:45593", "issue:45600", - "issue:46132" + "issue:46326", + "issue:46328" ], "soft_pairs": [ - "issue:43550|issue:46132", "issue:30990|issue:33357", "issue:44295|issue:44297", "issue:43232|issue:45593", @@ -13029,251 +13155,239 @@ "issue:42907|issue:44945", "issue:43723|issue:44442", "issue:44261|issue:44373", - "issue:43723|issue:44779", "issue:42907|issue:43937", "issue:41628|issue:45278", - "issue:43756|issue:44060", "issue:43408|issue:43475", + "issue:43756|issue:44060", "issue:43784|issue:45600", - "issue:43122|issue:44514", - "issue:42907|issue:44964", "issue:43116|issue:45200", + "issue:42907|issue:44964", + "issue:43122|issue:44514", "issue:44625|issue:44829", "issue:44360|issue:44485", - "issue:43122|issue:44521", "issue:44038|issue:44297", "issue:43232|issue:45245", + "issue:43122|issue:44521", "issue:28218|issue:30990", - "issue:44038|issue:44295", "issue:42907|issue:43452", + "issue:44038|issue:44295", "issue:43122|issue:44779", "issue:36296|issue:43116", "issue:44038|issue:44222", + "issue:44279|issue:46328", "issue:45216|issue:45478", "issue:39401|issue:44488", - "issue:39401|issue:44521", - "issue:43824|issue:44351" + "issue:43122|issue:46326", + "issue:39401|issue:44521" ], - "prepared_review_unit_hash": "68e039eca2d9368d85eb0bdef569efe99e4b0ae0d05e58c48f73a42b341151da", + "prepared_review_unit_hash": "ced4de6b0d6b93832613714645f68811cf6d82d0c7ca84b1a09ae8072aa81276", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 36901, - "estimated_input_tokens": 9226, - "estimated_eval_tokens": 18708 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36034, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of distinct transformer regressions; the strongest common thread is tokenizer/processor loading or behavior changes in v5, but most pairs are not the same underlying bug.", + "summary": "The cluster is mostly heterogeneous; most soft pairs only share a broad subsystem name (tokenizers, Qwen3, save/load, etc.) but not the same concrete bug. I found no duplicate PRs, and only one issue looks like a reasonable umbrella representative for the tokenizer-regression subset.", "confidence": 0.41, - "canonical_issue_reason": "issue:43723 is the broadest representative of the recurring v5 tokenizer-loading regression theme, and is more central than the highly specific reports around it.", + "canonical_issue_reason": "issue:43122 is the broadest, most representative tokenizer-regression report in this set, and it best matches several of the tokenization-related soft matches; the rest of the cluster is too mixed for a single true canonical issue.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43723 best fits the cluster as a representative issue because it captures the generic AutoTokenizer v5 failure pattern seen across several neighboring reports.", + "best_issue_reason": "issue:43122 is the strongest overall issue anchor because it describes a generic v5 tokenization regression rather than a narrow model-specific symptom, and it sits closest to the related tokenizer candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:43550", - "right": "issue:46132", - "accept": false, - "reason": "Different problems: one is a torch.compile/SDPA failure on a specific model, the other is an AttentionInterface.register behavior change." - }, { "left": "issue:30990", "right": "issue:33357", "accept": false, - "reason": "Unrelated symptoms and models: loading hang for Sentence Transformers vs MacOS bus error for a community CLIP model." + "reason": "Different symptoms and subsystems: loading hang vs Mac bus error on a CLIP model." }, { "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "One is about reading position_ids after buffer registration; the other is tokenizer_class metadata written by save_pretrained." + "reason": "Unrelated bugs: buffer access on position_ids vs tokenizer_class mismatch on save_pretrained." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Different code paths and failures: generation kwargs after sync_gpus vs missing auxiliary losses in D-FINE." + "reason": "Generation kwargs handling and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "Both involve processing APIs, but the bugs differ: cached_file kwargs forwarding vs chat-template crashes with tool-call assistant messages." + "reason": "Different processor paths: cached_file kwargs forwarding vs chat template crashes with tool-call messages." }, { "left": "issue:42907", "right": "issue:44945", "accept": false, - "reason": "Different subsystems: dequantized model saving vs incorrect output under pipeline parallelism." + "reason": "Saving dequantized models is unrelated to incorrect output under pipeline parallelism." }, { "left": "issue:43723", "right": "issue:44442", "accept": false, - "reason": "Both are AutoTokenizer load regressions, but the concrete failures and tokenizer targets are different; not the same bug." + "reason": "Both mention tokenizer loading, but one is a broad v5 loading issue and the other is a specific tokenizer failure; not enough to \u0938\u093e\u092c\u093f\u0924 same bug." }, { "left": "issue:44261", "right": "issue:44373", "accept": false, - "reason": "Different issues: config.rms_norm_eps precision mismatch vs a wrong docstring for position_ids." - }, - { - "left": "issue:43723", - "right": "issue:44779", - "accept": false, - "reason": "Both mention tokenizer regressions in v5, but they affect different tokenizers and appear to be separate concrete failures." + "reason": "MLA norm precision/config bug and a docstring issue are not the same change." }, { "left": "issue:42907", "right": "issue:43937", "accept": false, - "reason": "Different bugs: save_pretrained/dequantization vs GenerationConfig validation for GLM-5." + "reason": "Different model workflows: dequantized save_pretrained vs invalid GenerationConfig." }, { "left": "issue:41628", "right": "issue:45278", "accept": false, - "reason": "One missing import is not the same as a broader collection of import errors after an upgrade." - }, - { - "left": "issue:43756", - "right": "issue:44060", - "accept": false, - "reason": "Different model-specific architecture issues: RoPE layer dropping vs tied-weights warning mapping." + "reason": "One import-name failure is too specific to merge with a broad version-upgrade import-error report." }, { "left": "issue:43408", "right": "issue:43475", "accept": false, - "reason": "Both are SAM 3 related, but one is a model-type warning and the other is a missing attribute in a different execution path." + "reason": "Different SAM 3 failures: model-type warning vs missing output attribute." }, { - "left": "issue:43784", - "right": "issue:45600", + "left": "issue:43756", + "right": "issue:44060", "accept": false, - "reason": "Different failures: NameError importing sentence-transformers vs auto_mappings.py referencing removed Sam3LiteText configs." + "reason": "Unrelated model internals: RoPE-layer count vs tied-weights warning." }, { - "left": "issue:43122", - "right": "issue:44514", + "left": "issue:43784", + "right": "issue:45600", "accept": false, - "reason": "Tokenizer-version regression vs multimodal chat-template crash; related area but not the same underlying bug." + "reason": "Different breakages: missing nn import in sentence-transformers vs stale auto_mappings references." }, { - "left": "issue:42907", - "right": "issue:44964", + "left": "issue:43116", + "right": "issue:45200", "accept": false, - "reason": "Distinct issues involving model saving/loading and a specific multimodal model load failure." + "reason": "Example-script classification output bug and mm_token_type_ids defaulting are unrelated." }, { - "left": "issue:43116", - "right": "issue:45200", + "left": "issue:43122", + "right": "issue:44514", "accept": false, - "reason": "Different behavior: example script returning empty classification results vs Gemma 4 fine-tuning requiring mm_token_type_ids." + "reason": "Tokenization regression vs batched chat-template crash are different code paths." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "Different model/training bugs: Qwen3.5 num_labels propagation vs flash_attention_3 degenerating sequence classification training." + "reason": "Label propagation in Qwen3.5 is unrelated to flash_attention_3 causing degenerate training." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "Unrelated technical areas: DSA indexer ReLU discussion vs GLM-5 RoPE implementation." - }, - { - "left": "issue:43122", - "right": "issue:44521", - "accept": false, - "reason": "Both touch chat/tokenization APIs, but one is a general tokenizer regression and the other is multimodal assistant_masks being all zero." + "reason": "DSA ReLU/indexer discussion is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:44038", "right": "issue:44297", "accept": false, - "reason": "Different issues: Qwen3-VL-Moe behavior in v5 vs tokenizer_class metadata mismatch on save_pretrained." + "reason": "Qwen3-VL-Moe bug and tokenizer save_pretrained class mismatch are different problems." }, { "left": "issue:43232", "right": "issue:45245", "accept": false, - "reason": "No shared code path: generation kwargs handling vs a category-count runtime limit." + "reason": "Generation state update bug and category-count limit error do not match." }, { - "left": "issue:28218", - "right": "issue:30990", + "left": "issue:43122", + "right": "issue:44521", "accept": false, - "reason": "Tokenizer spacing bug vs a loading hang; not the same underlying issue." + "reason": "General tokenizer regression vs multimodal assistant_mask zeroing are different symptoms." }, { - "left": "issue:44038", - "right": "issue:44222", + "left": "issue:28218", + "right": "issue:30990", "accept": false, - "reason": "Both are MoE-related only at a high level, but one is a model behavior bug and the other is FP8 save_pretrained support." + "reason": "Tokenizer spacing bug and SentenceTransformers loading hang are unrelated." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Different load/save failures: dequantized model saving vs gguf_file breaking AutoTokenizer/AutoModelForCausalLM loading." + "reason": "Saving dequantized models is unrelated to gguf_file load failures." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Different bug classes: Qwen3-VL-Moe incompatibility vs position_ids buffer access." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Similar theme of tokenization regressions in v5, but the reports describe different tokenizers and different failure modes." + "reason": "Both are tokenizer-related regressions, but one is a generic version-diff report and the other is DeepSeek-specific incorrect output; not clearly the same concrete defect." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor parallel training bug is unrelated to the multi-label classification example returning empty results." + "reason": "Tensor-parallel training bug is unrelated to the multi-label example-script issue." }, { - "left": "issue:45216", - "right": "issue:45478", + "left": "issue:44038", + "right": "issue:44222", "accept": false, - "reason": "Same model family, but one is save_pretrained checkpoint corruption and the other is from_pretrained loading failure." + "reason": "Qwen3-VL-Moe incompatibility and FP8 save_pretrained on moe are different issues." }, { - "left": "issue:39401", - "right": "issue:44488", + "left": "issue:44279", + "right": "issue:46328", + "accept": false, + "reason": "General dependency complaint and a SequenceFeatureExtractor.pad performance bug are not duplicates." + }, + { + "left": "issue:45216", + "right": "issue:45478", "accept": false, - "reason": "Different problems: Qwen3 offset_mapping regression vs a specific model load failure for cjvt/sleng-bert." + "reason": "Both involve Qwen3.5 and recent versions, but one is save_pretrained checkpoint corruption and the other is from_pretrained loading failure; different code paths." }, { "left": "issue:39401", - "right": "issue:44521", + "right": "issue:44488", "accept": false, - "reason": "Tokenizer offset_mapping bug and multimodal assistant_masks bug are separate issues." + "reason": "Wrong offset_mapping in Qwen3 tokenizer is unrelated to failing to load cjvt/sleng-bert." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:43122", + "right": "issue:46326", "accept": false, - "reason": "Both are import errors, but for unrelated symbols and packages." + "reason": "Generic tokenizer regression and mistral_common continue_final_message behavior are different bugs." }, { - "left": "issue:44360", - "right": "issue:44485", + "left": "issue:39401", + "right": "issue:44521", "accept": false, - "reason": "Different subjects entirely; no shared bug or code path is evident." + "reason": "Tokenizer offset_mapping bug and multimodal assistant_mask bug are unrelated." } ] }, @@ -13288,14 +13402,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 42, - "review_unit_count": 50, + "review_unit_index": 43, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:22355", "issue:28218", @@ -13311,19 +13425,19 @@ "issue:42831", "issue:43066", "issue:43116", - "issue:43122", "issue:43441", "issue:43493", "issue:43611", "issue:43784", + "issue:43824", "issue:43825", "issue:43874", - "issue:43906", "issue:43937", "issue:43976", "issue:43992", "issue:44038", "issue:44075", + "issue:44117", "issue:44297", "issue:44351", "issue:44355", @@ -13340,237 +13454,252 @@ "issue:45446", "issue:45478", "issue:45563", + "issue:45588", "issue:45753", "issue:46002", "issue:46077", "issue:46231" ], "soft_pairs": [ - "issue:22355|issue:28218", + "issue:43824|issue:44351", "issue:43784|issue:45446", + "issue:22355|issue:28218", "issue:22355|issue:29159", "issue:42757|issue:44351", - "issue:43122|issue:43906", "issue:43992|issue:44704", "issue:43066|issue:44779", "issue:44355|issue:46231", - "issue:43937|issue:44485", "issue:43611|issue:46002", - "issue:42371|issue:43874", - "issue:44075|issue:44936", + "issue:43937|issue:44485", "issue:42222|issue:43441", + "issue:44075|issue:44936", + "issue:42371|issue:43874", "issue:42831|issue:44297", "issue:43976|issue:45446", "issue:45357|issue:45478", "issue:44038|issue:45478", "issue:43116|issue:43825", "issue:43493|issue:45753", - "issue:45083|issue:45446", "issue:43116|issue:43493", + "issue:45083|issue:45446", "issue:43937|issue:45563", "issue:22355|issue:29127", - "issue:33453|issue:39401", "issue:44625|issue:46002", + "issue:33453|issue:39401", "issue:44380|issue:46077", "issue:38617|issue:45278", - "issue:42175|issue:44938" + "issue:42175|issue:44938", + "issue:44117|issue:45588", + "issue:39401|issue:44779" ], - "prepared_review_unit_hash": "becfb9322c52a52a2885f336cedf9f4174e1be0a65b109bec2139aeb901b8fbb", + "prepared_review_unit_hash": "5550e383d510ee526ef5c7aca4698a9e5ad592d464bd761dc2b275d0494525e4", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 28, - "serialized_chars": 34992, - "estimated_input_tokens": 8748, - "estimated_eval_tokens": 17752 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36225, + "estimated_input_tokens": 9057, + "estimated_eval_tokens": 18370 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose thematically similar set, not a true duplicate cluster: it mixes tokenizer regressions, import/API breakages, model-specific bugs, and a docs mismatch. None of the soft-edge pairs look like the same underlying bug/change, so I rejected them all. Among the issues, the broadest representative is the tokenizer regression report in 43122.", - "confidence": 0.77, - "canonical_issue_reason": "issue:43122 is the broadest concrete regression report in the dominant tokenizer theme: it describes behavior changing across versions for the same tokenizer, which makes it a better anchor than narrower loading/save/offset-specific reports.", + "summary": "This cluster is mostly a loose collection of unrelated transformer regressions and import/tokenizer issues; the broadest umbrella issue is the one about many import errors after upgrade.", + "confidence": 0.43, + "canonical_issue_reason": "issue:45278 is the best umbrella issue: it explicitly captures the broad post-upgrade import-error regression pattern that overlaps with the largest portion of this cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43122 is the best representative issue for triage because it is version-anchored, user-facing, and broad enough to sit near several other tokenizer-regression reports in this set.", + "best_issue_reason": "issue:45278 is the most representative global issue because it is broad, symptom-focused, and best matches the cluster\u2019s cross-cutting failure mode.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:22355", - "right": "issue:28218", + "left": "issue:43824", + "right": "issue:44351", "accept": false, - "reason": "Different failure modes: missing module import vs tokenizer spacing behavior; no shared code path or concrete fix." + "reason": "Both are import errors, but they involve different missing symbols and likely different code paths." }, { "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Unrelated import problems in different components (sentence-transformers import vs flex_attention version check)." + "reason": "Unrelated failures: one is a NameError on import, the other is a PyTorch version-check/import-guard bug." }, { "left": "issue:22355", - "right": "issue:29159", + "right": "issue:28218", "accept": false, - "reason": "One is an ONNX import error, the other is slow/fast tokenizer inconsistency; too broad to be the same bug." + "reason": "Completely different bugs: ONNX module import vs tokenizer spacing after added tokens." }, { - "left": "issue:42757", - "right": "issue:44351", + "left": "issue:22355", + "right": "issue:29159", "accept": false, - "reason": "Both are import errors, but for different symbols and different packages/APIs; not the same underlying issue." + "reason": "Different areas and symptoms: ONNX import failure vs slow/fast tokenizer inconsistency." }, { - "left": "issue:43122", - "right": "issue:43906", + "left": "issue:42757", + "right": "issue:44351", "accept": false, - "reason": "The second item is only a reproduction reference with no clear matching symptom; insufficient evidence of the same bug." + "reason": "Both are import failures, but for different packages/symbols and not the same underlying bug." }, { "left": "issue:43992", "right": "issue:44704", "accept": false, - "reason": "Different API paths and failures: missing model weight loading vs AutoProcessor kwargs forwarding." + "reason": "Different code paths: model weight loading vs AutoProcessor cached_file kwargs forwarding." }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions, but one is decoder-type metadata and the other is wrong tokenization results for Deepseek; not the same concrete bug." + "reason": "Both concern tokenizers, but the titles point to distinct regressions in different models/behaviors." }, { "left": "issue:44355", "right": "issue:46231", "accept": false, - "reason": "Compiled-Python runtime errors and a documentation parameter-name mismatch are unrelated." + "reason": "No overlap beyond being in the repo; compiled-file errors and a documentation typo are unrelated." }, { - "left": "issue:43937", - "right": "issue:44485", + "left": "issue:43611", + "right": "issue:46002", "accept": false, - "reason": "Same model family, but one is GenerationConfig validation and the other is RoPE implementation discussion; different code paths." + "reason": "Model loading with base_model_prefix is unrelated to NaNs in classification heads." }, { - "left": "issue:43611", - "right": "issue:46002", + "left": "issue:43937", + "right": "issue:44485", "accept": false, - "reason": "Loading with base_model_prefix is unrelated to NaNs in classification heads." + "reason": "Same model family, but invalid GenerationConfig and RoPE implementation are different concrete bugs." }, { - "left": "issue:42371", - "right": "issue:43874", + "left": "issue:42222", + "right": "issue:43441", "accept": false, - "reason": "TF32 settings guidance and a missing image-processor method are unrelated issues." + "reason": "Different subsystems and model families: vitpose breakage vs FlashAttention failure." }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Optimizer argument handling and trainer evaluate-after-train behavior are different subsystems and symptoms." + "reason": "Optimizer argument handling is unrelated to trainer.evaluate() failing after train()." }, { - "left": "issue:42222", - "right": "issue:43441", + "left": "issue:42371", + "right": "issue:43874", "accept": false, - "reason": "Different model breakages (ViTpose model loading vs Ministral FlashAttention) with no shared underlying defect." + "reason": "TF32 settings API and a GLM46V image-patch helper bug are unrelated." }, { "left": "issue:42831", "right": "issue:44297", "accept": false, - "reason": "FP8 accuracy and tokenizer save_pretrained metadata mismatch are unrelated." + "reason": "Different failure modes: FP8 accuracy issue vs tokenizer save_pretrained metadata mismatch." }, { "left": "issue:43976", "right": "issue:45446", "accept": false, - "reason": "Python-version compatibility regression vs a specific import/version gate bug in flex_attention; not the same issue." + "reason": "Both mention versioning, but one is a Python compatibility issue and the other is a PyTorch import guard bug." }, { "left": "issue:45357", "right": "issue:45478", "accept": false, - "reason": "Both concern Qwen3.5, but one is save_pretrained key persistence and the other is from_pretrained loading; different bugs." + "reason": "Related Qwen3.5 area, but save_pretrained key serialization and from_pretrained loading errors are not the same concrete bug." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Different Qwen model variants and different failure modes; too little to merge as one bug." + "reason": "Both involve Qwen3/Qwen3.5 MoE, but the reported failures are different load-time behaviors." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Example-script classification output bug and a pipeline error-message issue are unrelated." + "reason": "One is a classification example bug, the other is a pipeline error-message regression." }, { "left": "issue:43493", "right": "issue:45753", "accept": false, - "reason": "Different model families and symptoms: SigLIP2 implementation discrepancy vs Qwen3_5 infinite loop on a specific image." + "reason": "Different model behaviors: SigLIP2 implementation discrepancy vs Qwen3_5 infinite loop on a specific image." }, { - "left": "issue:45083", - "right": "issue:45446", + "left": "issue:43116", + "right": "issue:43493", "accept": false, - "reason": "Qwen3_omni_moe feature-length helper behavior and a flex_attention import/version check are unrelated." + "reason": "Different tasks and failure modes; only broad ML-model regression similarity." }, { - "left": "issue:43116", - "right": "issue:43493", + "left": "issue:45083", + "right": "issue:45446", "accept": false, - "reason": "Classification example behavior and SigLIP2 implementation parity are different problems." + "reason": "Unrelated: multimodal feature-length helper bug vs a flex_attention version check." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "GenerationConfig validation and a stale warning in paged generate() are separate generation-path issues." + "reason": "GenerationConfig validation and stale warning emission are different code paths." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "Importing transformers.onnx and a LayoutLMv3 error-message clarity issue are unrelated." + "reason": "ONNX import failure and LayoutLMv3 error-message clarity are unrelated." }, { - "left": "issue:33453", - "right": "issue:39401", + "left": "issue:44625", + "right": "issue:46002", "accept": false, - "reason": "Both are tokenizer regressions, but one is loading regression and the other is wrong offset mapping for Qwen3; not clearly the same bug." + "reason": "Different bug classes: config propagation vs NaNs during checkout/init." }, { - "left": "issue:44625", - "right": "issue:46002", + "left": "issue:33453", + "right": "issue:39401", "accept": false, - "reason": "Config propagation for Qwen3.5 and NaNs in classification heads are different defects." + "reason": "Both are tokenizer regressions, but they affect different loading/runtime behaviors and models." }, { "left": "issue:44380", "right": "issue:46077", "accept": false, - "reason": "GPT-2 attention scaling under SDPA/FlashAttention and Gemma4 bidirectional attention masking are separate attention-path bugs." + "reason": "Different attention-path bugs in different models; not the same concrete issue." }, { "left": "issue:38617", "right": "issue:45278", "accept": false, - "reason": "Both are import regressions, but they involve different missing symbols and likely different dependency/version breakages." + "reason": "issue:45278 is a broad umbrella, but this is a specific missing import symbol and not clearly the same bug." }, { "left": "issue:42175", "right": "issue:44938", "accept": false, - "reason": "Backend extras installation and Python 3.14 loading failure are unrelated environment/package issues." + "reason": "Backend packaging/install issue vs Python 3.14 load failure are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "A tokenizer mapping None bug and a flash_attention aux-state AttributeError are different failure modes." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but the reported symptoms and affected models differ." } ] }, @@ -13585,21 +13714,21 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 43, - "review_unit_count": 50, + "review_unit_index": 44, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:38617", "issue:39401", "issue:41628", "issue:42222", - "issue:42371", "issue:42673", + "issue:43012", "issue:43064", "issue:43066", "issue:43122", @@ -13607,6 +13736,7 @@ "issue:43408", "issue:43421", "issue:43450", + "issue:43577", "issue:43673", "issue:43742", "issue:43827", @@ -13614,14 +13744,12 @@ "issue:43986", "issue:44075", "issue:44117", - "issue:44261", "issue:44291", "issue:44410", "issue:44466", "issue:44483", "issue:44484", "issue:44496", - "issue:44779", "issue:44829", "issue:44877", "issue:44945", @@ -13636,18 +13764,17 @@ "issue:45405", "issue:45446", "issue:45464", - "issue:45588", + "issue:45542", "issue:45656", "issue:46002", "issue:46178", "issue:46231", - "issue:46298" + "issue:46298", + "issue:46328" ], "soft_pairs": [ - "issue:44117|issue:45588", - "issue:39401|issue:44779", - "issue:43064|issue:43673", "issue:43381|issue:44945", + "issue:43064|issue:43673", "issue:43827|issue:45446", "issue:43450|issue:43986", "issue:43937|issue:44977", @@ -13657,8 +13784,8 @@ "issue:44117|issue:45081", "issue:43122|issue:46298", "issue:44410|issue:45310", - "issue:44291|issue:45071", "issue:44829|issue:45216", + "issue:44291|issue:45071", "issue:42222|issue:46178", "issue:38617|issue:41628", "issue:39401|issue:43421", @@ -13668,212 +13795,202 @@ "issue:43937|issue:44496", "issue:43066|issue:43122", "issue:44483|issue:45464", - "issue:44075|issue:45656", + "issue:44117|issue:46328", "issue:44964|issue:45278", - "issue:42371|issue:44261" + "issue:44075|issue:45656", + "issue:42222|issue:45542", + "issue:43012|issue:43577" ], - "prepared_review_unit_hash": "a33378f76a051575f4908ea140c53a7a5128e13cffb71344fec3b158a39e5fe1", + "prepared_review_unit_hash": "1b8cf87b5bca7d3847db6990b31018fafbc39c9b67cdbf42d221a37e6cfeebe4", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35784, - "estimated_input_tokens": 8946, - "estimated_eval_tokens": 18148 + "serialized_chars": 35813, + "estimated_input_tokens": 8954, + "estimated_eval_tokens": 18164 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a grab-bag of unrelated Transformers issues. The soft pairs share broad keywords like tokenization, model loading, or optimization, but they do not describe the same concrete bug or change path, so none should be merged as duplicates.", - "confidence": 0.97, + "summary": "This cluster is highly heterogeneous: tokenizer regressions, model-loading failures, training/optimizer bugs, video/vision issues, docs, and backend/dependency errors. I don\u2019t see any convincing duplicate pairs, so there is no strong canonical duplicate group here.", + "confidence": 0.86, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Issue 43122 is the best standalone issue to anchor on if one must choose: it is a concrete, user-visible tokenizer regression with clear behavioral impact and broader relevance than the more narrowly scoped or auxiliary reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44117", - "right": "issue:45588", - "accept": false, - "reason": "Different subsystems: tokenizer mapping fallback vs flash-attention crash handling for sink-less models." - }, - { - "left": "issue:39401", - "right": "issue:44779", + "left": "issue:43381", + "right": "issue:44945", "accept": false, - "reason": "Both are tokenizer bugs, but one is Qwen3 offset mappings and the other is DeepSeek tokenization output; different concrete failures." + "reason": "Different failures: eval-mode checkpointing vs pipeline-parallel output corruption." }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Optimizer state sharding on FSDP2/PEFT is unrelated to GenerationMixin cache missing during chunked prefill." - }, - { - "left": "issue:43381", - "right": "issue:44945", - "accept": false, - "reason": "Eval-mode gradient checkpointing behavior is a different code path from pipeline-parallel incorrect outputs." + "reason": "Unrelated training-state bug vs generation cache/chunked-prefill issue." }, { "left": "issue:43827", "right": "issue:45446", "accept": false, - "reason": "Docs still mentioning pipeline() is unrelated to a runtime PyTorch version check bug." + "reason": "Docs cleanup about pipeline references is unrelated to a flex_attention import/version check." }, { "left": "issue:43450", "right": "issue:43986", "accept": false, - "reason": "Batched video processor shape handling is not the same as AutoProcessor crashing without torchvision." + "reason": "Batch video-shape bug vs missing-torchvision crash path; different code paths and symptoms." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "GenerationConfig validation failure is different from Qwen3.5 flash-attention generation behavior." + "reason": "GenerationConfig validation failure is unrelated to Qwen3.5 flash-attention generation behavior." }, { "left": "issue:44466", "right": "issue:46002", "accept": false, - "reason": "lm_head serialization/tied-weights issue is unrelated to NaNs in classification heads during checkout/init." + "reason": "Serialization/tied-weights issue is not the same as NaNs on checkout/init." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "A PEFT minimum-version bump is not the same bug as an AuxRequest import version check." + "reason": "Release/version pinning complaint is unrelated to flex_attention backend import logic." }, { "left": "issue:42673", "right": "issue:45072", "accept": false, - "reason": "VRAM leak in multithreaded Qwen3 inference is unrelated to dtype mismatches in CI inference tests." + "reason": "VRAM leak in Qwen3ForCausalLM is a different problem from dtype mismatches in inference." }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "Tokenizer mapping None and Mistral regex patch crashes affect different failure points." + "reason": "Tokenizer mapping None handling is not the same as the Mistral regex patch crash." }, { "left": "issue:43122", "right": "issue:46298", "accept": false, - "reason": "Tokenization output differences and a noisy logging message are unrelated." + "reason": "Tokenizer behavior regression is unrelated to a noisy logging message." }, { "left": "issue:44410", "right": "issue:45310", "accept": false, - "reason": "Missing Qwen3Next projections is a model-architecture bug, not the same as Qwen3.5 MoE from_pretrained loading failure." + "reason": "Missing projections in qwen3next layer 0 and Qwen3.5 from_pretrained failure are different bugs." }, { - "left": "issue:44291", - "right": "issue:45071", + "left": "issue:44829", + "right": "issue:45216", "accept": false, - "reason": "Unexpected _is_hf_initialized argument and PretrainedConfig type-checking are different compatibility issues." + "reason": "Flash-attention training degeneration is not the same as checkpoint serialization corruption." }, { - "left": "issue:44829", - "right": "issue:45216", + "left": "issue:44291", + "right": "issue:45071", "accept": false, - "reason": "Flash-attention training degeneration is not the same as save_pretrained checkpoint serialization regression." + "reason": "init_empty_weights argument mismatch is unrelated to PretrainedConfig type-checking." }, { "left": "issue:42222", "right": "issue:46178", "accept": false, - "reason": "VitPose model breakage and backend-mapping errors for tensorflow_text are unrelated load-path problems." + "reason": "VitPose breakage is not the same as the tensorflow_text backend mapping error." }, { "left": "issue:38617", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they involve different missing symbols and different removal/compatibility paths." + "reason": "Importing a removed helper from configuration_utils is a different import issue than AutoImageProcessor export failure." }, { "left": "issue:39401", "right": "issue:43421", "accept": false, - "reason": "Wrong offset mapping and runtime post-processor refresh behavior are different tokenizer issues." + "reason": "Wrong offset_mapping in Qwen3 tokenizer is a different bug from runtime post-processor updates." }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "Model-type mismatch warning for SAM3 trackers is unrelated to the MobileLLM config key error." + "reason": "sam3_video/sam3_tracker warning is unrelated to the MobileLLM config loading key error." }, { "left": "issue:44877", "right": "issue:46231", "accept": false, - "reason": "Strict config loading for granite_speech is unrelated to a docs parameter-name mismatch." + "reason": "Strict config loading for granite_speech is unrelated to a documentation parameter-name mismatch." }, { "left": "issue:44484", "right": "issue:45310", "accept": false, - "reason": "A question about max_shard_size has no overlap with a Qwen3.5 MoE loading error." + "reason": "Shard-size default question is not the same as Qwen3.5 MoE loading failure." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "Invalid GenerationConfig and unrecognized model/config.json issues are distinct loading failures." + "reason": "Invalid GenerationConfig and unrecognized model/config.json are different loading/validation problems." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Wrong tokenizer decoder type and changed tokenization output across versions are not the same concrete defect." + "reason": "Both are tokenizer-v5 related, but one is decoder-type metadata and the other is a tokenization-output regression; not the same concrete bug." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Chat/completions request rejection and streaming inference failure on Qwen3.5-0.8B are different API-path bugs." + "reason": "Generic chat/completions request rejection is different from a Qwen3.5 streaming inference failure." }, { - "left": "issue:44075", - "right": "issue:45656", + "left": "issue:44117", + "right": "issue:46328", "accept": false, - "reason": "SGD args being ignored is unrelated to deepspeed calling optimizer.step() twice." + "reason": "Tokenizer mapping lookup bug is unrelated to SequenceFeatureExtractor.pad performance waste." }, { "left": "issue:44964", "right": "issue:45278", "accept": false, - "reason": "A specific Phi-4 multimodal loading failure is not the same as broad import errors after upgrading transformers." + "reason": "Phi-4 multimodal loading failure is too specific to be the same as a broad import-error report." }, { - "left": "issue:42371", - "right": "issue:44261", + "left": "issue:44075", + "right": "issue:45656", "accept": false, - "reason": "TF32 configuration warnings are unrelated to MLA q_a_layernorm precision/config handling." + "reason": "SGD args being ignored is a different optimizer bug from deepspeed double-step behavior." }, { - "left": "issue:45278", - "right": "issue:41628", + "left": "issue:42222", + "right": "issue:45542", "accept": false, - "reason": "General import errors after upgrade are too broad to equate with one specific missing import symbol." + "reason": "VitPose model breakage is not the same as missing-TensorFlow backend resolution." }, { - "left": "issue:44977", - "right": "issue:45081", + "left": "issue:43012", + "right": "issue:43577", "accept": false, - "reason": "Qwen3.5 flash-attention generation problems and Mistral regex patch crashes are different tokenizer/model paths." + "reason": "Compile-time bfloat16 warning is not the same as model/qformer dtype staying float32 on load." } ] }, @@ -13888,14 +14005,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 44, - "review_unit_count": 50, + "review_unit_index": 45, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:38617", "issue:41628", @@ -13903,7 +14020,6 @@ "issue:42222", "issue:42371", "issue:42673", - "issue:42757", "issue:42831", "issue:43012", "issue:43064", @@ -13912,15 +14028,15 @@ "issue:43408", "issue:43441", "issue:43452", - "issue:43577", + "issue:43673", "issue:43874", "issue:43906", "issue:43931", "issue:43976", "issue:43986", "issue:44038", - "issue:44062", "issue:44117", + "issue:44188", "issue:44220", "issue:44261", "issue:44263", @@ -13932,29 +14048,31 @@ "issue:44485", "issue:44493", "issue:44829", + "issue:44913", "issue:44933", "issue:44945", "issue:44977", "issue:44987", "issue:45071", - "issue:45200", "issue:45440", "issue:45478", "issue:45542", "issue:45588", "issue:46050", "issue:46172", - "issue:46231" + "issue:46231", + "issue:46328" ], "soft_pairs": [ - "issue:42222|issue:45542", - "issue:43012|issue:43577", "issue:44410|issue:45478", + "issue:42371|issue:44261", + "issue:44188|issue:46328", + "issue:44913|issue:46328", "issue:42175|issue:42222", "issue:38617|issue:44220", - "issue:43874|issue:44261", "issue:43097|issue:44493", "issue:41628|issue:45071", + "issue:43874|issue:44261", "issue:44263|issue:44485", "issue:45071|issue:45542", "issue:42673|issue:44977", @@ -13964,256 +14082,248 @@ "issue:44360|issue:46172", "issue:44484|issue:45478", "issue:43441|issue:44829", - "issue:42371|issue:42831", "issue:43931|issue:44038", "issue:43335|issue:45071", + "issue:42371|issue:42831", "issue:43097|issue:43452", - "issue:43874|issue:44263", "issue:44933|issue:46231", "issue:44117|issue:44987", "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43673|issue:46328", "issue:43976|issue:44945", "issue:43986|issue:44484", "issue:45440|issue:46172", - "issue:43097|issue:45588", - "issue:43064|issue:44315", "issue:43097|issue:46050", - "issue:42673|issue:45200", - "issue:38617|issue:42757", - "issue:44062|issue:44117" + "issue:43097|issue:45588", + "issue:43064|issue:44315" ], - "prepared_review_unit_hash": "5bbef32ea2fb55d41feb3d8ba479ae302a0f7ff09ddebeb063740bbf238145e6", + "prepared_review_unit_hash": "395a1b1174bb924a40173848d443d777d712a6d7c6ba9b5836085a09dea12ad5", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37842, - "estimated_input_tokens": 9461, - "estimated_eval_tokens": 19178 + "soft_pair_count": 33, + "serialized_chars": 37494, + "estimated_input_tokens": 9374, + "estimated_eval_tokens": 19004 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft edge looks like a true duplicate; most pairs are only loosely related by subsystem, model family, or symptom type. I\u2019d anchor the cluster on issue:43097 as the clearest high-signal regression report, but there is no mergeable PR here.", - "confidence": 0.61, - "canonical_issue_reason": "issue:43097 is the clearest, most broadly impactful regression report in this set, with explicit references and a concrete API-break symptom.", + "summary": "This cluster is heterogeneous: the issues span unrelated import errors, model-specific bugs, config regressions, backend/runtime warnings, and a few performance problems. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:43097 is the strongest representative issue: it is specific, reproducible, and likely to attract the most relevant fix context.", + "best_issue_reason": "issue:43097 is the clearest broad regression report in the set: it is version-scoped, user-facing, and has some inbound references, whereas the other issues are mostly narrow, unrelated bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:42222", - "right": "issue:45542", + "left": "issue:44410", + "right": "issue:45478", "accept": false, - "reason": "Different failures: vitpose model breakage vs missing TF backend wiring." + "reason": "Different failures: qwen3next missing projections in one layer vs a Qwen3.5 MoE load-time error." }, { - "left": "issue:43012", - "right": "issue:43577", + "left": "issue:42371", + "right": "issue:44261", "accept": false, - "reason": "Both involve dtype/precision, but the model paths and bugs differ." + "reason": "TF32 API/settings warning is unrelated to an MLA layernorm epsilon precision bug." }, { - "left": "issue:44410", - "right": "issue:45478", + "left": "issue:44188", + "right": "issue:46328", + "accept": false, + "reason": "torch.compile attention branching and feature-extractor padding performance are different code paths and symptoms." + }, + { + "left": "issue:44913", + "right": "issue:46328", "accept": false, - "reason": "Different model families and different loader failures; not the same bug." + "reason": "GPTNeoX config reload regression is unrelated to SequenceFeatureExtractor.pad list conversion overhead." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "Packaging/backend dependency issue vs a specific model regression." + "reason": "TensorFlow missing from a torch install and broken vitpose models are separate issues." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "Unrelated import error versus audio feature extraction bug." - }, - { - "left": "issue:43874", - "right": "issue:44261", - "accept": false, - "reason": "Different GLM subcomponents and different failure modes." + "reason": "ImportError for layer_type_validation does not match an audio feature extraction bug." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Config-removal warning is not the same as unexpected position-id key errors." + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are distinct config regressions." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Import failure for AutoImageProcessor vs a type-checking regression." + "reason": "AutoImageProcessor import failure is unrelated to PreTrainedConfig type checking breakage." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-processor method in GLM46V is unrelated to MLA q_a_layernorm epsilon handling." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "Tokenizer/indexer split bug and RoPE implementation bug are distinct." + "reason": "torch.split return-value handling in GlmMoeDsaIndexer does not match the GLM-5 RoPE implementation issue." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "Type checking regression is unrelated to TF backend installation problems." + "reason": "Type-checking regression and tensorboard-without-TensorFlow backend error are different problems." }, { "left": "issue:42673", "right": "issue:44977", "accept": false, - "reason": "VRAM leak in threaded loading is not the flash-attention generation bug." + "reason": "VRAM leak in multi-threaded dataloading and flash-attention generation failure are not the same bug." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "No evidence they describe the same underlying bug." + "reason": "The reproduction of issue 38071 is not the same underlying defect as the Qwen3ForCausalLM VRAM leak." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "Different model-specific warnings with different causes." + "reason": "bfloat16 precision warning during compile and a sam3 model-type warning are unrelated." }, { "left": "issue:44263", "right": "issue:46172", "accept": false, - "reason": "Different tensor-shape/indexing issues in different model code paths." + "reason": "GlmMoeDsaIndexer split handling and deepseek-v4 comb transpose are different model internals." }, { "left": "issue:44360", "right": "issue:46172", "accept": false, - "reason": "Activation omission and dtype/transpose bug are unrelated." + "reason": "Missing ReLU in the DSA indexer is unrelated to the deepseek-v4 transpose bug." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "Shard-size question vs Qwen3.5 model-loading failure." + "reason": "save_pretrained shard-size semantics are unrelated to a Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both mention flash attention, but the models and symptoms differ." - }, - { - "left": "issue:42371", - "right": "issue:42831", - "accept": false, - "reason": "TF32 warning/config discussion is not the same as FineGrainedFP8 accuracy loss." + "reason": "Ministral-3 flash-attention failure and flash_attention_3 causing degenerate training are different failure modes." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Related model family, but different load-time errors and code paths." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-VL-Moe version breakage are separate load-time issues." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "Sparse-layer config bug is unrelated to PretrainedConfig type checking." + "reason": "SwitchTransformers sparse-layer construction bug is unrelated to PreTrainedConfig type checking." }, { - "left": "issue:43097", - "right": "issue:43452", + "left": "issue:42371", + "right": "issue:42831", "accept": false, - "reason": "API removal warning and gguf loading breakage are different issues." + "reason": "TF32 behavior settings and FineGrainedFP8 accuracy are not the same underlying defect." }, { - "left": "issue:43874", - "right": "issue:44263", + "left": "issue:43097", + "right": "issue:43452", "accept": false, - "reason": "Different GLM bugs: missing method vs incorrect split outputs." + "reason": "A removed config option and gguf_file load failures affect different APIs and code paths." }, { "left": "issue:44933", "right": "issue:46231", "accept": false, - "reason": "Missing import and documentation typo are not duplicates." + "reason": "Nonexistent image_utils import and a documentation parameter-name mismatch are unrelated." }, { "left": "issue:44117", "right": "issue:44987", "accept": false, - "reason": "Tokenizer mapping assumption bug versus a specific model loading failure." + "reason": "Tokenizer mapping None handling and loading physical-intelligence/fast are separate loading failures." }, { "left": "issue:43408", "right": "issue:44368", "accept": false, - "reason": "Different warning text and different model/config contexts." + "reason": "sam3 type warning and tie_word_embeddings warning are distinct config validation issues." }, { - "left": "issue:43976", - "right": "issue:44945", + "left": "issue:43874", + "right": "issue:44263", "accept": false, - "reason": "Python version compatibility issue vs pipeline-parallelism output corruption." + "reason": "Missing GLM46V image-processor method and torch.split return handling are unrelated bugs." }, { - "left": "issue:43986", - "right": "issue:44484", + "left": "issue:43673", + "right": "issue:46328", "accept": false, - "reason": "AutoProcessor torchvision dependency issue is unrelated to max shard size." + "reason": "Missing generation cache in chunked_prefill is unrelated to padding performance in feature extraction." }, { - "left": "issue:45440", - "right": "issue:46172", + "left": "issue:43976", + "right": "issue:44945", "accept": false, - "reason": "Different DeepSeek model generations and different implementation bugs." + "reason": "Python version compatibility failure and incorrect pipeline-parallel output are different regressions." }, { - "left": "issue:43097", - "right": "issue:45588", + "left": "issue:43986", + "right": "issue:44484", "accept": false, - "reason": "Config-removal warning is unrelated to flash-attention AttributeError." + "reason": "AutoProcessor crash without torchvision and max_shard_size documentation/question are unrelated." }, { - "left": "issue:43064", - "right": "issue:44315", + "left": "issue:45440", + "right": "issue:46172", "accept": false, - "reason": "Distributed optimizer-state bug is not the same as Liger kernel application." + "reason": "Native DeepseekV3MoE divergence and deepseek-v4 comb transpose are different model implementation issues." }, { "left": "issue:43097", "right": "issue:46050", "accept": false, - "reason": "API removal warning and quantized save/load breakage are distinct." - }, - { - "left": "issue:42673", - "right": "issue:45200", - "accept": false, - "reason": "Threaded VRAM leak has nothing to do with Gemma 4 multimodal token IDs." + "reason": "Removed tie_embeddings option and quantized save/load breakage are not the same bug." }, { - "left": "issue:38617", - "right": "issue:42757", + "left": "issue:43097", + "right": "issue:45588", "accept": false, - "reason": "Both are import errors, but for different symbols and modules." + "reason": "tie_embeddings removal and flash_attention s_aux=None crash are unrelated code paths." }, { - "left": "issue:44062", - "right": "issue:44117", + "left": "issue:43064", + "right": "issue:44315", "accept": false, - "reason": "Tokenizer AddedToken construction bug is unrelated to tokenizer-mapping None handling." + "reason": "FSDP2/PEFT optimizer-state corruption and Liger Kernel not applied with model_init are different training issues." } ] }, @@ -14228,17 +14338,19 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 45, - "review_unit_count": 50, + "review_unit_index": 46, + "review_unit_count": 52, "status": "reviewed", "reason": null, "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:38617", "issue:42617", + "issue:42673", + "issue:42757", "issue:42890", "issue:42907", "issue:43012", @@ -14255,27 +14367,25 @@ "issue:43986", "issue:43992", "issue:44038", + "issue:44062", "issue:44117", "issue:44162", - "issue:44222", "issue:44261", "issue:44351", "issue:44368", "issue:44410", - "issue:44483", "issue:44484", "issue:44485", - "issue:44514", "issue:44655", "issue:44704", "issue:44938", "issue:44964", "issue:45103", + "issue:45200", "issue:45290", "issue:45341", "issue:45372", "issue:45375", - "issue:45478", "issue:45561", "issue:45588", "issue:45712", @@ -14287,24 +14397,27 @@ "issue:46298" ], "soft_pairs": [ + "issue:42673|issue:45200", + "issue:38617|issue:42757", + "issue:44062|issue:44117", "issue:44410|issue:45375", "issue:42890|issue:46298", - "issue:43931|issue:44410", "issue:44038|issue:44410", + "issue:43931|issue:44410", "issue:43502|issue:43992", "issue:45341|issue:45859", "issue:38617|issue:44351", "issue:43097|issue:43873", - "issue:44261|issue:44485", "issue:44964|issue:45341", + "issue:44261|issue:44485", "issue:44704|issue:45103", "issue:43986|issue:44117", "issue:42617|issue:45341", "issue:43986|issue:45372", "issue:43066|issue:43906", "issue:43986|issue:45290", - "issue:45341|issue:45561", "issue:45341|issue:45588", + "issue:45341|issue:45561", "issue:43208|issue:43550", "issue:43986|issue:45341", "issue:43992|issue:44484", @@ -14317,236 +14430,240 @@ "issue:43097|issue:46298", "issue:44162|issue:46172", "issue:43792|issue:46123", - "issue:44938|issue:46178", - "issue:44483|issue:44514", - "issue:44222|issue:45478" + "issue:44938|issue:46178" ], - "prepared_review_unit_hash": "075f77b9897e489523074f0f0cdffc3c8ad10d4d5020bcbea4171cef992bf546", + "prepared_review_unit_hash": "06eadb4b1ec78a7e11a2d53b03f2f6cf795748693643a6ba2265c06d4e4690a3", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37333, - "estimated_input_tokens": 9334, - "estimated_eval_tokens": 18924 + "soft_pair_count": 34, + "serialized_chars": 37692, + "estimated_input_tokens": 9423, + "estimated_eval_tokens": 19102 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous. The soft edges are all superficial similarities (often same model family or same broad area) but the underlying bugs differ, so none should be merged as duplicates.", - "confidence": 0.97, - "canonical_issue_reason": null, + "summary": "This set is not a single duplicate cluster; it is a grab bag of unrelated Transformers issues. I rejected all soft edges because each pair points to a different underlying bug or code path, even when the titles share a subsystem or model family.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out: the items are mostly unrelated, with only weak thematic overlap among a few import/model-loading/Qwen3 reports.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:43986 is the best representative issue: it is specific, reproducible, and tied to one concrete loading path with a clear environment dependency.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42673", + "right": "issue:45200", + "accept": false, + "reason": "Different failures: VRAM leak in Qwen3 CausalLM threading vs Gemma 4 text-only fine-tuning config default." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different missing symbols from different modules; not the same bug." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "Different tokenizer problems: AddedToken argument collision vs TOKENIZER_MAPPING_NAMES returning None." + }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Different bugs: missing projections in qwen3next vs a config field dropped by strict validation in Qwen3.5 MoE." + "reason": "Both mention Qwen3 models, but one is missing attention projections and the other is a missing config field; distinct defects." }, { "left": "issue:42890", "right": "issue:46298", "accept": false, - "reason": "Unrelated: seed-related SAM HQ test instability vs a noisy logging message." + "reason": "Unrelated: flaky test seeding issue vs a noisy logging message." }, { - "left": "issue:43931", + "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Different failure modes and model families: Qwen3-VL load mismatch vs qwen3next missing projections." + "reason": "Different model-path failures: Qwen3-VL-Moe compatibility issue vs missing layer projections in qwen3next." }, { - "left": "issue:44038", + "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Both mention Qwen3, but one is a v5/MoE compatibility issue and the other is missing layer projections; not the same bug." + "reason": "Different concrete failures and model variants; one is a shape mismatch during load, the other is missing projections." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "Different code paths: unwanted network access with local_files_only vs missing embed_tokens weight on UMT5 loading." + "reason": "Different loading behaviors: network access despite local_files_only vs missing embed_tokens.weight on UMT5Encoder." }, { "left": "issue:45341", "right": "issue:45859", "accept": false, - "reason": "Unrelated: testing utils bug vs Qwen3.5 MoE CPU-offload incompatibility." + "reason": "Unrelated: testing utility bug vs CPU offload incompatibility in Qwen3_5Moe rotary embedding." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different symbols and likely different modules/releases." + "reason": "Both are import errors, but they concern different APIs and different missing exports." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "Different problems: a removed config API vs quantization/offloading behavior." + "reason": "Different concerns: removed config option documentation vs quantization offloading behavior." }, { - "left": "issue:44261", - "right": "issue:44485", + "left": "issue:44964", + "right": "issue:45341", "accept": false, - "reason": "Distinct model bugs: MLA RMS norm epsilon handling vs GLM-5 RoPE implementation." + "reason": "Completely different: multimodal model load failure vs a small testing utility bug." }, { - "left": "issue:44964", - "right": "issue:45341", + "left": "issue:44261", + "right": "issue:44485", "accept": false, - "reason": "Completely unrelated: Phi-4 multimodal loading vs a testing_utils bug." + "reason": "Different model-specific math/config issues: MLA layernorm epsilon vs GLM-5 RoPE implementation." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "Different layers: AutoProcessor kwargs forwarding vs auto_docstring annotation crash." + "reason": "Different code paths: AutoProcessor kwarg forwarding vs auto_docstring crashing on future annotations." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "Different surfaces: processor loading without torchvision vs tokenizer mapping returning None." + "reason": "Different failures: video-model loading without torchvision vs tokenizer mapping assumptions." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "Unrelated: 3d_parallel.py runtime issue vs testing_utils bug." + "reason": "Unrelated: 3d_parallel.py runtime failure vs a testing helper bug." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Different import/dep issues affecting different processor paths and models." + "reason": "Different missing-dependency/import problems affecting different processor/model-loading paths." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Tokenizer decoder mismatch in v5 is not the same as the isolated reproduction of another issue." + "reason": "Too little evidence that these are the same bug; one is a tokenizer decoder type regression, the other is only a reproduction of an older issue." }, { "left": "issue:43986", "right": "issue:45290", "accept": false, - "reason": "Different chat/processor paths: missing torchvision dependency vs apply_chat_template tool-call crash." + "reason": "Different crash locations: AutoProcessor video-model import path vs chat template handling of tool-call assistant messages." }, { "left": "issue:45341", - "right": "issue:45561", + "right": "issue:45588", "accept": false, - "reason": "Testing-utils bug vs xdist race in captured_info.txt are different issues." + "reason": "Unrelated: testing utility bug vs flash_attention crash on sink-less models." }, { "left": "issue:45341", - "right": "issue:45588", + "right": "issue:45561", "accept": false, - "reason": "Different areas: testing utils vs flash_attention crash on s_aux=None." + "reason": "Unrelated: testing utility bug vs xdist race on captured_info.txt." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "Both are training/compile-related, but the concrete bugs are different: xLSTM training blockers vs Bamba SDPA torch.compile failure." + "reason": "Different issues: xLSTM training bugs vs Bamba torch.compile SDPA failure." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "Processor/torchvision crash is unrelated to the testing_utils bug." + "reason": "Unrelated: video-model loading crash vs testing utility bug." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Model weight loading mismatch vs save_pretrained shard-size question; different code paths." + "reason": "Different behaviors: missing checkpoint weight vs question about the default shard size." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "Different symptoms: precision warning during bfloat16 compilation vs a model-specific torch.compile failure." + "reason": "Not the same bug: a warning during bfloat16 compilation vs an actual model failure with SDPA." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Pipeline chat/task messaging issue vs inability to save Pipeline objects; unrelated behavior." + "reason": "Different pipeline issues: misleading translation support message vs inability to save Pipeline objects." }, { "left": "issue:43012", "right": "issue:44368", "accept": false, - "reason": "Unrelated: a PyTorch warning on bfloat16 compile vs a tie_word_embeddings config warning." + "reason": "Different surface areas: compile-time precision warning vs tie_word_embeddings warning in fine-tuning." }, { "left": "issue:45712", "right": "issue:46298", "accept": false, - "reason": "Left is a concrete leftover dummy-class repo hygiene bug; right is an unspecified noisy logging message." + "reason": "Different problems: leftover dummy classes vs noisy logging." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Saving dequantized models is not the same as saving Pipeline objects." + "reason": "Different bugs: failure saving dequantized models vs failure saving Pipeline objects." }, { "left": "issue:42907", "right": "issue:45753", "accept": false, - "reason": "Different bugs: dequantized model save failure vs Qwen3_5 infinite-loop generation." + "reason": "Different symptoms and code paths: save/dequantization bug vs infinite loop on a specific image." }, { "left": "issue:43097", "right": "issue:46298", "accept": false, - "reason": "A removed API warning/behavior is unrelated to a generic noisy log message." + "reason": "Different issues: config removal/documentation concern vs noisy logging." }, { "left": "issue:44162", "right": "issue:46172", "accept": false, - "reason": "Different model/runtime failures: ESM2 breakage vs DeepSeek-V4 dtype/transpose issue." + "reason": "Different model-specific failures: ESM2 breakage vs deepseek-v4 dtype/transpose bug." }, { "left": "issue:43792", "right": "issue:46123", "accept": false, - "reason": "Whisper cannot run vs partial-batch mask generation dropping results are unrelated." + "reason": "Different pipelines entirely: Whisper model run failure vs mask generation batch-finalization bug." }, { "left": "issue:44938", "right": "issue:46178", "accept": false, - "reason": "Python 3.14 load failure is not the same as an unknown BACKENDS_MAPPING backend error." - }, - { - "left": "issue:44483", - "right": "issue:44514", - "accept": false, - "reason": "Different request paths: chat-completions endpoint rejection vs Qwen2.5-VL chat template batching crash." - }, - { - "left": "issue:44222", - "right": "issue:45478", - "accept": false, - "reason": "Related domain but different operations: FP8 save_pretrained problem vs Qwen3.5 MoE from_pretrained error." + "reason": "Different environments and failures: Python 3.14 import/load issue vs an invalid backend mapping entry." } ] }, @@ -14561,14 +14678,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 46, - "review_unit_count": 50, + "review_unit_index": 47, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:36010", "issue:36683", @@ -14594,32 +14711,34 @@ "issue:43867", "issue:43881", "issue:43901", - "issue:43906", "issue:43937", "issue:44038", + "issue:44222", "issue:44230", "issue:44242", "issue:44380", "issue:44483", "issue:44485", + "issue:44514", "issue:44625", "issue:44655", "issue:44683", "issue:45216", "issue:45276", "issue:45290", + "issue:45478", "issue:45600", "issue:45698", - "issue:45753", "issue:46077", "issue:46082", "issue:46123", - "issue:46132", "issue:46172", "issue:46209", "issue:46298" ], "soft_pairs": [ + "issue:44483|issue:44514", + "issue:44222|issue:45478", "issue:43208|issue:43526", "issue:43012|issue:44683", "issue:42490|issue:43012", @@ -14633,240 +14752,237 @@ "issue:43064|issue:44380", "issue:43618|issue:43761", "issue:43299|issue:43867", - "issue:43066|issue:46209", "issue:36683|issue:43475", - "issue:42994|issue:44655", + "issue:43066|issue:46209", "issue:45276|issue:46077", + "issue:42994|issue:44655", "issue:43901|issue:44655", "issue:44625|issue:46077", - "issue:43352|issue:43937", - "issue:43611|issue:44655", "issue:36010|issue:42757", + "issue:43611|issue:44655", + "issue:43352|issue:43937", "issue:43867|issue:45216", "issue:46077|issue:46082", "issue:43502|issue:44485", "issue:36683|issue:43525", "issue:43618|issue:45216", "issue:36683|issue:44242", - "issue:44380|issue:46132", - "issue:36683|issue:43881", - "issue:43906|issue:45753", - "issue:43299|issue:45753" + "issue:36683|issue:43881" ], - "prepared_review_unit_hash": "f12a4213e247b18bdd010f3fd71cec91345de9e9cf12b9cf7f29151db0308b30", + "prepared_review_unit_hash": "eb4d45b58e6ea2c66027ace20af009cd0e22d6dedb7b85e5bb6d9da1ecc28519", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 36833, - "estimated_input_tokens": 9209, - "estimated_eval_tokens": 18674 + "soft_pair_count": 31, + "serialized_chars": 36510, + "estimated_input_tokens": 9128, + "estimated_eval_tokens": 18512 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is not a true duplicate set: the items span unrelated Transformers regressions, import failures, config/schema issues, saving/loading bugs, and model-specific behavior changes. None of the soft edges look like the same concrete bug or change.", - "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue cleanly represents the cluster; the topics are too heterogeneous. If forced to pick one representative, issue 45698 is the broadest active save/load regression, but it does not cover the rest.", + "summary": "This cluster is a bundle of related-but-distinct Transformers regressions and API breakages, not a duplicate set. I rejected every soft edge because the paired issues target different code paths, models, or behaviors.", + "confidence": 0.97, + "canonical_issue_reason": "No clear canonical issue: the items span unrelated bugs (imports, loading/saving, generation, pipeline behavior, quantization, and model-specific regressions), so there is no single duplicate to represent the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45698 is the best representative only in a loose sense because it is an active, broadly described save/load regression with multiple references, but it is not a duplicate umbrella for the other items.", + "best_issue_reason": "No single issue is a good global representative; the nearest matches still describe different concrete failures and should not be merged as one bug.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Different surfaces: `/v1/chat/completions` request handling vs batched `apply_chat_template` crash with `padding=False`." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Different directions and failures: FP8 `save_pretrained` bug vs Qwen3.5 MoE `from_pretrained` load error." + }, { "left": "issue:43208", "right": "issue:43526", "accept": false, - "reason": "Different bugs: xLSTM training blockers vs a BeitImageProcessorFast label-reduction bug." + "reason": "Unrelated models/features: xLSTM training bugs vs BeitImageProcessorFast `reduce_labels` returning one label." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "Different failures: a PyTorch warning during bfloat16 compilation vs a hard compile error in flex_attention on torch>=2.9." + "reason": "Both are compile-related, but one is a bfloat16 warning and the other is a torch>=2.9 flex_attention failure." }, { "left": "issue:42490", "right": "issue:43012", "accept": false, - "reason": "Unrelated symptoms: local-path slash import warning vs bfloat16 precision warning." + "reason": "Local-path trailing-slash import warning is unrelated to bfloat16 compile warning behavior." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different symbols and modules; not the same underlying breakage." + "reason": "Both are import errors, but for different symbols from different modules (`is_offline_mode` vs `Qwen2_5_VLForConditionalGeneration`)." }, { "left": "issue:45600", "right": "issue:46298", "accept": false, - "reason": "CI break from removed Sam3LiteText configs vs a noisy logging message; not the same bug." + "reason": "CI break from removed Sam3LiteText refs is unrelated to a noisy logging message." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "ImportError for layer_type_validation vs API requests despite local_files_only; unrelated code paths." + "reason": "Different offline/import problems: missing `layer_type_validation` import vs unwanted network requests with `local_files_only=True`." }, { "left": "issue:45698", "right": "issue:46172", "accept": false, - "reason": "Save/load custom module regression vs a deepseek-v4 tensor/dtype transpose issue; different code paths." + "reason": "Custom-module reload after save is unrelated to a DeepSeek dtype/transpose bug." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Both mention Qwen3-VL-Moe, but one is a loading regression and the other is fp8 inference support; not the same bug." + "reason": "Different Qwen/MoE FP8 issues: one is a v5 regression, the other is FP8 inference support." }, { "left": "issue:43673", "right": "issue:46123", "accept": false, - "reason": "Generation cache missing in chunked prefill vs batch-finalization dropping results in MaskGenerationPipeline; unrelated." + "reason": "Generation cache regression is unrelated to MaskGenerationPipeline dropping final partial-batch results." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Both touch chat APIs, but one is a v5.3 /v1/chat/completions request rejection and the other is a chat-template crash with tool calls." + "reason": "API request acceptance problem is unrelated to chat-template tokenization crashing on tool-call assistant messages." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "Distributed optimizer-state corruption vs GPT2 attention-scaling being ignored in SDPA/FlashAttention; different problems." + "reason": "FSDP2/PEFT optimizer-state bug is unrelated to GPT2 attention scaling being ignored under SDPA/FlashAttention." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both are CLIP v5 regressions, but one is missing attentions and the other missing hidden_states; too different to merge as one bug." + "reason": "Both touch CLIP outputs, but one is missing attentions and the other is missing hidden states; not the same concrete bug." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Qwen3VL-Moe loading regression vs a state_dict-sorting load error; not the same underlying failure." - }, - { - "left": "issue:43066", - "right": "issue:46209", - "accept": false, - "reason": "Wrong tokenizer decoder type vs FP8 inference on B200; unrelated issues." + "reason": "Qwen3VL MoE loading breakage is unrelated to a state_dict-sorting load error." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Different missing attributes on different model objects: Gemma3Config.vocab_size vs Sam3VisionEncoderOutput.fpn_position_embeddings." + "reason": "Gemma3Config missing `vocab_size` is unrelated to SAM 3 Video missing `fpn_position_embeddings`." }, { - "left": "issue:42994", - "right": "issue:44655", + "left": "issue:43066", + "right": "issue:46209", "accept": false, - "reason": "Quantized model saving failure vs Pipeline save_pretrained serialization; related area but different concrete bugs." + "reason": "Wrong tokenizer decoder type and FP8 inference on B200 are different regressions." }, { "left": "issue:45276", "right": "issue:46077", "accept": false, - "reason": "Gemma4 embedding resize propagation bug vs Gemma4 attention-mask construction bug; different code paths." + "reason": "Gemma4 token embedding resize bug is unrelated to bidirectional attention still building causal masks." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure and pipeline `save_pretrained` failure affect different objects and paths." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Docs/behavior mismatch for return_all_scores vs inability to save Pipeline objects; unrelated." + "reason": "Docs mismatch for `return_all_scores` is unrelated to pipeline serialization failure." }, { "left": "issue:44625", "right": "issue:46077", "accept": false, - "reason": "Qwen3.5 num_labels propagation issue vs Gemma4 attention masking; different models and bugs." + "reason": "Qwen3.5 `num_labels` propagation bug is unrelated to Gemma4 attention-mask behavior." }, { - "left": "issue:43352", - "right": "issue:43937", + "left": "issue:36010", + "right": "issue:42757", "accept": false, - "reason": "Flash Attention 2 support gap in Nemotron vs invalid GenerationConfig in GLM-5; unrelated." + "reason": "Different missing imports from different modules; same broad symptom, different bug." }, { "left": "issue:43611", "right": "issue:44655", "accept": false, - "reason": "Loading with base_model_prefix regression vs Pipeline save_pretrained failure; different lifecycle stages and failures." + "reason": "Base-model-prefix loading regression is unrelated to pipeline save_pretrained failure." }, { - "left": "issue:36010", - "right": "issue:42757", + "left": "issue:43352", + "right": "issue:43937", "accept": false, - "reason": "Different import errors from different packages and symbols; not the same duplicate." + "reason": "FlashAttention2 support error for Nemotron is unrelated to GLM-5 GenerationConfig validation." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "State_dict-sorting load error vs incorrect checkpoint saved by save_pretrained; related to serialization but not the same bug." + "reason": "Load failure with sorted state_dict and incorrect Qwen3.5 checkpoint saving are related only broadly to model I/O, not the same bug." }, { "left": "issue:46077", "right": "issue:46082", "accept": false, - "reason": "Gemma4 causal-mask regression vs LlamaConfig head_dim validation; unrelated." + "reason": "Gemma4 attention-mask regression is unrelated to LlamaConfig rejecting explicit `head_dim`." }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "Offline/local-files-only network leak vs GLM-5 RoPE implementation discussion; no shared concrete bug." + "reason": "`local_files_only=True` still making requests is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Two different missing config attributes (vocab_size vs pad_token_id); same pattern, but not the same underlying bug." + "reason": "Missing `vocab_size` in Gemma3Config is unrelated to Llama4Config missing `pad_token_id`." }, { - "left": "issue:36683", - "right": "issue:44242", + "left": "issue:43618", + "right": "issue:45216", "accept": false, - "reason": "Gemma3Config attribute error vs missing load-balancing loss when output_router_logits=False; unrelated." + "reason": "CLIP attentions regression is unrelated to Qwen3.5 checkpoint corruption on save_pretrained." }, { - "left": "issue:44380", - "right": "issue:46132", + "left": "issue:36683", + "right": "issue:44242", "accept": false, - "reason": "GPT2 attention scaling ignored in backend kernels vs AttentionInterface.register changing function behavior; different features and bugs." + "reason": "Gemma3Config attribute bug is unrelated to MoE load-balancing loss handling." }, { "left": "issue:36683", "right": "issue:43881", "accept": false, - "reason": "Gemma3Config missing vocab_size vs glm-4v-9b loading failed; both are load/config problems but not the same one." - }, - { - "left": "issue:43906", - "right": "issue:45753", - "accept": false, - "reason": "An isolated reproduction of another issue vs an infinite-loop bug on a specific image; insufficient evidence of the same underlying defect." - }, - { - "left": "issue:43299", - "right": "issue:45753", - "accept": false, - "reason": "Qwen3VL-Moe loading regression vs Qwen3_5 infinite loop on one image; different symptoms and code paths." + "reason": "Gemma3Config missing attribute is unrelated to glm-4v-9b loading failure." } ] }, @@ -14881,24 +14997,24 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 47, - "review_unit_count": 50, + "review_unit_index": 48, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:28282", "issue:33453", "issue:36296", "issue:36683", "issue:41669", - "issue:42548", "issue:42890", "issue:43064", "issue:43097", + "issue:43299", "issue:43352", "issue:43441", "issue:43502", @@ -14906,6 +15022,7 @@ "issue:43576", "issue:43618", "issue:43867", + "issue:43906", "issue:43976", "issue:43992", "issue:44062", @@ -14913,13 +15030,11 @@ "issue:44117", "issue:44222", "issue:44246", - "issue:44351", "issue:44355", "issue:44360", "issue:44380", "issue:44492", "issue:44655", - "issue:44749", "issue:44855", "issue:44857", "issue:44938", @@ -14934,11 +15049,15 @@ "issue:45479", "issue:45561", "issue:45600", + "issue:45753", "issue:46132", "issue:46202", "issue:46285" ], "soft_pairs": [ + "issue:44380|issue:46132", + "issue:43906|issue:45753", + "issue:43299|issue:45753", "issue:43352|issue:43976", "issue:43992|issue:45310", "issue:43441|issue:44380", @@ -14946,8 +15065,8 @@ "issue:44355|issue:44855", "issue:43867|issue:46202", "issue:44380|issue:45479", - "issue:43867|issue:45375", "issue:43352|issue:44380", + "issue:43867|issue:45375", "issue:36683|issue:44117", "issue:43618|issue:44380", "issue:41669|issue:44246", @@ -14970,256 +15089,256 @@ "issue:42890|issue:44112", "issue:42890|issue:45600", "issue:44222|issue:45125", - "issue:43576|issue:46132", - "issue:44355|issue:44749", - "issue:45125|issue:45478", - "issue:42548|issue:44351" + "issue:43576|issue:46132" ], - "prepared_review_unit_hash": "c211c314d48ef32cd94d158030c34668bac6708acf565e33931c77cc453b445e", + "prepared_review_unit_hash": "aaa841390cb083a09e808529813330706a5b779759182bfe7a0fcdc7febec37b", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 35, - "serialized_chars": 37289, - "estimated_input_tokens": 9323, - "estimated_eval_tokens": 18902 + "serialized_chars": 37255, + "estimated_input_tokens": 9314, + "estimated_eval_tokens": 18884 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is a loose collection of Transformers issue reports spanning unrelated regressions (imports, tokenizer/model loading, flash-attention, tensor parallelism, save/load, CI, and Python-version compatibility). None of the soft pairs look like the same underlying defect, so there is no clear canonical duplicate anchor.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "The cluster is mostly a grab bag of unrelated Transformers regression reports across different models, versions, and failure modes. The only plausible duplicate edge is the import-time slowdown pair (41669/44246); the rest should stay separate.", + "confidence": 0.87, + "canonical_issue_reason": "issue:41669 is the clearest root-cause report for the import-time slowdown and best matches the only likely duplicate subgroup.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:41669 is the best representative issue here because it describes the underlying import-performance problem rather than just the symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44380", + "right": "issue:46132", + "accept": false, + "reason": "Different bugs: GPT2 attention scaling under SDPA/FlashAttention vs AttentionInterface.register changing registered-function behavior." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "Unrelated regressions: an isolated reproduction of one issue versus a Qwen3.5 image-specific infinite loop." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Different model-loading failures on different Qwen variants; no shared concrete code-path." + }, { "left": "issue:43352", "right": "issue:43976", "accept": false, - "reason": "Both mention model/runtime breakage, but one is a FlashAttention support issue for NemotronH and the other is a Python-version compatibility problem for Transformers 5.1.0." + "reason": "Flash-Attention support/reporting issue vs Python version compatibility issue; not the same bug." }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Different failures: UMT5Encoder missing embed_tokens.weight vs Qwen3.5 MoE from_pretrained error." + "reason": "Different Qwen/UMT5 loading problems with different missing fields and failure modes." }, { "left": "issue:43441", "right": "issue:44380", "accept": false, - "reason": "Both involve attention backends, but one is Ministral-3 failing with FlashAttention while the other is GPT2 ignoring attention scaling config under SDPA/FlashAttention; different code paths." + "reason": "Both involve attention backends, but they target different models and different broken behaviors." }, { "left": "issue:43352", "right": "issue:45478", "accept": false, - "reason": "Same broad FlashAttention theme, but distinct model families and reported symptoms; not the same concrete bug." + "reason": "Different model-specific failures: FlashAttention support for Nemotron vs Qwen3.5 MoE from_pretrained error." }, { "left": "issue:44355", "right": "issue:44855", "accept": false, - "reason": "Both are import-time failures, but one is about compiled Python files and the other is a Python 3.13 torch.jit.script parsing/IndentationError issue." + "reason": "Both are import/load errors, but one is compiled-Python handling and the other is a torch.jit/script parsing issue in a specific model." }, { "left": "issue:43867", "right": "issue:46202", "accept": false, - "reason": "Both are model loading/roundtrip-related, but the specific failures differ: sorted state_dict loading vs Gemma pipeline roundtrip on the \u2581 token." + "reason": "Different problems: state_dict ordering sensitivity vs Gemma pipeline roundtrip on the \u2581 token." }, { "left": "issue:44380", "right": "issue:45479", "accept": false, - "reason": "Attention/ML terms overlap, but one is backend-specific config being ignored and the other is a sequence-classification loss bug." + "reason": "Attention backend config regression vs classification-loss degeneracy; unrelated code paths." }, { - "left": "issue:43867", - "right": "issue:45375", + "left": "issue:43352", + "right": "issue:44380", "accept": false, - "reason": "A load-model issue vs a missing vision config field; unrelated root causes." + "reason": "Different attention-related issues with different models and failure symptoms." }, { - "left": "issue:43352", - "right": "issue:44380", + "left": "issue:43867", + "right": "issue:45375", "accept": false, - "reason": "Both reference FlashAttention, but one is lack of support and the other is ignored scaling config; not mergeable as one fix." + "reason": "Model-loading order issue vs missing vision-config field; not the same root cause." }, { "left": "issue:36683", "right": "issue:44117", "accept": false, - "reason": "Different objects and failures: Gemma3Config missing vocab_size vs tokenizer mapping sometimes returning None." + "reason": "Gemma config missing vocab_size vs tokenizer-mapping None handling; different assumptions and code paths." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "Different model API regressions: CLIPOutput attentions missing vs GPT2 attention scaling ignored under certain backends." + "reason": "CLIP attentions assignment regression vs GPT2 attention scaling under backends." }, { "left": "issue:41669", "right": "issue:44246", - "accept": false, - "reason": "Import-* cleanup/performance discussion vs intermittent slow import of transformers; related only at a very high level." + "accept": true, + "reason": "Both describe the same import-time slowdown for `transformers`; 41669 gives the underlying cause, while 44246 reports the symptom." }, { "left": "issue:43097", "right": "issue:43352", "accept": false, - "reason": "One is an API removal/change notice, the other is a model FlashAttention support bug; not the same defect." + "reason": "Embeddings/tie-weights API removal vs FlashAttention support; unrelated regressions." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "A flaky integration test missing set_seed() vs a pytest-xdist race in captured_info.txt; both test-related but different issues." + "reason": "A SamHQ seeding problem in integration tests vs an xdist race on captured_info.txt." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "Training/FSDP optimizer-state corruption vs a typo in cache strategies; unrelated." + "reason": "Distributed training optimizer-state corruption vs a cache-strategy typo." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both are Python-version compatibility complaints, but they target different versions and likely different breakpoints." + "reason": "Different Python-version compatibility reports with different symptoms and likely causes." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Load-time state_dict ordering problem vs save_pretrained writing incorrect visual encoder keys." + "reason": "State-dict ordering load failure vs Qwen3.5 visual-key save regression; different model paths." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Different models and failures; no shared code path beyond both being from_pretrained reports." + "reason": "UMT5 missing embed_tokens weight vs Qwen3.5 MoE from_pretrained regression." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Tensor-parallel training bug vs OOM when loading a large Qwen model with tp; related area, different underlying problems." + "reason": "Both mention tensor parallelism/OOM, but the model, failure mode, and root cause are different." }, { "left": "issue:43064", "right": "issue:44655", "accept": false, - "reason": "Wrong optimizer state under v5/FSDP2/PEFT vs inability to save Pipeline objects; both serialization/training-adjacent but distinct." + "reason": "Wrong optimizer states under FSDP2/PEFT vs inability to save Pipeline objects." }, { "left": "issue:28282", "right": "issue:33453", "accept": false, - "reason": "ImportError about missing PyTorch vs tokenizer loading regression; different subsystems and symptoms." + "reason": "PyTorch-missing ImportError for AutoModel vs tokenizer-loading regression; unrelated." }, { "left": "issue:43618", "right": "issue:46285", "accept": false, - "reason": "Both concern CLIP model structure, but one is output attentions and the other is inconsistent text model structure; not the same bug." + "reason": "Different CLIP regressions affecting different classes and structures." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions regression vs LwDetrImageLoss crashing under float16 AMP; unrelated." + "reason": "CLIP attentions regression vs LwDetrImageLoss AMP crash; unrelated." }, { "left": "issue:44655", "right": "issue:44938", "accept": false, - "reason": "Saving Pipeline objects vs Python 3.14 import/load failure; different failure modes." + "reason": "Pipeline save_pretrained issue vs Python 3.14 load failure; different code paths." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "Different attention-related reports on different models; one is missing attentions in CLIPOutput, the other is Qwen3.5 generation failing with flash-attention." + "reason": "CLIP output field regression vs Qwen3.5 flash-attention generation bug." }, { "left": "issue:44360", "right": "issue:45440", "accept": false, - "reason": "A DSA/indexer discussion vs DeepseekV3MoE implementation divergence; no shared bug." + "reason": "DSA indexer ReLU omission vs DeepseekV3MoE divergence from remote implementation." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "Local-files-only still making API requests vs AddedToken constructor argument conflict; unrelated." + "reason": "local_files_only network leak vs AddedToken keyword-argument error; not the same issue." }, { "left": "issue:42890", "right": "issue:44964", "accept": false, - "reason": "Flaky test seeding issue vs inability to load a specific multimodal model on latest Transformers." + "reason": "Test seeding flake vs multimodal model load failure." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Both are test failures, but one is missing set_seed coverage and the other is a stale device-override CI failure." + "reason": "Different test failures: missing set_seed coverage vs stale device override behavior on CI." }, { "left": "issue:42890", "right": "issue:45600", "accept": false, - "reason": "Test flakiness vs auto_mappings referencing removed configs; different root causes." + "reason": "SamHQ test flakiness vs auto_mappings referencing removed configs." }, { "left": "issue:44222", "right": "issue:45125", "accept": false, - "reason": "FP8 save_pretrained bug for MoE vs missing _tp_plan for tensor parallelism; same model family, different functionality." + "reason": "Different MoE/tensor-parallel problems: FP8 save_pretrained vs missing _tp_plan." }, { "left": "issue:43576", "right": "issue:46132", "accept": false, - "reason": "Broken transformers env command vs AttentionInterface.register behavior change; unrelated command/API issues." - }, - { - "left": "issue:44355", - "right": "issue:44749", - "accept": false, - "reason": "Compiled-file import errors vs a performance regression after upgrading Transformers; different problems." - }, - { - "left": "issue:45125", - "right": "issue:45478", - "accept": false, - "reason": "Missing tensor-parallel plan vs Qwen3.5 MoE from_pretrained error; likely adjacent but not the same defect." - }, - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Top-level import errors, but different missing symbols: PreTrainedModel vs HybridCache." + "reason": "Broken `transformers env` CLI vs AttentionInterface.register behavior change." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded in the packet and appropriately conservative. The summary fits the issue titles and the only accepted duplicate edge, 41669/44246, is well supported by the import-time slowdown theme. The remaining soft-edge rejections are cautious and do not overclaim equivalence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15227,14 +15346,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 48, - "review_unit_count": 50, + "review_unit_index": 49, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:30333", "issue:30990", @@ -15258,11 +15377,10 @@ "issue:43874", "issue:43901", "issue:43976", - "issue:44038", "issue:44222", "issue:44230", - "issue:44273", "issue:44315", + "issue:44351", "issue:44355", "issue:44360", "issue:44368", @@ -15270,22 +15388,25 @@ "issue:44556", "issue:44623", "issue:44655", + "issue:44749", "issue:44908", "issue:44938", "issue:44961", - "issue:45003", "issue:45071", "issue:45125", "issue:45230", "issue:45278", "issue:45375", "issue:45468", - "issue:45542", + "issue:45478", "issue:45656", "issue:45850", "issue:46209" ], "soft_pairs": [ + "issue:42548|issue:44351", + "issue:44355|issue:44749", + "issue:45125|issue:45478", "issue:44387|issue:44556", "issue:30333|issue:33453", "issue:45125|issue:45375", @@ -15293,9 +15414,9 @@ "issue:30990|issue:31795", "issue:43723|issue:44556", "issue:43502|issue:44222", - "issue:42831|issue:43874", "issue:43010|issue:45850", "issue:43010|issue:44368", + "issue:42831|issue:43874", "issue:43502|issue:44961", "issue:30333|issue:36296", "issue:44355|issue:45071", @@ -15304,8 +15425,8 @@ "issue:44315|issue:44360", "issue:33453|issue:34689", "issue:43299|issue:44556", - "issue:42757|issue:43576", "issue:33453|issue:36296", + "issue:42757|issue:43576", "issue:43576|issue:45071", "issue:43010|issue:45656", "issue:43576|issue:43824", @@ -15316,282 +15437,237 @@ "issue:43576|issue:44938", "issue:44908|issue:44961", "issue:44315|issue:46209", - "issue:36296|issue:43901", "issue:41628|issue:42548", + "issue:36296|issue:43901", "issue:36296|issue:43526", - "issue:44623|issue:45230", - "issue:44273|issue:45542", - "issue:44038|issue:45125", - "issue:44273|issue:45003" + "issue:44623|issue:45230" ], - "prepared_review_unit_hash": "4d11498e82557383630a78f9e85bf2f6e27316f3038cfbfdc497b33deff10384", + "prepared_review_unit_hash": "f57689b9ce12bd3b3205c1199d3c3a93edc29bc7987aaeaa41a46b9f2320641d", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 37, - "serialized_chars": 38083, - "estimated_input_tokens": 9521, - "estimated_eval_tokens": 19298 + "serialized_chars": 37616, + "estimated_input_tokens": 9404, + "estimated_eval_tokens": 19064 }, "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 issues: import/load regressions, FP8/MoE bugs, tensor-parallel problems, docs mismatches, and unrelated runtime errors. None of the soft pairs look like the same concrete underlying bug or change.", - "confidence": 0.66, - "canonical_issue_reason": "Issue 45278 is the broadest umbrella-style report here (v4.57 -> v5.5 import failures), so it is the closest canonical issue among otherwise heterogeneous reports.", + "summary": "These items are not a true duplicate cluster; they span many distinct Transformers v5 regressions, import errors, loading failures, docs issues, FP8 problems, and tensor-parallel bugs that only share a broad theme.", + "confidence": 0.92, + "canonical_issue_reason": "No single issue is a clear canonical duplicate target here; the set is too heterogeneous, with only a broad \u201cv5 broke many things\u201d theme in common.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45278 is the best representative issue because it is the most general v5 regression report and overlaps conceptually with several other loading/import complaints, even though the cluster is not a true duplicate set.", + "best_issue_reason": "issue:45850 is the broadest umbrella title for the cluster, but it is too vague to serve as a precise canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (PreTrainedModel vs HybridCache), so they are not the same bug." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "One reports errors with compiled Python files; the other reports a large slowdown after upgrade. Different failures." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Tensor-parallel `_tp_plan` support and a Qwen3.5 MoE `from_pretrained` load error are related in model family, but not the same concrete code-path bug." + }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Both are v5 regressions, but one is an int4/OOM memory issue and the other is a checkpoint reload/loading failure; different bugs and code paths." + "reason": "Int4 quantization memory/OOM regression is distinct from failure to reload a v4.57 checkpoint after upgrading to v5.2/v5.3." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLFlow failed-job reporting and tokenizer loading regression are unrelated." + "reason": "MLflow reporting on failed training jobs and tokenizer-loading regressions are unrelated." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Both involve Qwen3_5Moe, but one is tensor-parallel plan support and the other is a config field being dropped; not the same bug." + "reason": "One is about missing tensor-parallel plan metadata; the other is about a missing config field silently dropped by strict serialization." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "No-grad decoration for cache/layer updates is unrelated to broad import errors after upgrading to v5.5.0." + "reason": "A `no_grad` decoration bug on cache/layer updates is not the same as a broad set of import errors after version upgrade." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "Sentence Transformers hanging on load is not the same as a documentation issue about model.forward arguments." + "reason": "A loading hang in Sentence Transformers is unrelated to documentation confusion about `input_ids` and `past_key_values`." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Both are loading problems, but one is AutoTokenizer loading in v5 and the other is a checkpoint reload regression; too different to merge." + "reason": "Tokenizer loading in v5 and checkpoint reloading after upgrade are both load failures, but not the same specific defect." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "Local-files-only network leakage and FP8 save_pretrained issues are unrelated." - }, - { - "left": "issue:42831", - "right": "issue:43874", - "accept": false, - "reason": "An FP8 accuracy issue is not the same as a missing image-processor method causing an AttributeError." + "reason": "`local_files_only=True` still making API calls is a networking bug, not an FP8 `save_pretrained` bug." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "A specific no-grad bug is not the same as a broad complaint that v5 breaks many models." + "reason": "The cache/layer update bug is a concrete fixable path; the other is only a vague umbrella complaint about many models breaking." }, { "left": "issue:43010", "right": "issue:44368", "accept": false, - "reason": "Cache update gradients and a tie_word_embeddings warning are unrelated." + "reason": "`@torch.no_grad` on update methods and a warning about `tie_word_embeddings` are different issues." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "An FP8 accuracy regression and a missing image-patch helper causing an AttributeError are unrelated." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "local_files_only API requests and an unrelated 'racoon' issue do not match." + "reason": "`local_files_only` network leakage is unrelated to the placeholder/garbled issue title." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLFlow reporting and tensor-parallel training are distinct issues." + "reason": "MLflow reporting on failure and tensor-parallel training behavior are different subsystems and failures." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled Python file errors and PretrainedConfig type checking are different regressions." + "reason": "Compiled-file runtime errors are not the same as `PretrainedConfig` type-checking breakage." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs still referencing pipeline() and an unrelated 'racoon' issue are not duplicates." + "reason": "Docs still mentioning `pipeline()` is unrelated to the unrelated placeholder issue." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled-file errors and saving Pipeline objects are separate save/load problems." + "reason": "Running compiled Python files and saving pipeline objects are different code paths and problems." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger Kernel application and a DSA indexer ReLU complaint are unrelated." + "reason": "Liger Kernel application under `model_init` and a DSA indexer ReLU discussion are unrelated." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer loading regression and Llama 3.2 model-loading failure are both load-related but not the same underlying bug." + "reason": "Tokenizer-loading regression and Llama 3.2 Vision model-loading failure are different concrete bugs." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Qwen3VL MoE loading breakage and generic checkpoint reload breakage are different failures." + "reason": "Both are loading regressions, but for different model families and different failure modes." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "A missing huggingface_hub import and the transformers env command bug are unrelated." - }, - { - "left": "issue:33453", - "right": "issue:36296", - "accept": false, - "reason": "Tokenizer loading regression and tensor-parallel training bug do not share the same code path." + "reason": "A missing `huggingface_hub` symbol import is unrelated to the broken `transformers env` command." }, { "left": "issue:43576", "right": "issue:45071", "accept": false, - "reason": "Broken env CLI and PretrainedConfig type checking are unrelated." - }, - { - "left": "issue:43010", - "right": "issue:45656", - "accept": false, - "reason": "Cache/layer update no-grad handling is not the same as double optimizer stepping under deepspeed." + "reason": "CLI/env command breakage and config type-checking are separate issues." }, { "left": "issue:43576", "right": "issue:43824", "accept": false, - "reason": "Broken env CLI and a missing Qwen2_5_VLForConditionalGeneration import are different issues." + "reason": "The `env` command issue is not the same as an import error for `Qwen2_5_VLForConditionalGeneration`." }, { "left": "issue:31795", "right": "issue:38617", "accept": false, - "reason": "Documentation confusion in model.forward and an ImportError for layer_type_validation are unrelated." + "reason": "Documentation confusion and an import error from `configuration_utils` are not the same bug." }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "An empty/placeholder issue and a Gemma-4 audio positional-encoding bug are not duplicates." + "reason": "The placeholder issue title is unrelated to the Gemma-4 audio positional encoding bug." }, { "left": "issue:44222", "right": "issue:44230", "accept": false, - "reason": "Both mention FP8/MoE, but one is save_pretrained behavior and the other is inference support; different concrete bugs." - }, - { - "left": "issue:43010", - "right": "issue:43976", - "accept": false, - "reason": "Cache update no-grad behavior is unrelated to Python 3.9/3.10 compatibility." + "reason": "FP8 model save/load corruption and FP8 inference support for Qwen3-VL/Qwen3.5 MoE are different requests." }, { - "left": "issue:44273", - "right": "issue:45542", - "accept": false, - "reason": "Lazy loading problems and a TensorBoard-without-TensorFlow backend error are not the same bug." - }, - { - "left": "issue:44038", - "right": "issue:45125", - "accept": false, - "reason": "Both are Qwen3-Moe-related, but one is a broad v5/Qwen3-VL-Moe bug and the other is a missing tensor-parallel plan; not enough to call them duplicates." - }, - { - "left": "issue:44273", - "right": "issue:45003", - "accept": false, - "reason": "Lazy loading issues and sys.modules access in modeling_utils may be related conceptually, but they are not clearly the same concrete bug." - }, - { - "left": "issue:44623", - "right": "issue:45230", - "accept": false, - "reason": "processor.save_pretrained missing files and a generic bug report are not duplicates." - }, - { - "left": "issue:44273", - "right": "issue:45003", + "left": "issue:44908", + "right": "issue:44961", "accept": false, - "reason": "Same as above: possible relation to import/lazy-loading, but not a clear same-bug match." + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue." }, { "left": "issue:44315", "right": "issue:46209", "accept": false, - "reason": "Liger Kernel application and FP8 inference on B200 are separate issues." + "reason": "Liger Kernel application under `model_init` is unrelated to FP8 inference failures on B200." }, { - "left": "issue:36296", - "right": "issue:43901", + "left": "issue:41628", + "right": "issue:42548", "accept": false, - "reason": "Tensor-parallel training and docs about return_all_scores are unrelated." + "reason": "Different missing imports (`AutoImageProcessor` vs `PreTrainedModel`) indicate separate export regressions." }, { - "left": "issue:41628", - "right": "issue:42548", + "left": "issue:36296", + "right": "issue:43901", "accept": false, - "reason": "Import errors for AutoImageProcessor and PreTrainedModel are both namespace issues, but not the same symbol or failure mode." + "reason": "Tensor-parallel training bug and pipeline docs mentioning `return_all_scores` are unrelated." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training and BeitImageProcessorFast reduce_labels behavior are unrelated." + "reason": "Tensor-parallel training bug and BeitImageProcessorFast `reduce_labels` behavior are different problems." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Processor save_pretrained file omissions and a generic bug report are not the same issue." - }, - { - "left": "issue:44273", - "right": "issue:45542", - "accept": false, - "reason": "Lazy loading and TensorBoard/TensorFlow backend configuration are different problems." - }, - { - "left": "issue:44038", - "right": "issue:45125", - "accept": false, - "reason": "Qwen3-VL-Moe breakage and missing _tp_plan are related only at a high level; not the same underlying defect." - }, - { - "left": "issue:44273", - "right": "issue:45003", - "accept": false, - "reason": "Lazy loading and unsafe sys.modules access are too loosely related to merge as duplicates." + "reason": "Missing files from `processor.save_pretrained(...)` is concrete; the other item is too vague to match any specific bug." } ] }, @@ -15606,14 +15682,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 49, - "review_unit_count": 50, + "review_unit_index": 50, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:31795", "issue:33453", @@ -15629,6 +15705,7 @@ "issue:43827", "issue:43874", "issue:43976", + "issue:44038", "issue:44077", "issue:44230", "issue:44246", @@ -15637,26 +15714,25 @@ "issue:44297", "issue:44315", "issue:44351", - "issue:44360", "issue:44373", "issue:44393", "issue:44492", "issue:44556", - "issue:44655", "issue:44704", "issue:44829", "issue:44861", "issue:44908", "issue:44961", + "issue:45003", "issue:45071", "issue:45092", + "issue:45125", "issue:45230", "issue:45278", - "issue:45310", "issue:45341", "issue:45362", - "issue:45468", "issue:45478", + "issue:45542", "issue:45753", "issue:45850", "issue:46095", @@ -15665,13 +15741,16 @@ "issue:46218" ], "soft_pairs": [ + "issue:44273|issue:45542", + "issue:44038|issue:45125", + "issue:44273|issue:45003", "issue:44393|issue:45071", "issue:44230|issue:46095", "issue:44373|issue:44961", "issue:44393|issue:45753", "issue:43576|issue:44556", - "issue:41669|issue:43673", "issue:43525|issue:45850", + "issue:41669|issue:43673", "issue:44556|issue:45092", "issue:43572|issue:45850", "issue:45362|issue:45850", @@ -15699,269 +15778,272 @@ "issue:31795|issue:33453", "issue:41669|issue:44492", "issue:44315|issue:44829", - "issue:42371|issue:44492", "issue:43576|issue:44273", - "issue:44655|issue:44861", - "issue:44360|issue:45468", - "issue:45230|issue:45310", - "issue:44273|issue:44908", - "issue:43576|issue:46218", - "issue:43827|issue:44492" + "issue:42371|issue:44492" ], - "prepared_review_unit_hash": "ed8235708529f42e87927a2891745a401a0bdea062e7d56ad15d4d95a17105b0", + "prepared_review_unit_hash": "b5d2487ef8d3ef667e3d173615602281197d5a0c6cc15d6e39b0b70e39895c6f", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 42, - "serialized_chars": 39625, - "estimated_input_tokens": 9907, - "estimated_eval_tokens": 20070 + "soft_pair_count": 39, + "serialized_chars": 38789, + "estimated_input_tokens": 9698, + "estimated_eval_tokens": 19652 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly closed/open issue reports about Transformers v5 regressions: import/lazy-loading slowdowns, model-loading/config compatibility breakages, and API changes. No PRs are present in the cluster.", - "confidence": 0.78, - "canonical_issue_reason": "issue:45850 is the broadest umbrella report in the set: it explicitly frames a wide v5 regression affecting many models, making it the best single issue to anchor the cluster even though it is vague.", + "summary": "This cluster is a loose mix of Transformers v5 regressions, model-specific failures, and a few docs/config issues. The strongest representative issue is the broad v5 breakage report, but the soft pairs mostly describe different concrete bugs and should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45850 is the broadest umbrella for the shared theme of v5 regressions breaking many models, so it best represents the cluster at a high level.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45850 is the best global representative because it is broad, current, and covers the same general family of v5 breakage complaints seen across the cluster.", + "best_issue_reason": "issue:45278 is the most actionable representative because it describes a concrete upgrade symptom (many import errors after moving to v5.5.0) while still matching the cluster\u2019s overall regression theme.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Both are import/runtime problems, but one is lazy-loading behavior and the other is a TensorBoard/TensorFlow backend error; different code paths." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Same broad Qwen3/MoE area, but one is a Qwen3-VL bug and the other is missing tensor-parallel metadata; not the same fix." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Import-related, but one is lazy loading and the other is unsafe sys.modules access; distinct underlying issues." + }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Different problems: Qwen3-VL multimodal output failure vs PretrainedConfig type checking regression." + "reason": "Different symptoms and subsystems: Qwen3-VL multimodal output issue vs a PretrainedConfig type-checking regression." }, { "left": "issue:44230", "right": "issue:46095", "accept": false, - "reason": "Unrelated model/features: fp8 inference support for Qwen3-VL/Qwen3.5 MoE vs DeepSeekV4 weight conversion question." + "reason": "A feature/support request for fp8 inference is not the same as asking for a weight conversion script." }, { "left": "issue:44373", "right": "issue:44961", "accept": false, - "reason": "Docstring bug vs a completely unrelated issue titled 'racoon'." + "reason": "Unrelated: docstring typo for position_ids versus an unrelated placeholder issue." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Both are Qwen-family vision issues, but the failure modes differ materially: bbox hallucination/error vs infinite loop on a specific image." + "reason": "Same model family, but one is bounding-box hallucination/error and the other is an infinite loop on a specific image; not the same bug." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Both are v5 regressions, but one is the `transformers env` command and the other is checkpoint reload compatibility; not the same code path." + "reason": "Both are v5 regressions, but one breaks the transformers env command and the other breaks checkpoint reload after upgrade." }, { - "left": "issue:41669", - "right": "issue:43673", + "left": "issue:43525", + "right": "issue:45850", "accept": false, - "reason": "Import-star cleanup/performance issue vs missing generation cache during chunked prefill; different subsystems and fixes." + "reason": "A specific Llama4Config attribute bug is too different from the broad 'many models break' complaint." }, { - "left": "issue:43525", - "right": "issue:45850", + "left": "issue:41669", + "right": "issue:43673", "accept": false, - "reason": "Specific `pad_token_id`/config attribute error vs a broad complaint about many models breaking in v5." + "reason": "Import-performance regression from import * usage is not the same as a missing GenerationMixin cache during chunked prefill." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both concern v5 checkpoint loading, but one is generic reload failure and the other is remote-code/meta-init incompatibility; too different to treat as duplicates." + "reason": "Both concern v5 upgrade incompatibilities, but they affect different model/loading paths and are not one concrete bug." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "Specific StableLmConfig `pad_token_idx` regression vs a broad v5 breakage umbrella issue." + "reason": "Specific StableLmConfig attribute regression versus a broad v5 breakage report; too different to merge." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "Qwen3.5 chat crash is a concrete model bug, not the same as a general v5 breakage report." + "reason": "Qwen3.5 chat crash is a model-specific failure, not the same underlying issue as the generic v5 complaint." }, { - "left": "issue:45278", - "right": "issue:45850", + "left": "issue:41669", + "right": "issue:46218", "accept": false, - "reason": "Broad overlap in release complaints, but one is about import errors after upgrade and the other is a generic 'too many models' regression; not a single concrete bug." + "reason": "Both touch imports, but one is import-star performance and the other is a missing exported model symbol; different fixes." }, { - "left": "issue:44273", + "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "Lazy loading/import behavior vs inverse_sqrt scheduler kwargs; unrelated code paths." + "reason": "Test flakiness from missing set_seed is unrelated to scheduler kwargs handling." }, { - "left": "issue:44297", - "right": "issue:45230", + "left": "issue:44246", + "right": "issue:44273", "accept": false, - "reason": "Tokenizer save_pretrained metadata mismatch vs an empty generic bug report; no evidence they are the same defect." + "reason": "Importing transformers slowly and lazy loading not working properly are related at a high level but not the same concrete bug." }, { - "left": "issue:46143", - "right": "issue:46144", + "left": "issue:43408", + "right": "issue:44315", "accept": false, - "reason": "Both involve RoFormer, but one is kwargs propagation and the other is attention-interface usage; related area, not the same bug." + "reason": "Different areas: model-type mismatch warning versus Liger Kernel not being applied with model_init." }, { - "left": "issue:43827", - "right": "issue:44492", + "left": "issue:44704", + "right": "issue:44908", "accept": false, - "reason": "Documentation reference to removed pipelines vs a typo in cache strategies; unrelated." + "reason": "Both mention kwargs passing, but they are different APIs and code paths." }, { - "left": "issue:44295", - "right": "issue:45230", + "left": "issue:43352", + "right": "issue:44393", "accept": false, - "reason": "position_ids buffer access error vs generic bug report; no shared concrete failure." + "reason": "Flash Attention 2 support error for Nemotron is unrelated to Qwen3-VL bounding-box behavior." }, { - "left": "issue:44655", - "right": "issue:44908", + "left": "issue:44297", + "right": "issue:45230", "accept": false, - "reason": "Pipeline save/load issue vs scheduler kwargs handling; unrelated." + "reason": "Tokenizer save_pretrained mismatch is a specific serialization bug; the other issue is too vague to match it." }, { - "left": "issue:41669", - "right": "issue:46218", + "left": "issue:43976", + "right": "issue:44393", "accept": false, - "reason": "Import performance cleanup vs an import error for a specific Qwen3_5 symbol; same broad import area, but not the same bug." + "reason": "Python version compatibility regression is unrelated to the Qwen3-VL multimodal bug." }, { - "left": "issue:44360", - "right": "issue:45468", + "left": "issue:44295", + "right": "issue:45230", "accept": false, - "reason": "DSA indexer/ReLU discussion vs Gemma4Audio positional encoding bug; different models and failures." + "reason": "position_ids buffer access error is a distinct model state/buffer bug, not the generic placeholder issue." }, { - "left": "issue:45230", - "right": "issue:45310", + "left": "issue:43576", + "right": "issue:44908", "accept": false, - "reason": "A generic bug report vs a specific Qwen3.5 MoE from_pretrained error; no concrete match." - }, - { - "left": "issue:44246", - "right": "issue:44273", - "accept": true, - "reason": "Both point at the same underlying import/lazy-loading regression: import transformers becoming slow and lazy loading not functioning properly." + "reason": "Broken env command and inverse_sqrt scheduler kwargs are unrelated subsystems." }, { - "left": "issue:43874", - "right": "issue:45850", + "left": "issue:44908", + "right": "issue:45071", "accept": false, - "reason": "Specific GLM46V multimodal token counting failure vs a broad v5 breakage umbrella issue." + "reason": "Scheduler kwargs propagation and PretrainedConfig type checking are unrelated bugs." }, { - "left": "issue:44077", - "right": "issue:44861", + "left": "issue:41669", + "right": "issue:44351", "accept": false, - "reason": "Different defects in different utilities: patchtsmixer post_init handling vs tied-weight key attribute crash." + "reason": "Import-star slowdown and missing HybridCache export are both import-related but not the same underlying problem." }, { - "left": "issue:43976", - "right": "issue:46218", + "left": "issue:41669", + "right": "issue:45341", "accept": false, - "reason": "Python-version compatibility complaint vs a specific missing import symbol; not the same issue." + "reason": "Performance-heavy import behavior is unrelated to a small testing_utils bug." }, { - "left": "issue:43827", - "right": "issue:44908", + "left": "issue:45278", + "right": "issue:45850", "accept": false, - "reason": "Docs referencing removed pipeline APIs vs scheduler kwargs handling; unrelated." + "reason": "Both are broad v5 complaints, but one is about import errors after upgrade and the other is a generic 'many models break' report; not one concrete bug." }, { - "left": "issue:31795", - "right": "issue:33453", + "left": "issue:43673", + "right": "issue:44492", "accept": false, - "reason": "Documentation confusion vs tokenizer loading regression; not the same underlying bug." + "reason": "Generation cache missing during chunked prefill is unrelated to a typo in cache strategy docs or code." }, { - "left": "issue:41669", - "right": "issue:44492", + "left": "issue:46143", + "right": "issue:46144", "accept": false, - "reason": "Import-star performance regression vs a typo in cache-strategy docs; unrelated." + "reason": "Both involve RoFormer, but one is kwargs passthrough and the other is attention-interface usage; different fixes." }, { - "left": "issue:44315", - "right": "issue:44829", + "left": "issue:43874", + "right": "issue:45850", "accept": false, - "reason": "Liger Kernel application bug vs degenerate training with flash_attention_3; different behavior and fixes." + "reason": "A specific multimodal token-counting AttributeError is not the same as a broad v5 breakage report." }, { - "left": "issue:42371", - "right": "issue:44492", + "left": "issue:44393", + "right": "issue:45478", "accept": false, - "reason": "TF32 settings migration issue vs cache-strategy typo; unrelated." + "reason": "Different models and symptoms: Qwen3-VL output bug versus Qwen3.5-Moe from_pretrained failure." }, { - "left": "issue:43576", - "right": "issue:44273", + "left": "issue:44077", + "right": "issue:44861", "accept": false, - "reason": "Broken `transformers env` command vs lazy loading not working properly; both v5 issues, but different code paths." + "reason": "PatchTSMixer post_init policy and tied-weight key AttributeError are unrelated." }, { - "left": "issue:44655", - "right": "issue:44861", + "left": "issue:43976", + "right": "issue:46218", "accept": false, - "reason": "Saving Pipeline objects vs `_tied_weight_keys` attribute crash; unrelated." + "reason": "Python 3.9 compatibility and a missing Qwen3_5ForCausalLM import are unrelated failures." }, { - "left": "issue:44360", - "right": "issue:45468", + "left": "issue:43827", + "right": "issue:44908", "accept": false, - "reason": "Different problem domains and no shared code path." + "reason": "Documentation still referencing pipeline() is unrelated to scheduler kwargs behavior." }, { - "left": "issue:45230", - "right": "issue:45310", + "left": "issue:31795", + "right": "issue:33453", "accept": false, - "reason": "Generic report vs specific Qwen3.5 MoE loading failure; not duplicates." + "reason": "Doc confusion around input_ids/past_key_values does not match a tokenizer-loading regression." }, { - "left": "issue:44273", - "right": "issue:44908", + "left": "issue:41669", + "right": "issue:44492", "accept": false, - "reason": "Lazy loading regression vs scheduler kwargs bug; unrelated." + "reason": "Import-star slowdown and a cache-strategy typo are unrelated." }, { - "left": "issue:43576", - "right": "issue:46218", + "left": "issue:44315", + "right": "issue:44829", "accept": false, - "reason": "Broken env command vs missing Qwen3_5 import; not the same issue." + "reason": "Liger Kernel not applied with model_init and degenerate training with flash_attention_3 are different training-path issues." }, { - "left": "issue:43827", + "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "Docs about removed pipelines vs cache-strategy typo; unrelated." + "reason": "TF32 API guidance and a cache-strategy typo have no meaningful overlap." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: the cluster is dominated by closed/open Transformers v5 regression issues, and issue:45850 is a reasonable broad umbrella representative. The soft-edge verdicts are conservative overall, with one plausible accept on the import/lazy-loading pair and the rest appropriately rejected based on distinct titles/code paths. No PRs are present." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -15969,14 +16051,14 @@ "label": "issue", "component_index": 1, "component_count": 18, - "review_unit_index": 50, - "review_unit_count": 50, + "review_unit_index": 51, + "review_unit_count": 52, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-441", + "cluster_id": "cluster-10000-443", "nodes": [ "issue:30333", "issue:31515", @@ -15984,35 +16066,39 @@ "issue:33453", "issue:34689", "issue:36296", - "issue:37934", "issue:38617", "issue:41669", "issue:42371", "issue:42913", "issue:42936", "issue:43066", - "issue:43240", "issue:43298", "issue:43352", "issue:43502", "issue:43519", "issue:43525", "issue:43572", + "issue:43576", "issue:43606", "issue:43668", "issue:43704", "issue:43717", - "issue:43813", + "issue:43827", "issue:44031", "issue:44230", "issue:44261", "issue:44263", + "issue:44273", "issue:44351", + "issue:44360", "issue:44485", + "issue:44492", "issue:44623", + "issue:44655", "issue:44861", "issue:44908", "issue:44998", + "issue:45230", "issue:45290", "issue:45310", "issue:45468", @@ -16024,6 +16110,12 @@ "issue:46218" ], "soft_pairs": [ + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43576|issue:46218", + "issue:43827|issue:44492", "issue:46018|issue:46172", "issue:43519|issue:44485", "issue:43519|issue:44908", @@ -16061,327 +16153,412 @@ "issue:43298|issue:44230", "issue:43717|issue:46144", "issue:42936|issue:46018", - "issue:43668|issue:44031", - "issue:42936|issue:43240", - "issue:43240|issue:46144", - "issue:42936|issue:44031", - "issue:42936|issue:46144", - "issue:42936|issue:43813", - "issue:43240|issue:43668", - "issue:43668|issue:43813", - "issue:37934|issue:43668", - "issue:42936|issue:43668" + "issue:43668|issue:44031" ], - "prepared_review_unit_hash": "04ff93f98507054db59ea683e1f2a01d441f814f00ef1ec4da933e5355fd3870", + "prepared_review_unit_hash": "b9618afd4e36275691461d9b89f35ac4e9cd9c223ae110fac97b77c5a37af8f6", "component_budget": { - "node_count": 441, - "item_count": 441, - "soft_pair_count": 1620, - "serialized_chars": 840343, - "estimated_input_tokens": 210086, - "estimated_eval_tokens": 420428 + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 }, "budget": { - "node_count": 44, - "item_count": 44, - "soft_pair_count": 47, - "serialized_chars": 38701, - "estimated_input_tokens": 9676, - "estimated_eval_tokens": 19608 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 44, + "serialized_chars": 39952, + "estimated_input_tokens": 9988, + "estimated_eval_tokens": 20232 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose Transformers v5 regression/loading/tokenizer cluster with many superficially similar but distinct issues. I found no true duplicate soft edges; the candidates mostly share only broad subsystem or version-regression wording. No PRs are present.", - "confidence": 0.89, - "canonical_issue_reason": "issue:45850 is the broadest umbrella report for the v5 breakage/regression theme and can serve as the cluster anchor better than the more specific failures.", + "summary": "This cluster is mostly loose semantic similarity around Transformers v5, model-loading, and tokenizer/config regressions rather than true duplicates. I would not merge any soft pair; the safest representative issue is the broad v5-breakage umbrella report.", + "confidence": 0.31, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set; it captures the general v5 regression theme that many of the other reports orbit, even though it is still too vague to be a perfect duplicate target.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45850 has the widest scope and strongest discussion signal, so it is the best representative issue even though the cluster is too heterogeneous for true deduping.", + "best_issue_reason": "issue:45850 is the best cluster representative because it is the most general user-facing report of widespread v5 breakage, which is the closest common thread across the candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Save-pretrained pipeline serialization and tied-weight-key attribute handling are different code paths and failures." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "A DSA indexer missing ReLU is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained regression; not the same issue." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading behavior and inverse_sqrt scheduler kwargs are unrelated subsystems." + }, + { + "left": "issue:43576", + "right": "issue:46218", + "accept": false, + "reason": "Broken env command and Qwen3_5 import failure are different failures with no shared code path." + }, + { + "left": "issue:43827", + "right": "issue:44492", + "accept": false, + "reason": "Pipeline-docs-after-v5-removals and a cache-strategy typo are not the same underlying bug." + }, { "left": "issue:46018", "right": "issue:46172", "accept": false, - "reason": "Different model families and bugs: DeepSeek-V4 gating vs a deepseek-v4 dtype/transpose problem." + "reason": "DeepSeek-V4 shared-expert gating and a tensor transpose issue are different model implementation problems." }, { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Qwen3VL timestamp math is unrelated to GLM-5 RoPE implementation." + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are separate model-specific bugs." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Processor timestamp calculation and scheduler kwargs handling are unrelated code paths." + "reason": "Processor timestamp math and scheduler kwarg handling are unrelated." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-star performance/footprint cleanup is unrelated to a VRAM leak in dataloader threads." + "reason": "Import-star cleanup/perf and a VRAM leak in multi-threaded loading are not the same bug." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Documentation confusion in forward args is not the same as a model-loading regression." + "reason": "Documentation confusion around forward args does not match a concrete model-loading regression." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Slow checkpoint loading and forward-doc confusion are different issues." + "reason": "Slow checkpoint loading and confusing forward documentation are different issues." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "Both touch positional/attention-style internals, but they are different models and different failures." + "reason": "GLM-5 RoPE and Gemma-4 audio positional encoding are unrelated model implementations." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak in threaded loading is unrelated to GLM-5 RoPE math." + "reason": "VRAM leakage in dataloader threads is unrelated to a RoPE implementation bug." }, { "left": "issue:43298", "right": "issue:46095", "accept": false, - "reason": "Audio continuous batching support and DeepSeek-V4 weight conversion are different feature requests." + "reason": "Audio model continuous batching support and DeepSeek-V4 weight conversion are different requests." }, { "left": "issue:45850", "right": "issue:46218", "accept": false, - "reason": "Broad v5 breakage versus a specific import failure for Qwen3_5ForCausalLM." + "reason": "Broad v5 breakage is too general to equate with a specific Qwen3_5 import error." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Offline file-only network calls are unrelated to Qwen3VL timestamp calculation." + "reason": "Accidental network requests with local_files_only and Qwen3VL timestamp math are different failure modes." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 settings guidance and a dataloader-thread VRAM leak are unrelated." + "reason": "TF32 API guidance and a VRAM leak are unrelated." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Processor timestamp math and processor.save_pretrained missing files are different bugs." + "reason": "Timestamp calculation in a processor is not the same as missing files from processor.save_pretrained()." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Qwen3VL timestamp math and multi-thread VRAM leakage do not share the same failure." + "reason": "Processor timestamp logic and dataloader-thread VRAM leak are distinct bugs." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch is unrelated to Gemma4 audio positional encoding." + "reason": "CPU offload device mismatch and Gemma-4 audio positional encoding are unrelated." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "torch.split return-value handling in GLM-MoE is unrelated to Gemma4 audio positional encoding." + "reason": "torch.split return-value handling and audio positional encoding are different issues." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm is a different model/config bug." + "reason": "Missing config.rms_norm_eps and Gemma-4 audio positional encoding are not the same code path." }, { "left": "issue:44351", "right": "issue:46218", "accept": false, - "reason": "Different missing imports for different symbols/modules." + "reason": "HybridCache import failure and Qwen3_5 import failure are both import-related but not the same symbol or fix." }, { "left": "issue:43352", "right": "issue:46218", "accept": false, - "reason": "Flash Attention support gating and a Qwen3_5 import failure are unrelated." + "reason": "Flash Attention support gating and a module import error are different problems." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both are tokenizer/v5 related, but one is behavior drift and the other is a decoder type bug." + "reason": "Both mention tokenizer v5 changes, but one is broad behavior drift while the other is a specific decoder-type bug." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs bug and an off-topic issue are unrelated." + "reason": "Scheduler kwargs being ignored is unrelated to the placeholder issue titled Unemployment." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Tied-weight key handling and chat-template tool-call crashing are different code paths." + "reason": "Tied-weights helper crash and apply_chat_template tool-call crash are different code paths." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id in config is unrelated to tied-weight key extraction." + "reason": "Missing pad_token_id in Llama4Config does not match tied-weights-key list handling." }, { "left": "issue:43704", "right": "issue:44998", "accept": false, - "reason": "VRAM leak and off-topic issue are unrelated." - }, - { - "left": "issue:43572", - "right": "issue:44861", - "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is unrelated to tied-weight key crashes." - }, - { - "left": "issue:41669", - "right": "issue:44998", - "accept": false, - "reason": "Import-star cleanup and off-topic issue are unrelated." + "reason": "VRAM leak in Qwen3ForCausalLM and the unrelated placeholder issue are not duplicates." }, { "left": "issue:43066", "right": "issue:44998", "accept": false, - "reason": "Tokenizer decoder-type regression and off-topic issue are unrelated." + "reason": "Wrong tokenizer decoder type and the unrelated placeholder issue are not related." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Checkpoint load slowness is unrelated to an ImportError for layer_type_validation." + "reason": "Slow checkpoint loading and a missing import symbol are different failures." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support request is unrelated to missing processor save files." + "reason": "FP8 inference support for Qwen models and processor.save_pretrained missing files are unrelated." }, { "left": "issue:44998", "right": "issue:46218", "accept": false, - "reason": "Off-topic issue and a Qwen3_5 import failure are unrelated." + "reason": "The placeholder issue has no meaningful relation to a Qwen3_5 import failure." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow reporting after failed training and slow from_pretrained checkpoint loading are unrelated." + "reason": "MLflow reporting on failed training jobs and slow from_pretrained checkpoint loading are unrelated." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Checkpoint load slowness and tensor-parallel training bug are different failures." + "reason": "Checkpoint load slowness and tensor-parallel training bugs are different problems." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 inference support and Qwen3.5 MoE from_pretrained error are not the same bug." + "reason": "FP8 support request and a Qwen3.5 MoE from_pretrained regression are not the same bug." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Slow checkpoint loading and tokenizer-loading regression are distinct issues." + "reason": "Slow checkpoint loading and tokenizer-loading regression are only broadly similar, not the same issue." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Audio continuous batching support and FP8 inference support are unrelated." + "reason": "Continuous batching for audio models and FP8 inference support are separate feature requests." }, { "left": "issue:43717", "right": "issue:46144", "accept": false, - "reason": "Mamba init_weights behavior is unrelated to RoFormer attention interface usage." + "reason": "Mamba init_weights usage and RoFormer attention-interface usage are unrelated implementation concerns." }, { "left": "issue:42936", "right": "issue:46018", "accept": false, - "reason": "Mask2former ignore_value handling is unrelated to DeepSeek-V4 shared-expert gating." + "reason": "Mask2Former ignore_value handling and DeepSeek-V4 shared-expert gating are different model bugs." }, { "left": "issue:43668", "right": "issue:44031", "accept": false, - "reason": "A type-hint issue in ModernBERTConfig is unrelated to tokenizer regex warnings." - }, + "reason": "A type-hint mismatch in ModernBERTConfig is unrelated to tokenizer regex warnings." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 52, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031", + "issue:46144" + ], + "soft_pairs": [ + "issue:42936|issue:43240", + "issue:43240|issue:46144", + "issue:42936|issue:44031", + "issue:42936|issue:46144", + "issue:42936|issue:43813", + "issue:43240|issue:43668", + "issue:43668|issue:43813", + "issue:37934|issue:43668", + "issue:42936|issue:43668" + ], + "prepared_review_unit_hash": "dccbe49a0db64d8f40d9dda8ee189ba180a9d14519a66878d431e8821e532f2c", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 6639, + "estimated_input_tokens": 1660, + "estimated_eval_tokens": 3576 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are not duplicates; the cluster is heterogeneous across unrelated model bugs, config/type issues, a typo, and tokenizer warnings. No soft pair looks like the same underlying change or bug.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue cleanly represents this cluster because the topics are unrelated. If forced to pick the broadest functional bug, 43240 is the closest, but it is not a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "43240 is the strongest standalone issue for triage because it describes an actionable runtime bug in a core loss path, unlike the narrower config/typo/reporting items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Ignore_value usage in Mask2former and loss-kwargs forwarding are unrelated." + "reason": "Different bugs: Mask2Former ignore_value handling vs kwargs not forwarded to loss calculation. No shared codepath or concrete duplicate behavior." }, { "left": "issue:43240", "right": "issue:46144", "accept": false, - "reason": "Loss kwargs forwarding and RoFormer attention interface are unrelated." + "reason": "Loss-function kwargs forwarding is unrelated to RoFormer attention-interface usage." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "Mask2former ignore_value and tokenizer regex warning are unrelated." + "reason": "Mask2Former ignore_value handling and tokenizer regex warnings are unrelated subsystems with different failure modes." }, { "left": "issue:42936", "right": "issue:46144", "accept": false, - "reason": "Mask2former ignore_value and RoFormer attention interface are unrelated." + "reason": "Different model components and symptoms; one is a loss/ignore_value bug, the other is an attention API integration issue." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Mask2former ignore_value and a quantization-operation typo are unrelated." + "reason": "Mask2Former loss handling and a typo in quantization_operation are unrelated." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Loss kwargs forwarding and a config type-hint typo are unrelated." + "reason": "A kwargs-passing bug in loss calculation is not the same as an incorrect type hint in ModernBERTConfig." }, { "left": "issue:43668", "right": "issue:43813", "accept": false, - "reason": "Config type-hint correctness and a quantization-operation typo are different issues." + "reason": "These are separate metadata/code-quality issues: type hint correctness vs a typo in a symbol name." }, { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Llama4TextL2Norm semantics and ModernBERTConfig type hints are unrelated." + "reason": "Llama4TextL2Norm/RMS norm behavior is a model-implementation question, not the ModernBERT norm_eps type hint issue." }, { "left": "issue:42936", "right": "issue:43668", "accept": false, - "reason": "Mask2former ignore_value and a ModernBERTConfig type hint are unrelated." + "reason": "Different concerns: a runtime ignore_value bug versus a type annotation mistake." } ] }, @@ -16400,8 +16577,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-10519-3", "nodes": [ @@ -16414,7 +16591,7 @@ "issue:10519|issue:11005", "issue:11005|issue:11307" ], - "prepared_review_unit_hash": "c96d02fdde0fc3e7748f502effef9f622ce56178adb91d01270bf86cad702203", + "prepared_review_unit_hash": "11ba899bfd1988c607b44b0b9a82166bdc6163b147fea35b54917beccef74186", "component_budget": { "node_count": 3, "item_count": 3, @@ -16436,30 +16613,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues are about unrelated areas: token truncation behavior, learning-rate scheduler functionality, and Wav2Vec2 word time offsets. They do not describe the same underlying bug or feature request, so the cluster should not be merged as duplicates.", - "confidence": 0.98, - "canonical_issue_reason": null, + "summary": "This cluster does not look like a duplicate set: the three issues cover unrelated topics (token truncation behavior, ReduceLROnPlateau-like scheduling, and Wav2Vec2 word time offsets). None of the soft pairs should be merged.", + "confidence": 0.96, + "canonical_issue_reason": "Issue #10519 is the clearest, most concrete feature request in the cluster and is the best anchor only in the sense of being the most well-scoped item; it is not actually a duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "#10519 is the strongest standalone issue: it has a specific, actionable request about truncation direction and clear parameter context. The other issues are unrelated and less suitable as a cluster representative.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:10519", "right": "issue:11307", "accept": false, - "reason": "Different feature areas and requests: truncation strategy in tokenization vs word start/end timestamps in Wav2Vec2. No shared code-path or concrete duplicate symptom." + "reason": "Different problem domains: truncation strategy for token inputs versus extracting word time offsets from Wav2Vec2. No shared code-path or concrete bug overlap." }, { "left": "issue:10519", "right": "issue:11005", "accept": false, - "reason": "Unrelated topics: token truncation direction vs ReduceLROnPlateau-like scheduler behavior. They do not appear to be the same bug or change." + "reason": "Unrelated requests: text truncation direction versus ReduceLROnPlateau-like scheduler behavior. They do not describe the same underlying change." }, { "left": "issue:11005", "right": "issue:11307", "accept": false, - "reason": "Different ML features: learning-rate scheduling vs extracting token time offsets from speech models. No plausible single fix or merged PR target." + "reason": "One is about learning-rate scheduling logic, the other about speech model alignment/time offsets. These are clearly distinct issues." } ] }, @@ -16478,8 +16655,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-13244-3", "nodes": [ @@ -16491,7 +16668,7 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "2e45e3e60be5be66820c62f40ee2c17efa7ef14551655c89acd275263076d6b7", + "prepared_review_unit_hash": "034f022a674ebc0e0d160ef3eb5703ff90a6bfc2163dcbcafdadfaed3c4954e5", "component_budget": { "node_count": 3, "item_count": 3, @@ -16513,24 +16690,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster does not look like a single bug family: one issue is about TAPAS tokenization differing from TensorFlow code, one about a private-model download/login error, and one about failing to load bert-base-uncased. The soft links are likely superficial Hugging Face model-related similarity rather than the same underlying problem.", - "confidence": 0.89, - "canonical_issue_reason": "issue:16618 is the most concrete and broadly representative user-facing failure in the set (a model loading bug), whereas the others concern unrelated tokenization behavior and private-model authentication messaging.", + "summary": "These issues do not look like true duplicates. One is about Tapas tokenization behavior, one about the error message for private-model downloads without login, and one about failure to load bert-base-uncased. The latter is the broadest and most central, but the overlap is only superficial.", + "confidence": 0.72, + "canonical_issue_reason": "Issue #16618 is the broadest and most representative of the cluster because it describes a general model-loading failure, whereas the other two are about a specific tokenization mismatch and a specific auth/error-message case.", "canonical_pr_reason": null, - "best_issue_reason": "issue:16618 is the best standalone issue because it describes a specific, actionable load failure with a common model name and is easier to triage than the more specialized or ancillary reports.", + "best_issue_reason": "#16618 is the best single issue to keep as the cluster anchor since it is the most general user-facing loading problem; the others are narrower and clearly refer to different failure modes.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Tokenization mismatch in TAPAS and inability to load bert-base-uncased are different code paths and different failure modes; they do not appear to be the same underlying bug." + "reason": "Tapas tokenization mismatch is a different bug from a model-loading failure; they do not appear to share the same underlying code path." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "Private-model download/login error is an authentication/message issue, while bert-base-uncased load failure is a separate model-loading problem; no clear shared root cause." + "reason": "Private-model download auth/error-message behavior is a distinct scenario from failing to load bert-base-uncased, so these are not the same bug." } ] }, @@ -16549,8 +16726,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-26350-2", "nodes": [ @@ -16560,12 +16737,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "2c9b694aa1bef3b70a6daeefa69a15e923d7d3fa679b71e776bb8c94d07b709f", + "prepared_review_unit_hash": "df54e4b1b59438a43e1aa75fea0e57ad0a4f77e70e4e54832bde72459e0a93dc", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16573,7 +16750,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -16582,18 +16759,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate community contribution requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. They share a broad theme of architecture support, but not the same underlying bug or change.", - "confidence": 0.98, - "canonical_issue_reason": "No canonical issue: the issues track different feature requests for different code paths and are not duplicates.", + "summary": "These are two separate community contribution feature requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. They share only a broad theme and are not duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "No single best issue for deduplication; each issue represents a distinct enhancement area rather than a duplicate of the other.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:26350 (Community contribution: Adding Flash Attention 2 support for more architectures)", - "right": "issue:33260 (Community contribution: Adding GGUF support for more architectures)", + "left": "issue #26350: Community contribution: Adding Flash Attention 2 support for more architectures", + "right": "issue #33260: Community contribution: Adding GGUF support for more architectures", "accept": false, - "reason": "Different capabilities and likely different implementation paths; they share only a broad \"support more architectures\" theme, so they are not the same underlying request." + "reason": "Different underlying feature requests targeting different code paths and integrations; the shared phrase 'more architectures' is too broad to treat as the same bug/change." } ] }, @@ -16612,8 +16789,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-27088-8", "nodes": [ @@ -16652,184 +16829,184 @@ "issue:44370|issue:46226", "issue:46222|issue:46226" ], - "prepared_review_unit_hash": "48debc4ac5c4516ca7ae7ae2544714a2d73ea8679f6fef2a0396b60e5b960593", + "prepared_review_unit_hash": "3e864c8cfdce97503f5162a1101a1ffdd593f94203bfe54d644813bcc595ab45", "component_budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 24, - "serialized_chars": 13528, - "estimated_input_tokens": 3382, - "estimated_eval_tokens": 7020 + "serialized_chars": 13522, + "estimated_input_tokens": 3381, + "estimated_eval_tokens": 7018 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 24, - "serialized_chars": 13528, - "estimated_input_tokens": 3382, - "estimated_eval_tokens": 7020 + "serialized_chars": 13522, + "estimated_input_tokens": 3381, + "estimated_eval_tokens": 7018 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Mixed i18n cluster: Turkish/Spanish/Romanian translation requests are distinct, while the three generic placeholder issues form one duplicate subgroup and the two Thai-text issues form another exact duplicate pair. No single issue cleanly canonicalizes the whole set.", - "confidence": 0.94, - "canonical_issue_reason": "No single canonical issue fits the full cluster because it contains separate language-specific requests plus two independent duplicate subgroups.", + "summary": "This cluster is mostly separate i18n translation requests, but it contains two clear duplicate subgroups: three identical generic template issues and one exact Thai-title duplicate pair. I would not merge the language-specific issues with those subgroups.", + "confidence": 0.81, + "canonical_issue_reason": "issue:43834 is the earliest of the identical generic-template translation issues and is the cleanest representative of the only larger duplicate subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43834 is the best representative of the placeholder-template duplicate subgroup, but it is not a good global representative for the language-specific requests or the Thai duplicate pair.", + "best_issue_reason": "issue:43834 is the strongest global issue representative because it is earliest, canonical-looking, and part of the most clearly duplicated set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Different target language/request; Turkish vs generic placeholder text." + "reason": "Different language-specific translation requests; only similar by template wording, not the same underlying issue." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Different target language/request; Turkish vs generic placeholder text." + "reason": "Turkish vs. generic placeholder translation request; not the same concrete issue." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "Turkish translation request is separate from the generic placeholder issue." + "reason": "Turkish request and generic template issue are different translation tasks." }, { "left": "issue:27088", "right": "issue:38435", "accept": false, - "reason": "Different language requests: Turkish vs Romanian." + "reason": "Different target languages; these are separate translation requests, not duplicates." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "Different language requests: Turkish vs Spanish." + "reason": "Turkish and Spanish translation requests are distinct issues." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "Spanish translation request is separate from the generic placeholder issue." + "reason": "Spanish request does not match the generic placeholder issue; different underlying task." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "Spanish translation request is separate from the generic placeholder issue." + "reason": "Different language-specific request vs. generic placeholder issue." }, { "left": "issue:28936", "right": "issue:38435", "accept": false, - "reason": "Different language requests: Spanish vs Romanian." + "reason": "Spanish and Romanian translation requests are separate issues." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "Spanish translation request is separate from the generic placeholder issue." + "reason": "Spanish request and generic placeholder request are not the same issue." }, { "left": "issue:38435", "right": "issue:44370", "accept": false, - "reason": "Romanian translation request is separate from the generic placeholder issue." + "reason": "Romanian translation request is distinct from the generic placeholder issues." }, { "left": "issue:38435", "right": "issue:44365", "accept": false, - "reason": "Romanian translation request is separate from the generic placeholder issue." + "reason": "Different translation request; similarity is only at the template level." }, { "left": "issue:38435", "right": "issue:43834", "accept": false, - "reason": "Romanian translation request is separate from the generic placeholder issue." + "reason": "Romanian request and generic placeholder issue are not the same underlying change." }, { "left": "issue:38435", "right": "issue:46222", "accept": false, - "reason": "Different content: Romanian translation request vs Thai-text issue." + "reason": "Different titles and different issue content; not enough to treat as the same request." }, { "left": "issue:38435", "right": "issue:46226", "accept": false, - "reason": "Different content: Romanian translation request vs Thai-text issue." + "reason": "Romanian docs translation and Thai-titled issue are unrelated." }, { "left": "issue:43834", "right": "issue:44370", "accept": true, - "reason": "Same generic placeholder translation issue; looks like a duplicate copy of the same template artifact." + "reason": "Same exact generic placeholder title and near-identical issue shape; looks like a duplicate submission of the same translation template." }, { "left": "issue:43834", "right": "issue:44365", "accept": true, - "reason": "Same generic placeholder translation issue; looks like a duplicate copy of the same template artifact." + "reason": "Identical title and highly similar body/template indicate the same underlying issue." }, { "left": "issue:43834", "right": "issue:46222", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "Generic placeholder translation issue vs. Thai-titled issue; not clearly the same underlying request." }, { "left": "issue:43834", "right": "issue:46226", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "Different titles and no concrete evidence they refer to the same issue." }, { "left": "issue:44365", "right": "issue:44370", "accept": true, - "reason": "Same generic placeholder translation issue; looks like a duplicate copy of the same template artifact." + "reason": "Exact same generic template title; these are duplicate issue submissions." }, { "left": "issue:44365", "right": "issue:46222", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "No clear evidence the generic template issue and Thai-titled issue are the same." }, { "left": "issue:44365", "right": "issue:46226", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "Different issue content; only superficial similarity." }, { "left": "issue:44370", "right": "issue:46222", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "Generic placeholder translation issue and Thai-titled issue are not the same underlying bug/change." }, { "left": "issue:44370", "right": "issue:46226", "accept": false, - "reason": "Generic placeholder issue vs distinct Thai-text issue; not the same underlying request." + "reason": "Different titles and no shared concrete target." }, { "left": "issue:46222", "right": "issue:46226", "accept": true, - "reason": "Exact duplicate Thai-text issue; same title/content and same underlying artifact." + "reason": "Exact same Thai title and matching body size strongly indicate duplicate issues." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet: the three language-specific translation requests are reasonably treated as separate, the three placeholder-template issues form a coherent duplicate subgroup, and the two Thai-title issues are an exact duplicate pair. The soft-edge verdicts are conservative overall, with no clear overstatement of evidence." + "feedback": "The summary is grounded in the packet: the three generic placeholder issues share the exact same title, and the Thai-titled pair also has identical titles and body length. The non-duplicate verdicts between language-specific issues and these subgroups are conservative given the limited evidence. No obvious overstatement." }, "evaluator_used": true, "retried": false, @@ -16905,112 +17082,112 @@ "issue:43837|issue:45177", "issue:45322|issue:46133" ], - "prepared_review_unit_hash": "367b5977816929a064581045ac4cd146d26f6ed4f931f163f5287b5854c9193e", + "prepared_review_unit_hash": "678ebc2ecda6126d87bf4b4684ac63bfbffd6ad9b5546b154f656b90f5f9253e", "component_budget": { "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21662, - "estimated_input_tokens": 5416, - "estimated_eval_tokens": 11088 + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 }, "budget": { "node_count": 16, "item_count": 16, "soft_pair_count": 36, - "serialized_chars": 21662, - "estimated_input_tokens": 5416, - "estimated_eval_tokens": 11088 + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a broad semantic grouping of unrelated model-request issues (different models, modalities, and code paths), not a set of true duplicates. All soft edges should be rejected.", - "confidence": 0.93, - "canonical_issue_reason": "No single true canonical issue: the items span many distinct model additions (BERT variants, vision detectors, audio/TTS/ASR, OCR, sparse transformers), so they do not share one underlying change or bug.", + "summary": "This cluster is a broad set of model-addition requests, not a duplicate set. The titles point to different concrete models or model families, so none of the soft edges look like the same underlying bug/change.", + "confidence": 0.11, + "canonical_issue_reason": "Issue 41115 is the broadest and most representative standalone request in the set, but there is no exact duplicate here.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43671 is the closest thing to a representative anchor because it sits in the densest similarity neighborhood, but it is still only a loose exemplar and not a valid duplicate hub.", + "best_issue_reason": "Issue 41115 is the best single representative because it is a clear, actionable model-architecture request with decent discussion activity; however, it should not be treated as a duplicate of the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "Different model families and architectures; both are generic add-model requests, not the same underlying change." + "reason": "Different requested models (EuroBert vs DEIMv2); same broad theme, but not the same change." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert vs Qwen3-TTS are unrelated model requests with different modalities and code paths." + "reason": "EuroBert config support and Qwen3-TTS support are unrelated model integrations." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "BERT config addition and RF-DETR support are unrelated models, so this is only superficial similarity." + "reason": "EuroBert and RF-DETR are different model families and would require separate code paths." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are distinct detector/model requests; not the same fix." + "reason": "RF-DETR and DEIMv2 are distinct models with separate implementation work." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "Object detection vs audio model support; different implementations and purposes." + "reason": "Object detection (RF-DETR) versus audio model support (LFM2.5 Audio) are not the same request." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR support and sparse-transformer support are different model integrations." + "reason": "RF-DETR and OpenAI weight-sparse transformer support are different concrete architectures." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR and Qwen3-ASR are unrelated requests across different modalities." + "reason": "RF-DETR and Qwen3-ASR are unrelated model additions." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS are different models and not mergeable into one PR." + "reason": "RF-DETR and Qwen3-TTS are different models and modalities." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT and Qwen3-ASR are different model additions with separate code paths." + "reason": "NeoBERT and Qwen3-ASR target different model families and implementation paths." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "A BERT-family model request and a sparse-transformer request are not the same underlying change." + "reason": "NeoBERT and circuit-sparse transformer support are unrelated changes." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio are unrelated model targets." + "reason": "NeoBERT and LFM2.5 Audio are different model requests." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are distinct models; similarity is only in the generic add-model phrasing." + "reason": "RF-DETR and NeoBERT are separate model additions, not duplicates." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different model families and not a single duplicate." + "reason": "NeoBERT and ModernVBERT are distinct BERT-like families, but not the same model or bug." }, { "left": "issue:41115", @@ -17022,133 +17199,133 @@ "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 and the weight-sparse transformer request are unrelated changes." + "reason": "MiniCPM3 and the OpenAI weight-sparse transformer request are unrelated code changes." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are different model requests, not one concrete bug/change." + "reason": "MiniCPM3 and ModernVBERT are different model-specific requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral TTS target different model families and likely different implementation paths." + "reason": "MiniCPM3 and Voxtral TTS support are separate model additions with different code paths." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are distinct model additions, not duplicates." + "reason": "DEIMv2 and Qwen3-TTS are different model support requests." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are different model support requests." + "reason": "ModernVBERT and Qwen3-ASR are unrelated concrete model requests." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are unrelated model integrations." + "reason": "ModernVBERT and Qwen3-TTS are different model families." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "A specific model addition and a broad RoPE feature request are not the same underlying change." + "reason": "ModernVBERT support and a generic RoPE-related BERT-like request are not the same underlying change." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "General RoPE support for BERT-like models and Voxtral TTS support are different problems." + "reason": "A generic BERT-like RoPE request and Voxtral TTS support are unrelated." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are sister requests but different tasks/code paths; they would not be one PR." + "reason": "Qwen3-TTS and Qwen3-ASR share a prefix but are different modalities and separate implementations." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS and Voxtral TTS are different model families despite both being audio-related." + "reason": "Qwen3-TTS and Voxtral-4B-TTS-2603 are different model-specific support requests." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "TTS support and OCR model support are unrelated changes." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated models." }, { "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "Audio TTS support and sparse-transformer support are different concrete implementations." - }, - { - "left": "issue:43671", - "right": "issue:43909", - "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio are different audio-model requests with different code paths." + "reason": "Qwen3-TTS support and a weight-sparse transformer request are different code-path problems." }, { "left": "issue:43837", "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio are different model additions, not the same bug." + "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are different audio model requests." }, { "left": "issue:43837", "right": "issue:45322", "accept": false, - "reason": "ASR support and EUPE vision-language encoder support are unrelated requests." + "reason": "Qwen3-ASR and EUPE are unrelated model additions." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "Audio model support and SAM3-LiteText support are completely different modalities." + "reason": "Audio model support and SAM3-LiteText are different model families." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are separate audio-model requests." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Sparse transformer support and EUPE support are distinct model requests." + "reason": "Weight-sparse transformer support and EUPE are not the same implementation problem." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "ASR support and sparse-transformer support do not share one concrete code-path fix." + "reason": "Qwen3-ASR support and the weight-sparse transformer request are unrelated." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech model requests, not duplicates." + "reason": "Qwen3-ASR and Voxtral-4B-TTS-2603 are different model requests." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated model integrations." + "reason": "NeoBERT and Voxtral TTS are unrelated model additions." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "ASR support and DeepSeek-OCR2 support are different modalities and implementations." + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different models and code paths." }, { "left": "issue:45322", "right": "issue:46133", "accept": false, - "reason": "EUPE and TIPSv2 are different research models with separate support work." + "reason": "EUPE and TIPSv2 are both vision-language related, but they are distinct model requests and not mergeable as one fix." } ] }, @@ -17167,8 +17344,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-41084-2", "nodes": [ @@ -17178,7 +17355,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "e940da8bb581782bf6d4b3ef3f8b36c70f45fb8a583a2bfe387241a705d44e1c", + "prepared_review_unit_hash": "9a4d98ec567b2bd946dc344a65723a5567aaf848c6fd3cc1b24db87f79179dce", "component_budget": { "node_count": 2, "item_count": 2, @@ -17200,18 +17377,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are not duplicates: one is about block decoding, the other is about adding DeepSeek v3.2 support. They describe different features/problems with no shared target or code path.", + "summary": "The two issues are unrelated: one is about enabling block decoding, while the other requests DeepSeek v3.2 support. They do not describe the same underlying bug or change.", "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative because they target different features/problems with no overlap in scope.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "Different topics and likely different code paths; block decoding is unrelated to DeepSeek model support." + "reason": "Different requests: block decoding vs model support for DeepSeek v3.2. No shared code-path or concrete duplicate behavior is indicated." } ] }, @@ -17230,8 +17407,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43598-2", "nodes": [ @@ -17241,12 +17418,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "3b73fc8e8f885e0913655ff4a86d78ff1ced2108635afee613a6dc41ea6aa593", + "prepared_review_unit_hash": "52e2e9669865109e3c88be0c3b2fe0ff9cef675dcc2ee70f71dbd5e5bd6c6308", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -17254,7 +17431,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -17263,18 +17440,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues both mention Trainer customization, but they describe different problems: one is about `remove_unused_column` behavior, the other about FLOPS estimation for custom trainers. They should not be treated as duplicates.", - "confidence": 0.95, - "canonical_issue_reason": "No strong canonical issue emerges because the topics are distinct rather than overlapping reports of the same bug.", + "summary": "The two issues are thematically related to Trainer customizability, but they describe different problems in different code paths: one about `remove_unused_column`, the other about FLOPS estimation for custom trainers. They should not be treated as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": "If one must be chosen as the representative issue, #43598 is the better fit because it directly concerns Trainer behavior/customizability; however, it does not cover the FLOPS-estimation problem in #43600.", "canonical_pr_reason": null, - "best_issue_reason": "Issue #43598 is slightly more specific and actionable around a concrete Trainer setting, so it is the better representative if one must be chosen.", + "best_issue_reason": "#43598 is the more central/general issue in this small cluster, but it is still not a true superset of #43600.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43598", "right": "issue:43600", "accept": false, - "reason": "Different underlying concerns: one is about column-removal customizability in Trainer, the other about FLOPS accounting for custom trainers. Shared Trainer context is too broad to treat as the same issue." + "reason": "Related by theme, but not the same underlying bug: #43598 is about `remove_unused_column` customizability, while #43600 is about estimating FLOPS for custom trainers." } ] }, @@ -17293,8 +17470,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43684-2", "nodes": [ @@ -17304,7 +17481,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "3c603234892ba3ead0b7c30c3952d891c4d5084dd7c129512050878b5cc25296", + "prepared_review_unit_hash": "ea27712a6b42066d5e5989d6e97c7a1bbe56c66eddf1c559275abf7a58c198b7", "component_budget": { "node_count": 2, "item_count": 2, @@ -17326,18 +17503,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are related only at the very broad level of adding AutoModel support, but they target different model families and different auto classes, so they are not duplicates.", - "confidence": 0.93, + "summary": "Related but distinct enhancement requests: one adds Qwen3-Omni registration to AutoModel/AutoModelForConditionalGeneration, the other requests AutoModelForSequenceClassification support for Qwen3.5. They target different model families and different auto-model heads.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 43684 is the broader request: it covers Qwen3-Omni registration for both AutoModel and AutoModelForConditionalGeneration, whereas 44405 is a narrower, separate request for sequence classification on Qwen3.5.", + "best_issue_reason": "Issue 43684 is the broader, higher-level registration request, but it is not a duplicate of 44405 because the model family and target auto-classes differ.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Different underlying features/models: Qwen3-Omni auto-registration vs Qwen3.5 sequence-classification support. They do not describe the same bug or change path and would not be merged into one fix." + "reason": "Different underlying change: Qwen3-Omni auto-registration vs Qwen3.5 sequence-classification support. They touch different model/task code paths and should not be merged as duplicates." } ] }, @@ -17356,8 +17533,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-43835-4", "nodes": [ @@ -17374,12 +17551,12 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "3461e2b8c6ce78d0b69667ade54a7017554095fb126ad3695b9c3001cc0f9e11", + "prepared_review_unit_hash": "fede1aece86d0ce1cfac34cfb33df7d7740af5f5a8902cacd0a9efae6ac26052", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -17387,7 +17564,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4263, + "serialized_chars": 4264, "estimated_input_tokens": 1066, "estimated_eval_tokens": 2388 }, @@ -17396,58 +17573,55 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster appears to contain one unrelated issue ('Fett') and a duplicate trio of near-identical 'huggingface ' issues. With no substantive bodies, the safest canonical choice is the earliest huggingface issue.", - "confidence": 0.92, - "canonical_issue_reason": "issue:43845 is the earliest of the three identical 'huggingface ' issues and is the best representative for that duplicate set; issue:43835 ('Fett') looks unrelated.", + "summary": "The cluster appears to be low-information / likely spammy duplicate issues with generic titles. There is not enough concrete bug detail to safely merge any pair as the same underlying issue.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 43859 is the slightly best representative only because it has the most activity, but none of these issues contains enough real problem description to be a strong canonical choice.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43845 is the strongest global issue representative because it matches the other two huggingface issues exactly in title and is earliest, while the only other title in the cluster is unrelated.", + "best_issue_reason": "43859 is the most suitable issue to keep if one must be chosen, since it has discussion activity and is at least marginally more substantive than the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "Different titles with no shared substantive details; nothing indicates the same underlying report." + "reason": "Different titles and no shared issue details beyond weak similarity; no concrete evidence they describe the same bug." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "Different titles with no shared substantive details; nothing indicates the same underlying report." + "reason": "Different titles and no concrete body information tying them to the same underlying problem." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "Different titles with no shared substantive details; nothing indicates the same underlying report." + "reason": "Generic title overlap is not enough; the issues do not provide a shared bug description or target." }, { "left": "issue:43845", "right": "issue:43846", - "accept": true, - "reason": "Same normalized title ('huggingface ') and close creation times, with no evidence of distinct topics." + "accept": false, + "reason": "Even though the titles match, the bodies provide no concrete evidence of the same underlying issue." }, { "left": "issue:43845", "right": "issue:43859", - "accept": true, - "reason": "Same normalized title ('huggingface ') and close creation times; likely duplicate submissions of the same issue." + "accept": false, + "reason": "Same broad keyword only; insufficient detail to conclude these are duplicates of the same bug." }, { "left": "issue:43846", "right": "issue:43859", - "accept": true, - "reason": "Same normalized title ('huggingface ') and close creation times, consistent with duplicates of one report." + "accept": false, + "reason": "Matching generic titles are not enough without a shared technical description or explicit target." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is well grounded in the packet: the three \"huggingface \" issues are title-identical and closely timed, while \"Fett\" is distinct. The canonical choice of the earliest huggingface issue is conservative, and the soft-edge verdicts do not overstate evidence." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -17459,8 +17633,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-44371-5", "nodes": [ @@ -17481,7 +17655,7 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "d53f1092e43db99dd1fa31b3ae01c9423542bf97eae17fc59f5a890c967f15ba", + "prepared_review_unit_hash": "626018c5d05aa92824ce938d7a51637ad3601d8e836cc93b173cc0eccf7fbf90", "component_budget": { "node_count": 5, "item_count": 5, @@ -17503,66 +17677,66 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is dominated by near-empty/spam-like issues with no concrete bug or change details. Issue 44418 is the only somewhat substantive topic, but there is still not enough evidence that any pair is a true duplicate.", - "confidence": 0.34, - "canonical_issue_reason": "issue:44418 has the most meaningful, non-spam title and is the only item that looks like a real triage target; the others are generic spam placeholders.", + "summary": "These issues do not look like duplicates of one concrete bug or change; they are mostly spammy or generic placeholders with no body/detail evidence tying them together.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:44418 is the best representative of the cluster because it is the only issue with an identifiable subject matter and some potential triage value.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are just '' with no body detail; identical placeholder titles are not enough to prove the same underlying issue." + "reason": "Both are only spam placeholders with no description or target; superficial title similarity is not enough to imply the same underlying issue." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Both are just '' with no actionable description, so there is no concrete evidence they report the same problem." + "reason": "Same as above: generic spam titles with no concrete shared bug or change." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "One is spam-like and the other is a generic documentation request; the titles do not indicate the same underlying bug or change." + "reason": "One is spam-like and the other is a vague documentation suggestion; no evidence they refer to the same problem." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "The placeholder spam title and the specific 'Google LLC' title are unrelated on their face, with no body evidence tying them together." + "reason": "Completely different titles and no body detail; not enough to indicate a shared issue." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "A documentation enhancement request and a spam placeholder do not describe the same issue; there is no shared concrete problem statement." + "reason": "A documentation enhancement request is not the same underlying item as a spam placeholder." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "The documentation suggestion is too generic, and the other item is empty spam; no basis to merge as duplicates." + "reason": "Generic documentation request vs. spam placeholder; no concrete overlap." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Matching spam placeholders alone do not establish a duplicate; there is no description or target to confirm the same underlying report." + "reason": "Both are spam placeholders, but there is no evidence they describe the same underlying bug or change." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "A spam placeholder and a specific entity-name title are not the same reported problem, and there is no supporting detail." + "reason": "No shared concrete topic: spam placeholder versus a specific quoted-name title." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "These titles are not describing the same concrete bug or request, and the bodies provide no evidence of a shared root cause." + "reason": "No meaningful evidence of the same underlying issue; titles are unrelated." } ] }, @@ -17581,8 +17755,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45145-2", "nodes": [ @@ -17592,12 +17766,12 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "a64c90beeda203331664a7c1862ba6065c02a171e9900ce7eeb28bc31b169da5", + "prepared_review_unit_hash": "d7f98b4ad2677b10270ff684761c8628b381de868a8ae32a3c11384e39079146", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -17605,7 +17779,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1645, + "serialized_chars": 1646, "estimated_input_tokens": 412, "estimated_eval_tokens": 1080 }, @@ -17614,24 +17788,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues share an identical title and some textual overlap, but the evidence is not strong enough to call them near-identical duplicates or to consolidate them as the same report.", - "confidence": 0.9, - "canonical_issue_reason": null, + "summary": "The two issues are highly similar and likely related, but the evidence is not strong enough to call them confirmed duplicates. #45145 is the better canonical issue because it was opened first and already has an inbound reference.", + "confidence": 0.84, + "canonical_issue_reason": "#45145 is the earlier issue and already has an inbound reference, so it is the best anchor for deduplication discussion.", "canonical_pr_reason": null, - "best_issue_reason": "issue #45145 is the slightly better cluster representative because it is earlier and already has an inbound reference, but this is only a mild preference, not a duplicate determination.", + "best_issue_reason": "#45145 is the strongest issue representative for the cluster because it predates #45151 and has the existing linkage.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", "accept": false, - "reason": "Identical titles and moderate similarity suggest related reports, but the packet does not show sufficiently similar bodies or evidence of the same underlying issue to justify duplicate consolidation." + "reason": "The titles are identical and the bodies are moderately similar, but there are no explicit links, shared targets, or filenames; this supports a likely related/possible-duplicate relation rather than a confirmed same-underlying-issue duplicate." } ] }, "evaluator_result": { "accept": false, - "feedback": "The pairing is only supported as a soft similarity match with identical titles and moderate Jaccard similarity; the packet does not show the bodies are \"highly similar\" or that the issues are \"near-identical duplicates.\" The consolidation/duplicate language is a bit too strong for the evidence, so this should be rejected as overstated." + "feedback": "The canonical-choice reasoning is grounded, but the cluster/soft-edge language is a bit too strong for the packet. The pair only has soft-similarity evidence with a moderate Jaccard score, so calling them \"near-certain duplicates\" and accepting the edge as same underlying issue overstates the evidence. A more conservative verdict would be that they are likely related or possible duplicates, not confirmed duplicates." }, "evaluator_used": true, "retried": true, @@ -17701,8 +17875,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45672-2", "nodes": [ @@ -17712,12 +17886,12 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "0e6650b004bf55a238b3d2999a96a9ab90dcb286490a30050c01223489a249c6", + "prepared_review_unit_hash": "33c9923270017b6566109b48727de562ca0ac1b30bbeaa25fc01ea45236b3f49", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1670, + "serialized_chars": 1671, "estimated_input_tokens": 418, "estimated_eval_tokens": 1092 }, @@ -17725,7 +17899,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1670, + "serialized_chars": 1671, "estimated_input_tokens": 418, "estimated_eval_tokens": 1092 }, @@ -17734,18 +17908,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related only at a high level (both involve 4-bit inference), but they describe different bugs: one is a torch.finfo() failure on uint8 audio-module weights, the other is a BitsAndBytesConfig skip-module regression that drops the default lm_head exclusion and triggers an AssertionError.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 45674 is the better canonical representative because it is the more general, currently open regression with clearer reproduction around BitsAndBytesConfig behavior and 4-bit inference.", + "summary": "These are two separate 4-bit inference bugs, not duplicates: one is Gemma4/audio-module uint8 weight handling leading to a `torch.finfo()` TypeError, the other is a `BitsAndBytesConfig.llm_int8_skip_modules` regression that drops the default `lm_head` exclusion and triggers an AssertionError. They overlap only at a broad \u201c4-bit inference\u201d level.", + "confidence": 0.95, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Issue 45674 is the best overall issue in the cluster: it is broader, more actionable, and likely to gather the most useful triage attention for the 4-bit inference path.", + "best_issue_reason": "If a single issue had to represent the cluster, 45674 is the more general/config-level regression and is phrased more directly around the failing behavior; 45672 is model-specific and narrower.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Reject: these appear to be distinct bugs with different symptoms and code paths. 45672 is a torch.finfo() TypeError on uint8 audio-module weights, while 45674 is a BitsAndBytesConfig skip-module handling regression that removes the default lm_head exclusion and causes an AssertionError." + "reason": "Different failure modes and code paths: Gemma4 audio-module `torch.finfo()` on uint8 weights vs `BitsAndBytesConfig` skip-module handling removing the default `lm_head` exclusion. Same broad 4-bit context, but not the same underlying bug." } ] }, @@ -17764,8 +17938,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45762-2", "nodes": [ @@ -17775,7 +17949,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "aeb748a30b21ab9a3edbacf594a998ee1d4142181cd086af6f8393d45addcc32", + "prepared_review_unit_hash": "6f195e32dfb7fd2498d40ebbc254b311ea9d89546bc1c548b623a2e8bee2bace", "component_budget": { "node_count": 2, "item_count": 2, @@ -17797,18 +17971,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are not duplicates of the same underlying bug; they appear to be separate name/date entries with no technical context. The soft similarity is superficial only.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "Two closed issues with superficially similar personal-name/date titles, but they refer to different individuals and do not describe the same bug or request. No PRs are present.", + "confidence": 0.95, + "canonical_issue_reason": "Neither issue is a meaningful canonical duplicate target; they are separate, non-technical, name-only reports with no shared underlying problem description.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "If forced to pick one, issue #45762 is marginally clearer only because it has a fuller name string, but it is not a good canonical issue overall.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Titles share a similar personal-name/date pattern, but there is no evidence they describe the same problem or request; they look like distinct entries." + "reason": "Both are just different person-name/date titles and lack evidence of the same underlying bug or change; they should not be merged as duplicates." } ] }, @@ -17827,8 +18001,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45764-2", "nodes": [ @@ -17838,7 +18012,7 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "f6a653532046d023650df77efcfc20b583ac910ec692a97d99e6cc5806e017a2", + "prepared_review_unit_hash": "2f37ca9f2afbbd031564320b9823ff02a9bca77a9e757a911f37122a5d294866", "component_budget": { "node_count": 2, "item_count": 2, @@ -17860,18 +18034,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues only share a loose textual similarity in personal-name/date formatting and do not show any evidence of the same underlying bug or request.", - "confidence": 0.97, + "summary": "The two issues are unrelated standalone entries with different names/dates and no shared context, so this is not a duplicate cluster.", + "confidence": 0.99, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "Neither issue is a good canonical choice because there is no evidence they describe the same bug or request; both look like separate, unrelated tickets.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "The titles refer to different people and different dates; there is no issue body, linkage, or code context indicating a shared defect or duplicate report." + "reason": "Different subjects entirely; no shared description, targets, or repository context indicating the same underlying issue." } ] }, @@ -17890,8 +18064,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45810-2", "nodes": [ @@ -17901,12 +18075,12 @@ "soft_pairs": [ "issue:45810|issue:46295" ], - "prepared_review_unit_hash": "3e8d6bf0b1330236a40e752aede04a703a87cef620dbf1666a0e1b32ebe3b08e", + "prepared_review_unit_hash": "9b2e3a0937f7b1d00356dfccefe1cf8973ed98d9119e714ede3097ea61ed96a9", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1541, + "serialized_chars": 1542, "estimated_input_tokens": 386, "estimated_eval_tokens": 1028 }, @@ -17914,7 +18088,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1541, + "serialized_chars": 1542, "estimated_input_tokens": 386, "estimated_eval_tokens": 1028 }, @@ -17923,18 +18097,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are not duplicates: one asks for a new token-classification class for Qwen3.5, while the other requests FP8 training support. They touch different features and code paths.", + "summary": "The two issues are unrelated: one requests a new Qwen3_5 token-classification/value-model feature, while the other asks for FP8 training support. They should not be clustered as duplicates or merged into a single canonical item.", "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "issue:46295 is the broader, more general feature request, but it is still unrelated to issue:45810 and should not be treated as a duplicate target.", + "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45810", "right": "issue:46295", "accept": false, - "reason": "Different underlying requests: model-specific token classification support versus FP8 training support. They do not describe the same bug or change." + "reason": "Different feature requests in different areas (model head support vs FP8 training); no shared code-path or concrete underlying bug/change." } ] }, @@ -17953,8 +18127,8 @@ "review_unit_count": 1, "status": "reviewed", "reason": null, - "source": "cache", - "cache_hit": true, + "source": "llm", + "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-45869-5", "nodes": [ @@ -17974,12 +18148,12 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "ac47b6e4fb64cd07a9076b6f05ff817a1fd77993cdbdc64e724c4f5f14b55528", + "prepared_review_unit_hash": "b3ea6e2aa179a13fa4c4365f7ee825ab3cca3e79291795d529fd4364f17c62e8", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5725, + "serialized_chars": 5727, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -17987,7 +18161,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 8, - "serialized_chars": 5725, + "serialized_chars": 5727, "estimated_input_tokens": 1432, "estimated_eval_tokens": 3120 }, @@ -17996,69 +18170,69 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not a single duplicate set: it contains two exact-duplicate issue pairs about different DataForge examples, plus one unrelated dataset promotion issue. Accept the two exact-title duplicates and reject the cross-topic soft similarities.", - "confidence": 0.96, - "canonical_issue_reason": "If forced to pick one representative, issue #45870 is the cleanest canonical for the exact duplicate pair #45870/#45871; however, the cluster actually splits into two separate issue topics, so a single true canonical does not exist.", + "summary": "The cluster appears to split into one unrelated dataset item (45869), plus two likely duplicate pairs: 45870/45871 and 45872/45873. The duplicate evidence is fairly strong from identical titles and matching body sizes, but it is still only soft-similarity evidence, so the conclusion should remain tentative rather than exact.", + "confidence": 0.86, + "canonical_issue_reason": "45870 is a reasonable canonical issue for the DataForge example pair because it has the same title as 45871 and slightly more discussion activity, making it a better representative for that likely duplicate pair.", "canonical_pr_reason": null, - "best_issue_reason": "#45870 is the best issue candidate because it is the clearest, most general example issue and has an exact duplicate partner. Still, it should not absorb #45872/#45873 since those describe a different example/change.", + "best_issue_reason": "45870 is the best issue to anchor deduping in this cluster: it sits in a likely duplicate pair with 45871, has slightly more activity than its twin, and 45869 is clearly separate while 45872/45873 form a second likely duplicate pair.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Dataset bundle promo and a DataForge example are related only by theme, not the same underlying issue." + "reason": "Both mention financial/DataForge topics, but 45869 is a dataset bundle/free sample while 45870 is an example about time series prediction; different underlying request." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Same as above; no evidence they describe the same bug or change." + "reason": "Same as 45869 vs 45870: shared theme, but the artifacts describe different content and purpose." }, { "left": "issue:45870", "right": "issue:45871", "accept": true, - "reason": "Exact same title and clearly the same example issue; this is a straightforward duplicate." + "reason": "Identical titles and matching body length make these look like the same issue submitted twice, even though the evidence is only soft-similarity based." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Both are DataForge-related, but one is an example issue and the other is a separate time-series + scraping service topic." + "reason": "45870 is an example post about prediction, while 45872 is a request about a time-series + scraping service; related domain, but not the same concrete issue." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Different concrete topic despite similar keywords; not the same underlying change." + "reason": "Same as 45870 vs 45872: similar theme, but different request scope and title." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "These are two distinct issue topics, not one duplicate bug/report." + "reason": "The example-prediction issue and the service request are different underlying items despite both being DataForge-related." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Same as above; similarity is only at the broad subsystem/topic level." + "reason": "Same reasoning as 45871 vs 45872: related theme, but not the same issue." }, { "left": "issue:45872", "right": "issue:45873", "accept": true, - "reason": "Exact same title and evidently the same issue; strong duplicate match." + "reason": "Identical titles and matching body length strongly suggest these are duplicate submissions of the same service-related request." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: 45870/45871 are identical, 45872/45873 are identical, and 45869 is a distinct dataset-promo item. The canonicalization note is conservative, and the soft-edge verdicts do not overclaim beyond the available evidence." + "accept": false, + "feedback": "The summary is a bit too strong for the evidence in the packet. The identical titles for 45870/45871 and 45872/45873 do support likely duplication, but the packet only marks these as soft_similarity and every pair has deterministic_accept=false, so calling them \"clear duplicate pairs\"/\"exact duplicate\" overstates certainty. The 45869 split is grounded, but the duplicate-pair conclusions should be phrased more conservatively." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -18094,8 +18268,8 @@ ], "soft_pairs": [ "pull_request:39895|pull_request:43424", - "pull_request:41855|pull_request:43823", "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", "pull_request:42668|pull_request:43823", "pull_request:43251|pull_request:43823", "pull_request:43251|pull_request:44827", @@ -18114,12 +18288,12 @@ "pull_request:46048|pull_request:46268", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "f072cf42325b97c08ee5dc2c8e3e8e1bc44f41938aad5d757472575b7ef39108", + "prepared_review_unit_hash": "8edeccc0b4a0a62222a11427b9e67968bac6c33191f1365bfce6afb92809563f", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 20, - "serialized_chars": 40310, + "serialized_chars": 40309, "estimated_input_tokens": 10078, "estimated_eval_tokens": 20412 }, @@ -18127,7 +18301,7 @@ "node_count": 15, "item_count": 15, "soft_pair_count": 20, - "serialized_chars": 40310, + "serialized_chars": 40309, "estimated_input_tokens": 10078, "estimated_eval_tokens": 20412 }, @@ -18136,138 +18310,138 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated open PRs that happen to touch adjacent transformer subsystems. The only true duplicate-looking pair is the two `fixed_cross_entropy` fixes for the same loss helper; everything else is a broad-similarity false positive.", - "confidence": 0.97, + "summary": "This cluster is mostly heterogeneous false-positive similarity. The only true duplicate pair is the two fixed_cross_entropy PRs; the rest are unrelated model additions, docs, kernel routing, or test-only changes.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "`pull_request:43251` is the better canonical PR for the loss-helper fix: it targets the explicit issue `43240`, patches the same `fixed_cross_entropy` code path, and is the more directly framed implementation of the duplicate change.", + "canonical_pr_reason": "PR 43254 is the clearest canonical representative of the only real duplicate pair: it directly adds supported kwargs to fixed_cross_entropy and cleanly captures the shared cross-entropy fix.", "best_issue_reason": null, - "best_pr_reason": "`pull_request:43251` is the best representative PR overall because it is the only clear same-bug duplicate candidate in the set and has the strongest issue linkage and clearest scope.", + "best_pr_reason": "PR 43254 is the best overall PR candidate because it most directly represents the cluster\u2019s only genuine overlap; the other PRs are not the same underlying change.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Different models and goals: VideoPrism addition vs. an Executorch dynamic-shape test. Shared export/test themes are too broad to indicate the same underlying change." + "reason": "Videoprism model integration vs ExecuTorch export tests; unrelated changes." }, { "left": "pull_request:41855", - "right": "pull_request:43823", + "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer method additions for MistralCommon vs. adding a new MobileLLM model. No shared code path or same bug/change." + "reason": "Tokenizer helper methods vs export/dynamic-shape testing; different code paths." }, { "left": "pull_request:41855", - "right": "pull_request:43424", + "right": "pull_request:43823", "accept": false, - "reason": "A tokenizer API patch and an Executorch export test are unrelated changes; only superficial test/utility similarity." + "reason": "Mistral tokenizer methods vs adding a new MobileLLM model; no shared bug/change." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness vs. adding MobileLLM. Different subsystems and different fixes." + "reason": "Processor auto-loading robustness vs new MobileLLM model implementation; unrelated." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-function kwargs support and a new model addition are unrelated; same file cluster here does not mean same bug." + "reason": "Cross-entropy kwargs fix vs MobileLLM model addition; different subsystem." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "`fixed_cross_entropy` kwargs support is unrelated to Mistral4 test/model updates." + "reason": "Cross-entropy loss helper change vs Mistral4 test fixes; not the same code-path." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch dynamic-shape tests and Mistral4 fixes do not share a concrete code-path problem." + "reason": "ExecuTorch export test vs Mistral4 model/test changes; unrelated work." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "A test for dynamic exportability and a new model implementation are not the same change." + "reason": "Export dynamic-shape test vs model addition; no common underlying fix." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New MobileLLM model code and config-resolution ordering in `modeling_utils.py` are unrelated." + "reason": "New model implementation vs config-resolution ordering fix; unrelated." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition vs. Falcon output-collection refactor; no common bug or mergeable unified fix." + "reason": "New model addition vs Falcon refactor for output collection; different changes." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon refactor and the model-creation skill are completely different changes." + "reason": "Falcon output-interface refactor vs model-creation skill docs; not the same artifact." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon standardized-output refactor vs. Mistral4 test fixes are not the same underlying issue." + "reason": "Falcon refactor vs Mistral4 test fixes; different models and problems." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test/model work vs. a CLIP-style `layrnorm` spelling fix are unrelated." + "reason": "Mistral4 test fixes vs CLIP-family layernorm rename; unrelated." }, { "left": "pull_request:44827", "right": "pull_request:46267", "accept": false, - "reason": "Mistral4 fixes and chat-response parsing updates address different functionality." + "reason": "Mistral4 fixes vs chat parsing/serve overhaul; unrelated code paths." }, { "left": "pull_request:44827", "right": "pull_request:46048", "accept": false, - "reason": "Mistral4 test fixes and TDT loss-kernel plumbing are unrelated code paths." + "reason": "Mistral4 tests vs TDT loss kernel integration; different areas." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4-specific work and config resolution ordering in core model loading are different problems." + "reason": "Mistral4 tests vs config-resolution fix; unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "A model test fix and a model-creation skill PR are not the same change." + "reason": "Model test fixes vs skill/documentation PR; not a duplicate change." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "Adding MobileLLM and adding a model-creation skill are unrelated." + "reason": "Model implementation vs skill/docs; no shared underlying bug." }, { "left": "pull_request:46048", "right": "pull_request:46268", "accept": false, - "reason": "Both touch `hub_kernels.py`, but one adds a TDT loss kernel and the other adds ROCm AITER routing; different functionality and no shared bug." + "reason": "TDT loss kernel integration vs ROCm AITER kernel routing; both kernel-related but different functionality." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "These are two near-identical fixes for `src/transformers/loss/loss_utils.py` that both add `weight`/`label_smoothing` support to `fixed_cross_entropy` for the same issue `43240`; they target the same concrete code path and could be merged into one PR." + "reason": "Both PRs fix the same fixed_cross_entropy API gap by forwarding supported nn.functional.cross_entropy kwargs; they are alternate implementations of the same change." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary is grounded in the packet, and the only accepted pair (`43251`/`43254`) is well-supported as a mergeable same-bug fix: same file, same helper, same issue target, and nearly identical scope. The other soft-edge rejections stay conservative and do not overclaim shared bugs." + "feedback": "The summary is well grounded in the packet and stays conservative: it identifies the only explicitly supported duplicate pair (43251/43254) and treats the remaining soft matches as unrelated. The accepted pair is plausibly the same fixed_cross_entropy bugfix, and the rejected pairs do not look mergeable into a single PR for the same change." }, "evaluator_used": true, "retried": false, @@ -18286,48 +18460,71 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-40546-2", + "cluster_id": "cluster-40546-4", "nodes": [ "pull_request:40546", - "pull_request:42781" + "pull_request:42781", + "pull_request:46331", + "pull_request:46332" ], "soft_pairs": [ - "pull_request:40546|pull_request:42781" + "pull_request:40546|pull_request:42781", + "pull_request:42781|pull_request:46331", + "pull_request:42781|pull_request:46332", + "pull_request:46331|pull_request:46332" ], - "prepared_review_unit_hash": "b3c14529dd32acc04f654921a9cd07007e7fe88ace2a7c27e76c8759d78cab1d", + "prepared_review_unit_hash": "a663a0e9fe475d8bd8bc056fbdd85d306283901f57193af8dcb24239578d9582", "component_budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 7226, - "estimated_input_tokens": 1807, - "estimated_eval_tokens": 3870 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 14484, + "estimated_input_tokens": 3621, + "estimated_eval_tokens": 7498 }, "budget": { - "node_count": 2, - "item_count": 2, - "soft_pair_count": 1, - "serialized_chars": 7226, - "estimated_input_tokens": 1807, - "estimated_eval_tokens": 3870 + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 14484, + "estimated_input_tokens": 3621, + "estimated_eval_tokens": 7498 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs concern the VibeVoice model family, but they are not duplicates: #40546 implements the base VibeVoice integration, while #42781 is a separate VibeVoice Realtime follow-up with acoustic tokenizer and generation changes.", - "confidence": 0.91, + "summary": "These PRs are all in the audio/ASR model-registration area, but they add different models or variants (VibeVoice core, VibeVoice Realtime, Parakeet-RNNT, Nemotron ASR). The shared docs/auto-mapping edits are superficial; none are the same underlying change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No true duplicate canonical PR; #40546 is the earlier baseline integration, while #42781 is a distinct realtime extension rather than the same change.", + "canonical_pr_reason": "No canonical PR: the cluster contains separate feature additions for different models/variants rather than duplicates of one change.", "best_issue_reason": null, - "best_pr_reason": "#42781 is the more focused and more complete follow-up for the realtime/VibeVoice expansion, but it should be tracked separately from the base implementation in #40546.", + "best_pr_reason": "40546 is the broadest standalone implementation, but it is not a duplicate of the others and only serves as a weak cluster representative.", "soft_edge_verdicts": [ { - "left": "pull_request:40546", - "right": "pull_request:42781", + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Same model family, but different changes: core VibeVoice implementation vs VibeVoice Realtime with additional tokenizer/generation work. Not one mergeable duplicate fix." + }, + { + "left": "pull_request:42781", + "right": "pull_request:46331", + "accept": false, + "reason": "Different models and code paths: VibeVoice Realtime vs Parakeet-RNNT. Shared auto-registration files are not enough to make them duplicates." + }, + { + "left": "pull_request:42781", + "right": "pull_request:46332", "accept": false, - "reason": "Reject: shared VibeVoice files reflect the same model family, but the PRs target different scopes. #40546 adds the core VibeVoice model/docs; #42781 adds VibeVoice Realtime plus an acoustic tokenizer and related generation updates. These are not the same concrete code-path fix and would not plausibly be merged into one duplicate PR." + "reason": "Different model additions: VibeVoice Realtime vs Nemotron ASR Streaming. Similar framework plumbing, but not the same underlying change." + }, + { + "left": "pull_request:46331", + "right": "pull_request:46332", + "accept": false, + "reason": "Both are ASR-related PRs, but they add different models (Parakeet-RNNT vs Nemotron ASR) and cannot plausibly be merged as one duplicate change." } ] }, @@ -18357,7 +18554,7 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "c496363d1b0cf383f6324352f21b6a0d4e9c1bb0eeda23d00d676d63d9126e20", + "prepared_review_unit_hash": "8f53d817d5f4dba7dcdaaa1914200136989df6f0298c3a0d291bb707e574ce20", "component_budget": { "node_count": 2, "item_count": 2, @@ -18379,18 +18576,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are unrelated feature additions: one adds TimesFM covariate forecasting, the other adds DINOv3 image-classification support. They touch different model families, different code paths, and are not duplicates.", - "confidence": 0.99, + "summary": "These are unrelated feature PRs in different model families: TimesFM covariate forecasting vs DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR #41224 is the cleaner representative of the set: it is a focused, concrete model-support addition with code, docs, and tests, whereas PR #40755 is a separate TimesFM feature for an unrelated forecasting capability.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "PR #41224 is the best standalone representative because it is a narrower, well-scoped feature PR with substantial review activity and explicit implementation changes; PR #40755 addresses a different problem domain.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different underlying changes: TimesFM covariate forecasting vs. DINOv3 image-classification support. They do not share the same concrete bug or fixable code path." + "reason": "Different models and different underlying changes: TimesFM covariate forecasting versus DINOv3 image classification support. They do not fix the same bug or implement the same feature and would not plausibly be merged into one PR." } ] }, @@ -18485,7 +18682,7 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "8657413fa3e84caedd9853303cf18fe894d3a6ab9f229ef51728f0334ea07c06", + "prepared_review_unit_hash": "b0bdeafd91ba55db087cae6f713b71e63db99fa56b30bc8197152f3c956a03db", "component_budget": { "node_count": 3, "item_count": 3, @@ -18507,24 +18704,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate model-addition pull requests. They share the same Transformers onboarding boilerplate, but each targets a different model and code path, so the overlap is not a duplicate relationship.", - "confidence": 0.98, + "summary": "These are three unrelated model-addition pull requests (DeepSeek OCR, Isaac, and Kimi2-6). They share the same project-area patterns, but they do not appear to fix or implement the same underlying code path or change set.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 45630 is the broadest and most complete standalone model-addition PR, but it still introduces a different model than the others and is not a duplicate.", + "best_pr_reason": "PR #45630 is the strongest single representative of the cluster because it is the most extensively reviewed and has the broadest integration surface among the three, but it is still not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different models (DeepSeek OCR vs Isaac). Shared files are generic model-registration/docs scaffolding, not the same underlying bug or change." + "reason": "Both are new-model addition PRs, but they target different models and different implementation details; this is shared scaffold, not the same underlying change." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different models (Isaac vs Kimi2-6) with distinct implementation details. Similar onboarding patterns only; not the same code-path fix or mergeable into one PR." + "reason": "These PRs add different model families with distinct files and code paths. Similar auto-mapping/docs updates are not enough to treat them as one fix or one feature." } ] }, @@ -18554,7 +18751,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "0c64c739e9bd75bd30d299025c3deaae3740c33ac79d8412ee89b7e678ccb51b", + "prepared_review_unit_hash": "c9b1f650c64e608ea683a0379e05eacc5e8a57556451853fce505f3ab1fdd305", "component_budget": { "node_count": 2, "item_count": 2, @@ -18576,18 +18773,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two unrelated workflow-maintenance PRs: one targets GitHub Actions Node 24 compatibility, the other bumps Docker/build actions and a few workflow actions to newer releases. They overlap in some workflow files but do not fix the same concrete problem.", - "confidence": 0.92, + "summary": "Two open PRs both update GitHub Actions versions, but they target different action families and different workflow failure modes: one is a Node 24 compatibility sweep for checkout/cache/upload-artifact, the other upgrades docker/build-push-action in Docker image workflows. They are related maintenance work, not duplicates.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the clearer canonical PR: it has a specific compatibility goal (Node 24) and a coherent set of related action-version updates across workflows.", + "canonical_pr_reason": "PR 42975 is the better canonical representative because it is the broader GitHub Actions compatibility sweep and explicitly addresses the Node 24 compatibility theme across many workflows.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the best representative because its purpose is explicit and narrowly defined, while PR 42976 is a broader version-bump PR with less precise intent.", + "best_pr_reason": "PR 42975 is the strongest overall representative of the cluster since it covers the most central workflow-action compatibility update and has the clearest overarching purpose.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "They both update workflow dependencies, but they address different changes: Node 24 compatibility vs. general/latest-version bumps for Docker actions. Shared workflow filenames alone are not enough to treat them as the same PR." + "reason": "Both are GitHub Actions upgrades, but they change different actions in different workflows (checkout/cache/upload-artifact vs docker/build-push-action) and do not look like the same underlying fix." } ] }, @@ -18624,12 +18821,12 @@ "pull_request:43448|pull_request:45490", "pull_request:43451|pull_request:45490" ], - "prepared_review_unit_hash": "a93fd6513bc29fba50928fc559f5cfcfac27835e8295072944c0daf6837e2e97", + "prepared_review_unit_hash": "7949d6f072fd82a689b0201d531615e0fbf4a3544b51d0ee4233f4029c2e8692", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 14183, + "serialized_chars": 14184, "estimated_input_tokens": 3546, "estimated_eval_tokens": 7348 }, @@ -18637,7 +18834,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 14183, + "serialized_chars": 14184, "estimated_input_tokens": 3546, "estimated_eval_tokens": 7348 }, @@ -18646,48 +18843,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All six soft pairs are false positives: these are separate model-addition PRs (ViT NEPA, Molmo, Molmo2, CTSM) that share only standard Transformers scaffolding files and docs. They do not appear to fix the same bug or implement the same change.", - "confidence": 0.98, + "summary": "These are four separate model-addition pull requests, not duplicates. They overlap only on shared infrastructure and docs registry files, but each introduces a different model family and distinct code paths.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR 43451 is the broadest and most active representative of the cluster, but it is still a distinct Molmo2 model-addition PR rather than a duplicate of the others.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "PR 43451 is the strongest single representative if one must be chosen: it has the most discussion, the widest set of model/processor/video files, and the clearest end-to-end model integration among the set.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "Different model families and codepaths: ViT NEPA vs Molmo. Overlap is limited to generic docs/auto-registry files, not the same underlying change." + "reason": "ViT NEPA vs Molmo are different model families with different implementation files and tests; shared auto/docs files are boilerplate, not the same underlying change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA and Molmo2 are unrelated model additions. Shared files are only common registration/docs plumbing, so they are not duplicate fixes." + "reason": "ViT NEPA and Molmo2 are separate model integrations with different model code, configs, and test suites; they do not fix the same bug or add the same feature." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM target different models and tasks. Similarity is superficial and does not indicate the same bug or mergeable change." + "reason": "ViT NEPA and CTSM are unrelated model additions; the overlap is only in shared registry/documentation files." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are distinct model releases with different implementations; this is not the same concrete code-path problem and should not be merged as duplicates." + "reason": "Molmo and Molmo2 are related in naming but are distinct model families with different files, processors, and support paths; not mergeable as one duplicate PR." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated additions. The shared auto/model docs files are routine boilerplate, not evidence of a duplicate PR." + "reason": "Molmo and CTSM target different models and different code paths, so this is only broad subsystem overlap." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM implement different model integrations with different filenames and targets. They do not look like one underlying fix or feature." + "reason": "Molmo2 and CTSM are separate model additions with distinct implementation and test files; no shared concrete bug/change." } ] }, @@ -18720,52 +18917,52 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "43c55b398643280397f9ab96c17281e01dc574f63f35a57d8e1d4518b74aceb5", + "prepared_review_unit_hash": "564fe1b455a126729c3fc5afbca29d78ca15569bbe5e0d92f8a2479e5ffc1490", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7091, - "estimated_input_tokens": 1773, - "estimated_eval_tokens": 3802 + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7091, - "estimated_input_tokens": 1773, - "estimated_eval_tokens": 3802 + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are not duplicates: one fixes Whisper decoding/tests, one is a test-only/contrived change in CLIP+ViT, and one is a FP8 dequantization/model-loading fix. They target different code paths and should not be clustered together as the same change.", + "summary": "These three PRs are not duplicates of one another: one is a Whisper tokenizer/test fix, one is a dummy test-only change, and one is a broader FP8/dequantization fix. The cluster is heterogeneous, so no soft edges should be merged.", "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44815 is the strongest representative because it contains a coherent, concrete fix across the FP8/model-loading path, while the others are either unrelated or mostly test-only.", + "canonical_pr_reason": "pull_request:44815 is the strongest representative PR: it has a coherent production bug fix with supporting code changes and tests, whereas pull_request:43291 is a narrower Whisper-specific patch and pull_request:43665 is clearly not a real functional fix.", "best_issue_reason": null, - "best_pr_reason": "PR 44815 is the best standalone PR in the set: it addresses a specific implementation bug with real code changes, unlike PR 43665 and the narrower Whisper test fix in PR 43291.", + "best_pr_reason": "pull_request:44815 is the best standalone PR in the set because it addresses a concrete code-path problem with the most complete fix and validation coverage.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Whisper tokenization/test changes are unrelated to the CLIP/ViT test-only patch; no shared bug or mergeable code-path fix." + "reason": "Different areas and different intent: Whisper tokenizer logic vs. placeholder test edits; they do not fix the same underlying bug." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Different subsystems and failure modes: Whisper decoding versus FP8 dequant/model loading. Not the same underlying bug." + "reason": "Both are real fixes, but for unrelated code paths: Whisper decoding/tests vs. FP8 dequantization/model loading in Mistral/finegrained FP8." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "The CLIP/ViT test edits are unrelated to the FP8 dequantization fix; they do not appear to solve the same concrete problem." + "reason": "Not the same change at all; 43665 is dummy test noise, while 44815 is a substantive dequantization fix." } ] }, @@ -18802,12 +18999,12 @@ "pull_request:45932|pull_request:46100", "pull_request:46100|pull_request:46114" ], - "prepared_review_unit_hash": "47f2b8d4661d138ef60a18df6f16fc6e34bf0ab5e1f31ecba27cca77a0e99ba9", + "prepared_review_unit_hash": "183a215021499e64644b8dec0adef24d227a15348e35c7e09d9158f329f1fd1b", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 12259, + "serialized_chars": 12257, "estimated_input_tokens": 3065, "estimated_eval_tokens": 6386 }, @@ -18815,7 +19012,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 5, - "serialized_chars": 12259, + "serialized_chars": 12257, "estimated_input_tokens": 3065, "estimated_eval_tokens": 6386 }, @@ -18824,42 +19021,42 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are unrelated \"don't merge\" / test / CI tinkering PRs with superficial overlap in shared test files. No pair looks like the same underlying fix or change, so this is not a duplicate cluster.", - "confidence": 0.91, + "summary": "This cluster is mostly synthetic \"do not merge\" PRs for CI/test-bot experimentation, but the changes are not duplicates of one another. The only high-overlap pair still edits different code paths and should not be merged together.", + "confidence": 0.78, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR 46114 is the most representative cluster member: it has the broadest synthetic test/CI footprint, touches multiple test files plus CI/config code, and links to the most other items via shared test-harness behavior.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "PR 46114 is the best overall representative because it is the most connected and widest-scoped example of the cluster\u2019s synthetic PRs.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:46114", "accept": false, - "reason": "Shared ViT test-file overlap is incidental; 43488 is about setup/version/dependency tweaks while 46114 is a broad CI/test migration PR with unrelated edits." + "reason": "Both are synthetic test PRs, but they change different things: 43488 is a version/dependency tweak plus a ViT test file, while 46114 is a broader migration/OTEL test harness change." }, { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Different changesets: 43488 touches packaging/versioning and a ViT test, while 43532 rewires workflow/comment CI and testing utilities. Not the same concrete bug or fix." + "reason": "They only overlap on the ViT test file, but the actual changes are unrelated: 43488 adjusts packaging/versioning, while 43532 rewires workflow and test infrastructure for diff display." }, { "left": "pull_request:43532", "right": "pull_request:46114", "accept": false, - "reason": "Both are CI/test-oriented, but they change different paths and goals; 43532 is workflow/comment handling, 46114 is migration/telemetry and assorted test edits." + "reason": "Both are CI/test harness experiments, but they target different code paths and purposes; they are not the same concrete fix/change." }, { "left": "pull_request:45932", "right": "pull_request:46100", "accept": false, - "reason": "Despite both touching testing, 45932 spans workflow/model implementation changes, while 46100 only injects failing assertions in ViT tests. Not mergeable as one fix." + "reason": "Even though both are synthetic test PRs, 45932 changes CI, model code, and multiple model files, while 46100 only adds failing assertions in ViT tests." }, { "left": "pull_request:46100", "right": "pull_request:46114", "accept": false, - "reason": "The shared ViT test file is not enough; 46100 is a tiny test-only prank, while 46114 is a broader CI/model/test migration PR with different intent." + "reason": "Shared test-file overlap is not enough here: 46100 is a small ViT test migration, whereas 46114 is a much broader CI/test and utility change." } ] }, @@ -18889,12 +19086,12 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "32a94e5b464e69e150e315eb2e18222da60baef14b579437efefbd9e1f322cec", + "prepared_review_unit_hash": "5c641370d61b2db88083c5d3d3effe7dd3a22cc9875c0b1cc69de23443d36e04", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -18902,7 +19099,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6082, + "serialized_chars": 6083, "estimated_input_tokens": 1521, "estimated_eval_tokens": 3298 }, @@ -18911,18 +19108,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two distinct PRs adding different segmentation pipelines: one for promptable concept segmentation and one for promptable visual segmentation. They share some docs/registry plumbing, but they target different features and code paths, so they should not be clustered as duplicates.", - "confidence": 0.95, + "summary": "These are related segmentation feature PRs, but they are not duplicates: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation with different model integrations and tests. The overlap is mostly shared docs/registry plumbing.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43613 is the broader and more reusable representative of the segmentation-pipeline additions, with more model integrations and tests, but it is still a separate feature from #43612 rather than a duplicate.", + "canonical_pr_reason": "No canonical PR for a duplicate cluster: the two PRs target different pipeline features and different concrete code paths.", "best_issue_reason": null, - "best_pr_reason": "PR #43613 is the best single representative of this cluster because it is the more expansive pipeline addition and touches the widest set of related files, though it is not interchangeable with #43612.", + "best_pr_reason": "Neither PR is a good global duplicate representative because they solve different feature gaps; 43613 is broader, but it is still a separate change from 43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different concrete features: concept segmentation vs visual segmentation. They share framework/docs scaffolding, but the pipeline names, task docs, model integrations, and tests target different code paths and would not plausibly be merged into one PR." + "reason": "Different underlying features and code paths: concept segmentation vs visual segmentation. Shared documentation and registry files are incidental and not enough to merge as duplicates." } ] }, @@ -18952,40 +19149,40 @@ "soft_pairs": [ "pull_request:43649|pull_request:46301" ], - "prepared_review_unit_hash": "16cb215b6ebc87e1c9ca832bb5fceb8b75b555b7c5754fa9034d9600771675d9", + "prepared_review_unit_hash": "b2cd26ed2bdfdebe9a4cf51651b9622e1f26b00fde5f6d0b3482814eea5cd5d1", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4550, - "estimated_input_tokens": 1138, - "estimated_eval_tokens": 2532 + "serialized_chars": 4652, + "estimated_input_tokens": 1163, + "estimated_eval_tokens": 2582 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4550, - "estimated_input_tokens": 1138, - "estimated_eval_tokens": 2532 + "serialized_chars": 4652, + "estimated_input_tokens": 1163, + "estimated_eval_tokens": 2582 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are unrelated and should not be treated as duplicates: one is about CI/self-comment reporting workflows, while the other changes CircleCI test selection and tensor-parallel test code.", - "confidence": 0.94, + "summary": "The two PRs are not duplicates: one updates failure-reporting/CI automation, while the other injects test failures and adjusts CircleCI test selection. They overlap on a ViT test file, but they do not appear to fix the same underlying bug or implement the same change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43649 is the clearer representative: it has a substantive, specific title and a coherent CI/reporting change, whereas #46301 is a vague 'check' PR focused on different test infrastructure.", + "canonical_pr_reason": "PR 43649 is the better canonical representative because it has a clear, substantive failure-reporting/CI workflow change and broader scope; PR 46301 is a narrow test-injection/check change with different intent.", "best_issue_reason": null, - "best_pr_reason": "PR #43649 is the better standalone representative because it is more clearly scoped and described; #46301 is too generic and addresses a separate code path.", + "best_pr_reason": "PR 43649 is the strongest standalone PR in the cluster due to its clearer purpose, larger implementation footprint, and direct relation to CI/failure reporting rather than an isolated test modification.", "soft_edge_verdicts": [ { "left": "pull_request:43649", "right": "pull_request:46301", "accept": false, - "reason": "Different underlying changes: #43649 edits workflow/reporting logic and test utilities, while #46301 changes CircleCI job markers and tensor-parallel test handling. They do not appear mergeable into one fix." + "reason": "Reject: the shared ViT filename is incidental. 43649 changes self-comment/scheduled CI and failure-reporting utilities, while 46301 changes CircleCI markers and adds deliberate failing assertions in tests. They do not target the same concrete code-path problem and would not plausibly merge into one PR." } ] }, @@ -19015,7 +19212,7 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "f3fac0e6eb0cf3a88463c46fd3d41ac03db7efca325eb5cccf2c8ed5e84ee49c", + "prepared_review_unit_hash": "2dd7cc13e06264d55a5f0772c587ca6e1c63742190a7e49aa9161bdb187f69f9", "component_budget": { "node_count": 2, "item_count": 2, @@ -19037,18 +19234,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both items are open PRs touching `trainer.py`, but they address different extension points: gradient-accumulation loss scaling vs. signature-column filtering. They are not the same underlying change.", - "confidence": 0.97, + "summary": "The two open PRs both touch `src/transformers/trainer.py`, but they address different trainer extensibility points: one changes gradient-accumulation loss scaling, the other adds a hook for signature-column filtering. They are not the same underlying change.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: 43651 changes training loss scaling behavior, while 43663 changes input column filtering; they solve different problems in different code paths.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "If a single representative had to be chosen, 43651 is the more self-contained trainer behavior change, but it does not subsume 43663 and this cluster should not be collapsed around it.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Different concrete code paths and behaviors: one changes loss scaling during training steps, the other refactors model signature inspection for dataset column filtering. Shared file/subsystem alone is not enough to treat them as duplicates." + "reason": "Different features in `Trainer`: 43651 adds a loss-scaling hook for gradient accumulation, while 43663 adds a signature-column override for dataset filtering. They are independently mergeable and not the same bug/change." } ] }, @@ -19078,7 +19275,7 @@ "soft_pairs": [ "pull_request:43656|pull_request:43842" ], - "prepared_review_unit_hash": "2ca0ca98a53061574d96da0e5c557607ff037d3b9f4293d59b8cbdf28d21bc73", + "prepared_review_unit_hash": "935460f30b107192d9f9dad46c09b25246c839951a4b849e9e3419cd6e9f7c85", "component_budget": { "node_count": 2, "item_count": 2, @@ -19100,18 +19297,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch the same CLI file and both mention TypeAdapter, but they appear to fix different annotation/runtime issues rather than the same underlying bug.", - "confidence": 0.84, + "summary": "Two PRs in the same CLI module, but they target different TypeAdapter-related failure modes: one is a general NameError fix, the other is specifically about running without pydantic installed.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the patches address different failure modes in `src/transformers/cli/serve.py`.", + "canonical_pr_reason": "PR 43656 is the more central representative: it is earlier, has more discussion, and directly targets the base TypeAdapter CLI NameError.", "best_issue_reason": null, - "best_pr_reason": "PR 43842 is the more directly targeted fix for the concrete `TypeAdapter` NameError when `pydantic` is unavailable.", + "best_pr_reason": "PR 43656 is the best single representative for the cluster because it has the broader bug report and the stronger review/discussion signal.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Reject: 43656 focuses on `__future__` annotations and typing cleanup, while 43842 explicitly guards the `TypeAdapter` import for the no-pydantic case. Same file, but not the same concrete bug or mergeable fix." + "reason": "Reject: same file and symbol, but different concrete bugs. 43656 fixes the CLI TypeAdapter NameError generally; 43842 fixes the pydantic-optional import path. They are not the same underlying change and shouldn\u2019t be merged as duplicates." } ] }, @@ -19264,8 +19461,8 @@ "pull_request:44017|pull_request:44161", "pull_request:44017|pull_request:44073", "pull_request:44068|pull_request:44071", - "pull_request:44071|pull_request:44086", "pull_request:43997|pull_request:44073", + "pull_request:44071|pull_request:44086", "pull_request:44017|pull_request:44071", "pull_request:44073|pull_request:44101", "pull_request:44059|pull_request:44071", @@ -19274,7 +19471,7 @@ "pull_request:44056|pull_request:44101", "pull_request:44059|pull_request:44068", "pull_request:44101|pull_request:44161", - "pull_request:44017|pull_request:44018", + "pull_request:43997|pull_request:44017", "pull_request:43997|pull_request:44056", "pull_request:44071|pull_request:44076", "pull_request:44074|pull_request:44101", @@ -19303,364 +19500,358 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "8f72a6d50bde5850c553d6d784d7c890744dcc6b4fa1a66332d1e7ec4a1c8f90", + "prepared_review_unit_hash": "0c2182ac47925b7bf2946b5ac85860ff21144cc20914d95779c6b577b1df27c5", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84902, - "estimated_input_tokens": 21226, - "estimated_eval_tokens": 42708 + "serialized_chars": 84890, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75097, - "estimated_input_tokens": 18775, - "estimated_eval_tokens": 37806 + "serialized_chars": 75087, + "estimated_input_tokens": 18772, + "estimated_eval_tokens": 37800 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a broad family of model-specific output-tracing refactors, not duplicates of one another. The only strong duplicate-ish overlaps are within GPT-J and GPT-Neo; the rest target different model code paths and should stay separate.", - "confidence": 0.91, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the clearest representative of the GPT-J output-tracing refactor: it targets the same concrete code path as the other GPT-J variants, has an explicit tracking issue, and includes the related CodeGen copy as well.", - "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the best overall representative because it is the most complete/explicit instance of the shared GPT-J tracing refactor and most clearly captures the intended standardized decorator-based change.", + "summary": "This cluster is mostly a set of model-specific refactors around the shared standardized output-tracing initiative tracked by #43979. Most PRs are parallel implementations for different architectures, not true duplicates; the only clear duplicate-like pairs are within the GPT-Neo and GPT-J refactor branches.", + "confidence": 0.88, + "canonical_issue_reason": "Issue #43979 is the common umbrella tracker explicitly referenced by many of the PRs and matches the shared standardized output-tracing refactor theme.", + "canonical_pr_reason": "PR #44722 is the strongest representative of the cluster: it explicitly targets #43979 and covers the same standardized output-tracing migration across the closely related GPT-J/CodeGen code paths.", + "best_issue_reason": "#43979 is the only clear shared issue target and best captures the underlying initiative that ties the cluster together.", + "best_pr_reason": "#44722 is the most complete and representative PR in the cluster, with explicit issue linkage and concrete changes to the core GPT-J/CodeGen tracing path.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families (CVT/FNet vs GPT-J); same tracking issue alone is not enough." + "reason": "Same umbrella refactor theme, but CVT/FNet and GPT-J are different model code paths and not a single duplicate change." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different model families and different code paths; only the broader output-tracing theme overlaps." + "reason": "Different model families (CVT/FNet vs DeBERTaV2); too broad to treat as the same change." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Same GPT-J output-tracing refactor on the same concrete code path; one PR is effectively a broader/superset variant." + "reason": "Both are GPT-J output-tracing refactors on the same underlying code path; one is broader, but the GPT-J change is the same kind of fix." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet vs EfficientNet are separate model implementations, so this is not the same fix." + "reason": "RegNet/ResNet and EfficientNet are separate implementations; same initiative, not the same bug/change." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "Different model code paths (EfficientNet vs GPT-J/CodeGen); shared refactor style is too broad to merge as duplicates." + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated model paths despite sharing the umbrella issue." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen vs EfficientNet; unrelated concrete changes." + "reason": "GPT-J/CodeGen output tracing and EfficientNet output tracing are different concrete refactors." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTa are unrelated model paths." + "reason": "MobileNetV2 and DeBERTaV2 are separate model implementations; not a duplicate." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen vs MGP-STR; same high-level pattern only." + "reason": "GPT-J/CodeGen vs MGP-STR are different architectures and cannot be merged as one concrete fix." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen vs MPT; different implementation targets." + "reason": "GPT-J/CodeGen and MPT are different code paths; same theme only." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Both are GPT-Neo output-tracing refactors for the same model/code path; these look like duplicate or superseding versions." + "reason": "Both PRs refactor the same GPT-Neo output-tracing code path, so they look like duplicate implementations of the same change." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; same initiative, different model path." + "reason": "GPT-Neo and GPT-J/CodeGen are different model families; not the same underlying change." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen vs GPT-Neo; not the same underlying change." + "reason": "GPT-J/CodeGen vs GPT-Neo are separate model refactors, not one duplicate PR." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet vs GPT-J/CodeGen; only the output-tracing theme overlaps." + "reason": "ResNet and GPT-J/CodeGen are unrelated concrete code paths." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J are separate code paths." + "reason": "MGP-STR and GPT-J/CodeGen are different model implementations." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet vs GPT-J; unrelated concrete change." + "reason": "ResNet and GPT-J are different architectures; same umbrella issue does not make them duplicates." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo vs ResNet are unrelated model implementations." + "reason": "GPT-Neo and ResNet are unrelated model refactors." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet vs MPT; different code paths." + "reason": "ResNet and MPT are separate code paths, so this is not a duplicate change." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo vs Flaubert; same refactor style, different model." + "reason": "GPT-Neo and Flaubert are different model families; shared topic only." }, { - "left": "pull_request:44071", - "right": "pull_request:44076", + "left": "pull_request:44018", + "right": "pull_request:44116", "accept": false, - "reason": "MPT vs ImageGPT; not the same concrete bug/change." + "reason": "GPT-Neo and Flaubert are distinct concrete implementations." }, { - "left": "pull_request:44074", - "right": "pull_request:44101", + "left": "pull_request:44068", + "right": "pull_request:44722", "accept": false, - "reason": "TextNet vs Flaubert/XLM; different model paths." + "reason": "GPT-Neo and GPT-J/CodeGen are separate refactors." }, { - "left": "pull_request:44017", + "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "Segformer vs GPT-J/CodeGen; only the tracking-theme overlaps." + "reason": "MPT and GPT-J/CodeGen are different code paths and not mergeable as one PR." }, { - "left": "pull_request:44017", - "right": "pull_request:44161", + "left": "pull_request:44018", + "right": "pull_request:44085", "accept": false, - "reason": "Segformer vs LongT5; different implementations." + "reason": "GPT-Neo vs GPT-J are different model branches; not the same underlying change." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:44018", + "right": "pull_request:44086", "accept": false, - "reason": "Segformer vs VisualBert; not the same fix." + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." }, { - "left": "pull_request:44073", - "right": "pull_request:44101", + "left": "pull_request:44068", + "right": "pull_request:44086", "accept": false, - "reason": "VisualBert vs Flaubert/XLM; different code paths." + "reason": "GPT-Neo and MGP-STR are different concrete changes." }, { - "left": "pull_request:44059", - "right": "pull_request:44086", + "left": "pull_request:44098", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-2 vs MGP-STR; unrelated model paths." + "reason": "ViLT and XLM/Flaubert are separate model code paths." }, { - "left": "pull_request:44059", - "right": "pull_request:44071", + "left": "pull_request:44017", + "right": "pull_request:44161", "accept": false, - "reason": "GPT-2 vs MPT; different concrete changes." + "reason": "Segformer and LongT5 are different models; same issue target is not enough to merge them." }, { - "left": "pull_request:44068", - "right": "pull_request:44722", + "left": "pull_request:44017", + "right": "pull_request:44073", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; same refactor family, different model." + "reason": "Segformer and VisualBERT are distinct implementations." }, { - "left": "pull_request:44071", - "right": "pull_request:44722", + "left": "pull_request:43997", + "right": "pull_request:44073", "accept": false, - "reason": "MPT vs GPT-J/CodeGen; different code paths." + "reason": "RegNet and VisualBERT are unrelated concrete refactors." }, { - "left": "pull_request:44085", - "right": "pull_request:44086", + "left": "pull_request:44056", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-J vs MGP-STR; not the same change." + "reason": "MPNet and Flaubert are different model paths." }, { - "left": "pull_request:44098", - "right": "pull_request:44101", + "left": "pull_request:44059", + "right": "pull_request:44086", "accept": false, - "reason": "ViLT vs Flaubert/XLM; different models and code paths." + "reason": "GPT-2 and MGP-STR are not the same bug/change." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:44098", + "right": "pull_request:44161", "accept": false, - "reason": "Segformer vs VisualBert; unrelated concrete changes." + "reason": "ViLT and LongT5 are different model refactors." }, { - "left": "pull_request:44010", + "left": "pull_request:44059", "right": "pull_request:44071", "accept": false, - "reason": "SqueezeBERT vs MPT; not the same bug/change." + "reason": "GPT-2 and MPT are separate code paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44073", + "left": "pull_request:44085", + "right": "pull_request:44086", "accept": false, - "reason": "SqueezeBERT vs VisualBert; different code paths." + "reason": "GPT-J and MGP-STR are different model implementations." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44018", + "right": "pull_request:44059", "accept": false, - "reason": "RegNet vs GPT-Neo; only the output-tracing initiative overlaps." + "reason": "GPT-Neo and GPT-2 are distinct model families; not a duplicate." }, { - "left": "pull_request:43997", - "right": "pull_request:44056", + "left": "pull_request:44073", + "right": "pull_request:44161", "accept": false, - "reason": "RegNet vs MPNet; different model-specific refactors." + "reason": "VisualBERT and LongT5 are unrelated concrete changes." }, { - "left": "pull_request:43997", - "right": "pull_request:44161", + "left": "pull_request:44056", + "right": "pull_request:44068", "accept": false, - "reason": "RegNet vs LongT5; not the same concrete change." + "reason": "MPNet and GPT-Neo are different model paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44059", + "right": "pull_request:44722", "accept": false, - "reason": "RegNet vs TextNet; separate code paths." + "reason": "GPT-2 and GPT-J/CodeGen are separate refactors." }, { - "left": "pull_request:44018", - "right": "pull_request:44085", + "left": "pull_request:44017", + "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo vs GPT-J; same family of refactors, but not the same model path." + "reason": "Segformer and MPT are unrelated model implementations." }, { - "left": "pull_request:44018", + "left": "pull_request:44056", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo vs MGP-STR; unrelated concrete changes." + "reason": "MPNet and MGP-STR are different concrete code paths." }, { - "left": "pull_request:44071", - "right": "pull_request:44161", + "left": "pull_request:44073", + "right": "pull_request:44101", "accept": false, - "reason": "MPT vs LongT5; different model paths." + "reason": "VisualBERT and Flaubert are separate model refactors." }, { - "left": "pull_request:44059", - "right": "pull_request:44722", + "left": "pull_request:43997", + "right": "pull_request:44017", "accept": false, - "reason": "GPT-2 vs GPT-J/CodeGen; not the same underlying fix." + "reason": "RegNet and Segformer are different architectures; not duplicates." }, { - "left": "pull_request:44018", - "right": "pull_request:44019", + "left": "pull_request:44074", + "right": "pull_request:44101", "accept": false, - "reason": "GPT-Neo vs ResNet; unrelated models." + "reason": "TextNet and Flaubert/XLM are different model code paths." }, { - "left": "pull_request:44059", - "right": "pull_request:44068", + "left": "pull_request:43996", + "right": "pull_request:44161", "accept": false, - "reason": "GPT-2 vs GPT-Neo; same pattern, different code paths." + "reason": "CVT/FNet and LongT5 are unrelated concrete refactors." }, { - "left": "pull_request:44019", - "right": "pull_request:44154", + "left": "pull_request:43996", + "right": "pull_request:44017", "accept": false, - "reason": "ResNet vs Vits; different concrete implementations." + "reason": "CVT/FNet and Segformer are different model implementations." }, { - "left": "pull_request:44044", - "right": "pull_request:44129", + "left": "pull_request:44010", + "right": "pull_request:44044", "accept": false, - "reason": "DeBERTa vs SpeechT5; separate model code paths." + "reason": "SqueezeBERT and DeBERTaV2 are distinct model paths." }, { "left": "pull_request:44044", - "right": "pull_request:44154", + "right": "pull_request:44074", "accept": false, - "reason": "DeBERTa vs Vits; not the same change." + "reason": "DeBERTaV2 and TextNet are unrelated concrete changes." }, { - "left": "pull_request:43996", - "right": "pull_request:44129", - "accept": false, - "reason": "CVT/FNet vs SpeechT5; unrelated concrete fixes." + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same underlying GPT-J/CodeGen standardized tracing refactor; the broader PR is a plausible superset of the same change." }, { - "left": "pull_request:44056", - "right": "pull_request:44161", - "accept": false, - "reason": "MPNet vs LongT5; different model paths." + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both center on the GPT-J tracing refactor, and the changes are close enough to be merged into one PR." }, { - "left": "pull_request:44056", - "right": "pull_request:44101", + "left": "pull_request:44085", + "right": "pull_request:44129", "accept": false, - "reason": "MPNet vs Flaubert/XLM; only the tracing refactor theme is shared." + "reason": "GPT-J and SpeechT5 are different model families; shared issue target only." }, { - "left": "pull_request:44019", - "right": "pull_request:44071", + "left": "pull_request:43996", + "right": "pull_request:44007", "accept": false, - "reason": "ResNet vs MPT; different concrete changes." + "reason": "FNet/CVT and RegNet/ResNet are different model code paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44044", + "left": "pull_request:43996", + "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBERT vs DeBERTa; unrelated implementations." + "reason": "FNet/CVT and SpeechT5 are unrelated concrete refactors." }, { "left": "pull_request:44044", - "right": "pull_request:44074", - "accept": false, - "reason": "DeBERTa vs TextNet; different model paths." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44086", + "right": "pull_request:44129", "accept": false, - "reason": "MPT vs MGP-STR; not the same underlying bug/change." + "reason": "DeBERTaV2 and SpeechT5 are different implementations." }, { - "left": "pull_request:44056", - "right": "pull_request:44074", + "left": "pull_request:44044", + "right": "pull_request:44154", "accept": false, - "reason": "MPNet vs TextNet; separate model-specific refactors." + "reason": "DeBERTaV2 and ViTS are separate model paths." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative: it correctly characterizes most items as separate model-specific output-tracing refactors, and the only accepted soft pairs are plausible duplicate/superset variants within GPT-J and GPT-Neo. I did not see an overstated mergeability claim in the accepted pairs." + "feedback": "The summary is well grounded in the packet: #43979 is the common umbrella issue, and #44722 is a reasonable canonical PR because it\u2019s the most complete GPT-J/CodeGen representative with explicit issue linkage. The soft-edge verdicts are conservative overall and the accepted pairs do look mergeable as single PRs for the same GPT-Neo / GPT-J-style output-tracing refactors." }, "evaluator_used": true, "retried": false, @@ -19698,70 +19889,70 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "96b70376cff42be79e8f1c3255d97ec6c62a7028b6597f06649e7d82937e99e2", + "prepared_review_unit_hash": "efb78bb485eac13b17d9360a03914340d7d48cc06ac6624cea0a43064c6630fc", "component_budget": { "node_count": 28, "item_count": 28, "soft_pair_count": 78, - "serialized_chars": 84902, - "estimated_input_tokens": 21226, - "estimated_eval_tokens": 42708 + "serialized_chars": 84890, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 }, "budget": { "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17126, - "estimated_input_tokens": 4282, - "estimated_eval_tokens": 8820 + "serialized_chars": 17124, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These PRs are all model-specific refactors toward standardized output tracing/capture, but they affect different code paths and should not be merged as duplicates. The cluster is thematically related, not a true duplicate set.", - "confidence": 0.91, + "summary": "These PRs are thematically similar but are model-specific refactors for standardized output tracing/capture across different code paths. They are not duplicates and should not be merged together.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "44129 is the strongest single representative because it has an explicit issue target and a fuller, self-contained output-tracing refactor; however, it is still model-specific and not a duplicate of the others.", + "canonical_pr_reason": "PR 44129 is the clearest anchor for the cluster: it has an explicit issue link, a well-scoped standardized output-capture refactor, and a concrete model-specific code-path change.", "best_issue_reason": null, - "best_pr_reason": "No single PR is a good duplicate target for the whole cluster. If one must be picked as the most representative change, 44129 is the closest because of its explicit issue link and broader implementation detail.", + "best_pr_reason": "PR 44129 is the best representative of the overall theme because it is the most explicitly justified and most concrete standardized output tracing change among the set.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are standardized output-capture refactors, but they touch different models and different implementation paths. Same theme, not the same underlying bug/change." + "reason": "Both are output-capture refactors, but for different models (FocalNet vs ImageGPT) with separate implementation paths; not the same underlying fix." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "VisualBert and TextNet are separate model implementations with separate forward/output plumbing. They are related refactors, not a single duplicate fix." + "reason": "Both touch standardized output tracing, but one is VisualBert and the other is TextNet; these are distinct model-specific changes, not one shared bug." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert have different model-specific output-tracing code paths. Shared decorator usage is too broad to treat as a duplicate." + "reason": "MPNet and VisualBert are different model implementations; the refactors follow the same pattern but do not fix the same concrete code-path problem." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are distinct model refactors in different files and code paths; they do not appear to fix the same concrete problem." + "reason": "Different models and different forward/output plumbing; similarity is only at the refactor pattern level, which is too broad for duplicate acceptance." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model implementations. Both migrate output handling, but not the same code-path bug or change." + "reason": "RegNet and SqueezeBert are unrelated model code paths; both are output-tracing refactors, but not the same underlying change." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "Both touch output-tracing standardization, but for different models and different internal logic. The overlap is thematic rather than duplicate." + "reason": "SqueezeBert and SpeechT5 are distinct implementations; the shared theme is standardized output capture, but the concrete fixes are not the same." } ] }, @@ -19840,100 +20031,94 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "cbd8cae8eff134e25d00a60d5ce3b7f156043516e0ca764291d7e76170401d6b", + "prepared_review_unit_hash": "90fc77609ffb16de1cc52f2c35755d2f9a5a10755ad4cd667d1f450b6a00a3b1", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39789, - "estimated_input_tokens": 9948, - "estimated_eval_tokens": 20152 + "serialized_chars": 39786, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39789, - "estimated_input_tokens": 9948, - "estimated_eval_tokens": 20152 + "serialized_chars": 39786, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster is a batch of similar-looking output-tracing refactors across unrelated model implementations. They share a theme, but not the same concrete bug/change, so the soft pairs should be treated as non-duplicates. No issues are present; PR 44025 is the best representative because it is the broadest multi-file example in the group.", - "confidence": 0.43, + "summary": "These PRs all share a broad \u201coutput tracing / can_return_tuple\u201d refactor theme, but they target different model implementations and code paths, so they are not duplicates. PR 44003 is the strongest representative because it spans two closely related mamba-family files and adds the most concrete tracing plumbing.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is the best canonical representative because it is a substantive multi-file output-tracing refactor in the same style as the rest of the cluster, making it the most central exemplar of the batch.", + "canonical_pr_reason": "PR 44003 is the most central and substantive representative: it updates both falcon_mamba and mamba, adds output-capture plumbing, and is broader than the single-model refactors.", "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the strongest overall representative of the cluster: broader than the single-model refactors and clearly part of the same output-tracing cleanup pattern.", + "best_pr_reason": "44003 is the best overall representative for the cluster because it is the broadest concrete implementation change rather than a narrow one-file refactor.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different models and code paths; only the refactor theme is shared." + "reason": "Same refactor theme, but timm_backbone and UperNet are different model code paths." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Unrelated model implementations; same high-level tracing cleanup only." + "reason": "Both are output-tracing refactors, but timm_backbone and vision_text_dual_encoder are unrelated implementations." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different subsystems with no shared concrete bug or change." + "reason": "Different models and behavior: timm_backbone vs UnivNet." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Different model families; similar output-tracing refactor pattern only." - }, - { - "left": "pull_request:43998", - "right": "pull_request:44004", - "accept": false, - "reason": "No shared code path; both are just output-tracing refactors." + "reason": "Different subsystems: timm_backbone refactor versus mamba/falcon_mamba tracing changes." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures and files; only the refactor theme overlaps." + "reason": "Both touch tracing helpers, but timm_backbone and rwkv are distinct model paths." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "Mobilenet and UnivNet are unrelated; no same underlying change." + "reason": "Different model families: MobileNetV1 vs UnivNet." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths; shared theme is too broad." + "reason": "Different code paths: MobileNetV1 versus UperNet." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Different models and outputs; not the same fix." + "reason": "MobileNetV1 and Depth Anything are separate models; similar refactor only." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "No common concrete bug; only similar refactoring style." + "reason": "Different implementations: MobileNetV1 versus VisionEncoderDecoder." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Distinct encoder-decoder stack vs Mobilenet; not duplicates." + "reason": "Different models and forward paths: MobileNetV1 vs SpeechEncoderDecoder." }, { "left": "pull_request:44000", @@ -19945,169 +20130,169 @@ "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different models; same output-tracing umbrella is not enough." + "reason": "Different models: vision-text dual encoder versus UperNet." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Separate model families; no plausible single merged PR." - }, - { - "left": "pull_request:44000", - "right": "pull_request:44004", - "accept": false, - "reason": "CodeGen and vision-text dual encoder are unrelated implementations." + "reason": "Same umbrella refactor idea, but vision-text dual encoder and mamba/falcon_mamba are different implementations." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Different tasks and model families; only superficial similarity." + "reason": "Different model families: vision-text dual encoder vs Depth Anything." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are different models with different code paths." + "reason": "UnivNet and UperNet are different models and cannot be merged as one fix." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "No shared concrete bug; only the output-tracing refactor motif." + "reason": "Different concrete code paths: UnivNet versus mamba/falcon_mamba." }, { "left": "pull_request:44001", - "right": "pull_request:44004", + "right": "pull_request:44025", "accept": false, - "reason": "Different model implementations; not the same change." + "reason": "Different models: UnivNet and Depth Anything." }, { - "left": "pull_request:44001", - "right": "pull_request:44025", + "left": "pull_request:44002", + "right": "pull_request:44029", "accept": false, - "reason": "Unrelated model families; not mergeable as one fix." + "reason": "UperNet and RWKV are unrelated implementations; only the refactor pattern matches." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Different subsystems and fixes; similarity is only thematic." + "reason": "Different model code paths: UperNet versus mamba/falcon_mamba." }, { - "left": "pull_request:44002", + "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "UperNet and CodeGen touch different code paths." + "reason": "Different model families: mamba/falcon_mamba vs CodeGen." }, { - "left": "pull_request:44002", - "right": "pull_request:44029", + "left": "pull_request:43998", + "right": "pull_request:44004", "accept": false, - "reason": "Different models; no same underlying bug or change." + "reason": "TimmBackbone and CodeGen are unrelated code paths despite similar tracing refactor wording." }, { - "left": "pull_request:44003", + "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "Falcon/Mamba and CodeGen are unrelated refactors." + "reason": "UnivNet and CodeGen are different model implementations." }, { - "left": "pull_request:43998", + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet and CodeGen are different subsystems with different forward logic." + }, + { + "left": "pull_request:44000", "right": "pull_request:44004", "accept": false, - "reason": "Different model code and behavior; just a common refactor style." + "reason": "Vision-text dual encoder and CodeGen do not fix the same underlying bug." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything and Vision Encoder-Decoder are unrelated changes." + "reason": "Different models: Depth Anything versus VisionEncoderDecoder." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Different model stacks; not the same concrete fix." + "reason": "Different model families: Depth Anything vs SpeechEncoderDecoder." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Depth estimation vs SuperPoint; no shared code path." + "reason": "Depth Anything and SuperPoint are separate code paths." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures; same tracing-cleanup theme only." + "reason": "Different models: Depth Anything versus RWKV." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Distinct model implementations and behavior changes." + "reason": "Depth Anything and DPR are unrelated implementations." }, { "left": "pull_request:44026", - "right": "pull_request:44027", + "right": "pull_request:44029", "accept": false, - "reason": "Vision Encoder-Decoder and Speech Encoder-Decoder are separate stacks." + "reason": "VisionEncoderDecoder and RWKV are different code paths." }, { "left": "pull_request:44026", - "right": "pull_request:44028", + "right": "pull_request:44027", "accept": false, - "reason": "No common bug; unrelated model code." + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are separate, non-duplicate refactors." }, { "left": "pull_request:44026", - "right": "pull_request:44029", + "right": "pull_request:44028", "accept": false, - "reason": "Different models and execution paths; not duplicates." + "reason": "Different models: VisionEncoderDecoder versus SuperPoint." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Unrelated model families; only the refactor pattern matches." + "reason": "VisionEncoderDecoder and DPR are unrelated model implementations." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech Encoder-Decoder and SuperPoint are unrelated." + "reason": "SpeechEncoderDecoder and SuperPoint are different model code paths." }, { "left": "pull_request:44027", - "right": "44029", + "right": "pull_request:44029", "accept": false, - "reason": "Different model code paths; not the same change." + "reason": "Different models: SpeechEncoderDecoder versus RWKV." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Separate subsystems and fixes; no duplicate signal." + "reason": "SpeechEncoderDecoder and DPR are unrelated." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated model implementations." + "reason": "SuperPoint and RWKV are distinct implementations." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different concrete changes in different model families." + "reason": "Different code paths: SuperPoint versus DPR." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR touch different code paths; only the theme overlaps." + "reason": "RWKV and DPR are different model families; similar tracing theme only." } ] }, @@ -20140,7 +20325,7 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "68dd51482b3871793de6008c3e4cae18e18e387d9bfa315b44ca7c185c78e9c1", + "prepared_review_unit_hash": "81e130e1d0d80a0e23cc09526b303e7d61f7ac25ae42abe0cc92c7560b50b646", "component_budget": { "node_count": 3, "item_count": 3, @@ -20162,30 +20347,30 @@ "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 some boilerplate files and auto-registry updates, but they do not fix the same underlying problem or implement the same change.", - "confidence": 0.99, + "summary": "These are three separate model-addition PRs (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS), not duplicates of the same change. They share the common Transformers boilerplate for adding a new model, but each targets a different architecture, fileset, and model-specific code path.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs are for different models and different implementations, so there is no single duplicate to anchor the cluster.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "PR 45075 is the strongest representative only in the sense that it is the most complete/established model-addition PR in the set, but it is not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model families and codepaths: PenguinVL implementation vs Voxtral TTS support. Shared docs/auto-registration are generic model-addition boilerplate, not evidence of a duplicate change." + "reason": "PenguinVL and Voxtral TTS are unrelated model additions with different model-specific files and code paths; shared Transformers registration/docs boilerplate is not enough to treat them as the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Both are new model integrations, but for unrelated models (PenguinVL vs DeepSeek-OCR-2). They touch similar framework plumbing, yet do not represent the same concrete fix or mergeable PR." + "reason": "PenguinVL and DeepSeek-OCR-2 add different models with distinct implementations, converters, and tests; they are not the same underlying bug or feature." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model additions with different filenames, tests, and implementation targets. Similar auto-mapping/docs edits are too broad to treat as duplicates." + "reason": "DeepSeek-OCR-2 and Voxtral TTS are separate model integrations touching different model directories and behavior, so they should not be merged as duplicates." } ] }, @@ -20215,12 +20400,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "2d7f649b02a7d6b6cd77fa94599104f99d452f095e4d8d13424f53dc787fd6cd", + "prepared_review_unit_hash": "7e45a14750b2a56c0f3d28fa579dea054d27e60f3ba1393fccc13fd6d15d38d3", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4408, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -20228,7 +20413,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4408, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -20237,18 +20422,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related to fusion/fused modules, but they target different layers and scopes: #44979 adds a general Module Fusion API, while #45363 implements a specific n-to-1 kernel fusion path via KernelConfig and integration changes. They are not the same underlying change.", - "confidence": 0.91, + "summary": "These are related kernel/module-fusion efforts, but they are not the same change: #44979 introduces a generic Module Fusion API and supporting abstractions, while #45363 wires up n-to-1 kernel fusion through KernelConfig and integrations. They overlap in theme but target different code paths and could not reasonably be merged as one PR.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "#45363 is the more concrete end-user feature: it wires kernel fusion into model loading/execution through KernelConfig and supporting integration code. #44979 is a lower-level API foundation and not the same deliverable.", + "canonical_pr_reason": "#45363 is the more concrete, user-facing implementation of fusion behavior via KernelConfig and integration hooks; #44979 is a broader API scaffold. If one PR must represent the cluster, #45363 is the better anchor for the actual feature path.", "best_issue_reason": null, - "best_pr_reason": "#45363 is the best representative PR for this cluster because it includes the actual end-to-end kernel fusion workflow and example usage, whereas #44979 is only the API groundwork.", + "best_pr_reason": "#45363 is the best representative of the cluster because it adds an end-to-end fusion workflow and touches the runtime integration points, whereas #44979 is mainly foundational API work.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related fusion work, but not the same bug/change: #44979 introduces a generic module fusion API, while #45363 adds n-to-1 kernel fusion through KernelConfig and model integration. They would not be merged as one PR." + "reason": "Both are about fusion, but they implement different layers: #44979 adds a generic Module Fusion API/module abstraction, while #45363 implements n-to-1 kernel fusion via KernelConfig and integration code. They do not appear to fix the same concrete bug or change the same code path, so they should not be merged as duplicates." } ] }, @@ -20278,7 +20463,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "df08bf72d082e49a5a5851c98a54ef19868296f42de40da44a8e12d85606dc08", + "prepared_review_unit_hash": "ebf7b4fa2ca6f4c2abc01bb52a999585046cd198ccfc4a2d67569fbafbeb1579", "component_budget": { "node_count": 2, "item_count": 2, @@ -20300,18 +20485,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs patch the same Mistral regex/pre-tokenizer AttributeError in the same file; 45317 is the more complete version because it includes tests in addition to the code fix.", + "summary": "Two PRs implement the same Mistral regex fix in the same file; the second is a broader version with tests, so they are duplicate/change-equivalent enough to cluster together.", "confidence": 0.98, - "canonical_issue_reason": "Issue 45081 is the shared upstream bug report both PRs target, so it is the natural canonical issue for this cluster.", - "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 and adds test coverage, making it the more complete duplicate/primary patch.", - "best_issue_reason": "No issue artifact is present in the cluster; if selecting by target, 45081 is the shared issue these PRs resolve.", - "best_pr_reason": "45317 is the best PR candidate because it contains the same code-path fix as 45086 plus regression tests, so it is the most merge-ready representative.", + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45317 is the better canonical PR because it contains the same core fix plus test coverage, making it the more complete representation of the change.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45317 is the best PR overall: same concrete bug fix, same touched code path, and it adds tests, so it is the most complete candidate.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Accept: both PRs change the same function in the same file to fix the same AttributeError in _patch_mistral_regex; 45317 is essentially the same fix with added tests." + "reason": "Both PRs patch the same AttributeError in _patch_mistral_regex within tokenization_utils_tokenizers.py and are plausibly mergeable into one PR; the second mainly adds tests." } ] }, @@ -20341,7 +20526,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "9e863ca3f46c0521ac225da19e33936cc52efa8df32ad5c1c65a6f7e262cb6b4", + "prepared_review_unit_hash": "95eec3809039fb2b78fb1468e5aa03da069ada3c59c52ef68db7ca31a4785d20", "component_budget": { "node_count": 2, "item_count": 2, @@ -20363,18 +20548,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related to Nemotron H but address different changes: #45115 is a structural inheritance/refactor to make NemotronH align with GraniteMoeHybrid-style conversion and model wiring, while #45569 splits the family into separate NemotronH Dense/Sparse model docs and implementations. They overlap in files because they both touch the Nemotron H modeling stack, but they are not the same underlying fix/change.", - "confidence": 0.93, + "summary": "Two open NemotronH PRs overlap on the same model family, but they address different changes: one refactors the base NemotronH implementation/conversion mapping, while the other splits NemotronH into dense and sparse variants with docs and tests. They are related, but not duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear duplicate canonical PR: #45569 is the broader family-splitting implementation, but #45115 is a narrower refactor/conversion-mapping update with a different goal.", + "canonical_pr_reason": "PR #45569 is the better canonical PR for the cluster because it is the broader, more complete architectural change: it introduces the dedicated nemotron_h_dense and nemotron_h_sparse implementations, updates auto-mapping/docs, and includes tests, making it the likely end-state of the model refactor.", "best_issue_reason": null, - "best_pr_reason": "#45569 is the most representative PR for the cluster because it makes the larger user-facing architectural change (new Dense/Sparse model split, docs, auto-mappings, and tests).", + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the full user-facing model restructuring, whereas #45115 is a narrower internal refactor focused mainly on inheritance and weight conversion mapping.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Related Nemotron H work, but different concrete changes: #45115 focuses on inheritance/conversion mapping for NemotronH, while #45569 introduces separate NemotronHDense/NemotronHSparse model definitions and docs. Shared files alone are not enough to call them the same fix." + "reason": "Both are about NemotronH, but #45115 is a conversion/inheritance refactor and #45569 is a model-splitting/docs/tests change. They do not appear to fix the same concrete code-path problem and would not be merged as one PR." } ] }, @@ -20404,12 +20589,12 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "8ca345ff352092a16ff2961d9cfa3dd6a601e81791b82cebf5b725872ebdf088", + "prepared_review_unit_hash": "8a3f292571f90166e20a75cb135db5dc387aeb86066b182decd0bb39832f974c", "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 }, @@ -20417,7 +20602,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5397, + "serialized_chars": 5398, "estimated_input_tokens": 1350, "estimated_eval_tokens": 2956 }, @@ -20426,18 +20611,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two PRs are related but not duplicates: #45333 adds foundational per-layer heterogeneous config support, while #45332 builds on that to add heterogeneous modeling/cache behavior. They share files and theme, but they are different concrete changes.", - "confidence": 0.96, + "summary": "Two related but distinct PRs: one adds heterogeneous per-layer configuration support, while the other adds heterogeneous model/cache/runtime support. They overlap in infrastructure files, but they are not the same concrete change.", + "confidence": 0.84, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45333 is the better representative of the shared theme because it introduces the underlying per-layer heterogeneous configuration API that PR #45332 depends on and extends.", + "canonical_pr_reason": "PR 45332 is the broader, more complete feature PR; it includes the model/runtime work and builds on the config plumbing, so it is the better representative for the cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #45333 is the cleanest single representative of the cluster: it focuses on the core config-layer abstraction, whereas #45332 is a broader follow-on that adds modeling behavior.", + "best_pr_reason": "PR 45332 is the strongest standalone candidate because it covers the full heterogeneous-model feature rather than only the configuration layer.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related feature work, but not the same change: #45333 adds per-layer config support, while #45332 adds heterogeneous modeling/cache logic on top of that. They would not plausibly be merged as one duplicate PR." + "reason": "Related feature area, but different scopes: 45333 adds per-layer config support, while 45332 adds heterogeneous model/cache/runtime behavior. They are not the same underlying change and could be merged separately." } ] }, @@ -20467,12 +20652,12 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "0a98bfa5e3eab9bde6ad545efcfac718da7b129989f086d08d304a9d15a3e27b", + "prepared_review_unit_hash": "7aed025656c1f53c4a695c0b7892b5863e754e5d7768873eddb4c35ccaa18d96", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -20480,7 +20665,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5513, + "serialized_chars": 5514, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -20489,18 +20674,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both typing-related PRs, but they target different changes: one is a broad repository-wide type-checking cleanup, while the other adds specific protocol/type definitions to support particular code paths. They overlap in a few files, but do not look like the same underlying fix.", + "summary": "Two separate typing-focused PRs: one is a broad repository-wide type checking sweep, and the other is a narrower typing/helper update around modeling_utils/PEFT. The shared files look incidental, not duplicate work.", "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45425 is the more concrete change: it adds explicit typing/protocol support in _typing.py and related call sites/tests. PR 45415 is a broad type-checking sweep across many files and looks more like a separate cleanup pass than the same fix.", + "canonical_pr_reason": "PR 45415 is the broader, more representative cluster item: it changes type-checking config and touches many transformers modules in one sweep.", "best_issue_reason": null, - "best_pr_reason": "PR 45425 is the best representative of the cluster\u2019s substantive typing work because it introduces specific type abstractions and targeted code changes. PR 45415 is broader and more mechanical, so it is less suitable as the canonical representative for this pair.", + "best_pr_reason": "PR 45415 best represents the cluster because it is the largest and most central typing-related change, while 45425 is a narrower follow-up-style helper update.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared files and a type-checking theme are not enough: 45415 is a broad pyproject/type-checking sweep across many modules, while 45425 adds specific typing protocols and support for modeling_utils/PEFT-related code paths. They could be merged independently and do not fix the same concrete bug/change." + "reason": "They overlap on typing-related files, but they do not appear to fix the same concrete code-path problem. 45415 is a broad type-checking pass across many modules plus pyproject config, while 45425 adds typing protocols/helpers for modeling_utils and PEFT-related code. Not mergeable as one duplicate PR." } ] }, @@ -20530,12 +20715,12 @@ "soft_pairs": [ "pull_request:45513|pull_request:46084" ], - "prepared_review_unit_hash": "30f04877b6f90e78283595dbffabbbdd1ed211e8081280a20392e7ddfecc048f", + "prepared_review_unit_hash": "1129b193d63acb2335b696944d7bba2a433cb7ee8a225c4890fae36f7c9b8862", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4857, + "serialized_chars": 4858, "estimated_input_tokens": 1215, "estimated_eval_tokens": 2686 }, @@ -20543,7 +20728,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4857, + "serialized_chars": 4858, "estimated_input_tokens": 1215, "estimated_eval_tokens": 2686 }, @@ -20552,18 +20737,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are unrelated PRs: 45513 fixes cached multi-token forward for Qwen3.5/Qwen3-next/OlmoHybrid GDN linear attention, while 46084 fixes Mamba2 cache handling when seq_len > 1. They share a broad caching symptom but not the same code path or bug.", + "summary": "These are not duplicates: both are cache-related PRs, but they target different model families and different failure modes. PR #45513 fixes multi-token cached forward behavior in OLMo/Qwen3 variants for GDN linear attention, while PR #46084 fixes Mamba2 use_cache handling when seq_len > 1. They should be triaged separately.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: they target different model families and different cache/forward implementations.", + "canonical_pr_reason": "PR #46084 is the cleaner representative: it has an explicit issue target, a narrowly scoped fix, and a direct code-path description for the seq_len > 1 cache bug.", "best_issue_reason": null, - "best_pr_reason": "Neither PR is a global best for the cluster because they are not duplicates; 46084 is more focused and has an explicit issue link, but it fixes a separate Mamba2 bug.", + "best_pr_reason": "PR #46084 is the best standalone PR in this cluster because it is more specific, explicitly tied to issue #46032, and fixes one concrete cache path rather than spanning several model files.", "soft_edge_verdicts": [ { "left": "pull_request:45513", "right": "pull_request:46084", "accept": false, - "reason": "Reject: the overlap is only a generic cached-forward/seq_len>1 theme. The PRs touch different models, different kernels, and different concrete failure modes, so they are not the same underlying change." + "reason": "Both are about cached forward execution, but they fix different model implementations and different underlying bugs. #45513 changes OLMo/Qwen3-family linear attention behavior for multi-token cached continuation; #46084 changes Mamba2 cache handling when seq_len > 1. They are not the same change and could not plausibly be merged into one PR." } ] }, @@ -20593,12 +20778,12 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "f0d0702991fc73e450e35c6acffc6f90b2262d08aae3f3d2d07b95fed39086fa", + "prepared_review_unit_hash": "a357636a21a7f9232be0aec2f8d4225a5f358197734f075610ecc8de397e6bef", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4508, + "serialized_chars": 4507, "estimated_input_tokens": 1127, "estimated_eval_tokens": 2510 }, @@ -20606,7 +20791,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4508, + "serialized_chars": 4507, "estimated_input_tokens": 1127, "estimated_eval_tokens": 2510 }, @@ -20615,18 +20800,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both touch transformer model loading and expert-parallel code, but they address different bugs: one fixes EP + DeepSpeed ZeRO-3 loading via accelerate/serialization, the other fixes experts being overwritten during FSDP2 load/broadcast. They are related in subsystem, not duplicates.", - "confidence": 0.91, + "summary": "These are both EP-related PRs, but they address different bugs: #45548 fixes EP + DeepSpeed ZeRO-3 loading under `accelerate launch`, while #45662 fixes EP + FSDP2 expert parameters being overwritten by rank-0 broadcast. The overlap is mostly in subsystem and `modeling_utils.py`, not the same code-path failure.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the better representative because it fixes a concrete, self-contained code-path bug in expert loading/wrapping during distributed model materialization, with clear diff signals in core_model_loading, moe, tensor_parallel, and trainer.", + "canonical_pr_reason": "#45662 is the more concrete and narrowly defined fix, with direct changes in the loading/broadcast path tied to expert parameters; #45548 is a separate loading/serialization fix.", "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the strongest standalone PR in the cluster: the bug is specific, the failure mode is explicit ('experts silently overwritten by rank-0 broadcast'), and the fix is tightly scoped to the affected distributed-loading path.", + "best_pr_reason": "#45662 best represents the cluster if one PR must be chosen because it targets the explicit expert-overwrite bug with clearer runtime impact and broader supporting code changes.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Both involve expert parallelism and model loading, but they fix different failure modes and code paths: #45548 is about EP + DeepSpeed ZeRO-3 loading/serialization via accelerate launch, while #45662 is about FSDP2/rank-0 broadcast overwriting expert parameters. They would not plausibly merge into one PR." + "reason": "Different underlying failures: one is EP + ZeRO-3 loading via accelerate launch, the other is EP + FSDP2 expert parameters being overwritten by rank-0 broadcast. Shared EP context is not enough to merge them as duplicates." } ] }, @@ -20656,40 +20841,40 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "a95c7e43470d5b46c434fc3a08de1ca333db92b8344feeb9518de3e1f71b2890", + "prepared_review_unit_hash": "d12da6c2ce84ea7810dbdeb894e61fadece56367010137d6520ff1013636632d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, - "estimated_input_tokens": 1148, - "estimated_eval_tokens": 2552 + "serialized_chars": 4588, + "estimated_input_tokens": 1147, + "estimated_eval_tokens": 2550 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, - "estimated_input_tokens": 1148, - "estimated_eval_tokens": 2552 + "serialized_chars": 4588, + "estimated_input_tokens": 1147, + "estimated_eval_tokens": 2550 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same xdist/captured_info logging collision bug (issue 45561); 45645 appears to be the broader, more complete version, while 45639 is a narrower subset.", - "confidence": 0.91, + "summary": "Both PRs address the same xdist-related captured_info logging collision in transformers testing utilities; one is a narrower implementation, the other also updates CI log collection to handle split files.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the better canonical PR because it covers the core xdist-safe captured_info fix and also updates the CI/reporting path to read multiple captured_info files, making it the more complete end-to-end change.", + "canonical_pr_reason": "pull_request:45645 is the more complete and representative fix: it changes the xdist-safe output path, updates tests, and adapts CI to consume multiple captured_info files.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 best represents the underlying fix: it addresses the same concrete xdist artifact-collision problem as 45639, but also preserves CI debug log collection across multiple worker files.", + "best_pr_reason": "pull_request:45645 best fits as the primary PR because it covers the full end-to-end behavior change, not just the internal file-writing fix.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug and same core code path in testing_utils/tests for xdist-safe captured_info handling; 45645 is a broader superset that extends the same fix into CI artifact aggregation." + "reason": "Same underlying bug: xdist workers colliding on captured_info output. The fixes are directly related and could plausibly be merged into one PR." } ] }, @@ -20719,7 +20904,7 @@ "soft_pairs": [ "pull_request:45670|pull_request:46320" ], - "prepared_review_unit_hash": "d1883064239d9ea7e2b5c4d7afa863961eaee3ba99b105b6ab0ce819f8abebdf", + "prepared_review_unit_hash": "a46a6d8021aae8239544f78305f4f944200d6d42d077182ca018b3af123b5a53", "component_budget": { "node_count": 2, "item_count": 2, @@ -20741,18 +20926,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are unrelated: one only adds a model-to-AutoModel mapping entry for GLM-ASR, while the other implements RecurrentGemma attention-dispatch support plus related conversion/tests/docs changes.", - "confidence": 0.97, + "summary": "These two pull requests are unrelated: one adds AutoModel registry entries for glmasr/dia, the other implements RecurrentGemma attn_implementation dispatch plus supporting conversion/tests/docs. They should not be clustered as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46320 is the more substantive, self-contained change and clearly targets a concrete code-path improvement for RecurrentGemma.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 46320 is the best representative of the cluster because it has the broader, well-scoped feature fix and multiple supporting changes tied to one bug/feature.", + "best_pr_reason": "PR 46320 is the more substantial and self-contained change, but it is not a duplicate of PR 45670; the two address different code paths and model families.", "soft_edge_verdicts": [ { "left": "pull_request:45670", "right": "pull_request:46320", "accept": false, - "reason": "Reject: these address different models and different problems. 45670 is just an AutoModel registry addition for GLM-ASR, while 46320 adds RecurrentGemma attn_implementation dispatch with conversion and test updates. They are not the same underlying change and would not plausibly be merged into one PR." + "reason": "Different targets and functionality: AutoModel mapping for glmasr/dia vs RecurrentGemma attention-implementation support. No shared concrete bug/change to merge into one PR." } ] }, @@ -20774,56 +20959,48 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-45720-3", + "cluster_id": "cluster-45720-2", "nodes": [ "pull_request:45720", - "pull_request:46023", "pull_request:46259" ], "soft_pairs": [ - "pull_request:45720|pull_request:46259", - "pull_request:46023|pull_request:46259" + "pull_request:45720|pull_request:46259" ], - "prepared_review_unit_hash": "cb2b2715428f03bcd13b13bbf5b4cf8628ad2b9d7e2bf0e1b314f8d6b18dc49c", + "prepared_review_unit_hash": "54f5621e9bc1e55586d4aea04d84970e32831cc583f19a18b7ac5f97c8c572f7", "component_budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 2, - "serialized_chars": 10795, - "estimated_input_tokens": 2699, - "estimated_eval_tokens": 5654 + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7126, + "estimated_input_tokens": 1782, + "estimated_eval_tokens": 3820 }, "budget": { - "node_count": 3, - "item_count": 3, - "soft_pair_count": 2, - "serialized_chars": 10795, - "estimated_input_tokens": 2699, - "estimated_eval_tokens": 5654 + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7126, + "estimated_input_tokens": 1782, + "estimated_eval_tokens": 3820 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three separate linter/chore PRs for different rules and code paths: TRF003 on model forward signatures, rule 16 on video/image pre-processing flags, and TRF018 modeling-rule docs plus implementation. They are not duplicates.", - "confidence": 0.95, + "summary": "These are not duplicates: one PR implements a tuple-return linting behavior in model forward methods, while the other adds a new modeling rule about dead do_* flags in image/video processors. Different rule numbers, subsystems, and code paths.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:46259 is the most representative central change because it introduces a new modeling rule with docs and a broad implementation sweep, making it the clearest standalone linter-rule PR in the set.", + "canonical_pr_reason": "PR #45720 is the more concrete code-change PR: it updates model forward implementations to use can_return_tuple and removes explicit return_dict plumbing across several model files. That makes it a clearer anchor than the rule/docs-focused PR.", "best_issue_reason": null, - "best_pr_reason": "pull_request:46259 is the best overall representative PR: it has the broadest scope, explicit rule documentation, and a clear rule-definition focus, whereas the others are narrower fixes to different rules.", + "best_pr_reason": "PR #45720 is the better representative of the cluster because it contains the main runtime behavior changes across model forward paths, whereas PR #46259 is primarily a linter/rule-definition update with broader documentation and rule maintenance.", "soft_edge_verdicts": [ { "left": "pull_request:45720", "right": "pull_request:46259", "accept": false, - "reason": "Different rules and different behaviors: TRF003 changes model forward return_dict handling, while TRF018 is about unused do_* flags in image/video processors. Shared model filenames do not indicate the same underlying change." - }, - { - "left": "pull_request:46023", - "right": "pull_request:46259", - "accept": false, - "reason": "Different concrete bug/change: 46023 fixes do_convert_rgb consumption in processor preprocessing, while 46259 adds a new modeling rule and updates many model files. Same linter theme, but not the same code-path problem." + "reason": "Different underlying changes: TRF003 tuple-return handling in model forwards vs. TRF016 dead do_* flag detection in image/video processors. They do not fix the same bug and would not plausibly merge into one PR." } ] }, @@ -20926,70 +21103,70 @@ "pull_request:46154|pull_request:46317", "pull_request:46196|pull_request:46317" ], - "prepared_review_unit_hash": "561c895a6bdd0aaf9201cd4eacdd0ac8cd5f8f76e0f365c0f04112f49d8faf72", + "prepared_review_unit_hash": "f3703813ac6510d3757b744798b8e8271869ca7dec26a19ddb7e43d7b877f435", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 11129, - "estimated_input_tokens": 2783, - "estimated_eval_tokens": 5822 + "serialized_chars": 11166, + "estimated_input_tokens": 2792, + "estimated_eval_tokens": 5840 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 11129, - "estimated_input_tokens": 2783, - "estimated_eval_tokens": 5822 + "serialized_chars": 11166, + "estimated_input_tokens": 2792, + "estimated_eval_tokens": 5840 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: all four PRs add SDPA dispatch support, but each targets a different model family and code path (CTRL, T5, wav2vec2/SeamlessM4T variants, Zamba).", - "confidence": 0.96, + "summary": "These PRs are all about adding SDPA dispatch support, but each targets a different model family and implementation path, so they should not be merged as duplicates. The most representative PR is the broadest multi-model dispatch change.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No single PR canonically subsumes the others; they are separate model-specific feature implementations.", + "canonical_pr_reason": "PR 46196 is the most comprehensive representative: it covers multiple related model families (SeamlessM4T/v2 and wav2vec2 variants) plus tests, making it the broadest SDPA-dispatch change in the set.", "best_issue_reason": null, - "best_pr_reason": "PR 46154 is the cleanest representative of the cluster: it is narrowly scoped to T5 SDPA dispatch with tests/docs, but it is still distinct from the others.", + "best_pr_reason": "PR 46196 is the best cluster representative because it spans the widest scope among these similar dispatch-support PRs while still being a concrete, coherent change set.", "soft_edge_verdicts": [ { "left": "pull_request:46073", "right": "pull_request:46154", "accept": false, - "reason": "Same broad SDPA feature, but different model implementations (CTRL vs T5) and different forward code paths; not mergeable as one duplicate PR." + "reason": "Different model implementations (CTRL vs T5); same high-level feature, but not the same underlying code-path bug or mergeable change." }, { "left": "pull_request:46073", "right": "pull_request:46196", "accept": false, - "reason": "Different model families and attention stacks (CTRL vs wav2vec2/SeamlessM4T variants); these are separate fixes, not one underlying change." + "reason": "CTRL SDPA dispatch and SeamlessM4T/wav2vec2 SDPA dispatch are separate model-specific fixes with different code paths." }, { "left": "pull_request:46073", "right": "pull_request:46317", "accept": false, - "reason": "CTRL and Zamba are unrelated model-specific SDPA dispatch additions with different code paths; not the same change." + "reason": "CTRL attention dispatch and Zamba attention dispatch are distinct model changes, not the same concrete bug fix." }, { "left": "pull_request:46154", "right": "pull_request:46196", "accept": false, - "reason": "Both are SDPA dispatch support, but for different architectures and files; too broad to treat as one duplicate PR." + "reason": "T5 SDPA support and SeamlessM4T/wav2vec2 SDPA support affect different architectures and kernels; not a single duplicate PR." }, { "left": "pull_request:46154", "right": "pull_request:46317", "accept": false, - "reason": "T5 and Zamba require different integration points and tests; they are separate model-specific PRs." + "reason": "T5 and Zamba are different model code paths; shared theme alone is insufficient to treat them as duplicates." }, { "left": "pull_request:46196", "right": "pull_request:46317", "accept": false, - "reason": "Distinct model families and implementations; similar feature theme does not make them the same underlying code-path fix." + "reason": "SeamlessM4T/wav2vec2 SDPA dispatch and Zamba dispatch are unrelated model-specific changes, even though both enable attention dispatch." } ] }, @@ -21019,7 +21196,7 @@ "soft_pairs": [ "pull_request:46126|pull_request:46269" ], - "prepared_review_unit_hash": "e84a9c3332f859ce1d4aa705e7e865859c1da2f8ad65fa683ea32ffe894c8d22", + "prepared_review_unit_hash": "d82301e5eb1a44226c09c6644ec60a60f607b07de823c27d364b8a1a795a372d", "component_budget": { "node_count": 2, "item_count": 2, @@ -21041,18 +21218,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs touch overlapping distributed/tensor-parallel files, but they are not the same change: one is a focused EP + Trainer integration, the other is a broad distributed branch base spanning FSDP, tensor parallel, MoE, CI, and core loading code.", - "confidence": 0.82, + "summary": "These are related distributed-training PRs, but they are not the same change: #46126 is a focused EP + Trainer integration, while #46269 is a much broader distributed branch base touching many subsystems. The shared files alone are not enough to treat them as duplicates.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #46126 is the more canonical candidate because it describes a specific feature slice (EP + Trainer integration on top of DistributedConfig) and its changes are concentrated around the relevant tensor-parallel/distributed paths.", + "canonical_pr_reason": "#46269 is the broader umbrella change and likely the better representative of the distributed branch work, while #46126 is a narrower follow-up/integration PR.", "best_issue_reason": null, - "best_pr_reason": "PR #46126 is the best PR for this cluster because it is narrower and more directly tied to a concrete code-path change, whereas PR #46269 is a large umbrella branch with many unrelated distributed updates.", + "best_pr_reason": "#46269 is the most central artifact in this cluster because it spans the widest set of distributed changes and subsumes the shared files seen in #46126.", "soft_edge_verdicts": [ { "left": "pull_request:46126", "right": "pull_request:46269", "accept": false, - "reason": "Reject: they overlap in some distributed files, but the scope is different. #46126 is a targeted EP/trainer integration change, while #46269 is a broad distributed branch base with FSDP, CI, MoE, and other unrelated edits; they do not look like the same underlying fix and would not plausibly merge into one PR." + "reason": "Reject: the PRs target different scopes and likely different merge units. #46126 is specifically EP/Trainer integration, whereas #46269 is a large distributed base branch with many unrelated file changes; they do not look like the same concrete code-path fix." } ] }, @@ -21082,7 +21259,7 @@ "soft_pairs": [ "pull_request:46152|pull_request:46207" ], - "prepared_review_unit_hash": "8ef6da9a9290e4e76f6981e315e8403bf9f1caa8eef399e8c449324754729aaf", + "prepared_review_unit_hash": "6f120d9bcabeb7262df6a965aa8aae9bf7fd2d14985e0f1b915491502717abbb", "component_budget": { "node_count": 2, "item_count": 2, @@ -21104,18 +21281,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are thematically similar\u2014both remove file-open-based source inspection\u2014but they target different modules and different code paths, so they are not duplicates.", - "confidence": 0.92, + "summary": "Two open PRs share a broad theme of avoiding direct file-open source inspection, but they target different code paths and different bugs, so they should not be merged as duplicates.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46207 is the cleaner representative of the cluster: it addresses a specific source-inspection path in modeling_utils and includes tests, while 46152 is a separate import_utils refactor.", + "canonical_pr_reason": "PR #46207 is the cleaner representative of the cluster because it fixes a concrete source-reading heuristic in _can_set_attn_implementation and includes a corresponding test update.", "best_issue_reason": null, - "best_pr_reason": "46207 is the best standalone PR to keep because it is narrowly scoped, test-backed, and tied to one concrete behavior change.", + "best_pr_reason": "PR #46207 is the strongest standalone PR: it addresses a specific modeling_utils behavior, has clearer semantics, and is more directly tied to a single code-path fix than #46152.", "soft_edge_verdicts": [ { "left": "pull_request:46152", "right": "pull_request:46207", "accept": false, - "reason": "Both replace open()-based source reading, but 46152 changes import_utils traversal logic while 46207 changes _can_set_attn_implementation in modeling_utils; they fix different code paths and do not look mergeable as one PR." + "reason": "Reject: both are about avoiding file-open source inspection, but #46152 changes import_utils path resolution for traversables, while #46207 changes modeling_utils' attention-implementation capability check. Different modules, different behavior, and not the same concrete fix." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 0caf0b54efc774d323ea1f2de94ff622d939375e..62bf8646702381a3f45f89b05616438323807708 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260601t120028z", + "analysis_id": "hybrid-model-20260601t180035z", "archived_artifacts": { - "hybrid": "snapshots/20260601T120028Z/analysis-runs/hybrid-model-20260601t120028z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260601T120028Z/analysis-runs/hybrid-model-20260601t120028z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-06-01T12:07:57Z", + "published_at": "2026-06-01T18:10:36Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260601T120028Z", + "snapshot_id": "20260601T180035Z", "variant": "hybrid" } diff --git a/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..bc1d46aec6bd8b1fb035d6d8a2db1ef51a21d38d --- /dev/null +++ b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json @@ -0,0 +1,1997 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260601T180035Z", + "generated_at": "2026-06-01T18:10:35Z", + "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": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.797, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.831, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 730, + 737 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 720, + 726 + ], + [ + 1331, + 1337 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.494, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.434, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3595, + 3602 + ], + [ + 3819, + 3853 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "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": [], + "duplicate_prs": [ + { + "cluster_id": "cluster-41115-3", + "canonical_pr_number": 45613, + "duplicate_pr_numbers": [ + 41116 + ], + "target_issue_number": 41115, + "reason": "PRs in cluster-41115-3 are treated as duplicates because they converge on issue #41115 with closing_reference evidence." + }, + { + "cluster_id": "cluster-41211-3", + "canonical_pr_number": 44339, + "duplicate_pr_numbers": [ + 41356 + ], + "target_issue_number": 41211, + "reason": "PRs in cluster-41211-3 are treated as duplicates because they converge on issue #41211 with closing_reference evidence." + }, + { + "cluster_id": "cluster-43240-3", + "canonical_pr_number": 43251, + "duplicate_pr_numbers": [ + 43254 + ], + "target_issue_number": 43240, + "reason": "PRs in cluster-43240-3 are treated as duplicates because they converge on issue #43240 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43698-3", + "canonical_pr_number": 43779, + "duplicate_pr_numbers": [ + 43816 + ], + "target_issue_number": 43698, + "reason": "PRs in cluster-43698-3 are treated as duplicates because they converge on issue #43698 with closing_reference, shared_issue_target evidence." + }, + { + "cluster_id": "cluster-43979-11", + "canonical_pr_number": 44007, + "duplicate_pr_numbers": [ + 43996, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "target_issue_number": 43979, + "reason": "PRs in cluster-43979-11 are treated as duplicates because they converge on issue #43979 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-44018-2", + "canonical_pr_number": 44068, + "duplicate_pr_numbers": [ + 44018 + ], + "target_issue_number": null, + "reason": "PRs in cluster-44018-2 are treated as duplicates because they share soft_similarity evidence." + }, + { + "cluster_id": "cluster-45081-3", + "canonical_pr_number": 45317, + "duplicate_pr_numbers": [ + 45086 + ], + "target_issue_number": 45081, + "reason": "PRs in cluster-45081-3 are treated as duplicates because they converge on issue #45081 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45561-3", + "canonical_pr_number": 45645, + "duplicate_pr_numbers": [ + 45639 + ], + "target_issue_number": 45561, + "reason": "PRs in cluster-45561-3 are treated as duplicates because they converge on issue #45561 with closing_reference, shared_issue_target, soft_similarity evidence." + }, + { + "cluster_id": "cluster-45647-3", + "canonical_pr_number": 45738, + "duplicate_pr_numbers": [ + 45737 + ], + "target_issue_number": 45647, + "reason": "PRs in cluster-45647-3 are treated as duplicates because they converge on issue #45647 with closing_reference, shared_issue_target evidence." + } + ], + "best_issue": { + "cluster_id": "cluster-45647-3", + "issue_number": 45647, + "reason": "Issue #45647 is the strongest global issue candidate because it is open, belongs to a cluster with 3 artifacts, and carries 13 discussion comments plus 8 inbound references.", + "score": 164.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..9cab89331f95a9c19a0270d01666f673a58d2db8 --- /dev/null +++ b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,21307 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260601T180035Z", + "generated_at": "2026-06-01T18:10:35Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43296", + "issue:43425", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43827", + "issue:43828", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44589", + "issue:44805", + "issue:44918", + "issue:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45800", + "issue:45823", + "issue:45859", + "issue:45874", + "issue:45901", + "issue:45902", + "issue:46015", + "issue:46165", + "issue:46294", + "issue:46304" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:45901|issue:46015", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44918|issue:46165", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43638|issue:46165", + "issue:44805|issue:46294", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44560|issue:46165", + "issue:43596|issue:46165", + "issue:43572|issue:46165", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:24643|issue:30277", + "issue:34928|issue:44805", + "issue:45859|issue:45902", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:45874|issue:46294", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43425|issue:44292", + "issue:34928|issue:41720", + "issue:43828|issue:45161", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:43716|issue:45685", + "issue:44918|issue:45161", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:45507|issue:45685", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44918|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:45237|issue:46015", + "issue:43039|issue:44805", + "issue:45800|issue:46304", + "issue:43296|issue:46304", + "issue:41762|issue:43596", + "issue:39290|issue:41720", + "issue:43901|issue:44512", + "issue:44589|issue:46304", + "issue:45823|issue:46294", + "issue:45237|issue:45901" + ], + "prepared_review_unit_hash": "7e71c731fa2d8e67e4bcd8005016539595c7ea54268134d7db30ca1f0966aa6c", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 67, + "serialized_chars": 47828, + "estimated_input_tokens": 11957, + "estimated_eval_tokens": 24170 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous cluster. The only clear duplicate family is the DeepSpeed ZeRO-3 \"index 0 is out of bounds\" reports around model init/loading; most other pairs are different models, APIs, or docs changes.", + "confidence": 0.66, + "canonical_issue_reason": "issue:43596 is the broadest representative of the ZeRO-3 index-out-of-bounds family, and it matches the accepted BERT/Gemma3-style reports on the same failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43596 best captures the shared DeepSpeed ZeRO-3 init/loading bug with a concise, generic title; it is the most reusable canonical issue among the close matches.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failure modes: missing Qwen3.5 config attribute vs streaming chat/completions error." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated problems: AMD GPU support for GPT-OSS vs an MPS histogram kernel error." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different model families and different error paths (dtype mismatch vs AMD GPU runtime failure)." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different concrete bug: autocast dtype mismatch in Phi-tiny-MoE vs GPT-OSS on AMD GPUs." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different model-specific runtime issues; no shared code path is evident." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different models and errors: Qwen-3 NVFP4 failure vs GPT-OSS AMD GPU failure." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "Both are failures, but on unrelated paths: DeepSpeed collective mismatch vs ONNX export." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "Different models and subsystems: export-to-ONNX vs FineGrainedFP8 runtime failure." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "No common concrete bug; ONNX export error vs Qwen3 auto device-map cuda assert." + }, + { + "left": "issue:45901", + "right": "issue:46015", + "accept": false, + "reason": "Different topics: table QA crash vs stale RAG examples documentation." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions after v5, but they are different removed features and different docs surfaces." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "Different issues: ModernBERT ONNX export vs GenerationMixin import failure." + }, + { + "left": "issue:44918", + "right": "issue:46165", + "accept": false, + "reason": "Different training problems: Qwen3.5 input embedding unpacking vs resume/trust_remote_code behavior." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Different tensor mismatch complaints on different models and code paths." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are IndexError-style reports, but the underlying path and model family differ." + }, + { + "left": "issue:43638", + "right": "issue:46165", + "accept": false, + "reason": "Unrelated: ZeRO-3 BERT index error vs training-resume/trust_remote_code issue." + }, + { + "left": "issue:44805", + "right": "issue:46294", + "accept": false, + "reason": "Different models and failure mechanisms; no shared underlying bug is apparent." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different error shapes: ZeRO-3 init IndexError vs mask/tensor shape mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Shape mismatch crash vs GPT-OSS tensor-parallel issue; different code paths." + }, + { + "left": "issue:44560", + "right": "issue:46165", + "accept": false, + "reason": "Different features: Qwen3-VL video StopIteration vs training resume/trust_remote_code." + }, + { + "left": "issue:43596", + "right": "issue:46165", + "accept": false, + "reason": "ZeRO-3 BERT init error is unrelated to the resume/trust_remote_code problem." + }, + { + "left": "issue:43572", + "right": "issue:46165", + "accept": false, + "reason": "Config regression (missing pad_token_idx) is unrelated to training resume behavior." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "Different subsystems: BarkProcessor voice preset vs ModernBERT ONNX export." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both involve DeepSpeed, but the specific failures and model paths are different." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds failure during model init/loading; likely the same underlying DeepSpeed bug." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Different problems: detokenization bug vs LoRA merge/save/reload mismatch." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Different issues: Liger Kernel cross-entropy call vs GPT-OSS tensor-parallel failure." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different models and bug classes; not a duplicate." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Different DeepSpeed training failures and different concrete error messages." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "FSDP/activation-checkpoint recomputation mismatch vs generic tensor mask shape mismatch." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": false, + "reason": "Same model family, but different bugs: CPU offload incompatibility vs uninitialized-memory after materialization." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 BERT index error is unrelated to GPT-OSS tensor-parallel failure." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Different training stack problems: checkpointing/FSDP mismatch vs custom trainer signature change." + }, + { + "left": "issue:45237", + "right": "issue:46015", + "accept": false, + "reason": "Different topics: AMD GPU support vs outdated RAG examples docs." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger Kernel cross-entropy issue and tensor shape mismatch are unrelated." + }, + { + "left": "issue:45800", + "right": "issue:46304", + "accept": false, + "reason": "Version compatibility complaints, but about different version pairs and different failures." + }, + { + "left": "issue:43296", + "right": "issue:46304", + "accept": false, + "reason": "Different incompatibilities: vLLM/PaddleOCR-VL loading vs USE_DISTRIBUTED=0 regression." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds error during model loading/init; Gemma3 and BERT look like repros of the same bug." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs cleanup items, but they refer to different removed APIs and different documentation pages." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different model-specific failures: image preprocessor dtype mismatch vs video StopIteration." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different kernel/runtime bugs: autocast dtype mismatch vs MPS histogram not implemented." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "Unrelated: Qwen3.5 SFT trainer input handling vs MPS MoE histogram error." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Different concrete paths: Liger Kernel cross_entropy vs Phi-tiny-MoE autocast mismatch." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "DeepSpeed collective mismatch and trainer signature error are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP checkpointing mismatch vs missing GenerationMixin import." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Different features and errors: GPT-OSS on AMD vs table-question-answering crash." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Same model family, but different bugs: device mismatch with auto device_map vs expensive reverse embedding lookup." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Version incompatibility vs model-specific NVFP4 runtime error." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "Different issues: activation checkpointing/FSDP mismatch vs Qwen3 auto device mapping cuda assert." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Different model/runtime failures with no clear shared code path." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Different model families and failure mechanisms." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different MoE/dtype issue vs Qwen NVFP4 runtime error." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Different bugs: image-preprocessor/model dtype mismatch vs MPS histogram kernel limitation." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different training/inference problems on different models." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model-specific runtime errors; no duplicate relationship is evident." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Different failures: Qwen-3 NVFP4 runtime error vs TRL SFT unpacking issue." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "GraniteMoEHybrid invalid method and MPS histogram Int error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger Kernel cross-entropy issue vs TRL SFT trainer embedding unpacking are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds error during model loading/init; both look like the same DeepSpeed issue." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different config/runtime problems: Gemma3TextConfig missing field vs Qwen3 device-map cuda assert." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Different docs mismatches: return_all_scores behavior vs removed run command." + }, + { + "left": "issue:44589", + "right": "issue:46304", + "accept": false, + "reason": "Different runtime problems: missing Float8 storage type vs USE_DISTRIBUTED=0 regression." + }, + { + "left": "issue:45823", + "right": "issue:46294", + "accept": false, + "reason": "Different model paths and symptoms: Gemma4 device mismatch vs Qwen3.5 video token/template mismatch." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Different model/runtime issues with no shared root cause." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The ZeRO-3 index-out-of-bounds cluster around 43596/43638/41762 is supported by the packet, and the rest of the pairwise rejections are conservative given the differing titles/subsystems. No obvious overstatement of evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 2, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36010", + "issue:39290", + "issue:41093", + "issue:41762", + "issue:43039", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43975", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44479", + "issue:44560", + "issue:44589", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45464", + "issue:45685", + "issue:45800", + "issue:45812", + "issue:45823", + "issue:45901", + "issue:45920", + "issue:46015", + "issue:46294", + "issue:46304" + ], + "soft_pairs": [ + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43975|issue:46015", + "issue:45812|issue:45920", + "issue:44863|issue:46015", + "issue:45020|issue:46304", + "issue:43866|issue:44863", + "issue:44292|issue:46015", + "issue:43872|issue:46304", + "issue:39290|issue:43531", + "issue:43854|issue:43866", + "issue:41093|issue:43638", + "issue:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue:39290|issue:45823", + "issue:43404|issue:43866", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:44841|issue:45084", + "issue:36010|issue:39290", + "issue:45800|issue:45823", + "issue:41093|issue:41762", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:43541|issue:45161", + "issue:44805|issue:44918", + "issue:44387|issue:45005", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:43716|issue:46294", + "issue:43531|issue:45070", + "issue:45020|issue:45800", + "issue:44479|issue:46294", + "issue:43541|issue:44589", + "issue:41093|issue:43596" + ], + "prepared_review_unit_hash": "b11c274fc829410e66a64e4aaff96a2ebf072f3d8c31270976e55a5a2ff455c7", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 42, + "serialized_chars": 39560, + "estimated_input_tokens": 9890, + "estimated_eval_tokens": 20036 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of mostly unrelated Transformers regressions and model-specific bugs. The soft pairs share superficial similarity, but they do not look like the same concrete underlying issue or change, so none should be merged.", + "confidence": 0.62, + "canonical_issue_reason": "issue:45020 is the broadest umbrella here: it describes a recent-version regression affecting remote-code models, which is the closest high-level match to the cluster\u2019s recurring compatibility/theme issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best single representative issue because it is broad, version-regression oriented, and open-ended enough to subsume multiple related compatibility reports without overfitting to one model.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Different failures: processor handling for Voxtral vs Gemma4 PLE device-map mismatch." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Different subsystems and symptoms: Liger Kernel cross-entropy routing vs Qwen3.5 video StopIteration." + }, + { + "left": "issue:43975", + "right": "issue:46015", + "accept": false, + "reason": "Different bugs: detokenization regression for DeepSeek coder vs outdated RAG examples/docs." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different model families and likely different code paths." + }, + { + "left": "issue:44863", + "right": "issue:46015", + "accept": false, + "reason": "NemotronH checkpoint loading failure is unrelated to documentation/example updates." + }, + { + "left": "issue:45020", + "right": "issue:46304", + "accept": false, + "reason": "Broad similarity around version breakage, but one is remote_code model support and the other is a USE_DISTRIBUTED=0 PyTorch compatibility issue." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Corrupted checkpoint / model artifact issue vs loader implementation failure for a different architecture." + }, + { + "left": "issue:44292", + "right": "issue:46015", + "accept": false, + "reason": "Model loading/runtime error versus docs/example maintenance; no shared concrete code path." + }, + { + "left": "issue:43872", + "right": "issue:46304", + "accept": false, + "reason": "bitsandbytes Int8Params signature breakage is unrelated to PyTorch distributed support changes." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Both mention sliding-window-related config issues, but they involve different models and distinct integration failures." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test model loading regression for GLM-4.7-Flash is unrelated to a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are IndexErrors with zero-sized tensors, but they occur in different Bert/deepspeed scenarios and are not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper model loading failure is unrelated to table-question-answering task crashes." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch version incompatibility and pydantic PretrainedConfig breakage are separate compatibility regressions." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "Both involve runtime/compatibility issues, but one is DeepSpeed ZeRO-3 with Bert and the other is torch 2.4.1 vs transformers 5.8.0." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Different failure domains: model detokenization regression versus QA pipeline crash." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper loading failure and pydantic config regression are unrelated code paths." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 problems: chat template crash versus streaming inference API failure." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "Model loading error and table QA crash do not share a concrete underlying bug." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failure modes: Gemma3 config attribute error vs Gemma4 device placement bug." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Tied-weight bug in Mistral3 is unrelated to a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Streaming chat/completions failure is unrelated to MPS histogram_int support in moe models." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Torch dynamo tracing grouped_mm error is a different code path from the MPS Int histogram failure." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Different precision/runtime issues: dynamo tracing grouped_mm vs autocast dtype mismatch." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor/model loading failure for Voxtral is unrelated to compilation errors for non-template nodes." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "ImportError for GenerationMixin and Gemma3 sliding_window_pattern are different API regressions." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "One is a torch/transformers compatibility issue; the other is a Gemma4 forward device-map mismatch." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are IndexErrors, but they involve different models and different zero-length tensor scenarios." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading failure and GGUF gpt-oss support are separate model-format issues." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is not the same as the pydantic PretrainedConfig regression." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing error is unrelated to GPT-OSS MoE tensor-parallel behavior." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Both mention shape/index errors, but they arise from different models and workflows." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 quantization OOM is a different problem from tied-weights translation-model regressions." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch and streaming inference API failure are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different issue than the pydantic config regression." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support is unrelated to Qwen3.5 streaming chat/completions failures." + }, + { + "left": "issue:43716", + "right": "issue:46294", + "accept": false, + "reason": "Different multimodal bugs: image preprocessor dtype mismatch vs video chat-template feature/token mismatch." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and pydantic PretrainedConfig breakage are distinct regressions." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Both are version regressions, but one targets remote_code models and the other targets PyTorch/USE_DISTRIBUTED compatibility." + }, + { + "left": "issue:44479", + "right": "issue:46294", + "accept": false, + "reason": "Both involve video input on Qwen variants, but one is a broad v5.3.0 regression and the other is a specific apply_chat_template feature/token mismatch." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing error is unrelated to missing Float8 storage type support." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Both are zero-size IndexErrors, but they occur in different models and initialization flows." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 3, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39186", + "issue:39692", + "issue:40990", + "issue:41553", + "issue:41762", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43404", + "issue:43644", + "issue:43645", + "issue:43716", + "issue:43828", + "issue:43866", + "issue:43872", + "issue:43873", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:43994", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45399", + "issue:45507", + "issue:45542", + "issue:45632", + "issue:45663", + "issue:45698", + "issue:45701", + "issue:45759", + "issue:45800", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:43054|issue:43994", + "issue:45759|issue:45902", + "issue:45542|issue:45800", + "issue:43716|issue:44918", + "issue:39186|issue:44918", + "issue:45632|issue:45698", + "issue:43645|issue:45399", + "issue:43404|issue:45005", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:42915|issue:45399", + "issue:43873|issue:45005", + "issue:44360|issue:44512", + "issue:44863|issue:45005", + "issue:44918|issue:45507", + "issue:44492|issue:44512", + "issue:43975|issue:44292", + "issue:44292|issue:45507", + "issue:43950|issue:44534", + "issue:39692|issue:43054", + "issue:43644|issue:43950", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:43866|issue:44403", + "issue:38175|issue:43054", + "issue:41553|issue:43883", + "issue:43054|issue:45701", + "issue:45663|issue:45902", + "issue:44910|issue:45859", + "issue:42947|issue:44387" + ], + "prepared_review_unit_hash": "a2b79151a67fbadd21e8558fc30c59b7cd3bc9729d6cbbe78fc3703657801113", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37142, + "estimated_input_tokens": 9286, + "estimated_eval_tokens": 18828 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated bug reports. The only clear duplicate cluster is the Transformers 5.x non-persistent buffer regression: issues 43644, 43950, and 44534 describe the same underlying `register_buffer(persistent=False)` corruption/junk-fill problem.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 43950 is the most explicit root-cause report for the non-persistent buffer regression (`from_pretrained()` corrupts `register_buffer(persistent=False)` buffers) and subsumes the related reports in 43644 and 44534.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the best global issue candidate because it is the clearest, most specific statement of the shared bug and is central to the only accepted duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Both mention SigLIP2, but one is about degraded text embeddings while the other is about nonsensical AutoModel/pipeline outputs; related area, not clearly the same bug." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Different failures: multimodal `from_config` not unwrapping `text_config` versus `inv_freq` reading uninitialized memory after `to_empty(cuda)` materialization." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "One is a missing TensorFlow backend / tensorboard-only environment issue; the other is a torch-transformers version incompatibility." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Different code paths: image preprocessor/model dtype mismatch versus TRL SFT embedding unpacking failure." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP `'weight' must be 2-D` and Qwen3.5 embedding unpacking are distinct training/loading bugs." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom model loading, but one is a cache-path collision and the other loads the wrong module after save/load; not the same defect." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Notebook custom-model initialization failure and flash-attn fallback gating are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both concern tied weights, but they affect different models and different tying paths; too broad to treat as one bug." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on GPT-OSS and a generic GLM5 issue are not the same underlying problem." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache group-type crash is unrelated to tied-weight handling." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "FineGrainedFP8Config failure and flash-attn fallback blocking are separate quantization/runtime issues." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization offloading behavior and tied-weights handling are different problems." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer ReLU discussion and a docs typo are unrelated." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure is not the same as translation-model tied-weight issues." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3.5 SFT embedding unpacking and GraniteMoEHybrid invalid method calls are unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "Cache-strategy typo and removed run-command docs are separate documentation issues." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Detokenization regression and Qwen-3 NVFP4 runtime error are different bugs." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "No shared underlying code-path problem is evident." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Both report the same Transformers 5.x regression where non-persistent buffers are mishandled/corrupted during loading." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "Different low-level bitsandbytes/storage errors with different symptoms and causes." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption and generic loading noise are not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Both are SigLIP2-related, but one is a model output-quality complaint and the other is a text-embedding degradation issue; insufficient evidence they are the same defect." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "AutoTokenizer loading error for Voxtral and missing `all_tied_weights_keys` on MolmoForCausalLM are unrelated." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "Model-quality regression and tokenization-version change are different problems." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared-state rebuild bug and Qwen3_5Moe rotary embedding uninitialized memory are distinct." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Flash-Attention illegal memory access from 3D position_ids is not the same as CPU offload incompatibility in rotary embedding." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing ineffective with LoRA and increased reserved memory under int4 quantization are different regressions." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same Transformers 5.x non-persistent buffer corruption/junk-fill regression, described from different angles." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch and RLHF NaN explosion are related only at a very high level; the concrete bugs differ." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Unexpected `num_items_in_batch` argument and DeepSpeed ZeRO-3 loading index error are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "Both involve initialization/materialization, but one is a non-persistent buffer regression and the other is a Qwen rotary-embedding uninitialized-memory bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Accepted. The summary is grounded in the packet: the only clearly supported duplicate cluster is 43644/43950/44534 around the Transformers v5 non-persistent buffer corruption regression. The soft-edge rejections are conservative and do not overclaim equivalence from broad thematic similarity alone." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 4, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:41553", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43257", + "issue:43404", + "issue:43493", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43940", + "issue:43950", + "issue:43975", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44509", + "issue:44661", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45520", + "issue:45588", + "issue:45685", + "issue:45715", + "issue:45823", + "issue:45923", + "issue:46315" + ], + "soft_pairs": [ + "issue:44403|issue:44451", + "issue:41553|issue:43881", + "issue:43975|issue:45520", + "issue:43054|issue:43493", + "issue:42947|issue:43856", + "issue:44403|issue:44488", + "issue:43643|issue:45020", + "issue:41762|issue:42915", + "issue:45685|issue:45823", + "issue:42491|issue:44368", + "issue:44991|issue:45399", + "issue:43824|issue:43872", + "issue:43881|issue:43883", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:45715|issue:46315", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43782|issue:44960", + "issue:45020|issue:45356", + "issue:43742|issue:45399", + "issue:43404|issue:43950", + "issue:43827|issue:44509", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:43257|issue:43866", + "issue:42915|issue:43872", + "issue:42947|issue:45923", + "issue:43940|issue:45313", + "issue:44928|issue:45588" + ], + "prepared_review_unit_hash": "e89a74dcbcb99a2136ebbd45c0180585026579f6892174cafbf35e6ce12f9245", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36355, + "estimated_input_tokens": 9089, + "estimated_eval_tokens": 18434 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose set of transformer loading/tokenizer regression reports, not a single duplicate set. The strongest common thread is recent v5 loading regressions, but most pairs are model-specific and should stay separate. I only accepted the clearest same-bug pairs.", + "confidence": 0.43, + "canonical_issue_reason": "Issue 45020 is the best umbrella representative of the cluster\u2019s main theme: recent transformers versions breaking model loading, especially around remote_code and related load-time regressions.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the most general and reusable issue in the set, so it is the best overall issue representative for triage among these reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Both involve loading behavior, but one is a generic noise/UX complaint and the other is a specific model load failure; not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Different models and different failure modes; the titles do not point to the same underlying loader bug." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Tokenizer detokenization behavior and a flash_attn import KeyError are unrelated issues." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": true, + "reason": "Both point to the same SigLIP2 HF-vs-reference implementation discrepancy, with worse text embeddings as a symptom of that mismatch." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "One is about gradient checkpointing with PEFT LoRA; the other is about Qwen3 MoE memory usage. Different bugs." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Generic loading noise vs a specific model that fails to load; no evidence they are the same defect." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "The first is a specific missing-fields bug in AutoConfig with trust_remote_code; the second is a broad umbrella about remote_code breakages, not the same concrete issue." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 index error and Qwen3 MoE FP8 failure are distinct model-specific problems." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS histogram-on-int error and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "A broken LoRA checkpoint migration issue is not the same as a tie_word_embeddings warning during fine-tuning." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure and flash-attn fallback gating are different code paths." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "ImportError for a missing model class and a bitsandbytes Int8Params constructor mismatch are unrelated." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "A model loading failure and a missing all_tied_weights_keys attribute are not the same bug." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote_code loading regressions and a Gemma4 device_map forward mismatch are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "A tokenizer-mapping edge case in add-new-model-like is different from the broader remote_code loading regression." + }, + { + "left": "issue:45715", + "right": "issue:46315", + "accept": false, + "reason": "Both are tokenizer performance regressions, but they affect different directions and likely different loops; not enough to merge." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch and PLE device mismatch are different runtime problems." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral regex patch crash and flash-attn fallback blocking are unrelated." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Different models and different failure categories; no shared underlying bug is evident." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "A broad remote_code regression and a tokenizer codec/regression issue are not the same defect." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "Model loading KeyError and flash-attn fallback checks are unrelated." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "A missing lm_head tying bug and a non-persistent buffer corruption regression are different code-path problems." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": false, + "reason": "These are related docs-only pipeline references, but they are different documentation cleanup reports rather than one duplicate bug." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper model runtime failure and a fbank feature extraction issue are not the same bug." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": false, + "reason": "Both mention _is_hf_initialized, but one is a bitsandbytes compatibility issue and the other is an init_empty_weights type error; close in theme but not the same concrete defect." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion/load behavior and an Ovis2 corrupted checkpoint are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 failure and bitsandbytes _is_hf_initialized incompatibility are different bugs." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing with LoRA and a missing supports_gradient_checkpointing flag are different issues even if both mention checkpointing." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": true, + "reason": "Both describe the same class of Qwen3-family DeepSpeed ZeRO-3 weight-loading failure, with parameters ending up missing during load; the model variant differs but the underlying loader problem is the same." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF gradient explosion from Qwen3.5 position_ids is unrelated to the flash_attention sinkless-model crash." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about duplicate links. The umbrella choice for issue 45020 is plausible as a broad representative of the remote_code / loading-regression theme, and the two accepted soft pairs are the clearest same-bug candidates. No obvious overstatement of evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 5, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:41093", + "issue:41553", + "issue:42617", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43645", + "issue:43646", + "issue:43824", + "issue:43828", + "issue:43854", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44991", + "issue:45030", + "issue:45305", + "issue:45325", + "issue:45584", + "issue:45663", + "issue:45685", + "issue:45823", + "issue:45834", + "issue:45902" + ], + "soft_pairs": [ + "issue:36331|issue:41093", + "issue:43854|issue:44863", + "issue:43257|issue:45305", + "issue:41553|issue:44991", + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:41553|issue:44488", + "issue:24643|issue:30064", + "issue:45325|issue:45902", + "issue:43366|issue:43828", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:44560|issue:45685", + "issue:43645|issue:43646", + "issue:43366|issue:44589", + "issue:42915|issue:43957", + "issue:44560|issue:44918", + "issue:43824|issue:43957", + "issue:42617|issue:43366", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:43632|issue:45834", + "issue:38175|issue:43994", + "issue:44155|issue:45584", + "issue:44560|issue:44805", + "issue:44877|issue:45030", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:43317|issue:44756" + ], + "prepared_review_unit_hash": "5d3eb8c8d5d28d45656a8c779ab2534bbc3222482d41305e199e48d7f757a820", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37670, + "estimated_input_tokens": 9418, + "estimated_eval_tokens": 19092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous bug reports; only two soft duplicate pairs stand out: the custom model-initialization regressions and the repeated mask-shape IndexError. Everything else looks like separate model- or subsystem-specific issues.", + "confidence": 0.83, + "canonical_issue_reason": "Issue 43646 is the cleanest and broadest statement of the shared custom-model initialization regression, without the notebook-specific framing from 43645.", + "canonical_pr_reason": null, + "best_issue_reason": "43646 is the best representative issue in the set because it states the underlying regression most generally and is the most suitable duplicate target among the accepted overlaps.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Different failures and likely different code paths: trainer API keyword mismatch vs a tensor mask-shape IndexError." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Different problems: one is a model-loading test failure for GLM-4.7, the other is a NemotronH checkpoint-loading bug." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Both involve Qwen/DeepSpeed, but the concrete bugs differ: weight conversion vs gradient averaging with GAS." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading related, but they target different models and different failure modes; not enough evidence of the same bug." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "Same underlying mask-shape mismatch IndexError; 44805 looks like a later/generalized report of the same runtime bug." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both touch Qwen video inputs, but one is a broad regression report and the other is a specific StopIteration symptom; not clearly the same code-path bug." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "Different subsystems and symptoms: PagedAttentionCache/group-type handling vs NemotronH checkpoint loading." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are load failures, but the titles point to different models and different loader issues." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Unrelated domains: DeepSpeed training RuntimeError vs image-processor segmentation-map handling." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Different bugs in different components: Qwen2.5-VL rope-index scaling vs Qwen3.5-MoE rotary embedding materialization." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF/gpt-oss support is unrelated to the Phi-tiny-MoE autocast dtype mismatch." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4-related, but one is an FSDP2 shared-kv state bug and the other is a device-map mismatch during forward." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "One is GGUF architecture support; the other is a Qwen3-MoE sliding_window behavior bug." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Non-persistent buffer corruption and Kosmos2.5 OCR index errors are different regressions." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different model families and failure modes: Bamba torch.compile/SDPA vs Qwen3.5 flash-attention position_ids handling." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Video-embedding StopIteration and MPS histogram-not-implemented are unrelated bugs." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Same underlying custom model initialization regression; 43646 is just the broader, cleaner wording." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF architecture support and missing Float8 storage are unrelated issues." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Both are load/config problems around Qwen-like models, but the concrete bugs differ: FineGrainedFP8Config vs meta-device loading." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen3.5 video/input behavior, but one is a video StopIteration regression and the other is an embedding unpacking failure; insufficient evidence of one bug." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Importing a missing Qwen2.5-VL class is not the same as meta-device loading breakage." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py execution failure is unrelated to GGUF gpt-oss support." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "ImportError for GenerationMixin and Qwen3Moe FineGrainedFP8Config failures are different regressions." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer-mapping-name failure and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:45834", + "accept": false, + "reason": "Both are IndexError reports, but they involve different models and different failure contexts." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": false, + "reason": "Same model family, but the reports are too different\u2014zero probabilities vs nonsensical AutoModel/pipeline results\u2014to treat as the same bug." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 batched-inference leakage and Whisper empty-transcription generation are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Both are runtime errors, but the video StopIteration and mask-shape IndexError point to different code paths." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Strict config blocking granite_speech and tiny-random glm4v config validation are different config-loading regressions." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Both involve model init/load failures, but one is a deepspeed zero3 Bert index error and the other is a tokenizer-mapping-name issue." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Zero-sized tensor/indexing with deepspeed zero3 is unrelated to tokenizer mapping registration." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer-mapping registration and mask-shape IndexError are different bugs." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Device-map offload loading and mmap OOM on Strix Halo are different memory-management issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The two accepted pairs are well-supported by the titles/body-level signals, and the rejections do not overclaim duplicate status for clearly different failures. No soft-edge verdict appears overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 6, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39404", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43720", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44164", + "issue:44291", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44756", + "issue:44910", + "issue:44960", + "issue:44977", + "issue:44991", + "issue:45276", + "issue:45292", + "issue:45313", + "issue:45335", + "issue:45357", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:44960|issue:44977", + "issue:41720|issue:42915", + "issue:45313|issue:45357", + "issue:44451|issue:44488", + "issue:42491|issue:45276", + "issue:43708|issue:44075", + "issue:43644|issue:44534", + "issue:42915|issue:44756", + "issue:39692|issue:43994", + "issue:43854|issue:43931", + "issue:45488|issue:45812", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42491|issue:43931", + "issue:43856|issue:44387", + "issue:43644|issue:43645", + "issue:42491|issue:45292", + "issue:44910|issue:45588", + "issue:44488|issue:44991", + "issue:44164|issue:44291", + "issue:45362|issue:45406", + "issue:45276|issue:45335", + "issue:43404|issue:43454", + "issue:36010|issue:39404", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:43425|issue:43957", + "issue:44402|issue:44488", + "issue:45663|issue:45759" + ], + "prepared_review_unit_hash": "eae3b60588c8a12bba190c01403c894d9dcb7edd56547b211f292d78f9af5fac", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37040, + "estimated_input_tokens": 9260, + "estimated_eval_tokens": 18776 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is a mixed bag of model-loading, tokenizer, training, and v5-regression reports. A few issue pairs are superficially similar, but the evidence is generally too thin to call them true duplicates; I would not collapse the cluster around a broad duplicate family.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43644 is the best representative issue because it is a clear, self-contained Transformers v5 regression with a broad symptom description. It is the most general issue in the set, but the cluster overall still looks heterogeneous rather than a single duplicate chain.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 is the strongest global issue candidate because it is broad, concrete, and centrally about a v5 buffer-initialization regression. It best captures one of the recurring subthemes without overstating the whole cluster as one duplicate family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same model family, but the problems differ: zero probabilities vs. docs/example model-processor and quantization failures." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Different code paths and failure modes: Qwen3 MoE LoRA compatibility vs. BitNet packed-weight loading." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different models and symptoms: GLM5 vs. Qwen3.5 flash-attention generation." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Both are Qwen-related, but one is an auto device-mapping CUDA assert and the other is a FineGrainedFP8Config loading issue." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Both touch Qwen3.5, but one is ZeRO-3 weight loading and the other is incorrect save_pretrained visual-encoder keys." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Similar wording around loading failures, but they involve different model families and no shared concrete code path is shown." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility is unrelated to Gemma4 resize_token_embeddings propagation." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer resume/max_steps logic is unrelated to SGD argument handling." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": false, + "reason": "The symptoms overlap, but the packet does not show enough evidence that these are the same non-persistent-buffer bug rather than two similar v5 regressions." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE FP8 failure is unrelated to disabling mmap to avoid OOM on Strix Halo." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Same SigLIP2 family, but one is a docs/example issue and the other is a runtime inference correctness problem." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different models and failures: GLM-4.7-Flash test loading vs. Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different tokenizer/model families with different symptoms." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MoE accelerate/deepspeed conversion is unrelated to GLM-4.7-Flash loading." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Related to memory/offloading broadly, but these are different regression types and not the same concrete bug." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility is unrelated to a generic model shape-mismatch load failure." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Different performance regressions: Qwen3 MoE training memory vs. int4 reserved-memory growth." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers v5 regressions, but one is buffer junk initialization and the other is custom-model initialization in Jupyter notebooks." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility is unrelated to a resize_token_embeddings output_embeddings bug." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both mention flash attention, but the concrete faults differ: packed-sequence position_ids vs. s_aux=None on sink-less models." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are loading regressions, but they affect different tokenizer/model paths and the packet does not show a shared root cause." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Saving/loading extra_state and init_empty_weights/_is_hf_initialized are different serialization/init issues." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Qwen3.5 chat crash and Gemma4Processor missing _tokenizer are unrelated." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "The titles are very similar, but they point to different model families and different embedding targets, so the evidence is not strong enough to merge them." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Similar symptom around lm_head tying, but different model implementations and not clearly the same code path." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "Importing GenerationMixin and Whisper return_language pipeline behavior are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "SigLIP2 docs/model issues are unrelated to GLM5." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/PEFT LoRA is unrelated to T5 using apex.FusedRMSNorm." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version compatibility and torch.device('meta') loading regressions are different problems." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size violation and a model loading failure are only broadly related, not the same bug." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states is unrelated to Qwen 3.5/3.6 text_config unwrapping." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall framing is mostly grounded, but the soft-edge judgments are not conservative enough. In particular, the analyst marked several pairs as true duplicates even though the packet labels them deterministic_accept=false, including issue:44451/issue:44488 and issue:45276/issue:45335, and also issue:43644/issue:44534. Those pairs may be similar, but the evidence in the packet is not strong enough to promote them to accept. The cluster summary also slightly overstates the duplicate/regression cohesion by calling the issue set a broad v5 regression pattern rather than a mixed bag with only a few similar pairs." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 7, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:39404", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43425", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43854", + "issue:43873", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44530", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44863", + "issue:44877", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:45084", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:46050", + "issue:46315" + ], + "soft_pairs": [ + "issue:45663|issue:45859", + "issue:43873|issue:44387", + "issue:44155|issue:45823", + "issue:44291|issue:44756", + "issue:44292|issue:44912", + "issue:44960|issue:46050", + "issue:43335|issue:45663", + "issue:44387|issue:44756", + "issue:42947|issue:43381", + "issue:45276|issue:45292", + "issue:43854|issue:45216", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:45684|issue:45698", + "issue:41720|issue:44155", + "issue:44479|issue:44877", + "issue:45588|issue:45663", + "issue:43957|issue:44756", + "issue:43646|issue:43708", + "issue:45812|issue:46315", + "issue:45292|issue:45335", + "issue:43645|issue:44164", + "issue:43828|issue:43957", + "issue:44402|issue:44451", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:43257|issue:44863", + "issue:44683|issue:45823", + "issue:39404|issue:45701", + "issue:43611|issue:43645", + "issue:43425|issue:45823", + "issue:44530|issue:45084", + "issue:43425|issue:43716" + ], + "prepared_review_unit_hash": "c3efc77e37542580c1f7ff8a28de7b58007a499844d96b5c3343e94df1041485", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37529, + "estimated_input_tokens": 9383, + "estimated_eval_tokens": 19022 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous issue set. The only clear duplicate chain is the `resize_token_embeddings` regression cluster, where the generic report is the best representative; most other soft pairs share a subsystem label but not the same underlying bug.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 45292 is the most generic and central wording in the clear duplicate chain (`resize_token_embeddings` not updating outputs), while 45276 and 45335 look like model-specific manifestations of the same API regression.", + "canonical_pr_reason": null, + "best_issue_reason": "45292 best represents the cluster because it states the core failure without narrowing to a specific model field, making it the most reusable duplicate target among the issue set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Different model families and failures: Gemma4 FSDP/shared_kv_state bug vs Qwen3.5 MoE rotary embedding CPU-offload incompatibility." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both mention quantization/OOM, but one is offloading behavior and the other is increased reserved memory under int4; not the same concrete bug." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference token leak and Gemma4 device-map mismatch are unrelated code-paths." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Unexpected `_is_hf_initialized` arg during init_empty_weights is unrelated to Strix Halo mmap/OOM handling." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Different quantization/loading problems on different models; no evidence of the same code path or fix." + }, + { + "left": "issue:44960", + "right": "issue:46050", + "accept": false, + "reason": "GLM5 model-loading issue and sinq save/load breakage are separate bugs." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "Sparse-layer config bug in SwitchTransformers vs Gemma4 FSDP attention-state rebuild; unrelated." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "OOM symptoms overlap, but the causes are different: int4 reserved-memory regression vs mmap on Strix Halo." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but one is ineffective LoRA checkpointing and the other is eval-mode restriction." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same underlying resize_token_embeddings regression affecting output embeddings; 45276 is a model-specific variant of 45292." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "One is a GLM-4.7-Flash loading problem; the other is a Qwen3.5 save_pretrained regression." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Gradient checkpointing eval-mode issue and RLHF NaN/SDPA math fallback issue are distinct." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "extra_state save/from_pretrained handling is unrelated to Strix Halo mmap OOM." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both concern custom-model save/load, but one is file permission propagation and the other is loading the wrong module; different bugs." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 device-map assert and AudioFlamingo3 batch leak are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Video-input regression and strict config loading are separate model/config issues." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Flash-attention sink handling bug vs Gemma4 FSDP shared_kv_states bug; different paths." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device model loading and Strix Halo mmap OOM are unrelated." + }, + { + "left": "issue:43645", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization in Jupyter and Trainer resume max_steps calculation are different problems." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Autocast dtype mismatch on Phi-tiny-MoE is not the same as meta-device loading breakage." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer/model loading failures, but they involve different models and likely different root causes." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility is too broad and does not match the specific autocast dtype mismatch bug." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to Strix Halo mmap OOM." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Qwen3 MOE conversion under accelerate+deepspeed and NemotronH checkpoint loading are separate model-loading failures." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language regression and tokenizer-version behavior change are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformers 5.0 custom-model regressions, but one is base_model_prefix loading and the other is notebook initialization; different concrete failures." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch 2.10 incompatibility and Gemma4 PLE device mismatch are not the same bug." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and non-template-node compile error are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch version incompatibility and Mistral-3 image-preprocessor dtype mismatch are separate issues." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same resize_token_embeddings regression family; 45335 is another manifestation where decoder.embed_tokens is not updated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft edges are the two resize_token_embeddings pairs, which are strongly supported by the titles and similarity signal. The rest of the verdicts avoid overclaiming by treating shared subsystems as insufficient for duplication, which matches the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 8, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43716", + "issue:43856", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44265", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44805", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45759", + "issue:45859", + "issue:46050", + "issue:46326" + ], + "soft_pairs": [ + "issue:43906|issue:44530", + "issue:44265|issue:44898", + "issue:39404|issue:44912", + "issue:44479|issue:44805", + "issue:43901|issue:44509", + "issue:44589|issue:45084", + "issue:43425|issue:44918", + "issue:44164|issue:45759", + "issue:43299|issue:43931", + "issue:36032|issue:43452", + "issue:43596|issue:44683", + "issue:43994|issue:44079", + "issue:43856|issue:44756", + "issue:44671|issue:44991", + "issue:44991|issue:45081", + "issue:43906|issue:46326", + "issue:39404|issue:44671", + "issue:44737|issue:45859", + "issue:44164|issue:44479", + "issue:44488|issue:45081", + "issue:43582|issue:43632", + "issue:44661|issue:44683", + "issue:43611|issue:43644", + "issue:40990|issue:43421", + "issue:32090|issue:39404", + "issue:43716|issue:45084", + "issue:46050|issue:46326", + "issue:44488|issue:44987", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:36032|issue:42915" + ], + "prepared_review_unit_hash": "2169594f1ab50ca33d3c02ee3a5414ae81113dc3bb6725d8fbcb48ff16ec7e1e", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37051, + "estimated_input_tokens": 9263, + "estimated_eval_tokens": 18782 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions: model/tokenizer loading failures, a few training/inference bugs, and some docs-only issues. The soft edges are mostly topical similarity rather than the same concrete defect, so I would not merge any of them.", + "confidence": 0.42, + "canonical_issue_reason": "Issue 43611 is the broadest representative of the cluster: a Transformers v5 model-loading regression affecting a generic code path (`base_model_prefix`) that matches the overall theme better than the narrower model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43611 is the best single issue to anchor this set because it describes a general v5 loading breakage rather than a one-off model or tokenizer symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "Different problems: an isolated reproduction of an older issue vs a Qwen3.5 PagedAttentionCache crash with linear_attention." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "Both are runtime failures, but one is torch.export/checkable-model logic and the other is Perceiver image-classification resolution handling." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language-return regression and git-oss-20b MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression for Qwen VL models vs a generic mask-shape IndexError; different code paths and symptoms." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs issues, but one is about `return_all_scores` text and the other about removed pipeline tasks; not the same fix." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and template-node compilation error are distinct failures." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch 2.10 compatibility vs TRL SFT trainer embedding unpacking are unrelated." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "Saving/loading `extra_state` and unwrapping `text_config` are different serialization/config bugs." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both concern Qwen3-VL loading, but one is a broad v5 dev regression and the other is a specific checkpoint weight-shape mismatch." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5 tokenizer special-token method conflict is not the same as gguf_file breaking AutoTokenizer/AutoModel loading." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "DeepSpeed ZeRO-3/BertModel index error and compiled flex_attention failing on newer torch are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "SigLIP2 bad outputs and ModelOutput key assignment with `None` are different bugs." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE training memory use and Strix Halo mmap OOM avoidance are not the same defect." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT masked-LM regression and est-roberta tokenizer load failure are separate model-specific issues." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer load failure for est-roberta vs a Mistral regex patch crash; same area, different root cause." + }, + { + "left": "issue:43906", + "right": "issue:46326", + "accept": false, + "reason": "An isolated reproduction issue and a mistral_common continue_final_message bug do not share the same code path." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline language return and CamemBERT masked-LM predictions are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both are device/offload-related, but XLNet positional encoding CPU placement and Qwen3.5 MoE rotary embedding offload compatibility are distinct." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Serialization of `extra_state` vs Qwen VL video-input regression are different bugs." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Loading cjvt/sleng-bert and a Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon warmup TypeError and `_is_hf_initialized` flag breakage are different low-level regressions." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Model registry generation failure and compiled flex_attention failure are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer corruption; different underlying bugs." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on gpt-oss and tokenizer post-processor refresh logic are not the same issue." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error and Whisper pipeline `return_language` regression are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral-3 image-preprocessor dtype mismatch and a template compilation TypeError are different problems." + }, + { + "left": "issue:46050", + "right": "issue:46326", + "accept": false, + "reason": "Quantized model save/load breakage and mistral_common final-message handling are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer load failure for cjvt/sleng-bert and physical-intelligence/fast loading failure are distinct model-specific issues." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "Missing fields from `trust_remote_code=True` config loading and Qwen3.5 PagedAttentionCache crash are unrelated." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token accounting and Qwen2.5-VL iterable-dataset multi-image finetuning are different bugs." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 9, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36032", + "issue:40444", + "issue:42175", + "issue:42915", + "issue:43089", + "issue:43262", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43540", + "issue:43541", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44206", + "issue:44220", + "issue:44265", + "issue:44403", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44488", + "issue:44530", + "issue:44534", + "issue:44610", + "issue:44683", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45584", + "issue:45987", + "issue:46178", + "issue:46315", + "issue:46326" + ], + "soft_pairs": [ + "issue:44811|issue:45584", + "issue:42915|issue:44530", + "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:43644|issue:43646", + "issue:44206|issue:44220", + "issue:44464|issue:45987", + "issue:43452|issue:43482", + "issue:43317|issue:43482", + "issue:43883|issue:44488", + "issue:44849|issue:45325", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:42175|issue:46178", + "issue:43262|issue:43377", + "issue:44987|issue:44991", + "issue:43646|issue:44534", + "issue:43089|issue:45987", + "issue:43404|issue:44466", + "issue:43994|issue:44610", + "issue:43322|issue:43540", + "issue:44403|issue:45081", + "issue:43883|issue:44991", + "issue:42915|issue:45084", + "issue:43377|issue:43819", + "issue:43645|issue:44534", + "issue:44265|issue:44610", + "issue:44991|issue:46315", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:45216|issue:45357", + "issue:44220|issue:44683", + "issue:40444|issue:46326", + "issue:36032|issue:43742" + ], + "prepared_review_unit_hash": "4c889e8818ef1d2a0a3cdbc797ba6ef8c595c94dadcce4decb978c4d559088c8", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37939, + "estimated_input_tokens": 9485, + "estimated_eval_tokens": 19226 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated one-off Transformers bugs. The only clear duplicate-like soft edge is the Qwen3.5 save_pretrained regression pair; the rest are too model-/path-specific or describe different failures.", + "confidence": 0.63, + "canonical_issue_reason": "issue:45216 is the broader, earlier report of the Qwen3.5 save_pretrained checkpoint corruption; it best captures the underlying regression.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45216 is the best cluster anchor because it states the core save_pretrained regression in a general way, while issue:45357 is a narrower follow-up.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both involve Whisper, but one is batch_decode skip_special_tokens behavior and the other is empty-transcription generation after align_special_tokens; different bugs." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Different subsystems and failures: FineGrainedFP8Config vs PagedAttentionCache linear_attention group handling." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Torch Dynamo grouped_mm tracing failure is unrelated to template-node compilation errors." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Both are load failures, but for different models and likely different code paths." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 regressions around custom models, but one is non-persistent buffer corruption and the other is custom model initialization; not the same bug." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Same audio area, but the first is an unsupported center arg crash and the second is a generic fbank feature extraction issue; not clearly the same defect." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency and StaticCache seq_length return type are different issues." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but one is a broad from_pretrained breakage and the other is a Qwen2.5-specific v5 failure; too little evidence they are the same bug." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "gpu/cpu offload dequantized loading and Qwen2.5-GGUF loading are different failure modes." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Missing all_tied_weights_keys in Molmo and inability to load a specific BERT model are unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 hidden_states output bug and Qwen2.5-VL rope index scaling are different code paths." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer add_special_tokens conflict and custom model initialization in notebooks are unrelated." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Template compilation failure and GraniteMoEHybrid invalid method calls are different problems." + }, + { + "left": "issue:42175", + "right": "issue:46178", + "accept": false, + "reason": "Both mention backend registration, but one is missing tensorflow from extras and the other is an unsupported tensorflow_text backend entry." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sample rate default and MIMI batch padding-mask behavior are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Different model-loading failures for different models; no clear shared concrete bug." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 custom-model regressions, but one is generic initialization and the other is non-persistent buffer junk; not the same defect." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation performance overhead is unrelated to StaticCache.get_seq_length return semantics." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both mention lm_head weight/tied weights, but one is a missing tie in Mistral3 and the other is inconsistent serialization by device." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 nonsensical outputs vs OmDet-Turbo input-size mismatch." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Llava Next loading segfault and Qwen3OmniMoe video-processing ValueError are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Generic load noise and a specific Mistral regex patch crash are not the same bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Molmo tied-weights attribute error and tokenizer load failure for EMBEDDIA/est-roberta are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "FineGrainedFP8Config and non-template-node compilation are completely different issues." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "MIMI padding-mask batching and DAC from_latents/STE mismatch are different model bugs." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom model initialization and non-persistent buffer junk are related only at a high level, not the same concrete bug." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export / torch_compilable_check and OmDet-Turbo processor image sizing are unrelated." + }, + { + "left": "issue:44991", + "right": "issue:46315", + "accept": false, + "reason": "Tokenizer load failure for a specific model and slow convert_tokens_to_ids are different problems." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Different models and code paths: ScandiBERT loading vs Mistral tokenizer regex patching." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "General model load failure vs Mistral tokenizer patch crash; not the same underlying bug." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Both describe the same Qwen3.5 save_pretrained checkpoint corruption; 45357 is a narrower continuation about visual encoder keys." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it only treats the Qwen3.5 save_pretrained pair as a likely duplicate-like match, and the other soft-edge rejections are plausibly cautious given the issue titles/descriptions. No overstatement of evidence is apparent." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 10, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43381", + "issue:43404", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43611", + "issue:43632", + "issue:43746", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:44062", + "issue:44079", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44829", + "issue:44877", + "issue:44977", + "issue:44987", + "issue:44991", + "issue:45020", + "issue:45127", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45538", + "issue:45663", + "issue:45812", + "issue:45923", + "issue:46326" + ], + "soft_pairs": [ + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:42915|issue:44589", + "issue:43404|issue:45127", + "issue:44062|issue:44987", + "issue:43611|issue:44534", + "issue:43531|issue:44877", + "issue:43296|issue:43531", + "issue:36032|issue:41720", + "issue:44479|issue:45325", + "issue:44977|issue:46326", + "issue:43425|issue:44403", + "issue:40990|issue:44811", + "issue:43746|issue:46326", + "issue:43792|issue:44589", + "issue:33666|issue:40444", + "issue:43421|issue:44568", + "issue:44403|issue:44991", + "issue:43632|issue:44534", + "issue:44079|issue:45663", + "issue:44683|issue:45020", + "issue:43381|issue:45923", + "issue:44462|issue:45812", + "issue:44829|issue:45479", + "issue:43482|issue:45538", + "issue:40444|issue:45325", + "issue:43317|issue:43856", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:43818|issue:45357" + ], + "prepared_review_unit_hash": "3245dcf64a1d65a3e4cacd83bd3c8e55c49bfea648546de97ca38da4a085272b", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36734, + "estimated_input_tokens": 9184, + "estimated_eval_tokens": 18624 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly a loose collection of unrelated bug reports, with only superficial overlap around Transformers v5 regressions, Qwen/VL models, tokenizers, and checkpointing. None of the soft pairs look like the same concrete bug/change, so I would keep them separate.", + "confidence": 0.18, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the strongest standalone representative: it is a concrete, high-impact AutoTokenizer regression affecting all Granite models and is better scoped than the broader, noisier reports here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Both are Transformers v5 loading/init regressions, but one is about FineGrainedFP8Config and the other about init_empty_weights/_is_hf_initialized; different failure modes." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "One is an init flag regression in Transformers v5; the other is a Strix Halo mmap OOM workaround. No shared underlying bug." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "Different model/runtime failures: FP8 config vs missing Float8 storage. Same broad era, not the same defect." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both mention weights/tied embeddings, but one is a missing lm_head tie in Mistral3 and the other is LoRA merge collapse with extended vocabulary. Not the same bug." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer AddedToken special-arg conflict vs a model-loading failure for physical-intelligence/fast; unrelated issues." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but one is base_model_prefix loading and the other is non-persistent buffer initialization junk. Different code paths." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and GraniteSpeech strict config loading are separate model/config problems." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL/vLLM load failure is unrelated to Qwen3-MoE sliding_window behavior." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer load conflict and cudaErrorAssert under auto device mapping are completely different bugs." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "Both are Qwen2.5-VL video/temporal-position issues, but one is a broad video-input regression and the other is a specific still-image rope-index scaling bug; not clearly the same failure." + }, + { + "left": "issue:44977", + "right": "issue:46326", + "accept": false, + "reason": "Qwen3.5 flash-attention generation failure vs mistral_common continue_final_message tokenizer behavior. Different subsystems and symptoms." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 compatibility is unrelated to noisy transformer loading logs." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss-20b and Whisper batch_decode skip_special_tokens handling are unrelated." + }, + { + "left": "issue:43746", + "right": "issue:46326", + "accept": false, + "reason": "GraniteSpeech PEFT local checkpoint loading and mistral_common continue_final_message are different tokenizer/model-loading paths." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and Float8 storage lookup failure do not share the same concrete root cause." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both involve Qwen2-VL/Qwen2.5-VL, but one is multi-GPU training and the other is IterableDataset multi-image finetuning; too different to merge." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Runtime special-token post-processing updates and add_special_tokens not adding BOS/EOS are related to tokens, but not the same bug." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "Generic loading noise and a tokenizer-load regression for EMBEDDIA/est-roberta are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "Both are Transformers v5 regressions, but one concerns _is_hf_initialized and the other non-persistent buffers. Different defects." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 FSDP2 shared_kv_states KeyError are unrelated." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading breakage are separate compatibility problems." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Eval-mode gradient checkpointing restriction and missing supports_gradient_checkpointing flag are different feature/flag bugs." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer-related, but one ignores tokenizer.json while the other returns wrong token IDs for Granite models. Not the same bug." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Degenerate training under flash_attention_3 and zero-loss classification with num_labels=1 are different training pathologies." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading under Transformers v5 and CLIPTokenizer model_max_length behavior are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Qwen2.5-VL multi-image IterableDataset finetuning failure and rope-index temporal scaling are distinct issues." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "device_map auto offload failure and Qwen3 MoE memory inefficiency are not the same bug." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument during init_empty_weights and missing Float8 storage are unrelated Transformers v5 breakages." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Qwen2.5-GGUF loading and Llama4Config missing pad_token_id are separate model/config issues." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA temporal-attention/weight-sharing bug and Qwen3.5 save_pretrained visual-key regression are different model families and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 11, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:35707", + "issue:40444", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43262", + "issue:43296", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43531", + "issue:43550", + "issue:43582", + "issue:43606", + "issue:43611", + "issue:43632", + "issue:43644", + "issue:43646", + "issue:43701", + "issue:43746", + "issue:43761", + "issue:43792", + "issue:43819", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45381", + "issue:45491", + "issue:45542", + "issue:45800", + "issue:45823", + "issue:45834", + "issue:45920" + ], + "soft_pairs": [ + "issue:42175|issue:45542", + "issue:41553|issue:43582", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:43531|issue:44291", + "issue:44265|issue:45072", + "issue:43611|issue:43646", + "issue:43632|issue:45072", + "issue:43994|issue:44898", + "issue:42175|issue:43296", + "issue:45325|issue:45834", + "issue:43792|issue:43957", + "issue:43454|issue:44466", + "issue:44079|issue:44534", + "issue:42915|issue:43482", + "issue:40444|issue:45381", + "issue:45325|issue:45381", + "issue:43644|issue:44079", + "issue:43761|issue:44079", + "issue:44387|issue:44617", + "issue:35707|issue:40444", + "issue:44479|issue:45823", + "issue:43606|issue:44265", + "issue:44291|issue:44877", + "issue:43296|issue:45800", + "issue:43701|issue:45325", + "issue:44568|issue:45920", + "issue:41720|issue:45823", + "issue:43606|issue:43819", + "issue:43454|issue:43550", + "issue:44186|issue:44265", + "issue:43262|issue:43746" + ], + "prepared_review_unit_hash": "951d5c8b1c57bfb37f10309458e091959a5af984e4269457bc5a199749fd0981", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37503, + "estimated_input_tokens": 9376, + "estimated_eval_tokens": 19008 + }, + "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 v5 regression reports across tokenizers, model loading/init, multimodal position IDs, device maps, and memory behavior. The soft edges are mostly theme-level similarities, not same underlying bugs, so they should all be rejected.", + "confidence": 0.89, + "canonical_issue_reason": "issue:43646 is the broadest representative of the v5 model-initialization regression family, which is the closest shared thread among the cluster items, even though the cluster is still heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best umbrella issue because it is generic, high-impact, and closest to the common v5 loading/initialization breakages represented here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both concern TensorFlow/backend packaging, but one is an install-extra omission and the other is a runtime backend detection error; different bugs." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "AutoTokenizer/Voxtral error messaging and an Apple Silicon allocator TypeError are unrelated code paths." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Both mention batching-related incorrect outputs, but they affect different models and different mechanisms (padding mask vs sliding-window/all-padding NaNs)." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Qwen3 device-map CUDA assert and a Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Both are v5 regressions, but sliding-window handling and init_empty_weights argument handling are distinct bugs." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export failures via torch_compilable_check and bfloat16 dtype mismatches are different failure modes." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are loading/init regressions, but base_model_prefix handling and custom model initialization are not the same concrete bug." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "_is_hf_initialized breakage and bfloat16 dtype mismatch are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Different vision-model bugs on different architectures; no shared concrete code path." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Packaging/backends versus model-loading compatibility in vLLM are separate issues." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both affect multimodal models, but one is a Qwen2.5-VL rope-index scaling bug and the other is a Kosmos2.5 OCR index error." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Whisper runtime failure and meta-device loading breakage are unrelated." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied lm_head weights, but one is a missing tie causing bad generation and the other is a serialization inconsistency depending on device." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer initialization are different internal behaviors." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3MoE FP8 config failure and Qwen2.5-GGUF loading failure are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both involve Qwen2.5-VL multimodal inputs, but multi-image iterable finetuning and video position_id calculation are distinct bugs." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen2.5-VL position-id issues, but one is still-image temporal scaling and the other is video-input vision_position_ids; not the same fix." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer junk and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and ModelOutput key assignment are different problems." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "General int4 memory growth and a Sam3Video OOM are not the same underlying bug." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values and multi-image finetuning failures are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Qwen video-input regression and Gemma4 PLE device mismatch are different model-specific bugs." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch and torch.export failures via torch_compilable_check are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected init_empty_weights argument and strict config loading for granite_speech are different loading issues." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "PaddleOCR-VL loading in vLLM and torch/transformers version incompatibility are too broad and not the same concrete bug." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "resume_from_checkpoint key mismatch and Qwen2.5-VL rope-index scaling are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but one is missing special tokens on one tokenizer and the other is wrong token IDs across multiple tokenizers." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both mention device mapping, but one is a CUDA assert in Qwen3 and the other is a forward-time device mismatch in Gemma4 PLE." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "CPU offload device mismatch and DAC.from_latents/forward divergence are unrelated." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "lm_head tying/generation issues and Bamba torch.compile SDPA failure are different bugs." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "LayoutLMv2 tokenizer padding/NER crashes and torch.export torch_compilable_check failures are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and GraniteSpeech PEFT checkpoint loading are separate issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 12, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42617", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43317", + "issue:43377", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43708", + "issue:43720", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:44008", + "issue:44186", + "issue:44423", + "issue:44466", + "issue:44488", + "issue:44610", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45406", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45823", + "issue:45923", + "issue:46291", + "issue:46305", + "issue:46315" + ], + "soft_pairs": [ + "issue:46305|issue:46315", + "issue:39692|issue:40444", + "issue:43881|issue:44488", + "issue:43377|issue:44610", + "issue:43454|issue:45072", + "issue:43257|issue:45923", + "issue:40990|issue:45584", + "issue:43317|issue:43873", + "issue:43572|issue:45759", + "issue:40990|issue:42947", + "issue:43377|issue:44898", + "issue:43873|issue:45701", + "issue:43454|issue:43720", + "issue:45325|issue:46315", + "issue:44466|issue:45357", + "issue:41720|issue:44977", + "issue:44991|issue:46291", + "issue:43526|issue:43883", + "issue:42617|issue:42915", + "issue:35707|issue:41720", + "issue:43881|issue:44991", + "issue:43577|issue:43708", + "issue:34634|issue:35707", + "issue:44008|issue:45823", + "issue:43404|issue:45357", + "issue:43450|issue:45701", + "issue:44186|issue:45072", + "issue:44877|issue:44991", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:36331|issue:42617", + "issue:42175|issue:46291", + "issue:44423|issue:45406" + ], + "prepared_review_unit_hash": "a2bb4f298566693659b5741f85135524198ccb6e257728c15b8d532b1ba39293", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37946, + "estimated_input_tokens": 9487, + "estimated_eval_tokens": 19230 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers bugs that only share broad themes like loading, offloading, multimodal models, or dtype/config issues. I found no soft pair that clearly describes the same underlying bug or change, so all soft edges are rejected.", + "confidence": 0.61, + "canonical_issue_reason": "Issue 43873 is the broadest and most central umbrella in this noisy cluster: it covers offloading/quantization behavior, which is the closest shared theme among the nearby loading/offload reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the best representative issue because it is open, clearly actionable, and has the widest scope among the candidates without being tied to a single narrow model or example.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:46305", + "right": "issue:46315", + "accept": false, + "reason": "One is a Moonshine streaming mask off-by-one bug; the other is tokenizer slowdown with many added tokens. Different code paths and symptoms." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 doc example errors and Qwen2.5-VL IterableDataset failures are different multimodal scenarios with different failure modes." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading failures, but they target different models and likely different model-specific config/tokenizer issues." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI batched-output inconsistency from padding masks is unrelated to OmDet-Turbo\u2019s processor/model image-size mismatch." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "One is a tied-weights serialization bug; the other is a bfloat16 dtype mismatch in inference. Same broad area, but not the same defect." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate/deepspeed and Nemotron gradient-checkpointing metadata are unrelated implementation issues." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "High perplexity on GPT-OSS and Whisper empty-transcription generation failure are different model/task bugs." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both mention offloading/quantization, but one is a device_map loading failure and the other is a broader offloading regression; not clearly the same bug." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "StableLm pad_token_idx config regression and Qwen composite-config unwrapping are separate config-loading problems." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Perplexity regression and LoRA gradient-checkpointing ineffectiveness are unrelated trainer/model-behavior bugs." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Both involve image-processing behavior, but one is batched-padding support and the other is non-default image resolution handling." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Quantized offloading behavior and tokenization changes across versions are different subsystems and failure modes." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Tied-weight serialization and packed-weight unpacking on accelerate load are different weight-management bugs." + }, + { + "left": "issue:45325", + "right": "issue:46315", + "accept": false, + "reason": "Qwen2.5-VL rope index scaling and tokenizer conversion slowdown are unrelated; one is multimodal positional math, the other is tokenizer performance." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Inconsistent lm_head serialization by device and incorrect visual encoder keys in Qwen3.5 save_pretrained are both save issues, but not the same underlying bug." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Both involve Qwen3.5/auto device mapping/flash-attention, but one is a cudaErrorAssert on A800 and the other is generation misbehavior with flash-attention." + }, + { + "left": "issue:44991", + "right": "issue:46291", + "accept": false, + "reason": "Tokenizer loading for a specific model and evaluate import failing due to kernels metadata are unrelated package-loading issues." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and Molmo tied-weights metadata are entirely different components." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "A 3d_parallel.py runtime problem and a Qwen3Moe FP8 configuration failure are different execution paths and bugs." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen3 auto device mapping cudaErrorAssert." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Different failing artifacts and different error classes: model loading for glm-4v-9b versus tokenizer loading for est-roberta." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "BLIP2 dtype propagation and Trainer resume/max_steps accounting are separate bugs in different subsystems." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "BarkProcessor voice_preset and progressive generation with past_key_values do not describe the same code path or symptom." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3n variable-name collision in forward and Gemma4 PLE device mismatch are distinct model-specific forward bugs." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Mistral3 tied lm_head weights and Qwen3.5 visual encoder save keys are different model serialization/tie-weight issues." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes and bfloat16 dtype mismatches are unrelated tokenizer versus inference-type bugs." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config loading for granite_speech and tokenizer loading for est-roberta are separate config/tokenizer compatibility issues." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Batched video processor shape bug and tokenizer behavior changes across versions are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 13, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:29159", + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36032", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43421", + "issue:43425", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43749", + "issue:43782", + "issue:43873", + "issue:43881", + "issue:44186", + "issue:44361", + "issue:44387", + "issue:44534", + "issue:44610", + "issue:44671", + "issue:44743", + "issue:44756", + "issue:44898", + "issue:44913", + "issue:45081", + "issue:45161", + "issue:45406", + "issue:45464", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:46050", + "issue:46291" + ], + "soft_pairs": [ + "issue:43873|issue:44756", + "issue:44387|issue:45704", + "issue:44610|issue:44898", + "issue:43749|issue:44534", + "issue:44186|issue:44610", + "issue:43550|issue:43606", + "issue:45632|issue:45684", + "issue:43322|issue:46050", + "issue:42915|issue:43317", + "issue:43295|issue:45701", + "issue:41720|issue:43322", + "issue:40990|issue:45701", + "issue:41720|issue:42617", + "issue:41720|issue:45161", + "issue:36010|issue:42617", + "issue:43425|issue:46291", + "issue:45081|issue:45812", + "issue:43525|issue:46291", + "issue:43531|issue:43572", + "issue:43316|issue:44913", + "issue:43540|issue:43782", + "issue:44671|issue:44743", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:43526|issue:43881", + "issue:29159|issue:36032", + "issue:45406|issue:45464", + "issue:43550|issue:43653", + "issue:30064|issue:34634" + ], + "prepared_review_unit_hash": "83f4e29f240462dc7f97da6179a8e36a3888a9eeb8ca8fe755b8d3bd069e5034", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36120, + "estimated_input_tokens": 9030, + "estimated_eval_tokens": 18316 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of superficially similar but actually unrelated regression reports across tokenizers, model loading, quantization/offloading, and vision processors. I do not see any soft pair that clearly describes the same underlying bug or a PR that could plausibly cover both sides, so all soft edges should be rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No single issue cleanly represents the cluster; the items are too heterogeneous to normalize around one canonical bug.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong best issue candidate. If forced, issue 45701 is the broadest tokenizer-regression report, but it does not subsume the rest of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both are offload/memory-related, but one is general quantization offloading and the other is a Strix Halo mmap OOM workaround; different bugs and fixes." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Both mention memory, but one is an int4 CUDA reserved-memory/OOM regression and the other is a T5-specific apex FusedRMSNorm leak; not the same code path." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Both are image-size/preprocessing mismatches, but they affect different model families and different processor/model contracts." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but one is FSDP CPU RAM efficient loading and the other is non-persistent buffer initialization; too different to merge." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes on task padding/truncation; OmDet-Turbo is a processor resolution mismatch. Unrelated failure modes." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different models and runtime paths: torch.compile+SDPA vs CPU offload device mismatch." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Both touch filesystem behavior, but cache-path collisions and read-only permission propagation are distinct bugs." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Segfault loading Llava Next is unrelated to sinq save/load breakage." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Different quantization/offload failures on different models; no shared concrete defect." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Both involve tokenization regressions, but one is processor.tokenizer/API breakage and the other is a broad tokenization-change report; not the same issue." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "CUDA assert on Qwen3 auto device mapping is unrelated to Llava Next segfaults." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "High perplexity could be caused by many things; the report does not match the broader tokenization-change issue concretely." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Different models and different distributed/runtime failures." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both mention parallelism/device mapping, but the concrete failures and affected models differ." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "GenerationMixin import failure is unrelated to not being able to run 3d_parallel.py." + }, + { + "left": "issue:43425", + "right": "issue:46291", + "accept": false, + "reason": "Both are dependency-compatibility issues, but Torch 2.10 incompatibility and kernels version/revision requirements are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is a Mistral regex patch crash and the other is wrong Granite token IDs; different models and fixes." + }, + { + "left": "issue:43525", + "right": "issue:46291", + "accept": false, + "reason": "A missing pad_token_id config field is unrelated to the kernels import/version error." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Both are config-related, but sliding_window behavior and missing pad_token_idx are separate API issues." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Config API inconsistency for Gemma3TextConfig is not the same as GPTNeoX rotary_pct not persisting on reload." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Both are Qwen3 multimodal loading/processing issues, but one is video input handling and the other is weight_only from_pretrained failure." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM predictions and Qwen3.5 recurrent-state reset are completely different model behaviors." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Runtime post-processor updates for special tokens are not the same bug as Granite token IDs being wrong." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer implementations, different task failures, and different exception modes." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "BEiT reduce_labels behavior is unrelated to glm-4v-9b loading failure." + }, + { + "left": "issue:29159", + "right": "issue:36032", + "accept": false, + "reason": "General slow/fast tokenizer inconsistency does not match the specific T5 add_special_tokens load conflict." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor _tokenizer missing and Qwen3.5 streaming API failure are unrelated." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision and read-only permission propagation are distinct filesystem issues." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile+SDPA failure in Bamba is unrelated to BigBirdTokenizer special-token registration." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Image processor void-segmentation-map handling and Bark voice_preset behavior share no underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 14, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:33666", + "issue:34567", + "issue:35707", + "issue:39692", + "issue:41720", + "issue:42490", + "issue:42886", + "issue:42915", + "issue:43322", + "issue:43329", + "issue:43381", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:44062", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44530", + "issue:44545", + "issue:44589", + "issue:44610", + "issue:44843", + "issue:44898", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45059", + "issue:45072", + "issue:45357", + "issue:45588", + "issue:45663", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45923", + "issue:46291" + ], + "soft_pairs": [ + "issue:43606|issue:43720", + "issue:44530|issue:46291", + "issue:43421|issue:45701", + "issue:42915|issue:43322", + "issue:43531|issue:45759", + "issue:43606|issue:43653", + "issue:44492|issue:44509", + "issue:34567|issue:35707", + "issue:43388|issue:45059", + "issue:43873|issue:45704", + "issue:44514|issue:44545", + "issue:42490|issue:43329", + "issue:41720|issue:43746", + "issue:43421|issue:43927", + "issue:44898|issue:45072", + "issue:45759|issue:45859", + "issue:44451|issue:44991", + "issue:33666|issue:35707", + "issue:43531|issue:44589", + "issue:45588|issue:45759", + "issue:44368|issue:45357", + "issue:44987|issue:45042", + "issue:44062|issue:44451", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:43421|issue:43653", + "issue:45663|issue:45923", + "issue:42886|issue:44843", + "issue:43381|issue:43844" + ], + "prepared_review_unit_hash": "c2f4914fdf8e57da1fb6d65ae8e138aaac61444de01d214565ded4cf5e9cd076", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 36188, + "estimated_input_tokens": 9047, + "estimated_eval_tokens": 18350 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, with one clear issue duplicate pair around Qwen2_5_VLProcessor batching; the rest are unrelated model/loading/tokenizer/training bugs and should not be merged together.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 44514 is the cleanest canonical: it is the earlier, more explicit report of the exact same Qwen2_5_VLProcessor.apply_chat_template batched-input/padding=False crash as 44545.", + "canonical_pr_reason": null, + "best_issue_reason": "44514 is the best representative issue because it precisely states the bug and has an exact duplicate in 44545; the remaining items are largely unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Different models and failure modes: CPU offload device mismatch vs unpacked packed weights during accelerate loading." + }, + { + "left": "issue:44530", + "right": "issue:46291", + "accept": false, + "reason": "Unrelated: Qwen3.5 PagedAttentionCache crash vs kernels import/version requirement in evaluate." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Both mention tokenization, but one is a runtime special-token post-processor bug and the other is a broad version-regression report." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Different code paths and symptoms: Qwen3Moe FP8 config failure vs Llava Next load segfault." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen configs, but one is a sliding-window issue and the other is missing text_config unwrapping for composite multimodal configs." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Completely different subsystems: model offload/device mismatch vs tokenizer special-token registration." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo fix and a docs cleanup are not the same underlying bug." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counting and progressive generation with past_key_values are unrelated issues." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Different areas: metrics gathering tuple handling vs SAM3 text/box behavior." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization/offloading behavior is unrelated to the T5 apex RMSNorm memory leak." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Exact same Qwen2_5_VLProcessor.apply_chat_template batched-input crash when padding=False; clearly the same bug." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Local-path slash import warning is unrelated to a multimodal token-counting video-branch NameError." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Different failures: auto device mapping cudaErrorAssert vs PEFT adapter checkpoint loading." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both are tokenizer/config related, but one is runtime post-processor refresh and the other is save/load token-ID loss." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Image resolution handling and bfloat16 dtype mismatches are different bugs." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Composite-config unwrapping and CPU-offload rotary embedding compatibility are separate Qwen issues." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer load failures, but they affect different models and likely different root causes." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL is unrelated to inputs_embeds/past_key_values generation behavior." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Sliding-window support and missing Float8 storage are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sink-less crash is unrelated to multimodal text_config unwrapping." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A warning about tie_word_embeddings is not the same as incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Loading a specific model failing in v5.1.0 and PIL processors wrongly requiring torchvision are different bugs." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken special-argument collision and ScandiBERT loading failure are not the same code-path." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both mention processor/model mismatches, but they concern different models and distinct preprocessing errors." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "A memory leak in T5 RMSNorm and a missing supports_gradient_checkpointing flag are unrelated." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Special-token post-processor refresh and BigBirdTokenizer mask-token registration are different tokenizer bugs." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Gemma4 FSDP2 KeyError and a trust_remote_code capability flag issue are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": false, + "reason": "Both involve HF_HUB_OFFLINE, but one is a general cache-load failure and the other is a specific model_info() call in _patch_mistral_regex." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing in eval mode and DeepSpeed ZeRO-3 gradient inflation are separate training bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 44514/44545 are an exact title match and a credible duplicate pair, and the remaining verdicts are conservative rejections of clearly different issues. I don\u2019t see any overstatement of evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 15, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42915", + "issue:43295", + "issue:43381", + "issue:43388", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43596", + "issue:43618", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43819", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45704", + "issue:45834", + "issue:45859", + "issue:45907", + "issue:46032", + "issue:46050", + "issue:46294" + ], + "soft_pairs": [ + "issue:44918|issue:44936", + "issue:45704|issue:45859", + "issue:34634|issue:41720", + "issue:43421|issue:44186", + "issue:43381|issue:45704", + "issue:43525|issue:43531", + "issue:45081|issue:45356", + "issue:43540|issue:46294", + "issue:39692|issue:43873", + "issue:44625|issue:45479", + "issue:43782|issue:45381", + "issue:43994|issue:44671", + "issue:45356|issue:45907", + "issue:43720|issue:43819", + "issue:30064|issue:36010", + "issue:43746|issue:46050", + "issue:44077|issue:44625", + "issue:43596|issue:44220", + "issue:43653|issue:43720", + "issue:42915|issue:43746", + "issue:43540|issue:44008", + "issue:44220|issue:44661", + "issue:43618|issue:43697", + "issue:43550|issue:45072", + "issue:43746|issue:43873", + "issue:43295|issue:45834", + "issue:43550|issue:43819", + "issue:45183|issue:45479", + "issue:43388|issue:46032", + "issue:44186|issue:44898", + "issue:43716|issue:44008" + ], + "prepared_review_unit_hash": "37c8d9ec912e7225b32bebddde86cfaf385cf1490f1ada9fdb521d205fdd9c27", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37250, + "estimated_input_tokens": 9313, + "estimated_eval_tokens": 18882 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous and does not contain any clear duplicate pair; most items are unrelated bug reports across different models, tokenizers, trainers, and quantization/offload paths. Best representative issue is the broad, active quantization/offloading report.", + "confidence": 0.91, + "canonical_issue_reason": "issue:43873 is the most central and broadly phrased report, with the highest discussion and reference activity in this set, so it is the best cluster anchor despite the cluster not being a true duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the strongest representative issue because it is active, widely discussed, and covers a general runtime behavior problem rather than a narrow model-specific edge case.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Both mention trainer-related failures, but one is about Qwen3.5 input embeddings unpacking and the other is about evaluate-after-train behavior; different bugs and code paths." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "T5 Apex RMSNorm memory leak and Qwen3_5MoE CPU offload incompatibility are unrelated model/runtime issues." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice preset handling and Qwen3 auto device mapping CUDA asserts are unrelated subsystems and failure modes." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "One is about TokenizersBackend not refreshing post-processing after runtime special-token changes; the other is a LayoutLMv2Tokenizer crash on NER padding/truncation." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing in eval mode and a T5 RMSNorm memory leak are distinct issues with no shared concrete code path." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Llama4Config missing pad_token_id and Qwen3-MoE sliding_window behavior are different configuration bugs." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both involve tokenizer regex/codec handling, but the reports target different models and different concrete failures; not the same bug." + }, + { + "left": "issue:43540", + "right": "issue:46294", + "accept": false, + "reason": "Both are video-input issues, but one is a Qwen3OmniMoe ValueError and the other is a Qwen3.5 chat-template token/feature mismatch; different failure points." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 documentation example errors and quantization/offloading behavior are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Qwen3.5 num_labels propagation and the zero-loss single-label-classification bug are different configuration problems across different model families." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Qwen3VL weight_only loading failure and Qwen2.5-VL video vision_position_ids mismatch are different multimodal bugs." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Different models and different symptoms: SigLIP2 nonsensical outputs vs CamemBERT masked-LM prediction regression." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Kimi tokenizer regression/warning and list_repo_files revision forwarding are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet packed-weight loading and DAC from_latents/STE mismatch are separate model implementation issues." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Image segmentation-map processing and a GenerationMixin import error are entirely unrelated." + }, + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "PEFT adapter checkpoint loading and sinq quantized save/load breakage are different persistence/loading bugs." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Optional post_init policy for patchtsmixer and Qwen3.5 num_labels propagation are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "DeepSpeed ZeRO3/BertModel initialization and _torch_extract_fbank_features are unrelated paths." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and BitNet packed-weight loading are unrelated tokenizer vs model-loading issues." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and GraniteSpeech PEFT checkpoint loading are different model-specific problems." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Qwen3OmniMoe video-input processing and Gemma3n forward variable collision are unrelated multimodal bugs." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction and add-new-model-like/tokenizer-mapping logic are different code paths." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "CLIPOutput attentions assignment and RTDetrV2 output differences in v5 are different regression reports." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "PEFT adapter checkpoint loading and quantization/offloading behavior do not describe the same underlying bug." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Processor.tokenizer regression and Kosmos2.5 OCR index errors are different model/input-processing issues." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Different failure modes: compiled SDPA on Bamba vs DAC latent reconstruction mismatch." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Validation error messaging for input_ids/inputs_embeds and degenerate zero loss are separate classification issues." + }, + { + "left": "issue:43388", + "right": "issue:46032", + "accept": false, + "reason": "gather_for_metrics label truncation and Mamba2Mixer use_cache correctness are unrelated trainer vs model logic bugs." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "LayoutLMv2Tokenizer batching crash and Perceiver non-default resolution interpolation failure are different model/tokenizer issues." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Mistral-3 image-preprocessor dtype mismatch and Gemma3n variable-name collision 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": 1, + "component_count": 18, + "review_unit_index": 16, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:30064", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:43322", + "issue:43335", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43653", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43950", + "issue:43994", + "issue:44062", + "issue:44186", + "issue:44442", + "issue:44448", + "issue:44479", + "issue:44485", + "issue:44488", + "issue:44509", + "issue:44561", + "issue:44671", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45381", + "issue:45584", + "issue:45685", + "issue:45834", + "issue:45987", + "issue:46192" + ], + "soft_pairs": [ + "issue:43335|issue:43756", + "issue:44062|issue:44488", + "issue:43653|issue:43819", + "issue:43531|issue:43643", + "issue:43950|issue:45987", + "issue:44843|issue:45081", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:43540|issue:45381", + "issue:44448|issue:44671", + "issue:30064|issue:36331", + "issue:43782|issue:44977", + "issue:43577|issue:43818", + "issue:39692|issue:45834", + "issue:45584|issue:45834", + "issue:44821|issue:45084", + "issue:43322|issue:45685", + "issue:43606|issue:45072", + "issue:44479|issue:45834", + "issue:43825|issue:43994", + "issue:44186|issue:44442", + "issue:34634|issue:36010", + "issue:44485|issue:44509", + "issue:44561|issue:45020", + "issue:45987|issue:46192", + "issue:43577|issue:43582" + ], + "prepared_review_unit_hash": "7478ce8b898c320bdf3c2613aa948ac94e1b35ee7188f0cd7f937fe3cab345e7", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35067, + "estimated_input_tokens": 8767, + "estimated_eval_tokens": 17790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a collection of unrelated issue reports; the soft-similarity pairs are largely false positives across different models, tokenizer behaviors, or API regressions. The closest thematic cluster is the remote_code/config-loading regressions, for which the broadest representative is issue #45020.", + "confidence": 0.4, + "canonical_issue_reason": "#45020 is the broadest umbrella report in the only clear thematic cluster (remote_code-related breakages), so it is the best representative issue title for triage.", + "canonical_pr_reason": null, + "best_issue_reason": "#45020 best captures the shared remote_code regression theme while remaining broad enough to represent adjacent config-loading breakages without being overly narrow.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different bugs: sparse-layer construction in SwitchTransformersConfig vs Smollm3 RoPE-layer dropping; no shared concrete code path." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "One is an AddedToken argument duplication error; the other is a model load failure for cjvt/sleng-bert. Same tokenizer area, but different root causes." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "BigBird special-token decoding bug vs DAC latent/STE mismatch; unrelated behavior and fix surface." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Qwen3-MoE sliding-window handling and remote_code config-field loss are different problems in different subsystems." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Both are regressions, but one corrupts non-persistent buffers in from_pretrained and the other returns the wrong type from StaticCache.get_seq_length()." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both involve _patch_mistral_regex, but one is an offline hub lookup issue and the other is an AttributeError on tokenizer object shape; not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both touch config loading, but one returns incomplete AutoConfig data while the other rejects strict granite_speech loading; distinct failures." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Runtime special-token/post-processor updates and Whisper batch_decode skip_special_tokens handling are different code paths." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both are video-input bugs, but they affect different Qwen model families and have different symptoms/root causes." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Pegasus v4/v5 output mismatch and CamemBERT masked-LM regressions are separate model-specific issues." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Void segmentation-map processing and CustomTrainer.compute_loss signature changes are unrelated." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3VL weight_only loading failure and Qwen3.5 flash-attention generation issues are different concrete bugs." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Blip2 dtype propagation and Video-LLaVA tower initialization/weight-sharing are not the same underlying defect." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "SigLIP2 docs/example errors and Kosmos2.5 long-OCR index errors are unrelated." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation and Kosmos2.5 OCR indexing are different model-specific failures." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-node compilation errors are unrelated." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next load segfault and MPS histogram_mps integer support error are different bugs." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "Both are CI/device-dtype regressions, but they affect different mechanisms and models; not a single fixable bug." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Qwen video-input regression and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is a stale pipeline error message/docs issue; the other is incorrect inference output for SigLIP2." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 NER/padding crash and AutoTokenizer loading FastSpeech2ConformerTokenizer are distinct tokenizer issues." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset handling and GenerationMixin import failure are unrelated." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion and docs mentioning removed pipeline tasks are not the same bug or change." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Both mention remote_code breakage, but #44561 is a specific is_torch_fx_available regression while #45020 is a broader umbrella report." + }, + { + "left": "issue:45987", + "right": "issue:46192", + "accept": false, + "reason": "Both are API regressions around tokenizer/cache inputs, but they affect different parameters and code paths." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype propagation and Apple Silicon caching_allocator_warmup TypeError are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 17, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28218", + "issue:29159", + "issue:42175", + "issue:43262", + "issue:43329", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43550", + "issue:43582", + "issue:43638", + "issue:43644", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43749", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:44060", + "issue:44368", + "issue:44589", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44811", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44991", + "issue:45003", + "issue:45020", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45538", + "issue:45600", + "issue:45701", + "issue:46209", + "issue:46285" + ], + "soft_pairs": [ + "issue:28218|issue:29159", + "issue:44610|issue:45072", + "issue:44805|issue:44936", + "issue:43720|issue:45072", + "issue:43452|issue:44991", + "issue:43825|issue:43827", + "issue:43582|issue:44857", + "issue:43404|issue:43782", + "issue:45081|issue:45406", + "issue:42175|issue:45081", + "issue:43906|issue:46209", + "issue:44671|issue:45701", + "issue:43262|issue:43819", + "issue:45003|issue:46285", + "issue:43526|issue:43697", + "issue:43653|issue:44912", + "issue:44060|issue:44368", + "issue:43650|issue:43906", + "issue:43742|issue:45020", + "issue:45084|issue:45538", + "issue:43329|issue:45600", + "issue:43746|issue:44811", + "issue:44589|issue:45042", + "issue:43644|issue:43749", + "issue:43638|issue:44936", + "issue:43550|issue:44912" + ], + "prepared_review_unit_hash": "ca3302152f2befd319661c03425339072a01ebcea43316ffd1689a8c0648c9d8", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35118, + "estimated_input_tokens": 8780, + "estimated_eval_tokens": 17816 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The items are mostly unrelated one-off issues; only one soft edge looks plausibly duplicate-level from titles alone. The rest appear to be distinct bugs affecting different models, loaders, or runtime paths.", + "confidence": 0.58, + "canonical_issue_reason": "issue:45020 is the best high-signal, broadly scoped regression report in this set; it is concrete enough to be actionable and broad enough to represent a wider breakage class.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 has the clearest user-facing regression framing and the broadest applicability among these unrelated issues, so it is the strongest canonical candidate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer spacing/inconsistency regression around added tokens; 29159 is the broader formulation of the same bug." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Different subsystems and failure modes: image size mismatch vs bfloat16 dtype mismatch." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "An indexing shape error during masking is unrelated to evaluate-after-train behavior." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading in BitNet is unrelated to dtype mismatches in inference." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading, but the concrete failure modes and affected code paths differ." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "One is an incorrect runtime error message, the other is stale docs; related topic, not the same bug." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon allocator TypeError and CUDA AMP loss crash are separate issues." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Different model families and distinct loading/tie-weight problems." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Different attributes, different components, and different model/processor paths." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend packaging mismatch is unrelated to Mistral regex patching." + }, + { + "left": "issue:43906", + "right": "issue:46209", + "accept": false, + "reason": "A reproduction of one earlier issue is not the same as an FP8 inference failure." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "Generic tokenization changes are too broad to be the same as CamemBERT masked-LM prediction regressions." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio sampling-rate defaulting and DAC latent reconstruction are unrelated." + }, + { + "left": "issue:45003", + "right": "issue:46285", + "accept": false, + "reason": "Unsafe sys.modules access is a different problem from CLIP text model structure inconsistency." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Label-reduction bug in BEIT preprocessing is unrelated to RTDetrV2 output drift." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Tokenizer special-token registration and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weight warnings, but the models and concrete failure descriptions differ enough that this is not clearly the same bug." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Placeholder issue text is unrelated to a technical reproduction report." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "MobileLLM loading key errors are not the same as broad remote_code breakage." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation errors and tokenizer max-length configuration are different issues." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token counting bug and auto_mappings CI breakage do not share the same underlying defect." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "Checkpoint loading with PEFT adapters is unrelated to Whisper batch_decode skipping special tokens." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup failure and torchvision dependency regression are separate." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer junk filling and FSDP CPU RAM efficient loading are different loading bugs." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO3 index error is unrelated to trainer.evaluate failing after train." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "Torch.compile/SDPA failure and MXFP4 quantization fallback are unrelated model execution paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The single accepted soft edge (28218/29159) is plausibly duplicate-level from the titles, while the other pairs are reasonably rejected as distinct bugs. Canonical issue choice is also defensible within this mixed set." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 18, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:29159", + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:42490", + "issue:42915", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43645", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:43931", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44610", + "issue:44811", + "issue:44849", + "issue:44912", + "issue:44977", + "issue:45042", + "issue:45356", + "issue:45372", + "issue:45459", + "issue:45701", + "issue:45759", + "issue:45803", + "issue:45859", + "issue:46326" + ], + "soft_pairs": [ + "issue:45372|issue:46326", + "issue:43819|issue:43927", + "issue:34634|issue:36331", + "issue:43854|issue:44977", + "issue:39692|issue:44912", + "issue:36010|issue:43645", + "issue:38175|issue:44610", + "issue:43720|issue:44610", + "issue:45459|issue:45803", + "issue:43454|issue:43577", + "issue:43526|issue:44554", + "issue:36010|issue:36331", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43257|issue:43329", + "issue:43643|issue:45759", + "issue:42490|issue:43257", + "issue:43329|issue:43450", + "issue:43606|issue:45859", + "issue:34567|issue:40990", + "issue:44568|issue:45356", + "issue:29159|issue:34567", + "issue:43329|issue:44479", + "issue:42915|issue:43742", + "issue:43257|issue:43931", + "issue:44291|issue:45042", + "issue:43452|issue:43582", + "issue:43927|issue:44912", + "issue:44849|issue:45701" + ], + "prepared_review_unit_hash": "3faa9713077b24b91377f6b3c3c6190280ef2ec493207d3510e866d96488eeb4", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37021, + "estimated_input_tokens": 9256, + "estimated_eval_tokens": 18768 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated. The only strong soft edge is the Qwen video regression pair, with 44479 as the broad umbrella report and 43329 as a narrower report on the same video-token counting path. No PRs were provided.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 44479 is the broadest and most representative report in the cluster for the Qwen video-input regression; 43329 is a narrower related report focused on the same video-token counting path.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44479 is the best global issue candidate because it captures the shared user-facing Qwen video regression across multiple VL/MoE variants and serves as the clearest umbrella report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45372", + "right": "issue:46326", + "accept": false, + "reason": "Both mention mistral_common/tokenizer behavior, but they describe different failures and code paths: Gemma 4 processor loading import error vs continue_final_message handling." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "Different models and bugs: DAC from_latents/STE mismatch versus DiaConfig save/load token ID loss." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Unrelated subsystems: BarkProcessor voice_preset versus Trainer compute_loss signature compatibility." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Both are model-loading/generation problems, but they affect different models and concrete code paths." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "SigLIP2 doc-example errors are unrelated to GPT-OSS MXFP4 quantization fallback." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import break and Jupyter custom-model initialization are distinct bugs." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Different image-model failures: zero probabilities in SigLIP2 versus wrong processor output size in OmDet-Turbo." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight loading for BitNet is unrelated to OmDet-Turbo input-shape mismatch." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both involve error handling, but they affect different code paths and different failure modes." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision lm_head tying and BLIP2 dtype propagation are separate model-loading bugs." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Beit label reduction and MPS attention correctness are unrelated issues." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "GenerationMixin import break and custom compute_loss signature incompatibility are different failures." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "Both touch loading, but FSDP CPU RAM efficient loading and init_empty_weights/_is_hf_initialized are different failure modes." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to the PIL backend torchvision requirement regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate defaults and Whisper batch_decode special-token handling are different processor bugs." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MOE weight conversion under accelerate+deepspeed is unrelated to the multimodal token-counting video branch bug." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config loading, but missing fields from trust_remote_code and unwrapping text_config for composite Qwen configs are different problems." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash import warning and Qwen3 MOE weight conversion are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both are video-related, but one is an undefined-helper bug in multimodal token counting and the other is a batched processor shape issue." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both mention CPU offload, but they affect different models and different code paths." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token-count tracking and GPT-OSS perplexity are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but they concern different models and different behaviors." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer fast/slow inconsistency and TrainerState num_input_tokens_seen are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "Same underlying Qwen video-input regression in the multimodal token/video path; 43329 isolates the undefined helper issue, while 44479 reports the broader regression across Qwen VL/MoE variants." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config and MobileLLM loading key errors are different model-loading bugs." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3 MOE weight conversion and Qwen3-VL weight-shape mismatch are separate loading failures." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to the PIL backend torchvision dependency change." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "gguf_file loading errors and Apple Silicon caching_allocator_warmup TypeError are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig token ID persistence and GPT-OSS MXFP4 fallback are different bugs." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-states behavior and a generic tokenization-version-change report are not the same concrete bug." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The soft-edge verdicts are mostly conservative, but the overall rationale slightly overstates the evidence: the packet supports 44479 as the broad Qwen video-regression issue and 43329 as a narrower related report, but it does not explicitly establish an \"accepted duplicate pair\" in the source data. Safer wording would avoid claiming duplicate-status beyond what the packet shows." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 19, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:24643", + "issue:29159", + "issue:33357", + "issue:34567", + "issue:36331", + "issue:38175", + "issue:41720", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43493", + "issue:43540", + "issue:43577", + "issue:43646", + "issue:43696", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44560", + "issue:44568", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44898", + "issue:44913", + "issue:44964", + "issue:44987", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45488", + "issue:45538", + "issue:45588", + "issue:45907", + "issue:45987", + "issue:46121" + ], + "soft_pairs": [ + "issue:43697|issue:45357", + "issue:41720|issue:43540", + "issue:42915|issue:44821", + "issue:44568|issue:45488", + "issue:42915|issue:45538", + "issue:33357|issue:34567", + "issue:44987|issue:45538", + "issue:43317|issue:45538", + "issue:44479|issue:45381", + "issue:43540|issue:44479", + "issue:43540|issue:44560", + "issue:24643|issue:29159", + "issue:45137|issue:45405", + "issue:44987|issue:45907", + "issue:43742|issue:44291", + "issue:43577|issue:45072", + "issue:38175|issue:44898", + "issue:44062|issue:44991", + "issue:44737|issue:45588", + "issue:43257|issue:43696", + "issue:43404|issue:45987", + "issue:34567|issue:36331", + "issue:43646|issue:43749", + "issue:44062|issue:45081", + "issue:44913|issue:46121", + "issue:43493|issue:43994", + "issue:43257|issue:43756", + "issue:43749|issue:44756", + "issue:44792|issue:44964", + "issue:43906|issue:45381", + "issue:44291|issue:44821" + ], + "prepared_review_unit_hash": "c35c5b6f31c52ec82edbeeeba79ab9f76b4472e55a820c858e4dbe9ac1fb6021", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37136, + "estimated_input_tokens": 9284, + "estimated_eval_tokens": 18824 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a mix of unrelated transformer/model-loading regressions. I only see two true duplicate-style pairs: the SigLIP2 implementation issue and the Qwen video-input regression pair.", + "confidence": 0.69, + "canonical_issue_reason": "issue:44479 is the broadest, most representative bug report here: it describes a concrete video-input regression across several Qwen variants and can subsume the closer duplicate-style report in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the strongest issue candidate because it is specific, user-facing, and broad enough to serve as the representative issue for the video-input subcluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Different bugs: one is a training/runtime failure with DeepSpeed, the other is a save_pretrained key regression for Qwen3.5 multimodal models." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Different model families and failures: CUDA device-mapping assert on Qwen3 vs. video-input ValueError on Qwen3OmniMoe." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Unrelated: Qwen3Moe FP8 loading failure vs. AutoImageProcessor URL loading problem." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Both are tokenizer bugs, but the concrete failures differ: mDeBERTa special-token handling vs. LlamaTokenizer overwriting ByteLevel pre-tokenization." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Unrelated issues: Qwen3Moe FP8 config failure vs. CLIPTokenizer model_max_length behavior." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "No shared bug path: MacOS bus error on a CLIP model vs. TrainerState token-count tracking not updating." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Different problems: model loading regression for physical-intelligence/fast vs. tokenizer max_length default for CLIPTokenizer." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Different failure modes: device_map/offload load error vs. tokenizer max_length semantics." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Same underlying video-input regression in Qwen multimodal code: 45381 is a specific manifestation of the broader v5.3.0 video-input bug described in 44479." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both involve video processing, but the model families and concrete error paths are different enough that this is not clearly the same bug." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "Unrelated: DeepSpeed training weight-shape error vs. tokenizer slow/fast inconsistency." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "Completely unrelated: DeepSpeed ZeRO3 deque error vs. version-bump issue for MIN_PEFT_VERSION." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "No common bug path: model loading regression vs. hub API revision-forwarding issue." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "Both are loading-time errors, but they are different code paths and failure causes: MobileLLM key error vs. init_empty_weights unexpected argument." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Different dtype issues in different models; not the same concrete bug." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 zero probabilities vs. Perceiver non-default-resolution failure." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Tokenizer loading bugs, but one is an AddedToken argument collision and the other is a model-specific tokenizer load failure." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "Unrelated: XLNet CPU allocation bug vs. flash-attention crash on sink-less models." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Different issues: Qwen3 MoE weight conversion with accelerate/deepspeed vs. GPT-oss-20b OOM." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Different code paths: lm_head tying bug vs. StaticCache sequence-length return type bug." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Both are Trainer-related, but one is a state counter update bug and the other is a breaking API signature change." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Unrelated: custom model initialization breakage vs. FSDP CPU RAM efficient loading regression." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer bugs: AddedToken keyword collision vs. Mistral regex patch crashing on backend_tokenizer access." + }, + { + "left": "issue:44913", + "right": "issue:46121", + "accept": false, + "reason": "Both involve RoPE/config handling, but one is silent reload fallback and the other is a validation TypeError with JSON-loaded lists." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same underlying SigLIP2 implementation discrepancy: 43994 is the user-facing symptom of the model behaving incorrectly compared with the reference implementation." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Different Qwen3-related issues: MoE weight conversion failure vs. Smollm3 RoPE-layer mismatch." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Both mention loading/memory, but one is an FSDP loading regression and the other is a Strix Halo mmap/OOM issue." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different multimodal failures: a janus image-generation test failure vs. Phi-4-multimodal model loading failure." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Cannot confirm same bug from the titles alone; 43906 is only a reproduction of another issue, while 45381 is a specific qwen2.5-vl video-input regression." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Different loading failures: init_empty_weights argument mismatch vs. AutoImageProcessor URL loading." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: 44479 is a broader Qwen video-input regression report, and the two accepted pairs (43493/43994 and 44479/45381) are conservatively framed as duplicate-style matches. The many rejected pairs are also appropriately cautious and mostly correspond to clearly different model families or bug classes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 20, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:24643", + "issue:28282", + "issue:29127", + "issue:34689", + "issue:36010", + "issue:41762", + "issue:42175", + "issue:43452", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43819", + "issue:43824", + "issue:43906", + "issue:44466", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44811", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44977", + "issue:45005", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45372", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45600", + "issue:45920", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:36010|issue:42175", + "issue:28282|issue:34689", + "issue:42175|issue:43824", + "issue:45042|issue:45081", + "issue:43452|issue:44488", + "issue:45357|issue:45920", + "issue:43742|issue:44589", + "issue:45405|issue:45600", + "issue:28282|issue:29127", + "issue:43526|issue:45479", + "issue:43643|issue:45375", + "issue:43531|issue:44821", + "issue:44625|issue:44877", + "issue:43756|issue:45325", + "issue:43697|issue:45216", + "issue:43582|issue:44977", + "issue:43720|issue:44898", + "issue:44514|issue:45381", + "issue:43452|issue:43577", + "issue:24643|issue:29127", + "issue:41762|issue:44936", + "issue:44466|issue:45005", + "issue:43452|issue:44843", + "issue:45372|issue:46170", + "issue:43819|issue:44811", + "issue:43906|issue:46202" + ], + "prepared_review_unit_hash": "8d47a178185e1fef8384ebe72b81b24de1581df6eca2674a5430768c61d425a7", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35404, + "estimated_input_tokens": 8851, + "estimated_eval_tokens": 17958 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly mixed: the soft-similar pairs mostly share broad themes like loading, config, tokenizer, or serialization, but they are not the same underlying bug/change. I would not merge any of the candidate pairs.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Different problems: missing GenerationMixin import vs packaging/backends missing TensorFlow in a torch install." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "One is PyTorch not installed; the other is a model-loading regression for Llama 3.2 Vision in 4.46.2." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Backend/package omission vs Qwen2_5_VL import failure; unrelated failure paths." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Torchvision dependency regression in image processors vs a Mistral regex patch AttributeError." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both involve loading, but one is gguf_file handling and the other is a specific model load failure; not the same bug." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Save_pretrained key regression vs tokenizer token-ID regression; different code paths." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "KeyError on one model load vs missing Float8 storage type; unrelated runtime failures." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "PEFT version pin issue vs stale auto_mappings references; different causes." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Missing PyTorch import and LayoutLMv3 box-validation messaging are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs sequence-classification zero-loss regression." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both config-related, but one is generic remote-code config field loss and the other is a specific Qwen3_5MoeVision strict-field drop." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Sliding-window bug in Qwen3-MoE vs AutoImageProcessor URL loading; unrelated." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "num_labels propagation bug vs strict config rejection for granite_speech; different underlying issues." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen/Smollm rope-position bugs with different models and mechanics." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "RTDetrV2 output drift in v5 vs Qwen3.5 save_pretrained regression; not the same bug." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "AppleSilicon allocator TypeError vs Qwen3.5 flash-attention generation issue; unrelated." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "BitNet packed-weight unpacking bug vs Perceiver resolution failure; different code paths." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Both Qwen2.5-VL, but one is chat-template batching/padding and the other is wrong video vision_position_ids." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "gguf_file loading regression vs BLIP2 dtype handling; unrelated." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "DeepSpeed training weight-shape runtime error vs LayoutLMv3 error-message clarity; not duplicates." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading failure vs trainer.evaluate() after train; different subsystems." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but one is device-dependent serialization and the other is translation-model weight handling; too broad to merge." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "gguf_file loading regression vs offline mistral regex patch calling model_info(); different bugs." + }, + { + "left": "issue:45372", + "right": "issue:46170", + "accept": false, + "reason": "Gemma 4 processor import dependency issue vs Windows ROCm torch.distributed dependency problem." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC.from_latents mismatch vs Whisper batch_decode skip_special_tokens handling; unrelated." + }, + { + "left": "issue:43906", + "right": "issue:46202", + "accept": false, + "reason": "A reproduction of a prior issue vs a Gemma pipeline roundtrip failure; no 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": 1, + "component_count": 18, + "review_unit_index": 21, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28282", + "issue:29159", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:38175", + "issue:41720", + "issue:43295", + "issue:43504", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44484", + "issue:44493", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44610", + "issue:44704", + "issue:44743", + "issue:44843", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45290", + "issue:45356", + "issue:45491", + "issue:45542", + "issue:45588", + "issue:45823", + "issue:46002", + "issue:46050", + "issue:46178", + "issue:46209" + ], + "soft_pairs": [ + "issue:43295|issue:45356", + "issue:30064|issue:33666", + "issue:44936|issue:45823", + "issue:44484|issue:44704", + "issue:43653|issue:44361", + "issue:44361|issue:44442", + "issue:38175|issue:43295", + "issue:45542|issue:46178", + "issue:44514|issue:45290", + "issue:43577|issue:43697", + "issue:43653|issue:44568", + "issue:44493|issue:46050", + "issue:44843|issue:44991", + "issue:29159|issue:33357", + "issue:44464|issue:44743", + "issue:43653|issue:43927", + "issue:43531|issue:43742", + "issue:44464|issue:44977", + "issue:43550|issue:43927", + "issue:43643|issue:44561", + "issue:44977|issue:46209", + "issue:43550|issue:44361", + "issue:43577|issue:45588", + "issue:32090|issue:34567", + "issue:28282|issue:35141", + "issue:45491|issue:46002", + "issue:32090|issue:33666", + "issue:44466|issue:46050", + "issue:43504|issue:43720", + "issue:43504|issue:43550", + "issue:41720|issue:44464", + "issue:43504|issue:44610", + "issue:33666|issue:36010" + ], + "prepared_review_unit_hash": "0d89c5d3a6a230273a45e4f358014289db71bbdb8d622f6872cba127d43e9f6e", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37777, + "estimated_input_tokens": 9445, + "estimated_eval_tokens": 19146 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous: most items are distinct bugs spanning tokenizer loading/behavior, training, generation, model loading, and backend availability. I do not see any soft pair that is the same underlying issue, so none should be merged as duplicates.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 43653 is the closest anchor because the cluster\u2019s soft links skew toward tokenizer-related failures, and it has inbound references; however, this is not a strong canonical due to the overall mix of unrelated bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "43653 is the most representative issue among these because it sits near the most repeated theme in the set (tokenizer behavior/load regressions), but the cluster is too diverse for a true duplicate hub.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer/regression reports, but they describe different failures and code paths (processor.tokenizer/images handling vs codec/fix_mistral_regex behavior)." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Different subsystems and symptoms: image processor void-segmentation handling vs multi-GPU training for Qwen2-VL." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Unrelated problems: trainer state after train/evaluate vs device-map forward mismatch in Gemma4 PLE." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "One is about default shard size in save_pretrained; the other is AutoProcessor not forwarding kwargs to cached_file." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer bugs, but they affect different tokenizers and different failure modes (special-token registration vs AttributeError on tasks)." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both involve tokenizers, but one is an AttributeError in MLukeTokenizer and the other is AutoTokenizer failing to load a specific tokenizer class." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Different model/runtime issues: zero probabilities in SigLIP2 vs custom processor/tokenizer regression." + }, + { + "left": "issue:45542", + "right": "issue:46178", + "accept": false, + "reason": "Both concern optional backend detection, but they target different backends and different error conditions; not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both crash in apply_chat_template, but the triggers are different (batched padding=False vs assistant tool-call messages without content)." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Distinct issues: dtype propagation when loading BLIP2 vs output differences in RTDetrV2 under Transformers v5." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both are special-token related, but one is BigBirdTokenizer mask-token registration and the other is mdeberta BOS/EOS insertion behavior." + }, + { + "left": "issue:44493", + "right": "issue:46050", + "accept": false, + "reason": "Different serialization/loading problems: unexpected position-id keys vs quantized sinq model breakage after save/load." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer load regressions, but one is offline model_info patching and the other is a specific tokenizer failing on a particular model." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Slow-vs-fast tokenizer inconsistency is not the same as the MacOS bus error with a community CLIP model." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both mention generation/cache, but one is chunked generation with compiled forward and the other is recurrent-state reset in a specific modular Qwen3.5 implementation." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Different bugs: BigBirdTokenizer special-token registration vs DiaConfig losing custom token IDs on save/load." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Distinct issues: Qwen3-MoE sliding_window behavior vs key error loading MobileLLM-125M." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but they concern different models and different mechanisms (compiled forward chunking vs flash-attention behavior)." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Different failure classes: torch.compile/SDPA on Bamba vs configuration token-ID loss on save/load." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both involve trust_remote_code-ish compatibility, but one is missing fields in AutoConfig and the other is removal of is_torch_fx_available." + }, + { + "left": "issue:44977", + "right": "issue:46209", + "accept": false, + "reason": "Unrelated model/runtime issues: Qwen3.5 flash-attention generation vs FP8 inference failing on B200." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "Different problems: Bamba torch.compile + SDPA vs MLukeTokenizer task AttributeError." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Both are model/runtime edge cases, but one is BLIP2 dtype loading and the other is flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast NoneType error and TrainerState token counter not updating are different trainer bugs." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "ImportError for missing PyTorch and embedding reinitialization after resizing are unrelated." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but one is a GPU sliding-window attention issue and the other is NaNs in classification heads after checkout/init." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Different areas: trainer GPU broadcast error vs Qwen2-VL multi-GPU training discussion." + }, + { + "left": "issue:44466", + "right": "issue:46050", + "accept": false, + "reason": "Different serialization/regression topics: lm_head.weight serialization vs sinq quantized save/load breakage." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Both are loading-related, but one is a legacy field in Beit semantic segmentation and the other is BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Distinct bugs in different models and stacks: Beit preset loading vs Bamba torch.compile with SDPA." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Qwen3 auto device-map cudaErrorAssert and chunked generation compiled-forward inconsistency are different failure paths." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Different model-loading vs preprocessing issues: Beit legacy field vs OmDet-Turbo processor output size mismatch." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and GenerationMixin import failure are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 22, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:36331", + "issue:39692", + "issue:43262", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43825", + "issue:43927", + "issue:43994", + "issue:44361", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44625", + "issue:44821", + "issue:44843", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45229", + "issue:45357", + "issue:45405", + "issue:45440", + "issue:45812", + "issue:45823", + "issue:46050", + "issue:46192", + "issue:46209", + "issue:46285" + ], + "soft_pairs": [ + "issue:43688|issue:45440", + "issue:43742|issue:44821", + "issue:45823|issue:46050", + "issue:28282|issue:32090", + "issue:43262|issue:43295", + "issue:28282|issue:33357", + "issue:43720|issue:43927", + "issue:43994|issue:46192", + "issue:43452|issue:44451", + "issue:43606|issue:43927", + "issue:44849|issue:46209", + "issue:33666|issue:36331", + "issue:43525|issue:43572", + "issue:43720|issue:44361", + "issue:43756|issue:44913", + "issue:43493|issue:43825", + "issue:39692|issue:43493", + "issue:44964|issue:45405", + "issue:44479|issue:44625", + "issue:43577|issue:44554", + "issue:44849|issue:45357", + "issue:43688|issue:43749", + "issue:44568|issue:45812", + "issue:43540|issue:44977", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:39692|issue:43295", + "issue:44493|issue:46285" + ], + "prepared_review_unit_hash": "81544dd06dbaefe6c2923c5eeaac12567e9c9795a9aeef68fd95d9fec1d903bd", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36165, + "estimated_input_tokens": 9042, + "estimated_eval_tokens": 18340 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are unrelated model/config/tokenizer regressions rather than duplicates. No soft edge looks like the same underlying bug, so all candidate merges are rejected. If forced to pick a representative issue, the broad tokenizer regression in Granite is the strongest single example.", + "confidence": 0.79, + "canonical_issue_reason": "issue:45812 is the broadest, clearest user-facing regression in the set: a silent AutoTokenizer token-ID bug affecting all Granite models, making it the best representative issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 has the strongest cluster-wide signal because it describes a general, high-impact tokenizer regression rather than a narrow model-specific edge case.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related, but they describe different failures and code paths: aux-loss normalization vs model implementation divergence." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "A model load KeyError for MobileLLM is unrelated to loading AutoImageProcessor from a URL." + }, + { + "left": "issue:45823", + "right": "issue:46050", + "accept": false, + "reason": "Gemma4 device-mapping forward mismatch and sinq save/load quantization breakage are different bugs." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "ImportError for missing PyTorch and a Trainer GPU broadcast NoneType TypeError are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate handling and multimodal processor/tokenizer regression are different code paths." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Missing PyTorch import error is unrelated to the MacOS CLIP bus error regression." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "BitNet packed-weight loading and DiaConfig token-ID persistence are different failures." + }, + { + "left": "issue:43994", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 wrong results and ignored return_tensors in text_kwargs are unrelated tokenizer/pipeline behaviors." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both involve loading models, but one is gguf handling for tokenizer/causal LM and the other is a specific model load failure." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch is unrelated to config token-ID loss on save/load." + }, + { + "left": "issue:44849", + "right": "issue:46209", + "accept": false, + "reason": "Qwen3.5 hidden-state output bug and FP8 B200 inference failure are different issues." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL and a custom Trainer signature error are not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both mention missing pad-token config fields, but they affect different model configs and different attributes." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading is unrelated to MLukeTokenizer AttributeError on tasks." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer omission and GPTNeoX rotary_pct reload regression are separate positional-encoding bugs." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and a misleading pipeline translation error message are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Documentation/example mistakes are not the same as the SigLIP2 HF-vs-JAX implementation divergence." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "A model load regression and an unreleased PEFT version bump are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression across Qwen variants and num_labels propagation in Qwen3.5 are different problems." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "BLIP2 dtype propagation and an MPS attention correctness issue are unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Output_hidden_states behavior and incorrect save_pretrained visual encoder keys are different regressions." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization and FSDP CPU RAM efficient loading are different training/runtime issues." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is special-token insertion for mDeBERTa and the other is wrong token IDs for Granite; different code paths." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Video processing in Qwen3OmniMoe and flash-attention generation in Qwen3.5 are not the same bug." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Text-only mm_token_type_ids behavior and Gemma4 multi-GPU inference OOM are unrelated." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "A model failing to load and an offline-mode tokenizer regex bug are different causes." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "A doc-example mismatch/quantization issue is unrelated to a processor.tokenizer API regression." + }, + { + "left": "issue:44493", + "right": "issue:46285", + "accept": false, + "reason": "Unexpected position-id keys and CLIP text-model structural inconsistency are different model-structure regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 23, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:29159", + "issue:29942", + "issue:30333", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:43257", + "issue:43278", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44792", + "issue:44964", + "issue:45083", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45584", + "issue:45588", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:43688|issue:45704", + "issue:43756|issue:45083", + "issue:43493|issue:43844", + "issue:43334|issue:43572", + "issue:43646|issue:44466", + "issue:45229|issue:45823", + "issue:33357|issue:33666", + "issue:43334|issue:45759", + "issue:43927|issue:44361", + "issue:43824|issue:44589", + "issue:44589|issue:45520", + "issue:43504|issue:43606", + "issue:43278|issue:43844", + "issue:44625|issue:45759", + "issue:43257|issue:43299", + "issue:43572|issue:44291", + "issue:43575|issue:45405", + "issue:43504|issue:43653", + "issue:43606|issue:44112", + "issue:44792|issue:45405", + "issue:43688|issue:45701", + "issue:45588|issue:46050", + "issue:44464|issue:45584", + "issue:43994|issue:44493", + "issue:44423|issue:44734", + "issue:29942|issue:30333", + "issue:43844|issue:44964", + "issue:43688|issue:43873", + "issue:29159|issue:32090" + ], + "prepared_review_unit_hash": "8e7e893484b0630698639ee4c0ea1b00902dd45428ac31fabeccf0361fd07890", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35897, + "estimated_input_tokens": 8975, + "estimated_eval_tokens": 18206 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The soft pairs are mostly superficial topical matches across unrelated bugs, model families, or code paths. None look like the same underlying defect, so no duplicate merge is justified. The broadest representative issue is the tokenizer-regression report (45701), but it is not a true canonical duplicate for the rest.", + "confidence": 0.8, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the broadest and most reusable report in the set because it describes a general tokenizer-version regression, but it still does not match the other reports closely enough to serve as a true canonical duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Different bugs: auxiliary-loss normalization in MoE models vs a T5/apex RMSNorm memory leak." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Unrelated failures: RoPE-layer dropping in Smollm3 vs a feature-extraction length helper issue in qwen3_omni_moe." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "Both are model-quality regressions, but one is SigLIP2 implementation mismatch and the other is ZeRO-3 gradient blowup; not the same code-path problem." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both mention missing config fields after the 5.0 update, but they affect different models and different attributes (`pad_token_id` vs `pad_token_idx`)." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage is not the same issue as device-dependent `lm_head.weight` serialization." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Same model family, but one is multi-GPU OOM and the other is a device-mismatch forward bug; different underlying failures." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "Completely different subsystems and symptoms: MacOS CLIP bus error vs Qwen2-VL multi-GPU training." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is a missing config attribute while the other is `from_config` not unwrapping `text_config`; not the same concrete bug." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer/config failures: lost custom token IDs after save/load vs a tokenizer AttributeError on tasks." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "ImportError for a missing Qwen2.5-VL class is unrelated to the Float8 storage type error." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Different failure modes: missing Float8 storage registration vs `flash_attn` KeyError on Python 3.13." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading issue for BEiT is unrelated to the Bark CPU-offload device mismatch." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype drift in evaluate is unrelated to the ZeRO-3 gradient anomaly." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "Both are Qwen3.5 config issues, but one is `num_labels` propagation and the other is `from_config` text-config unwrapping; too different to merge." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE loading, but one is accelerate+deepspeed weight conversion and the other is a dev-version load failure; not the same bug." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Both are 5.0 compatibility regressions, but one is a missing config field and the other is an unexpected `_is_hf_initialized` argument." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "CUDA OOM during tensor-parallel load is unrelated to an unmet PEFT version pin." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Different tokenizer issues: BEiT legacy-field loading vs BigBird mask token registration/empty decode." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "Different device-related problems: CPU offload mismatch vs a stale CI override test." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus image-generation test failure is unrelated to the PEFT version bump." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "MoE auxiliary-loss normalization is unrelated to a general tokenizer-version regression." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "Flash-attention sink handling error is unrelated to quantized save/load breakage." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency is unrelated to Whisper empty-transcription handling after token alignment." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 inference corruption and unexpected position-id keys are different problems." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve crashes, but one is a multimodal `.to` type error and the other is KV-cache indexing; different code paths." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention test failures are unrelated to MLflow reporting after training failure." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "Different model/runtime issues: ZeRO-3 gradient instability vs failure to load Phi-4 multimodal." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to quantization offloading behavior." + }, + { + "left": "issue:29159", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency is unrelated to the Trainer `_gpu_broadcast_one` NoneType error." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 24, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:33357", + "issue:34567", + "issue:38175", + "issue:39692", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43450", + "issue:43493", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43701", + "issue:43844", + "issue:43873", + "issue:43950", + "issue:43957", + "issue:44186", + "issue:44466", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44849", + "issue:44898", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45325", + "issue:45356", + "issue:45381", + "issue:45406", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45823", + "issue:46050", + "issue:46121", + "issue:46178", + "issue:46192", + "issue:46209", + "issue:46285" + ], + "soft_pairs": [ + "issue:28218|issue:34567", + "issue:44554|issue:45446", + "issue:45084|issue:45520", + "issue:15354|issue:38175", + "issue:43540|issue:45200", + "issue:44521|issue:45290", + "issue:43873|issue:46050", + "issue:45200|issue:45823", + "issue:43278|issue:43701", + "issue:45072|issue:45198", + "issue:44186|issue:46192", + "issue:45406|issue:46121", + "issue:43232|issue:44849", + "issue:45823|issue:46192", + "issue:43493|issue:43701", + "issue:28218|issue:33357", + "issue:43295|issue:43450", + "issue:43295|issue:44610", + "issue:39692|issue:46192", + "issue:44554|issue:45356", + "issue:45381|issue:46209", + "issue:43572|issue:44987", + "issue:43295|issue:43873", + "issue:44898|issue:45412", + "issue:43572|issue:43957", + "issue:43950|issue:46285", + "issue:44466|issue:45127", + "issue:43550|issue:43844", + "issue:45200|issue:45325", + "issue:45520|issue:46178", + "issue:43450|issue:43575" + ], + "prepared_review_unit_hash": "81ee6c8b1bc6940f69eae6c21e064ec08f667cb1b78697bcf55d2ef27384f72f", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37226, + "estimated_input_tokens": 9307, + "estimated_eval_tokens": 18870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a grab-bag of unrelated Transformers bugs and regressions across tokenization, chat templates, multimodal processors, generation, loading/serialization, quantization, and device/dtype handling. None of the soft pairs look like the same underlying bug/change, so no soft edge should be merged.", + "confidence": 0.97, + "canonical_issue_reason": "No single issue is a safe canonical because the items span many unrelated failure modes rather than one duplicate thread.", + "canonical_pr_reason": "No pull requests are present in the provided items, so there is no PR canonical to choose.", + "best_issue_reason": "No issue clearly subsumes the others; the set is too heterogeneous for a global best issue.", + "best_pr_reason": "No pull requests are present in the provided items, so there is no PR candidate to select.", + "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing bug vs TrainerState token-count update regression; different subsystems and symptoms." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness issue vs PyTorch version-check import bug; unrelated code paths." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Template-node compile error vs flash_attn backend lookup failure; not the same defect." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "torch.jit.script GeneratorExp limitation vs SigLIP2 probability anomaly; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video-input processing ValueError vs Gemma4 multimodal token-id defaulting; different model paths." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both touch chat templates, but one is all-zero assistant masks and the other is tool-call crash; different bugs." + }, + { + "left": "issue:43873", + "right": "issue:46050", + "accept": false, + "reason": "Quantization/offloading behavior vs sinq save/load corruption; different lifecycle stages." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Gemma4 mm_token_type_ids handling vs device_map auto forward device mismatch; unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "BF16-to-FP32 evaluation dtype drift vs resume checkpoint key mismatch; no shared root cause." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "bfloat16 inference dtype mismatch vs Wav2Vec2 save_pretrained/tokenization failure; different problems." + }, + { + "left": "issue:44186", + "right": "issue:46192", + "accept": false, + "reason": "LayoutLMv2 NER/padding crash vs return_tensors precedence bug; separate tokenizer issues." + }, + { + "left": "issue:45406", + "right": "issue:46121", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer vs rope-param dict conversion type error; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs update after sync_gpus vs Qwen3.5 hidden-states bug; different code paths." + }, + { + "left": "issue:45823", + "right": "issue:46192", + "accept": false, + "reason": "Device_map auto forward mismatch vs return_tensors being ignored; not the same bug." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 HF-vs-JAX discrepancy vs resume_from_checkpoint key mismatch; unrelated." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer extra-space bug vs MacOS bus error in CLIP model loading; different failure modes." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "processor.tokenizer regression vs batched video shape bug; different multimodal paths." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "processor.tokenizer regression vs OmDet processor/model size mismatch; unrelated." + }, + { + "left": "issue:39692", + "right": "issue:46192", + "accept": false, + "reason": "Documentation example errors vs tokenizer kwargs handling regression; not the same defect." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "Attention correctness on MPS vs Kimi-K2.5 tokenizer regression; unrelated." + }, + { + "left": "issue:45381", + "right": "issue:46209", + "accept": false, + "reason": "Qwen2.5-VL video position-id bug vs FP8 inference failure on B200; separate issues." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLmConfig missing pad_token_idx vs model-loading regression on v5.1.0; different root causes." + }, + { + "left": "issue:43950", + "right": "issue:46285", + "accept": false, + "reason": "from_pretrained buffer corruption vs CLIP text-model structure inconsistency; not the same bug." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resize/interpolation failure vs RT-DETR memory leak; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "lm_head serialization inconsistency vs LoRA merge collapse with extended vocab; different bugs despite tied-weights theme." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "torch.compile/SDPA failure vs ZeRO-3 gradient explosion; unrelated training/runtime issues." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma4 multimodal token-id defaulting vs Qwen2.5-VL rope scaling bug; different models and code paths." + }, + { + "left": "issue:45520", + "right": "issue:46178", + "accept": false, + "reason": "flash_attn import KeyError vs tensorflow_text backend mapping error; unrelated import machinery." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video shape bug vs OOM while loading a 57B model; no shared underlying defect." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 25, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43335", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43653", + "issue:43696", + "issue:43819", + "issue:43824", + "issue:43827", + "issue:43856", + "issue:43901", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44206", + "issue:44442", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44857", + "issue:45083", + "issue:45198", + "issue:45290", + "issue:45412", + "issue:45520", + "issue:45584", + "issue:45593", + "issue:45759", + "issue:46170", + "issue:46192", + "issue:46209", + "issue:46234", + "issue:46285", + "issue:46326" + ], + "soft_pairs": [ + "issue:43334|issue:43525", + "issue:37428|issue:43957", + "issue:42490|issue:43696", + "issue:43824|issue:43975", + "issue:43278|issue:43856", + "issue:45290|issue:46326", + "issue:43526|issue:46192", + "issue:38175|issue:43493", + "issue:43653|issue:44112", + "issue:42915|issue:43824", + "issue:43295|issue:43493", + "issue:44442|issue:45198", + "issue:38175|issue:45412", + "issue:37428|issue:43824", + "issue:43262|issue:43450", + "issue:44514|issue:44521", + "issue:45520|issue:46170", + "issue:45759|issue:46285", + "issue:44561|issue:46234", + "issue:41720|issue:46209", + "issue:44610|issue:44857", + "issue:43819|issue:44112", + "issue:43827|issue:43901", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:44857|issue:45593", + "issue:43335|issue:43550", + "issue:43606|issue:45083" + ], + "prepared_review_unit_hash": "591a66c154855ed8ee23c0f0a5edbfc40ce71846430645312506af0bc7c99f40", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35718, + "estimated_input_tokens": 8930, + "estimated_eval_tokens": 18116 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are different bugs, not true duplicates. The only strong duplicate candidates are the multimodal pad_token_id AttributeErrors and the SigLIP2 implementation-mismatch reports.", + "confidence": 0.72, + "canonical_issue_reason": "issue:43493 is the broader root-cause report for the SigLIP2 HF-vs-JAX discrepancy; issue:38175 reads like a specific symptom of that same model behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is open, actively discussed, has the most inbound references, and is a clean user-facing bug report suitable as a cluster anchor.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43334", + "right": "issue:43525", + "accept": true, + "reason": "Both report the same pad_token_id AttributeError in multimodal config handling; likely the same regression across model configs." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Different failures: a missing flash-attention import symbol vs meta-device loading breakage for some models." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Path-trailing-slash import warning and CUDA OOM are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "One is a missing Qwen2_5_VL export; the other is a detokenization regression." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Different symptoms and code paths: eval dtype drift vs MoE training memory usage." + }, + { + "left": "issue:45290", + "right": "issue:46326", + "accept": false, + "reason": "Both involve chat templates, but the concrete bugs differ: tool-call/no-content crash vs mistral_common continue_final_message behavior." + }, + { + "left": "issue:43526", + "right": "issue:46192", + "accept": false, + "reason": "Unrelated processor bugs: Beit reduce_labels shape/selection vs return_tensors being ignored with text_kwargs." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": true, + "reason": "Same SigLIP2 implementation mismatch; the zero-probability symptom fits the broader HF-vs-JAX discrepancy report." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Tokenizer special-token registration bug vs a stale CI device-override test." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Different models and failures: FineGrainedFP8Config issue vs Qwen2_5_VL import error." + }, + { + "left": "issue:43295", + "right": "issue:43493", + "accept": false, + "reason": "Processor.tokenizer regression and SigLIP2 numeric mismatch are different bugs." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Tokenizer loading failure and save_pretrained/tokenization failure are related only by tokenizer scope, not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 probability issue and RT-DETR memory release issue are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols and different model families." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio sampling-rate defaulting and batched video shape handling are different processor bugs." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both touch apply_chat_template, but one is a padding=False crash and the other is all-zero assistant masks; not the same concrete failure." + }, + { + "left": "issue:45520", + "right": "issue:46170", + "accept": false, + "reason": "flash_attn import KeyError on Python 3.13 is unrelated to Windows ROCm torch.distributed dependency issues." + }, + { + "left": "issue:45759", + "right": "issue:46285", + "accept": false, + "reason": "Both concern composite/text model structure, but they are different API regressions with different affected classes." + }, + { + "left": "issue:44561", + "right": "issue:46234", + "accept": false, + "reason": "Different missing helper symbols affecting different remote-code/model paths." + }, + { + "left": "issue:41720", + "right": "issue:46209", + "accept": false, + "reason": "Both are Qwen hardware/runtime failures, but one is auto device mapping on A800 and the other is FP8 inference on B200; different bugs." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor output size mismatch and AMP/CUDA loss crash are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "A forward-vs-from_latents mismatch is unrelated to a GraniteSpeech CI test issue." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs issues, but they target different pipelines and different deprecations." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "Different model/helper bugs with no shared code-path evidence." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center arg in an extractor is unrelated to Whisper empty-transcription generation." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "Float16 AMP crash and missing auxiliary losses are different D-FINE/LwDetr issues." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and Bamba torch.compile SDPA failures are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "Device-mismatch CPU offload bug and qwen3_omni_moe helper-length bug are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: 44521 has the strongest inbound-reference/activity profile, and the duplicate calls are conservative. The only accepted soft edges are plausibly the same bug class (pad_token_id config errors and the SigLIP2 discrepancy/symptom pair), while the rest are appropriately rejected as different failures." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 26, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28218", + "issue:29942", + "issue:32090", + "issue:35141", + "issue:37428", + "issue:39692", + "issue:42490", + "issue:43278", + "issue:43335", + "issue:43388", + "issue:43425", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43720", + "issue:43819", + "issue:43825", + "issue:43854", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44448", + "issue:44493", + "issue:44743", + "issue:44779", + "issue:44792", + "issue:44855", + "issue:44857", + "issue:45083", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45459", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859", + "issue:46234" + ], + "soft_pairs": [ + "issue:44792|issue:45563", + "issue:37428|issue:43425", + "issue:45200|issue:45588", + "issue:44448|issue:44743", + "issue:45127|issue:45245", + "issue:43611|issue:43931", + "issue:43335|issue:43653", + "issue:45290|issue:45381", + "issue:43819|issue:44493", + "issue:44855|issue:45083", + "issue:44206|issue:45823", + "issue:43550|issue:44112", + "issue:29942|issue:32090", + "issue:43335|issue:43504", + "issue:37428|issue:44351", + "issue:45588|issue:45859", + "issue:43278|issue:43825", + "issue:45459|issue:46234", + "issue:39692|issue:43526", + "issue:43388|issue:43526", + "issue:45310|issue:45478", + "issue:43335|issue:45083", + "issue:39692|issue:44493", + "issue:28218|issue:35141", + "issue:43720|issue:44112", + "issue:43335|issue:44112", + "issue:44448|issue:44779", + "issue:43335|issue:45593", + "issue:42490|issue:43854", + "issue:43606|issue:44857" + ], + "prepared_review_unit_hash": "558d53173a98bbc6bbe6b0440b053514a1b8d9b328e934f0dc8469851b2fd02b", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36338, + "estimated_input_tokens": 9085, + "estimated_eval_tokens": 18426 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a grab-bag of unrelated Transformers issues; only one soft pair looks like a true duplicate: the Qwen3.5 Moe from_pretrained regression reported twice with the same title and nearly identical scope.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45310 is the better canonical issue because it is the earlier report of the exact same Qwen3.5 Moe from_pretrained failure; issue:45478 reads like a later duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the strongest representative item in the cluster because it is a concrete, narrowly-scoped regression report and the only clear duplicate anchor here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Different bugs: a Janus generate_images test failure vs a stale warning in paged generate() for num_return_sequences." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "ImportError for a missing flash-attention helper is not the same issue as generic Torch 2.10 incompatibility." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 token-type-id behavior and a flash_attention.py s_aux=None crash are unrelated code paths." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output drift and Qwen3 recurrent-state reset are different model behaviors." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merging with extended vocab is unrelated to the 2^24 category-count runtime limit." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "Base_model_prefix loading regression and Qwen3-VL weight-shape mismatch are different load failures." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat-template tool-call handling and qwen2.5-vl vision_position_ids are separate bugs." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC.from_latents/STE mismatch is not the same underlying problem as unexpected position-id keys." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 IndentationError on import is unrelated to qwen3_omni_moe feature-extractor helper behavior." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Unsupported center argument in LasrFeatureExtractor and Gemma4 PLE device mismatch are different failures." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba-9B-v2 is unrelated to a stale GraniteSpeech device-override test." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures and a Trainer _gpu_broadcast_one NoneType error are different subsystems and symptoms." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers config creates sparse layers; Beit semantic-segmentation preset loading is a legacy-field issue." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Missing _flash_supports_window_size import and missing HybridCache import are both import errors but for different symbols and paths." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "flash_attention.py s_aux=None crash is not the same bug as Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype drift during evaluate and a stale pipeline translation warning are unrelated." + }, + { + "left": "issue:45459", + "right": "issue:46234", + "accept": false, + "reason": "Protobuf-related tokenizer error masking and a missing import_utils availability flag are different issues." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 documentation errors are unrelated to BeitImageProcessorFast reducing labels incorrectly." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "gather_for_metrics dropping tuple-label elements and BeitImageProcessorFast.reduce_labels are separate bugs." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same underlying bug: both report transformers>=5.4.0 / Qwen3.5 Moe from_pretrained failure with essentially identical scope and wording." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer creation and a qwen3_omni_moe helper function issue are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 docs example problems do not match the unexpected position-id key regression." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer adds an extra space after added token and output embedding reinitialization are different model/tokenizer behaviors." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "BitNet packed-weight unpacking during accelerate loading and a GraniteSpeech stale test are unrelated." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug and GraniteSpeech stale device-override test are not the same change or failure." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Pegasus output differences across versions and Deepseek tokenizer regressions are different model-specific issues." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformers config bug and D-FINE auxiliary-loss handling are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Local-path slash import warning and GLM-4.7-Flash unit-test loading failure are distinct loading problems." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch for bark-small and float16 AMP crash in LwDetrImageLoss are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, issue:45310 / issue:45478, is strongly supported by identical titles and near-identical scope, while the rest of the verdicts appropriately avoid overclaiming." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 27, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:25251", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:38175", + "issue:40444", + "issue:42490", + "issue:43278", + "issue:43381", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43611", + "issue:43653", + "issue:43701", + "issue:43746", + "issue:43927", + "issue:44360", + "issue:44448", + "issue:44466", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44743", + "issue:44779", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45803", + "issue:45823", + "issue:45920", + "issue:46192", + "issue:46209", + "issue:46285" + ], + "soft_pairs": [ + "issue:45920|issue:46192", + "issue:44360|issue:44561", + "issue:38175|issue:44493", + "issue:44857|issue:45072", + "issue:44977|issue:45229", + "issue:44448|issue:44977", + "issue:34689|issue:35141", + "issue:43701|issue:45083", + "issue:29127|issue:32090", + "issue:43550|issue:45083", + "issue:43927|issue:45698", + "issue:40444|issue:43526", + "issue:29942|issue:35141", + "issue:42490|issue:43575", + "issue:44561|issue:44779", + "issue:44977|issue:45563", + "issue:44857|issue:45588", + "issue:43412|issue:45588", + "issue:43746|issue:46209", + "issue:45372|issue:45588", + "issue:44568|issue:45491", + "issue:43278|issue:43381", + "issue:45588|issue:45823", + "issue:43611|issue:46285", + "issue:45198|issue:45803", + "issue:44448|issue:44466", + "issue:45245|issue:45563", + "issue:36010|issue:37428", + "issue:25251|issue:32090", + "issue:43653|issue:44743" + ], + "prepared_review_unit_hash": "bf02d94f5e77dece11ace7a70a6fec8f1070742d1546af4c621f5cb9572a9ebf", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36946, + "estimated_input_tokens": 9237, + "estimated_eval_tokens": 18730 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a collection of unrelated issue reports; the soft-pair similarities are mostly broad subsystem or version-regression overlap rather than the same concrete bug. No PRs are present. I would anchor the cluster on the broad tokenizer regression issue.", + "confidence": 0.91, + "canonical_issue_reason": "issue:45920 is the broadest and most representative concrete bug report here: an open, reproducible tokenizer regression affecting multiple named models, with clear impact and discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best single issue to represent the cluster because it is specific enough to be actionable yet broad enough to capture the main user-facing regression pattern in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45920", + "right": "issue:46192", + "accept": false, + "reason": "Different bugs: wrong token IDs from AutoTokenizer vs return_tensors being ignored when text_kwargs is passed." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "Unrelated failures: DSA indexer/ReLU discussion vs v5 trust_remote_code import break from removed helper." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Different symptoms and code paths: zero probabilities in SigLIP2 vs unexpected position-id key warnings." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "One is an AMP loss crash; the other is a bfloat16 dtype mismatch during inference." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Flash-attention generation bug vs multi-GPU CUDA OOM; not the same underlying issue." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Pegasus v4/v5 output regression is distinct from Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model loading failure for Llama 3.2 vision is not the same as post_init reinitializing lm_head after resize." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch and qwen3_omni_moe length helper behavior are different problems." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMv3 error-message clarity issue is unrelated to Trainer broadcasting NoneType errors." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA bug in Bamba is not the same as the qwen3_omni_moe feature-length helper bug." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load behavior, but one loses custom token IDs and the other loads the wrong custom module." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Multi-image IterableDataset finetuning failure is unrelated to BeitImageProcessorFast reduce_labels returning one label." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures and embedding reinitialization after resize are separate regressions." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Trailing-slash local model import warning is unrelated to tensor-parallel OOM on Qwen2-57B." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Removed is_torch_fx_available import break is distinct from DeepSeek tokenizer regression." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation malfunction is not the same as a stale warning about num_return_sequences." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "LwDetrImageLoss AMP crash and flash_attention.py s_aux=None crash are different code paths." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Gemma3n executorch export issues are unrelated to flash_attention integration null-handling." + }, + { + "left": "issue:43746", + "right": "issue:46209", + "accept": false, + "reason": "PEFT checkpoint loading failure and FP8 inference failure on B200 are unrelated." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "ReasoningEffort import break affects processor loading, not flash_attention None handling." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer add_special_tokens regression is unrelated to Gemma3 NaN embeddings with mixed-length batching." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift between train/eval is not the same as gradient checkpointing being disallowed in eval mode." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different forward-pass bugs." + }, + { + "left": "issue:43611", + "right": "issue:46285", + "accept": false, + "reason": "base_model_prefix load break in v5 is unrelated to CLIP text-model structure inconsistency." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure is distinct from FuyuBatchFeature's bare-except bug." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both are v4/v5 regressions, but one is generation output drift and the other is lm_head.weight serialization inconsistency." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-cardinality runtime error is unrelated to a stale generate() warning." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Both are import errors, but they concern different removed symbols and different loading paths." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting behavior is unrelated to Trainer GPU broadcast of NoneType." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to Qwen3.5 recurrent-state reset in cache mode." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 28, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:39692", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43329", + "issue:43381", + "issue:43421", + "issue:43575", + "issue:43611", + "issue:43653", + "issue:43701", + "issue:43756", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44442", + "issue:44462", + "issue:44479", + "issue:44610", + "issue:44734", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45229", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45712", + "issue:46121" + ], + "soft_pairs": [ + "issue:43065|issue:45412", + "issue:45459|issue:45712", + "issue:43611|issue:46121", + "issue:44186|issue:45198", + "issue:29127|issue:34567", + "issue:33357|issue:39692", + "issue:44871|issue:44977", + "issue:44361|issue:45198", + "issue:45372|issue:45459", + "issue:44206|issue:44479", + "issue:42915|issue:42994", + "issue:43994|issue:45412", + "issue:29942|issue:30064", + "issue:43976|issue:45440", + "issue:43066|issue:44462", + "issue:43278|issue:43575", + "issue:44265|issue:45198", + "issue:10000|issue:15354", + "issue:42490|issue:43873", + "issue:43873|issue:45229", + "issue:43065|issue:43994", + "issue:43381|issue:43701", + "issue:43421|issue:45491", + "issue:44734|issue:45406", + "issue:43653|issue:44442", + "issue:44610|issue:45412", + "issue:41720|issue:45229", + "issue:32090|issue:33357", + "issue:43756|issue:45440", + "issue:45372|issue:45406", + "issue:43278|issue:43329" + ], + "prepared_review_unit_hash": "c47ca10260b59cadf38a181aa1a96b1b657366f5ceceb4648311229e46acad23", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37103, + "estimated_input_tokens": 9276, + "estimated_eval_tokens": 18808 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers bugs that only share broad subsystem vocabulary (tokenizers, processors, quantization, serving). I found no true duplicate/merge-worthy soft edges; the best triage anchor is the broad open quantization/offloading report.", + "confidence": 0.44, + "canonical_issue_reason": "issue:43873 is the broadest, most reusable issue here: it is open, generic, and already has discussion/references around quantization/offloading failures, making it the best place to consolidate adjacent reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the strongest global canonical candidate because it is the most general active bug report in the set and most suitable as a triage sink for related quantization/offloading complaints.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Sam3PixelDecoder Conv2d and RT-DETR memory retention are unrelated bugs in different model paths." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Hidden tokenizer errors from missing protobuf and leftover dummy classes are different issues with different fixes." + }, + { + "left": "issue:43611", + "right": "issue:46121", + "accept": false, + "reason": "base_model_prefix loading regression and rope-params JSON list handling are unrelated code paths." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 NER/padding crash and Wav2Vec2 save/tokenization failure are different tokenizer bugs." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "A LayoutLMv3 error-message clarity issue is not the same as TrainerState token accounting." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS CLIP bus error and SigLIP2 doc example errors are separate model-specific problems." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos-token mismatch and Qwen3.5 flash-attention generation failure are distinct symptoms and fixes." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLuke tokenizer attribute errors and Wav2Vec2 save/tokenization failure are not the same underlying bug." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma4 processor import failure and tokenizer protobuf error masking are different failure points." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center argument in LasrFeatureExtractor and Qwen VL video-input regression are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "FineGrainedFP8Config failure and quantized-model saving failure are separate quantization bugs." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and RT-DETR memory leak do not share the same code path." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation-map processing are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version incompatibility and DeepseekV3MoE divergence are different classes of bugs." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 and ignoring tokenizer.json are both tokenizer-related but not the same defect." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype drift during eval and Qwen2 tensor-parallel OOM are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failures via torch_compilable_check and Wav2Vec2 save/tokenization issues are different." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel issue and GeneratorExp/JIT export failure are unrelated legacy bugs." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Path-with-slash import warning and quantization/offloading malfunction are not the same bug." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Offloading/quantization behavior and Gemma4 multi-GPU OOM are distinct resource-management problems." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Sam3 pixel decoder dummy Conv2d and SigLIP2 output corruption are unrelated model issues." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch are different trainer behaviors." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processing and Gemma3 mixed-length NaNs are not the same underlying bug." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation indexing in serve and Gemma4Processor missing _tokenizer are different serve failures." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and AutoTokenizer failing to load a tokenizer class are separate tokenizer issues." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "OmDet-Turbo processor image size mismatch and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "A800 cudaErrorAssert with auto device mapping and Gemma4 OOM are different hardware/runtime failures." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer NoneType broadcast error and MacOS CLIP bus error are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Smollm3 RoPE layer mismatch and DeepseekV3MoE divergence are different model-implementation discrepancies." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Both involve Gemma4, but one is an import-time processor-loading failure and the other is a missing attribute in transformers serve; not the same concrete bug." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "BF16/FP32 eval dtype drift and multimodal video-token counting are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 29, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:38175", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43334", + "issue:43381", + "issue:43452", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43701", + "issue:43723", + "issue:43761", + "issue:43824", + "issue:43931", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44554", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45245", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:29942|issue:36010", + "issue:43526|issue:45834", + "issue:43723|issue:44554", + "issue:43761|issue:45859", + "issue:45440|issue:45593", + "issue:43526|issue:44186", + "issue:43575|issue:43701", + "issue:44977|issue:45245", + "issue:43526|issue:44857", + "issue:43575|issue:44387", + "issue:42490|issue:43381", + "issue:43334|issue:43531", + "issue:43824|issue:44279", + "issue:44442|issue:45072", + "issue:43646|issue:44077", + "issue:42915|issue:43931", + "issue:29127|issue:35141", + "issue:43262|issue:44206", + "issue:44743|issue:44811", + "issue:43452|issue:45588", + "issue:44977|issue:45584", + "issue:33357|issue:38175", + "issue:44062|issue:45907", + "issue:28218|issue:32090", + "issue:44464|issue:45491", + "issue:33290|issue:34567" + ], + "prepared_review_unit_hash": "e73a8f4603d3da70477ce9bfbaab800618f25f718258b698f010c05ad32a1e36", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 26, + "serialized_chars": 35352, + "estimated_input_tokens": 8838, + "estimated_eval_tokens": 17932 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a broad mix of unrelated Transformers issues spanning tokenizers, model loading, training, quantization, attention, and hardware/backend-specific regressions. I don\u2019t see any soft pair that is the same underlying bug or a plausible single merged fix, so all candidate links should be rejected.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: the items do not form one duplicate family and cover many unrelated code paths, so there is no single issue that meaningfully represents the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because the cluster is not a coherent duplicate set; selecting one would be arbitrary.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures and a GenerationMixin import error are unrelated failures in different subsystems." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BEiT label reduction and Kosmos2.5 OCR long-input indexing are different vision preprocessor bugs." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading in v5 and an MPS attention correctness issue are not the same code-path problem." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIP hidden_states regression and Qwen3_Moe rotary embedding CPU offload incompatibility are unrelated." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3 divergence and D-FINE auxiliary-loss behavior are distinct model-specific issues." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "BEiT image processor label reduction and LayoutLMv2 tokenizer crashes are different tokenizer/processor bugs." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "TP OOM on Qwen2-57B loading and resume_from_checkpoint key mismatch are unrelated training/loading issues." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug and category-count limit errors are unrelated failures." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "These affect different components: BEiT image processing versus LwDetrImageLoss AMP behavior." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is TP model loading and the other is int4 quantization memory growth; not the same bug." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Path-trailing-slash import warning and gradient-checkpointing eval-mode restriction are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id loading failure and Qwen3-MoE sliding_window behavior are different model/config regressions." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "A missing Qwen2.5-VL import and a generic dependency issue are not the same concrete bug." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and dtype mismatch in inference are unrelated problems." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "General v5 custom model init breakage and a patchtsmixer-specific post_init restriction are not the same underlying issue." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "FineGrainedFP8 config failure and Qwen3-VL weight-shape mismatch are different model-loading errors." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and embedding reinitialization after resize are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and unsupported center argument in feature extraction are different audio-preprocessing bugs." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset and Whisper batch_decode skip_special_tokens handling are separate generation/decoder issues." + }, + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "gguf_file loading breakage and flash_attention s_aux=None crashes are unrelated loader versus attention failures." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 flash-attention generation and Whisper empty-transcription failure do not share a concrete code path." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "MacOS bus error on CLIP and SigLIP2 zero-probability outputs are distinct model/runtime issues." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken special-arg duplication and list_repo_files missing revision forwarding are unrelated API bugs." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer added-space behavior and Trainer _gpu_broadcast_one NoneType handling are entirely different subsystems." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward and Gemma3 NaNs under mixed-length sliding-window attention are not the same bug." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor+DeepSpeed OOM and TrainerState token counter not updating are unrelated training issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 30, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:36010", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43316", + "issue:43381", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43611", + "issue:43643", + "issue:43650", + "issue:43720", + "issue:43761", + "issue:43825", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44188", + "issue:44190", + "issue:44442", + "issue:44479", + "issue:44496", + "issue:44568", + "issue:44743", + "issue:44855", + "issue:44871", + "issue:44898", + "issue:44913", + "issue:44964", + "issue:44987", + "issue:45137", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45479", + "issue:45698", + "issue:45759", + "issue:45803", + "issue:46178", + "issue:46202", + "issue:46234" + ], + "soft_pairs": [ + "issue:44442|issue:44898", + "issue:43381|issue:43873", + "issue:44964|issue:45440", + "issue:43316|issue:43525", + "issue:34689|issue:43611", + "issue:32090|issue:33290", + "issue:43720|issue:44442", + "issue:43931|issue:45216", + "issue:34689|issue:36010", + "issue:44479|issue:45290", + "issue:44442|issue:45803", + "issue:43493|issue:43827", + "issue:43550|issue:44743", + "issue:42907|issue:45698", + "issue:42175|issue:46234", + "issue:43873|issue:44871", + "issue:43643|issue:44913", + "issue:43761|issue:44188", + "issue:43316|issue:45759", + "issue:44190|issue:44496", + "issue:44568|issue:45479", + "issue:33290|issue:34689", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:44987|issue:46178", + "issue:43650|issue:46202", + "issue:29127|issue:33357", + "issue:43295|issue:43825" + ], + "prepared_review_unit_hash": "728b2135f416f1f26e576ba38eee0ddaa0ad87264a51d4181d16674fc79bd736", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36423, + "estimated_input_tokens": 9106, + "estimated_eval_tokens": 18468 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly thematically similar Transformers bugs, but the soft-edge pairs do not describe the same underlying defect or change. I would not merge any of the proposed pairs as duplicates, and there are no PRs in this cluster.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Different failures in different model paths: tokenizer loading vs Perceiver image classification at non-default resolution." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Both are training/runtime issues, but one is gradient checkpointing in eval mode and the other is quantization offloading behavior." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Different multimodal model bugs with different symptoms and code paths: Phi-4-VL loading vs DeepSeekV3MoE implementation divergence." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config API mismatches, but they concern different models and different missing fields." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both involve model loading regressions, but the affected mechanisms and breakages are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer broadcast TypeError and DeepSpeed AdaFactor OOM are unrelated failures." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "Accelerate packed-weight loading bug vs tokenizer class loading bug; no shared underlying defect." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "One is a weight-shape mismatch on load, the other is a save_pretrained regression for Qwen3.5 checkpoints." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Both are loading/import regressions, but one is a specific model load breakage and the other is a GenerationMixin import-path issue." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Both touch multimodal/chat workflows, but one is a video-input regression and the other is a chat template crash on tool-call messages." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer loading failure and Fuyu tensor conversion error are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation mismatch vs documentation lag after pipeline removals are different issues." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba and recurrent-state reset in Qwen3.5 are distinct code-path bugs." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Both are save/load related, but one is dequantized model saving and the other is custom-module resolution after save_pretrained." + }, + { + "left": "issue:42175", + "right": "issue:46234", + "accept": false, + "reason": "Backend packaging gap for TensorFlow in a torch install is unrelated to a missing import_utils symbol." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization offloading behavior and Gemma EOS token config inconsistency do not share the same root cause." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "Both involve config persistence, but one is trust_remote_code returning missing fields and the other is GPTNeoX rotary_pct not surviving reload." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Hidden-states output regression in CLIPVisionModel vs attention-kernel divergence under torch.compile are different bugs." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy and AutoModelForCausalLM text_config unwrapping are related only broadly to config handling, not the same defect." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading in a training script and unrecognized-model config.json loading failure are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token insertion bug and sequence-classification zero-loss bug are completely separate." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "AdaFactor/deepspeed OOM and Llama 3.2 Vision model loading regression are unrelated." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "PatchTSMixer post_init validation and Qwen video-input regression are different model-specific issues." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 TorchScript parsing error and DeepSpeed ZeRO3 deque IndexError are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:46178", + "accept": false, + "reason": "Loading a specific model repo and missing tensorflow_text backend mapping are different failure modes." + }, + { + "left": "issue:43650", + "right": "issue:46202", + "accept": false, + "reason": "Placeholder 'ADD THE DATA' issue is not the same as a Gemma pipeline roundtrip failure." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity and CLIP bus error on macOS are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression and pipeline translation messaging bug are separate v5 regressions." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 31, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:33290", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43452", + "issue:43475", + "issue:43504", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43606", + "issue:43646", + "issue:43701", + "issue:43716", + "issue:43742", + "issue:43761", + "issue:44077", + "issue:44162", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44534", + "issue:44617", + "issue:44792", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45200", + "issue:45542", + "issue:45584", + "issue:45656", + "issue:45698", + "issue:45803", + "issue:46050", + "issue:46170", + "issue:46178", + "issue:46234" + ], + "soft_pairs": [ + "issue:25251|issue:28282", + "issue:42617|issue:43575", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43540|issue:44514", + "issue:33290|issue:35141", + "issue:43575|issue:43742", + "issue:43316|issue:43716", + "issue:33290|issue:45656", + "issue:44871|issue:45584", + "issue:43404|issue:43441", + "issue:43316|issue:44877", + "issue:43295|issue:44871", + "issue:44162|issue:44792", + "issue:45803|issue:46170", + "issue:43065|issue:44617", + "issue:41950|issue:43475", + "issue:44871|issue:46050", + "issue:43646|issue:44913", + "issue:45127|issue:45200", + "issue:43452|issue:44496", + "issue:43761|issue:44479", + "issue:43232|issue:43388", + "issue:43504|issue:45698", + "issue:43572|issue:46178", + "issue:44077|issue:44534", + "issue:45542|issue:46234" + ], + "prepared_review_unit_hash": "8ef1263ceaa76643d6ed4fb3d6d68319ed4923c15d7fe29be6639918a9aba4e0", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35731, + "estimated_input_tokens": 8933, + "estimated_eval_tokens": 18122 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: the paired issues mostly share only broad subsystem keywords (loading, config, generation, multimodal, deepspeed) but not the same underlying bug or fix path. I would not merge any soft-edge pair as duplicates.", + "confidence": 0.9, + "canonical_issue_reason": "No single canonical issue fits the cluster well; the soft pairs span unrelated bugs and regressions rather than one underlying problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 is the most broadly impactful and discussion-rich issue in the set, so it is the best representative issue overall, even though it is not a duplicate anchor for the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Different problems: pipeline top_k output shape vs missing PyTorch import for AutoModel." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "Both mention failures/OOM, but one is a script runtime problem and the other is model loading OOM with tensor parallelism." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated: torch.compile/SDPA failure in Bamba vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "Different code paths: CPU offload device mismatch vs checkpoint key mismatch on resume." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Both touch multimodal processing, but one is Qwen3OmniMoe video input handling and the other is batched chat template padding behavior." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "Deepspeed Adafactor OOM is unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Model-parallel OOM on Qwen2-57B is not the same as a KeyError when loading MobileLLM." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Config API discrepancy and image preprocessor dtype mismatch are distinct issues." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "Both involve deepspeed, but one is OOM and the other is duplicate optimizer stepping." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Token/eos configuration mismatch vs Whisper empty-transcription failure after token alignment are different bugs." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but one is tied weights in Mistral3ForConditionalGeneration and the other is FlashAttention in Ministral-3." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-related, but one is an API discrepancy and the other is strict config loading rejection." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Processor/tokenizer regression vs eos_token_id inconsistency are separate regressions." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 workflow breakage and Janus test failure are unrelated models and failure modes." + }, + { + "left": "issue:45803", + "right": "issue:46170", + "accept": false, + "reason": "Bare except in tensor conversion is unrelated to Windows ROCm distributed import issues." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Sam3Video OOM are not the same bug." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Image-processor lookup in a video-classification pipeline is unrelated to missing fpn_position_embeddings on Sam3VisionEncoderOutput." + }, + { + "left": "issue:44871", + "right": "issue:46050", + "accept": false, + "reason": "eos_token_id inconsistency is not the same as quantized save/load breakage." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Broad custom-init regression and GPTNeoX rotary_pct reload bug are different code paths." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge collapse with extended vocab is unrelated to Gemma 4 mm_token_type_ids defaults." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both concern model loading, but gguf_file handling and missing model_type in config.json are distinct failures." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are different models and outputs." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwarg sync behavior is unrelated to gather_for_metrics dropping label elements." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Both involve pretrained/save loading, but one is a legacy-field preset load failure and the other is wrong custom-module resolution after save/load." + }, + { + "left": "issue:43572", + "right": "issue:46178", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to tensorflow_text backend mapping errors." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Optional post_init policy in patchtsmixer is unrelated to non-persistent buffer initialization in v5." + }, + { + "left": "issue:45542", + "right": "issue:46234", + "accept": false, + "reason": "TensorBoard/TensorFlow backend mismatch and missing is_falcon_mamba_ssm_available are unrelated import-utility issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 32, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:35141", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43116", + "issue:43335", + "issue:43540", + "issue:43550", + "issue:43644", + "issue:43673", + "issue:43761", + "issue:43827", + "issue:43931", + "issue:43976", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44112", + "issue:44190", + "issue:44242", + "issue:44462", + "issue:44479", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45357", + "issue:45381", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45632", + "issue:45803", + "issue:45907", + "issue:45987", + "issue:46234" + ], + "soft_pairs": [ + "issue:43761|issue:44242", + "issue:43673|issue:44743", + "issue:44792|issue:44977", + "issue:44617|issue:45584", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:44792|issue:45600", + "issue:44479|issue:44734", + "issue:43827|issue:43994", + "issue:44855|issue:45588", + "issue:41720|issue:45245", + "issue:43065|issue:44610", + "issue:43931|issue:44060", + "issue:45803|issue:45987", + "issue:35141|issue:42490", + "issue:43644|issue:44913", + "issue:43976|issue:44855", + "issue:43335|issue:44855", + "issue:43550|issue:44190", + "issue:45632|issue:46234", + "issue:44077|issue:44877", + "issue:45127|issue:45357", + "issue:43540|issue:44734", + "issue:44462|issue:45907", + "issue:44521|issue:45381", + "issue:44737|issue:45803", + "issue:43335|issue:44190", + "issue:44112|issue:45600", + "issue:43116|issue:44190" + ], + "prepared_review_unit_hash": "72edd59a7953e5afd95b8e1c8185a4bec6e04e480f30df00f34cb68d57cfeb20", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35930, + "estimated_input_tokens": 8983, + "estimated_eval_tokens": 18222 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers issues. The only obvious thematic overlap is a small v5 regression subgroup around non-persistent buffers being initialized with junk; the rest are separate bugs spanning model loading, multimodal/video, generation, config reloads, CI, and docs.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:44534 is the broadest representative of the repeated v5 non-persistent-buffer regression theme, but it does not cover the cluster as a whole.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Different failures: CLIPVision hidden_states regression vs MoE load-balancing loss omission." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Both involve cache/state, but one is missing GenerationMixin cache in chunked prefill and the other resets recurrent states in Qwen3.5." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Janus image-generation test failure and Qwen3.5 flash-attention generation bug are different code paths." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "CUDA OOM in Sam3Video is unrelated to Whisper empty-transcription generation after token alignment." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Generic v5 buffer-junk regression vs GPTNeoX rotary_pct reload default bug." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading script issue vs model loading failure for Phi-4 multimodal." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Janus generate-images test failure vs stale auto_mappings CI breakage; unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Video-input regression across Qwen variants vs serve KV-cache continuation indexing bug." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() vs SigLIP model/pipeline producing wrong outputs." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 JIT parsing problem vs flash_attention AttributeError on sink-less models." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "cudaErrorAssert during Qwen3 auto device mapping is unrelated to the 2^24 category limit error." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs processor/model input-resolution mismatch." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs incorrect tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except swallowing errors vs StaticCache.get_seq_length() contract mismatch." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Embedding resize/reinit bug vs import warning for local paths ending with slash." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Shared theme is only broad v5 regression; buffer junk initialization is not the same as rotary_pct reset on reload." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Python version support issue vs IndentationError from @torch.jit.script comment parsing." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "Sparse-layer creation bug and JIT parsing failure are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Bamba torch.compile SDPA failure vs local dataset loading example issue." + }, + { + "left": "issue:45632", + "right": "issue:46234", + "accept": false, + "reason": "Cache-path collision for trust_remote_code models vs missing import_utils symbol." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Optional post_init policy issue vs strict config rejecting granite_speech config." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "Both touch Qwen models, but LoRA/extended-vocab collapse and incorrect visual-encoder save keys are different bugs." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Video-input processing ValueError in Qwen3OmniMoe vs serve KV-cache tensor indexing bug." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json vs list_repo_files not forwarding revision." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "assistant_masks all-zero in multimodal templates vs wrong video vision_position_ids; related area but not the same bug." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "XLNet CPU device placement bug vs broad exception swallowing in FuyuBatchFeature." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug vs local dataset loading failure." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "GraniteSpeech CI stale device override vs auto_mappings referencing removed configs." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Multi-label classification example returns empty results; unrelated to local dataset loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 33, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:42907", + "issue:43065", + "issue:43295", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43479", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43650", + "issue:43688", + "issue:43854", + "issue:43901", + "issue:44112", + "issue:44186", + "issue:44220", + "issue:44246", + "issue:44464", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44933", + "issue:44938", + "issue:44964", + "issue:45003", + "issue:45042", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45335", + "issue:45362", + "issue:45375", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45632", + "issue:46082", + "issue:46121" + ], + "soft_pairs": [ + "issue:46082|issue:46121", + "issue:43479|issue:45375", + "issue:44938|issue:45542", + "issue:45276|issue:45584", + "issue:43295|issue:45276", + "issue:45245|issue:45584", + "issue:44464|issue:45563", + "issue:43650|issue:44220", + "issue:36246|issue:41628", + "issue:43404|issue:45216", + "issue:44186|issue:44734", + "issue:44246|issue:45003", + "issue:44683|issue:45446", + "issue:38175|issue:43065", + "issue:44933|issue:45362", + "issue:43643|issue:44496", + "issue:43854|issue:44964", + "issue:44964|issue:45600", + "issue:44112|issue:44964", + "issue:45563|issue:45584", + "issue:36246|issue:38617", + "issue:44561|issue:45632", + "issue:44734|issue:45632", + "issue:42907|issue:43441", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:43295|issue:45335", + "issue:43441|issue:45588", + "issue:44496|issue:45042", + "issue:43388|issue:43688" + ], + "prepared_review_unit_hash": "8dd9f465f46c44a9566c123e8956156a5f96c6dbdaff4c2c30dbda3824126d63", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36130, + "estimated_input_tokens": 9033, + "estimated_eval_tokens": 18322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: it mixes import regressions, model-loading/config issues, generation bugs, training/eval bugs, and docs/perf reports. There is no clear duplicate stack across the whole set, so only a weak representative issue can be chosen.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 41628 is the broadest, cleanest user-facing regression report among the set: a straightforward top-level import failure with clear impact. It is not a true canonical for all items here, but it is the best single representative of the import-regression subset.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 41628 is the most triage-worthy representative because it is a concrete, broadly understandable import breakage and has the strongest chance of being actionable as a standalone bug report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:46082", + "right": "issue:46121", + "accept": false, + "reason": "Different failure surfaces: LlamaConfig head_dim validation vs rope-parameter dict conversion TypeError. Not the same bug or code path." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different models and different config-field bugs: Phi4Multimodal default init vs Qwen3.5 MoE vision field dropping." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "One is a Python 3.14 import/load failure; the other is a backend dependency issue with tensorboard-only installs. Distinct root causes." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 token-embedding resizing bug vs Whisper empty-transcription generation failure. Unrelated code paths." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer regression and embedding-resize bug are different model behaviors and fixes." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-count limit error is unrelated to Whisper empty transcription handling." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward chunked-generation inconsistency vs stale warning about num_return_sequences. Different generation bugs." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "No meaningful overlap: placeholder/nonspecific issue title vs fbank feature extraction bug." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they are for different symbols and different underlying breakages." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Weight-tying bug in Mistral3 generation is separate from Qwen3.5 save_pretrained checkpoint regression." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/truncation crash vs serve KV-cache tensor indexing crash; unrelated components." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import performance regression is not the same as unsafe sys.modules access, even if both concern import internals." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both mention flex_attention, but one is a compiled flex_attention failure on torch 2.9+ while the other is a version-check/import-path bug for AuxRequest." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Different models and symptoms: SigLIP2 zero probabilities vs Sam3PixelDecoder dummy Conv2d." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing image_utils import and Qwen3.5-35B chat crash are unrelated bugs." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Both are config/load related, but one is trust_remote_code missing fields and the other is an unrecognized model missing model_type. Different concrete problems." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different models and repro contexts: unit-test loading of GLM-4.7-Flash vs latest-transformers load failure for Phi-4 multimodal." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Phi-4 multimodal load regression and Sam3LiteText auto_mappings breakage are unrelated." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI stale device-override test in GraniteSpeech is not the same issue as model loading failure for Phi-4 multimodal." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale warning on paged generate() is different from Whisper failing on empty transcription after align_special_tokens." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and likely different version skew." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Removal of is_torch_fx_available breaking trust_remote_code models is unrelated to a local cache-path collision." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve KV-cache indexing crash and trust_remote_code cache-path collision are distinct bugs." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Saving dequantized Ministral/Devstral models and FlashAttention inference failure are different code paths and symptoms." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior and Sam3LiteText auto_mappings cleanup are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to TextClassificationPipeline docs mismatch." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Different regression targets: processor/tokenizer access vs token embedding resize propagation." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both touch flash_attention, but one is a Ministral-3 v5 RC failure and the other is an s_aux=None crash for sink-less models; not clearly the same fix." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config and PIL-backend torchvision requirement are separate loading/dependency issues." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "gather_for_metrics batch truncation and auxiliary-loss normalization are different training/eval bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 34, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42175", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43479", + "issue:43525", + "issue:43577", + "issue:43650", + "issue:43673", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44220", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44617", + "issue:44779", + "issue:44933", + "issue:45020", + "issue:45103", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45335", + "issue:45357", + "issue:45372", + "issue:45405", + "issue:45584", + "issue:45593", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:46209", + "issue:46234" + ], + "soft_pairs": [ + "issue:41950|issue:44016", + "issue:44075|issue:44368", + "issue:43673|issue:44336", + "issue:42175|issue:44279", + "issue:43299|issue:45216", + "issue:43901|issue:44496", + "issue:43381|issue:45593", + "issue:44016|issue:44220", + "issue:44496|issue:45759", + "issue:45372|issue:46234", + "issue:45335|issue:45584", + "issue:43650|issue:46209", + "issue:32090|issue:35141", + "issue:43479|issue:43525", + "issue:45103|issue:45372", + "issue:44242|issue:45200", + "issue:43577|issue:45216", + "issue:38175|issue:44617", + "issue:43299|issue:45357", + "issue:44279|issue:45405", + "issue:44351|issue:45278", + "issue:43824|issue:44933", + "issue:44779|issue:45812", + "issue:39692|issue:43901", + "issue:41950|issue:45020", + "issue:44016|issue:44062", + "issue:43295|issue:44779", + "issue:41950|issue:45823", + "issue:43299|issue:43854", + "issue:43976|issue:45405" + ], + "prepared_review_unit_hash": "6eacf922bb673c02b42c37a9ff430248edb9f6d259e613aa67be7c88015beb7d", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36144, + "estimated_input_tokens": 9036, + "estimated_eval_tokens": 18328 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is a loose similarity cluster of mostly unrelated Transformers issues: model-loading regressions, tokenizer/config bugs, import failures, docs problems, and a few pipeline/model-specific reports. The soft pairs do not look like true duplicates; issue 45020 is the closest umbrella representative, but it still does not subsume the rest of the set.", + "confidence": 0.89, + "canonical_issue_reason": "Issue 45020 is the broadest and most representative regression report in the cluster, covering the general theme of recent Transformers versions breaking model loading/remote-code workflows.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the best global issue representative because it is the broadest umbrella regression in the set, though the cluster remains too heterogeneous for a true duplicate canonical.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification processor lookup is unrelated to a notebook syntax error; different subsystems and failure modes." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD optimizer args being ignored is unrelated to a Qwen LoRA warning about tie_word_embeddings." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Chunked-prefill cache handling and ANSI output in loading_report are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Missing TensorFlow backend on install and a generic dependency issue are not the same bug." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both are regression reports, but one is model loading and the other is save_pretrained checkpoint serialization for different Qwen multimodal paths." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "A docs mismatch for return_all_scores is unrelated to an unrecognized model/config error." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing in eval mode and D-FINE denoising losses are unrelated training behaviors." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error and audio fbank feature extraction issue are different problems." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Unrecognized-model/config loading and AutoModel text_config unwrapping are both config-related, but they affect different code paths and model classes." + }, + { + "left": "issue:45372", + "right": "issue:46234", + "accept": false, + "reason": "Gemma4 processor import failure and missing falcon_mamba availability helper are unrelated import/export issues." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Token embedding resizing for T5Gemma is unrelated to Whisper generation on empty transcription." + }, + { + "left": "issue:43650", + "right": "issue:46209", + "accept": false, + "reason": "A placeholder data request and an FP8 inference failure on B200 are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast TypeError is unrelated to post_init reinitializing output embeddings after resize_token_embeddings." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Phi4Multimodal default config initialization and Llama4 missing pad_token_id are separate config bugs." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "auto_docstring annotation handling is unrelated to the Gemma4 processor import error." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "MoE load-balancing loss and Gemma4 mm_token_type_ids defaults do not describe the same bug." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "BLIP2 dtype loading and Qwen3.5 save_pretrained serialization are different multimodal issues." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "SigLIP2 zero probabilities and Sam3Video OOM are unrelated model/runtime failures." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Both mention Qwen multimodal regressions, but one is model loading and the other is incorrect visual-encoder keys on save; different concrete code paths." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A transformers dependency issue is unrelated to an unreleased MIN_PEFT_VERSION bump." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "HybridCache import failure and broad import errors after upgrade are related in theme only, not the same underlying defect." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Different missing-import reports from different modules; no shared concrete bug." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Deepseek tokenization regression and Granite token-id regression are separate tokenizer bugs." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "SigLIP2 doc example errors and TextClassificationPipeline docs mismatch are both documentation issues but not the same one." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video-classification processor lookup and remote_code breakages are both regressions, but they hit different pipelines and failure modes." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken keyword duplication are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom processor/tokenizer regression and Deepseek tokenizer regression are different code paths and models." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video-classification processor lookup and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3VL loading failure and GLM-4.7 unit-test loading failure are unrelated model-specific regressions." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python-version compatibility breakage and an unreleased PEFT minimum version bump are different dependency problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 35, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:42994", + "issue:43065", + "issue:43262", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43653", + "issue:43723", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44246", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44291", + "issue:44297", + "issue:44361", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:45081", + "issue:45276", + "issue:45325", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712", + "issue:45823", + "issue:45834", + "issue:45907", + "issue:46132" + ], + "soft_pairs": [ + "issue:44683|issue:45542", + "issue:43650|issue:46132", + "issue:44462|issue:45081", + "issue:43976|issue:44987", + "issue:44297|issue:44462", + "issue:43976|issue:44279", + "issue:43450|issue:44279", + "issue:45081|issue:45907", + "issue:44466|issue:45276", + "issue:44521|issue:45325", + "issue:43441|issue:45834", + "issue:42994|issue:43317", + "issue:45600|issue:45712", + "issue:43653|issue:45593", + "issue:44623|issue:44749", + "issue:43065|issue:44898", + "issue:44623|issue:45397", + "issue:44261|issue:44263", + "issue:44361|issue:45593", + "issue:44671|issue:44779", + "issue:43441|issue:44683", + "issue:44016|issue:45823", + "issue:43901|issue:43994", + "issue:43723|issue:44162", + "issue:43450|issue:44617", + "issue:43525|issue:43881", + "issue:44297|issue:45397", + "issue:43901|issue:44246", + "issue:43525|issue:43643", + "issue:43784|issue:45542", + "issue:44016|issue:44291", + "issue:43262|issue:44521" + ], + "prepared_review_unit_hash": "e027b1f16ceb83ee00e6e9e16730b7177a9830c128c8f247001e9fbe08df0018", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37170, + "estimated_input_tokens": 9293, + "estimated_eval_tokens": 18842 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a duplicate set; it mixes many unrelated Transformers v5 regressions across tokenizers, model loading, processors, attention kernels, docs, and CI. None of the soft edges look like the same underlying bug/change.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue: the cluster is heterogeneous. If forced, #44462 is the closest representative because it covers a broad tokenizer-loading regression, which is the nearest shared theme among several items.", + "canonical_pr_reason": null, + "best_issue_reason": "#44462 is the most representative issue in the cluster because it is a broad, user-facing tokenizer-loading regression; the other issues are mostly narrower, model-specific, or unrelated failures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Compiled flex_attention on new torch vs TensorBoard/TensorFlow backend setup; unrelated subsystems and failure modes." + }, + { + "left": "issue:43650", + "right": "issue:46132", + "accept": false, + "reason": "A placeholder issue title vs behavior change in AttentionInterface.register; no shared bug path." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Both touch tokenizers, but one is AutoTokenizer loading ignoring tokenizer.json and the other is a Mistral regex-patch crash; different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version support breakage vs loading a specific repo/model; too different to be duplicates." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer save_pretrained writes the wrong tokenizer_class, while this is AutoTokenizer loading the repo file; save vs load bugs." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "A Python compatibility issue vs an unspecified dependency problem; not the same underlying defect." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batch-shape bug vs generic dependency issue; no overlap in concrete code path." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Mistral tokenizer regex patch crash vs list_repo_files not forwarding revision; completely different functionality." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Serialization of tied lm_head weights vs resize_token_embeddings not updating Gemma4 embeddings; different model logic." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "assistant_masks generation bug vs Qwen2.5-VL rope index scaling; both multimodal, but distinct internals and symptoms." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "FlashAttention failure in Ministral vs OCR index error in Kosmos2.5; unrelated model-specific issues." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized save failure vs dequantized model load with gpu/cpu offload; both involve quantization, but different stages and bugs." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "auto_mappings.py stale config references vs leftover dummy classes in dummy_pt_objects.py; both repo hygiene/CI, but not the same issue." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug vs D-FINE auxiliary-loss behavior; unrelated areas." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "processor.save_pretrained missing files vs slow filtering after upgrade; different symptoms and code paths." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs Perceiver non-default resolution failure; both vision-related but not the same bug." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing files from processor.save_pretrained vs Gemma-4 zero3 from_pretrained; unrelated failures." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "MLA q_a_layernorm missing config.rms_norm_eps vs torch.split return values in GlmMoeDsaIndexer; different model components." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "MLukeTokenizer AttributeError vs D-FINE auxiliary-loss issue; unrelated subsystems." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "CamemBERT masked LM prediction regression vs Deepseek tokenizer regression; both output-quality bugs, but different models and code paths." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Model-specific FlashAttention failure vs compiled flex_attention failing on torch>=2.9; one is a model issue, the other a kernel/runtime compatibility issue." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error vs Gemma4 PLE device mismatch; completely different bug types." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Documentation mismatch for return_all_scores vs nonsensical model outputs; not the same underlying problem." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer loading regression vs ESM2 breakage; both are v5 regressions, but they affect different model families and mechanisms." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Incorrect batched video processor shape vs Sam3Video CUDA OOM; one is a shape bug, the other is memory usage." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config vs glm-4v-9b loading failure; both config/loading-related but not the same concrete defect." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer serialization mismatch vs Gemma-4 zero3 loading; unrelated bugs." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Docs inconsistency vs import-time slowness; different problem classes." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both involve config fields during loading, but one is a missing pad_token_id attribute and the other is trust_remote_code dropping fields; different root causes." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import NameError for sentence-transformers vs TensorBoard/TensorFlow backend error; unrelated dependency/import issues." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error vs init_empty_weights TypeError from unexpected argument; different failure modes." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Audio chat_template default sampling rate bug vs multimodal assistant_masks all-zero bug; both processor-related but not the same issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 36, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:42886", + "issue:43262", + "issue:43299", + "issue:43352", + "issue:43526", + "issue:43673", + "issue:43761", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44561", + "issue:44589", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44964", + "issue:45003", + "issue:45081", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45412", + "issue:45593", + "issue:45759", + "issue:46123", + "issue:46132" + ], + "soft_pairs": [ + "issue:44188|issue:44336", + "issue:41628|issue:43976", + "issue:44589|issue:45362", + "issue:43673|issue:43761", + "issue:16998|issue:22355", + "issue:42491|issue:43299", + "issue:44336|issue:44373", + "issue:44246|issue:44496", + "issue:44242|issue:45593", + "issue:44295|issue:45397", + "issue:44246|issue:44871", + "issue:43824|issue:43976", + "issue:44336|issue:44485", + "issue:41950|issue:44220", + "issue:43976|issue:44964", + "issue:36246|issue:42757", + "issue:42886|issue:46132", + "issue:36246|issue:44351", + "issue:44242|issue:44857", + "issue:44779|issue:45292", + "issue:45081|issue:45362", + "issue:43352|issue:45250", + "issue:43673|issue:44561", + "issue:44295|issue:44749", + "issue:44162|issue:45200", + "issue:43901|issue:45003", + "issue:43526|issue:45003", + "issue:44496|issue:45003", + "issue:45412|issue:46123", + "issue:45375|issue:45759", + "issue:43262|issue:44246" + ], + "prepared_review_unit_hash": "41776cb8f16087de9584fa1991849cb91c297a32158f40ab994160b10936d276", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36938, + "estimated_input_tokens": 9235, + "estimated_eval_tokens": 18726 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a grab bag of unrelated Transformers regressions and import/config bugs. I don\u2019t see any soft pair that clearly describes the same concrete bug or change, so no merges are warranted.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 41950 is the clearest, most user-facing concrete bug in the set: it names a specific pipeline misbehavior, has active discussion and inbound references, and is more actionable than the more ambiguous import/config reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 41950 is the strongest standalone issue candidate because it describes a specific failing code path with direct user impact and enough context to triage independently.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Different subsystems and symptoms: attention-kernel divergence under torch.compile vs ANSI color output in loading_report." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Both are import/version problems, but one is a missing symbol and the other is a Python-version compatibility regression; not the same bug." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage import failure and a Qwen3.5 chat crash are different failure modes and code paths." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Both mention v5 regressions, but one is missing GenerationMixin cache during chunked prefill and the other is CLIPVisionModel hidden_states behavior." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "Unrelated issues: DeBERTa model_max_length handling vs missing transformers.onnx module." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Same broad Qwen/MoE area, but one is LoRA compatibility across hf4.x/hf5.x and the other is multimodal model loading; not clearly the same bug." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI code emission and a position_ids docstring typo are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Import-time slowness is unrelated to unrecognized-model loading for a specific checkpoint." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Both concern missing losses, but they are different losses in different model families and different conditions." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "A position_ids buffer access error is not the same as a Gemma-4 ZeRO3 from_pretrained failure." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import slowness and eos_token_id config mismatch are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "A missing Qwen2_5_VL export and a Python compatibility issue are different problems." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading-report ANSI formatting has nothing to do with GLM-5 RoPE implementation." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Both touch pipelines/utilities, but one is video-classification using image processors and the other is audio feature extraction; different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "A Python version support bug is not the same as failing to load a specific multimodal model." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Both are ImportError reports, but they concern different missing symbols from different packages." + }, + { + "left": "issue:42886", + "right": "issue:46132", + "accept": false, + "reason": "Tokenizer cache/offline loading and AttentionInterface.register behavior are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: Qwen2_5_VLImageProcessor vs HybridCache." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "Missing MoE load-balancing loss and an AMP/CUDA crash in a detection loss are different issues." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer correctness regression and resize_token_embeddings not updating output embeddings are not the same bug." + }, + { + "left": "issue:45081", + "right": "issue:45362", + "accept": false, + "reason": "A Mistral regex patch crash and a Qwen3.5 chat crash are different model/path failures." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "The second title is too broad to establish the same concrete bug; one is a specific model lacking FA2 support." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available break different code paths." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "A buffer access error and a Chinese-reported slowdown after upgrade are not the same underlying defect." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma-4 mm_token_type_ids defaulting are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "A docs mismatch for return_all_scores is unrelated to unsafe sys.modules access." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "reduce_labels behavior in BeitImageProcessorFast is unrelated to sys.modules access in modeling_utils." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "An unrecognized model config and unsafe sys.modules access are different load-time problems." + }, + { + "left": "issue:45412", + "right": "issue:46123", + "accept": false, + "reason": "RT-DETR memory release and MaskGenerationPipeline partial-batch dropping are unrelated." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is a missing field being dropped by strict validation and the other is text_config unwrapping in from_config." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting is unrelated to import-time slowness." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 37, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36246", + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43408", + "issue:43475", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43673", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44297", + "issue:44336", + "issue:44368", + "issue:44466", + "issue:44479", + "issue:44483", + "issue:44623", + "issue:44734", + "issue:44877", + "issue:44977", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45292", + "issue:45335", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45701", + "issue:45987", + "issue:46082", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:43257|issue:45137", + "issue:45292|issue:45584", + "issue:36246|issue:43596", + "issue:45292|issue:45701", + "issue:44877|issue:45375", + "issue:45561|issue:45563", + "issue:43065|issue:43408", + "issue:43232|issue:44336", + "issue:44987|issue:45459", + "issue:45987|issue:46082", + "issue:44995|issue:45200", + "issue:44479|issue:46170", + "issue:44466|issue:45335", + "issue:43475|issue:43540", + "issue:45397|issue:45656", + "issue:44483|issue:46202", + "issue:45137|issue:45600", + "issue:43653|issue:44162", + "issue:44995|issue:45588", + "issue:44368|issue:44977", + "issue:44368|issue:45563", + "issue:44877|issue:46170", + "issue:43931|issue:44368", + "issue:42886|issue:45229", + "issue:44060|issue:44077", + "issue:45003|issue:45561", + "issue:43673|issue:44734", + "issue:45584|issue:46170", + "issue:44297|issue:44623" + ], + "prepared_review_unit_hash": "fefb0de649b01f84a68f22ba3d037bfe80c27ebf880cf103da8a5a60fecfa085", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35873, + "estimated_input_tokens": 8969, + "estimated_eval_tokens": 18194 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are unrelated bugs across different models, configs, and code paths. The soft pairs share only broad subsystem similarity (tokenization, generation, DeepSpeed, save/load, vision/video), not the same underlying defect.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a strong canonical representative; the cluster spans distinct regressions and model families rather than one duplicate bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Different failures: Qwen3 MOE weight conversion vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Resize-embeddings bug vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "ImportError for Qwen2.5 VL image processor is unrelated to BertModel/ZeRO3 index error." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize issue is not the same as a version-dependent tokenization change." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config loading, but they target different models and different field-handling failures." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file race and a stale generation warning are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Different SAM3 problems: pixel decoder implementation vs tracker/video config warning." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs syncing bug is unrelated to ANSI output in loading_report." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model loading failure and tokenizer error masking are different bugs." + }, + { + "left": "issue:45987", + "right": "issue:46082", + "accept": false, + "reason": "Cache length return type bug vs LlamaConfig head_dim validation are unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale indexer cache on second forward pass is unrelated to missing mm_token_type_ids defaults." + }, + { + "left": "issue:44479", + "right": "issue:46170", + "accept": false, + "reason": "Video-input regression and Windows ROCm import failure are separate code paths." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Serialization of tied weights is different from resize_token_embeddings not updating decoder embeddings." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "SAM3 video encoder output attribute bug vs Qwen3OmniMoe video processing ValueError." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 ZeRO3 loading issue and double optimizer step under DeepSpeed are different defects." + }, + { + "left": "issue:44483", + "right": "issue:46202", + "accept": false, + "reason": "Chat/completions request handling failure is unrelated to Gemma pipeline roundtrip tokenization." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "ZeRO3 deque underflow and auto_mappings stale config references are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "BigBirdTokenizer special-token registration bug is unrelated to ESM2 breakage." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale forward-pass cache bug is unrelated to flash_attention crashing on s_aux=None." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "Tie-word-embeddings warning in fine-tuning is not the same as flash-attention generation failure." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "These are different warnings in different paths with no shared bug mechanism." + }, + { + "left": "issue:44877", + "right": "issue:46170", + "accept": false, + "reason": "Strict config loading and Windows ROCm import/type errors are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch is unrelated to tie-word-embeddings warnings." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache tokenizer loading and Gemma4 multi-GPU OOM are not the same issue." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Incorrect tied-weights warning in Qwen3-Next is unrelated to patchtsmixer post_init policy." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "sys.modules access bug and xdist captured_info.txt race are different problems." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Missing GenerationMixin cache in v5.0.0 and wrong tensor indexing in serve are distinct generation bugs." + }, + { + "left": "issue:45584", + "right": "issue:46170", + "accept": false, + "reason": "Whisper empty-transcription failure is unrelated to Windows ROCm torch.distributed import errors." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch and processor save_pretrained missing files are related but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 38, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:36010", + "issue:41628", + "issue:42371", + "issue:42673", + "issue:42994", + "issue:43232", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43701", + "issue:43704", + "issue:43824", + "issue:43827", + "issue:44038", + "issue:44162", + "issue:44188", + "issue:44222", + "issue:44351", + "issue:44361", + "issue:44623", + "issue:44661", + "issue:44749", + "issue:44869", + "issue:44871", + "issue:44933", + "issue:44964", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45230", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45381", + "issue:45397", + "issue:45406", + "issue:45478", + "issue:45656", + "issue:46077", + "issue:46123", + "issue:46132", + "issue:46202" + ], + "soft_pairs": [ + "issue:44869|issue:45356", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:44749|issue:45656", + "issue:44623|issue:45656", + "issue:44871|issue:46132", + "issue:43701|issue:44749", + "issue:43673|issue:43827", + "issue:44188|issue:46202", + "issue:45230|issue:45397", + "issue:42994|issue:43482", + "issue:44038|issue:44623", + "issue:43475|issue:45381", + "issue:43475|issue:43643", + "issue:28282|issue:30990", + "issue:42371|issue:45092", + "issue:43232|issue:43673", + "issue:41628|issue:44933", + "issue:45375|issue:45478", + "issue:43475|issue:44661", + "issue:42994|issue:43525", + "issue:46077|issue:46123", + "issue:45310|issue:45375", + "issue:45081|issue:45103", + "issue:45406|issue:46202", + "issue:42673|issue:43704", + "issue:41628|issue:44351", + "issue:44964|issue:45137", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:44038|issue:45310", + "issue:36010|issue:41628" + ], + "prepared_review_unit_hash": "b38eac144f80188613c43cefefebdbd559394e44d9ffba0c130e12b908b28c63", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37089, + "estimated_input_tokens": 9273, + "estimated_eval_tokens": 18802 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy and mostly spans distinct Transformer regressions and model-specific issues. The only clear duplicate pair is the Qwen3ForCausalLM VRAM leak report; most other soft-similar pairs are related only at the subsystem/theme level, not the same underlying bug.", + "confidence": 0.84, + "canonical_issue_reason": "issue:42673 is the best canonical issue because issue:43704 appears to be an exact duplicate with the same title, and 42673 has higher discussion activity in the packet (10 vs 1).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the best overall issue candidate because it matches issue:43704 exactly by title and has more discussion activity, making it the clearest representative of that bug in the visible set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Different bugs: Whisper timestamp decoding crash vs Kimi tokenizer regression/codec handling." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "Different code paths: MLukeTokenizer task AttributeError vs a performance slowdown after upgrade." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Both are broad breakages, but they describe different affected models and failure modes; not the same concrete bug." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Unrelated symptoms: data filtering slowdown vs DeepSpeed optimizer stepping twice." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Different subsystems and failures: processor.save_pretrained file omission vs DeepSpeed optimizer double-step." + }, + { + "left": "issue:44871", + "right": "issue:46132", + "accept": false, + "reason": "Different features: Gemma eos token config mismatch vs AttentionInterface.register behavior change." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "Checkpoint key mismatch is not the same bug as the reported preprocessing slowdown." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache bug vs documentation still referencing removed pipeline APIs." + }, + { + "left": "issue:44188", + "right": "issue:46202", + "accept": false, + "reason": "Different failures: torch.compile attention-kernel divergence vs Gemma pipeline roundtrip/tokenization issue." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "One is a placeholder bug report, the other is a specific gemma-4 zero3 from_pretrained failure." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure is not the same as GGUF loading failure." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different bugs: Qwen3-VL-Moe/v5 compatibility vs missing files on processor.save_pretrained." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Different model families and failures: SAM 3 video attribute error vs Qwen2.5-VL video position-id bug." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM 3 vision encoder attribute error is unrelated to trust_remote_code field loss in AutoConfig." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "ImportError for missing PyTorch is not the same as a loading hang in Sentence Transformers." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 API settings change and remote-code/meta-init incompatibility are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both are generation-related, but they affect different code paths and reported failures." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import issues, but for different symbols and modules; not a clear duplicate." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5 Moe, but one is a missing config field being dropped and the other is a generic from_pretrained error; too different to merge." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM 3 vision encoder issue is unrelated to tokenizer-mapping logic in add-new-model-like." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure is not the same as Llama4Config missing pad_token_id." + }, + { + "left": "issue:46077", + "right": "issue:46123", + "accept": false, + "reason": "Different attention/masking bugs: Gemma4 causal-mask construction vs pipeline final-batch result dropping." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Same model family, but different concrete failures: from_pretrained loading error vs missing deepstack_visual_indexes field." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer regex patch crash and auto-docstring future-annotations crash are unrelated." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer is a different bug from Gemma pipeline roundtrip token handling." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact duplicate bug report: same Qwen3ForCausalLM VRAM leak in multiple dataloader threads, with identical title and matching symptom." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: AutoImageProcessor vs HybridCache." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal and DeepSpeed ZeRO3 deque underflow are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Save-pretrained FP8 moe bug and Qwen3.5 Moe from_pretrained loading bug are different operations and failures." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen MoE models, but they are different regressions/version contexts and not the same concrete code-path bug." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Tokenizer patch crash and auto-docstring annotation handling failure do not share the same underlying defect." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Gemma4 processor initialization failure is not the same as the Gemma pipeline roundtrip issue." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact duplicate bug report: same Qwen3ForCausalLM VRAM leak in multiple dataloader threads, with identical title and matching symptom." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different import errors involving different APIs and model classes." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The overall choice of issue:42673 is plausible, but the justification overstates the packet. There are no inbound references for either 42673 or 43704, so phrases like \"well-supported by discussion and references\" / \"richer discussion/inbound-reference trail\" are not grounded. Please keep the canonical/best-issue rationale limited to what is visible in the packet (identical titles and higher discussion activity on 42673)." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 39, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:42175", + "issue:42222", + "issue:42831", + "issue:42898", + "issue:43065", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43901", + "issue:44016", + "issue:44060", + "issue:44075", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44295", + "issue:44373", + "issue:44448", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45561", + "issue:45600", + "issue:45656", + "issue:45712", + "issue:45812", + "issue:46123", + "issue:46231", + "issue:46326" + ], + "soft_pairs": [ + "issue:42831|issue:44222", + "issue:42175|issue:45712", + "issue:44496|issue:45561", + "issue:43377|issue:44242", + "issue:45561|issue:45600", + "issue:43901|issue:45561", + "issue:42898|issue:44568", + "issue:43232|issue:44792", + "issue:30990|issue:35141", + "issue:43278|issue:45137", + "issue:42222|issue:45200", + "issue:43065|issue:46123", + "issue:44623|issue:45310", + "issue:30333|issue:33290", + "issue:43232|issue:44188", + "issue:44188|issue:44373", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:42898|issue:44779", + "issue:44734|issue:45103", + "issue:44016|issue:46231", + "issue:43874|issue:45092", + "issue:44075|issue:46231", + "issue:43723|issue:46326", + "issue:44060|issue:45125", + "issue:42898|issue:44448", + "issue:44295|issue:45656", + "issue:45405|issue:45712" + ], + "prepared_review_unit_hash": "4375470e0a3c0de8a8caa708b96879329048659232a9d9ba249e99dc0650a6bd", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36784, + "estimated_input_tokens": 9196, + "estimated_eval_tokens": 18648 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of unrelated Transformers issues, with only superficial overlap around tokenizers, v5 regressions, multimodal models, DeepSpeed, and packaging/import problems. None of the soft-edge pairs look like true duplicates or the same underlying fix.", + "confidence": 0.95, + "canonical_issue_reason": "issue:42898 is a clear, high-signal regression report with a well-defined tokenizer behavior change in v5, making it a good representative anchor for the cluster\u2019s tokenizer-regression subset.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42898 is the strongest representative issue: it is concrete, versioned, user-visible, and narrowly scoped enough to summarize a common failure mode seen elsewhere in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Both mention FP8, but one is an accuracy regression and the other is a save_pretrained/MoE serialization issue; different bug classes." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Both are backend/import packaging problems, but one is missing TensorFlow under the torch extra and the other is stale dummy classes leaking without torch; not the same defect." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model config loading and pytest-xdist file races are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "MIMI padding-mask batch consistency and MoE load-balancing loss gating are different model behaviors and code paths." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "A test-worker race on captured_info.txt is unrelated to auto_mappings referencing removed configs." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Documentation mismatch for TextClassificationPipeline does not share the same bug as the xdist file race." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer v5 regressions, but one is clean-up spacing behavior and the other is special-token insertion; different underlying fixes." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwarg sync logic and a Janus image-generation test failure are not the same issue." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence-Transformers loading hangs and token-embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "BF16-to-FP32 dtype drift in evaluation is unrelated to DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Broken vitpose models and Gemma 4 mm_token_type_ids defaults affect different model families and code paths." + }, + { + "left": "issue:43065", + "right": "issue:46123", + "accept": false, + "reason": "A dummy Conv2d placeholder in Sam3PixelDecoder is unrelated to MaskGenerationPipeline partial-batch handling." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor files on save and Qwen3.5 MoE from_pretrained failures are different serialization/loading problems." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting on failed training jobs and Adafactor OOM in DeepSpeed are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Both involve generation/attention internals, but one is kwarg update after sync_gpus and the other is bidirectional-skip branching under torch.compile; not the same bug." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "Attention-kernel divergence under compile is unrelated to a position_ids docstring issue." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one concerns cleanup spacing and the other wrong Granite token IDs; distinct root causes." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "A missing nn import in sentence-transformers and a missing Qwen2_5_VL class import are separate import errors." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading in v5 and missing BOS/EOS on add_special_tokens are different failure modes." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but Kimi codec handling/warning behavior is not the same as clean_up_tokenization_spaces changes." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Deepseek tokenization output corruption and cleanup spacing behavior are different tokenizer bugs." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "Serve-time KV-cache continuation indexing and auto_docstring annotation handling are unrelated." + }, + { + "left": "issue:44016", + "right": "issue:46231", + "accept": false, + "reason": "A syntax error in a notebook and a docstring parameter-name mismatch are different documentation issues." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing get_number_of_image_patches in GLM46V and meta-init incompatibility for InternVL2 are different multimodal issues." + }, + { + "left": "issue:44075", + "right": "issue:46231", + "accept": false, + "reason": "SGD arguments being ignored is a runtime optimizer bug, not a documentation typo." + }, + { + "left": "issue:43723", + "right": "issue:46326", + "accept": false, + "reason": "Tokenizer loading failures and continue_final_message behavior for mistral_common tokenizers are not the same underlying problem." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Wrong tied-weights warning and missing tensor-parallel plan for Qwen3.5 MoE are separate Qwen model bugs." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Reading position_ids after buffer registration and double optimizer.step under DeepSpeed are different execution bugs." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "A PyPI version pin problem and leftover dummy classes in dummy_pt_objects.py are unrelated maintenance issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 40, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:43122", + "issue:43232", + "issue:43475", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43873", + "issue:43976", + "issue:44079", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44623", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45092", + "issue:45103", + "issue:45245", + "issue:45310", + "issue:45381", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834", + "issue:46082", + "issue:46132", + "issue:46209", + "issue:46305" + ], + "soft_pairs": [ + "issue:44448|issue:46132", + "issue:42175|issue:44933", + "issue:44222|issue:44297", + "issue:44933|issue:45712", + "issue:43976|issue:44933", + "issue:43479|issue:44079", + "issue:44297|issue:45656", + "issue:44222|issue:44623", + "issue:30333|issue:34689", + "issue:42831|issue:44623", + "issue:45245|issue:46132", + "issue:44190|issue:46082", + "issue:30333|issue:36331", + "issue:45071|issue:46082", + "issue:43479|issue:44869", + "issue:30333|issue:35141", + "issue:28282|issue:30333", + "issue:43475|issue:46305", + "issue:44297|issue:45310", + "issue:41628|issue:42757", + "issue:44206|issue:45103", + "issue:43723|issue:44977", + "issue:45381|issue:46305", + "issue:43873|issue:44945", + "issue:43122|issue:46209", + "issue:43232|issue:45834", + "issue:44222|issue:44484", + "issue:44263|issue:45092", + "issue:44295|issue:44623", + "issue:43479|issue:43644", + "issue:44373|issue:44485", + "issue:44483|issue:45406" + ], + "prepared_review_unit_hash": "0936a506bdf9d219fe04926b43daad73ce9d77d403d1c94bead725286161ec15", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37061, + "estimated_input_tokens": 9266, + "estimated_eval_tokens": 18788 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose grab-bag of unrelated Transformers issues; the soft pairs do not look like duplicate bug reports or the same fixable change, so all suggested merges should be rejected.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 44483 is the clearest high-severity user-facing regression in this set and the best single anchor, though the cluster is still heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44483 is concrete, impactful, and well-scoped compared with the rest, which span unrelated imports, configs, serialization, training, and model-specific regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44448", + "right": "issue:46132", + "accept": false, + "reason": "Different problems: Pegasus output drift vs AttentionInterface.register changing a function wrapper's behavior." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Missing TensorFlow backend and a nonexistent image_utils import are separate import-path failures." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 save_pretrained on MoE models and tokenizer_config tokenizer_class mismatch are unrelated save_pretrained bugs." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "One is a bad import from image_utils; the other is leftover dummy PT classes leaking into dir(transformers)." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version/backend compatibility is not the same bug as an invalid image_utils import symbol." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Phi4MultimodalConfig default initialization and ModelOutput key assignment are different code paths and symptoms." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save metadata and DeepSpeed optimizer-step behavior are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "FP8 MoE save_pretrained and processor.save_pretrained missing files are both save-related but not the same defect." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLflow reporting on failed training jobs and a model-loading regression are distinct issues." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy and processor.save_pretrained file emission are different failures." + }, + { + "left": "issue:45245", + "right": "issue:46132", + "accept": false, + "reason": "Category limit overflow and AttentionInterface.register behavior have no shared underlying bug." + }, + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Local dataset loading in an example script is unrelated to LlamaConfig head_dim validation." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow job status handling and CustomTrainer.compute_loss signature breakage are separate training issues." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "PretrainedConfig type-checking regression is not the same as LlamaConfig head_dim rejection." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Multimodal config defaults and Whisper word-timestamp decoding are unrelated model-specific bugs." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Failed-job MLflow reporting and output embedding reinitialization after resize are different problems." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "A missing PyTorch import and MLflow reporting on failed jobs do not share a code path." + }, + { + "left": "issue:43475", + "right": "issue:46305", + "accept": false, + "reason": "SAM 3 Video missing attribute and Moonshine streaming mask off-by-one are different video-model bugs." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer class metadata mismatch and Qwen3.5 MoE from_pretrained failure are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and different dependency breakages." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Unsupported feature extractor arg and auto_docstring future-annotations crash are separate failures." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression in v5 and Qwen3.5 flash-attention generation failure are unrelated." + }, + { + "left": "issue:45381", + "right": "issue:46305", + "accept": false, + "reason": "Wrong vision_position_ids and sliding_window_mask_function off-by-one affect different model components." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization/offloading behavior and pipeline-parallel output correctness are not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:46209", + "accept": false, + "reason": "Tokenization changes across versions and FP8 inference on B200 are unrelated regressions." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus and long-OCR index errors have no common root cause." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained and max_shard_size defaults are different save_pretrained concerns." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split return handling in a MoE indexer and meta-init incompatibility for old checkpoints are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "position_ids buffer access and processor.save_pretrained missing files are different serialization bugs." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Incorrect multimodal config defaults and junk non-persistent buffers are not the same initialization issue." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "A docstring mistake for position_ids is unrelated to GLM-5 RoPE implementation behavior." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat-completions request rejection and Gemma4Processor missing _tokenizer are separate API failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 41, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43479", + "issue:43550", + "issue:43576", + "issue:43644", + "issue:43646", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44360", + "issue:44368", + "issue:44373", + "issue:44464", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44829", + "issue:44871", + "issue:44913", + "issue:44945", + "issue:45092", + "issue:45103", + "issue:45278", + "issue:45310", + "issue:45357", + "issue:45753", + "issue:46002", + "issue:46050", + "issue:46082", + "issue:46132", + "issue:46305" + ], + "soft_pairs": [ + "issue:43761|issue:46082", + "issue:43723|issue:44871", + "issue:30990|issue:38175", + "issue:45092|issue:45357", + "issue:42907|issue:46050", + "issue:44514|issue:45103", + "issue:44263|issue:44360", + "issue:43644|issue:46305", + "issue:44829|issue:46002", + "issue:44261|issue:45092", + "issue:43479|issue:44913", + "issue:42831|issue:45310", + "issue:22355|issue:28282", + "issue:41628|issue:43824", + "issue:42831|issue:44038", + "issue:44263|issue:44373", + "issue:39401|issue:44568", + "issue:42886|issue:42994", + "issue:44368|issue:46305", + "issue:42886|issue:43066", + "issue:44945|issue:45753", + "issue:42757|issue:45278", + "issue:44464|issue:46082", + "issue:43576|issue:43784", + "issue:43646|issue:46002", + "issue:44117|issue:44704", + "issue:43550|issue:46132", + "issue:42371|issue:44263" + ], + "prepared_review_unit_hash": "c5d50060078d00a46e989e335b8ee7c1ccc4dfed829f52192e26fc28351b21a3", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35858, + "estimated_input_tokens": 8965, + "estimated_eval_tokens": 18186 + }, + "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 import/runtime bugs, not a tight duplicate set. The best single anchor is the broad upgrade/import-regression report.", + "confidence": 0.31, + "canonical_issue_reason": "issue:45278 is the broadest umbrella here: it captures the common v5 upgrade/import breakage pattern better than the many narrow model- or tokenizer-specific bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best cluster anchor because it summarizes the recurring \u201cafter upgrade, imports break\u201d theme without overfitting to one specific symbol or model.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "Different failures: CLIPVisionModel hidden_states regression vs LlamaConfig head_dim validation. Not the same code path." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading regression vs eos_token_id config inconsistency. Related area, but distinct bugs." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence Transformers loading hang and siglip2 zero-probability output are unrelated failures." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Remote-code/meta-init incompatibility vs incorrect visual encoder keys on save_pretrained. Different concrete bugs." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantized saving/loading, but one is dequantized Ministrals/Devstrals save failure and the other is sinq round-trip breakage; not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched apply_chat_template crash and auto_docstring annotation crash are unrelated code paths." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention the DSA indexer, but one is torch.split return handling and the other is a missing ReLU. Different defects." + }, + { + "left": "issue:43644", + "right": "issue:46305", + "accept": false, + "reason": "Non-persistent buffer junk and sliding_window_mask off-by-one are separate logic issues." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Degenerate training with FA3 and NaNs in classification heads after checkout/init are different symptoms with different likely causes." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA layernorm precision issue vs remote-code checkpoint/meta-init incompatibility are unrelated." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Phi4MultimodalConfig default subconfig initialization and GPTNeoXConfig rotary_pct reload are distinct configuration bugs." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 Moe from_pretrained error do not describe the same underlying problem." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Missing transformers.onnx module and missing PyTorch for AutoModel are different import/runtime dependency issues." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols and model families." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Different bugs: FP8 accuracy regression vs Qwen3-VL-Moe transform/load failure." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "torch.split handling in GlmMoeDsaIndexer and a wrong docstring for position_ids are unrelated." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Wrong offset_mapping and missing BOS/EOS addition are both tokenizer bugs, but not the same concrete defect." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline cache loading and quantized model saving are separate failures." + }, + { + "left": "issue:44368", + "right": "issue:46305", + "accept": false, + "reason": "A tie_word_embeddings warning and a sliding_window_mask off-by-one bug are unrelated." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline tokenizer cache loading and wrong decoder type are different tokenizer-related regressions." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline parallelism output corruption and an infinite-loop multimodal prompt are different failure modes." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related regressions, but one is a specific huggingface_hub symbol and the other is a broad post-upgrade import breakage report." + }, + { + "left": "issue:44464", + "right": "issue:46082", + "accept": false, + "reason": "Chunked generation with compiled forward and LlamaConfig head_dim validation are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken transformers env CLI and a sentence-transformers NameError are separate import/CLI regressions." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Non-persistent buffer junk and NaNs in classification heads are not the same bug." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES returning None and AutoProcessor not forwarding kwargs to cached_file are different from_pretrained/processor issues." + }, + { + "left": "issue:43550", + "right": "issue:46132", + "accept": false, + "reason": "Bamba SDPA torch.compile failure and AttentionInterface.register behavior change are distinct attention-stack bugs." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 API warning and DSA indexer torch.split behavior are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 42, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28218", + "issue:30990", + "issue:33357", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42907", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43937", + "issue:44038", + "issue:44060", + "issue:44222", + "issue:44261", + "issue:44279", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44442", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44945", + "issue:44964", + "issue:45200", + "issue:45216", + "issue:45245", + "issue:45278", + "issue:45290", + "issue:45478", + "issue:45593", + "issue:45600", + "issue:46326", + "issue:46328" + ], + "soft_pairs": [ + "issue:30990|issue:33357", + "issue:44295|issue:44297", + "issue:43232|issue:45593", + "issue:44704|issue:45290", + "issue:42907|issue:44945", + "issue:43723|issue:44442", + "issue:44261|issue:44373", + "issue:42907|issue:43937", + "issue:41628|issue:45278", + "issue:43408|issue:43475", + "issue:43756|issue:44060", + "issue:43784|issue:45600", + "issue:43116|issue:45200", + "issue:42907|issue:44964", + "issue:43122|issue:44514", + "issue:44625|issue:44829", + "issue:44360|issue:44485", + "issue:44038|issue:44297", + "issue:43232|issue:45245", + "issue:43122|issue:44521", + "issue:28218|issue:30990", + "issue:42907|issue:43452", + "issue:44038|issue:44295", + "issue:43122|issue:44779", + "issue:36296|issue:43116", + "issue:44038|issue:44222", + "issue:44279|issue:46328", + "issue:45216|issue:45478", + "issue:39401|issue:44488", + "issue:43122|issue:46326", + "issue:39401|issue:44521" + ], + "prepared_review_unit_hash": "ced4de6b0d6b93832613714645f68811cf6d82d0c7ca84b1a09ae8072aa81276", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36034, + "estimated_input_tokens": 9009, + "estimated_eval_tokens": 18274 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly heterogeneous; most soft pairs only share a broad subsystem name (tokenizers, Qwen3, save/load, etc.) but not the same concrete bug. I found no duplicate PRs, and only one issue looks like a reasonable umbrella representative for the tokenizer-regression subset.", + "confidence": 0.41, + "canonical_issue_reason": "issue:43122 is the broadest, most representative tokenizer-regression report in this set, and it best matches several of the tokenization-related soft matches; the rest of the cluster is too mixed for a single true canonical issue.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43122 is the strongest overall issue anchor because it describes a generic v5 tokenization regression rather than a narrow model-specific symptom, and it sits closest to the related tokenizer candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Different symptoms and subsystems: loading hang vs Mac bus error on a CLIP model." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Unrelated bugs: buffer access on position_ids vs tokenizer_class mismatch on save_pretrained." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs handling and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "Different processor paths: cached_file kwargs forwarding vs chat template crashes with tool-call messages." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized models is unrelated to incorrect output under pipeline parallelism." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both mention tokenizer loading, but one is a broad v5 loading issue and the other is a specific tokenizer failure; not enough to \u0938\u093e\u092c\u093f\u0924 same bug." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "MLA norm precision/config bug and a docstring issue are not the same change." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Different model workflows: dequantized save_pretrained vs invalid GenerationConfig." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "One import-name failure is too specific to merge with a broad version-upgrade import-error report." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Different SAM 3 failures: model-type warning vs missing output attribute." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Unrelated model internals: RoPE-layer count vs tied-weights warning." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Different breakages: missing nn import in sentence-transformers vs stale auto_mappings references." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example-script classification output bug and mm_token_type_ids defaulting are unrelated." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Tokenization regression vs batched chat-template crash are different code paths." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Label propagation in Qwen3.5 is unrelated to flash_attention_3 causing degenerate training." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "DSA ReLU/indexer discussion is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe bug and tokenizer save_pretrained class mismatch are different problems." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation state update bug and category-count limit error do not match." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "General tokenizer regression vs multimodal assistant_mask zeroing are different symptoms." + }, + { + "left": "issue:28218", + "right": "issue:30990", + "accept": false, + "reason": "Tokenizer spacing bug and SentenceTransformers loading hang are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models is unrelated to gguf_file load failures." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Different bug classes: Qwen3-VL-Moe incompatibility vs position_ids buffer access." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer-related regressions, but one is a generic version-diff report and the other is DeepSeek-specific incorrect output; not clearly the same concrete defect." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bug is unrelated to the multi-label example-script issue." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Qwen3-VL-Moe incompatibility and FP8 save_pretrained on moe are different issues." + }, + { + "left": "issue:44279", + "right": "issue:46328", + "accept": false, + "reason": "General dependency complaint and a SequenceFeatureExtractor.pad performance bug are not duplicates." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3.5 and recent versions, but one is save_pretrained checkpoint corruption and the other is from_pretrained loading failure; different code paths." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Wrong offset_mapping in Qwen3 tokenizer is unrelated to failing to load cjvt/sleng-bert." + }, + { + "left": "issue:43122", + "right": "issue:46326", + "accept": false, + "reason": "Generic tokenizer regression and mistral_common continue_final_message behavior are different bugs." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer offset_mapping bug and multimodal assistant_mask bug are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 43, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:29159", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:43066", + "issue:43116", + "issue:43441", + "issue:43493", + "issue:43611", + "issue:43784", + "issue:43824", + "issue:43825", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44297", + "issue:44351", + "issue:44355", + "issue:44380", + "issue:44485", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44936", + "issue:44938", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002", + "issue:46077", + "issue:46231" + ], + "soft_pairs": [ + "issue:43824|issue:44351", + "issue:43784|issue:45446", + "issue:22355|issue:28218", + "issue:22355|issue:29159", + "issue:42757|issue:44351", + "issue:43992|issue:44704", + "issue:43066|issue:44779", + "issue:44355|issue:46231", + "issue:43611|issue:46002", + "issue:43937|issue:44485", + "issue:42222|issue:43441", + "issue:44075|issue:44936", + "issue:42371|issue:43874", + "issue:42831|issue:44297", + "issue:43976|issue:45446", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:43493|issue:45753", + "issue:43116|issue:43493", + "issue:45083|issue:45446", + "issue:43937|issue:45563", + "issue:22355|issue:29127", + "issue:44625|issue:46002", + "issue:33453|issue:39401", + "issue:44380|issue:46077", + "issue:38617|issue:45278", + "issue:42175|issue:44938", + "issue:44117|issue:45588", + "issue:39401|issue:44779" + ], + "prepared_review_unit_hash": "5550e383d510ee526ef5c7aca4698a9e5ad592d464bd761dc2b275d0494525e4", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36225, + "estimated_input_tokens": 9057, + "estimated_eval_tokens": 18370 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose collection of unrelated transformer regressions and import/tokenizer issues; the broadest umbrella issue is the one about many import errors after upgrade.", + "confidence": 0.43, + "canonical_issue_reason": "issue:45278 is the best umbrella issue: it explicitly captures the broad post-upgrade import-error regression pattern that overlaps with the largest portion of this cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most representative global issue because it is broad, symptom-focused, and best matches the cluster\u2019s cross-cutting failure mode.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols and likely different code paths." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated failures: one is a NameError on import, the other is a PyTorch version-check/import-guard bug." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "Completely different bugs: ONNX module import vs tokenizer spacing after added tokens." + }, + { + "left": "issue:22355", + "right": "issue:29159", + "accept": false, + "reason": "Different areas and symptoms: ONNX import failure vs slow/fast tokenizer inconsistency." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Both are import failures, but for different packages/symbols and not the same underlying bug." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "Different code paths: model weight loading vs AutoProcessor cached_file kwargs forwarding." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both concern tokenizers, but the titles point to distinct regressions in different models/behaviors." + }, + { + "left": "issue:44355", + "right": "issue:46231", + "accept": false, + "reason": "No overlap beyond being in the repo; compiled-file errors and a documentation typo are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "Model loading with base_model_prefix is unrelated to NaNs in classification heads." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "Same model family, but invalid GenerationConfig and RoPE implementation are different concrete bugs." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Different subsystems and model families: vitpose breakage vs FlashAttention failure." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer argument handling is unrelated to trainer.evaluate() failing after train()." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 settings API and a GLM46V image-patch helper bug are unrelated." + }, + { + "left": "issue:42831", + "right": "issue:44297", + "accept": false, + "reason": "Different failure modes: FP8 accuracy issue vs tokenizer save_pretrained metadata mismatch." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Both mention versioning, but one is a Python compatibility issue and the other is a PyTorch import guard bug." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Related Qwen3.5 area, but save_pretrained key serialization and from_pretrained loading errors are not the same concrete bug." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Both involve Qwen3/Qwen3.5 MoE, but the reported failures are different load-time behaviors." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "One is a classification example bug, the other is a pipeline error-message regression." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Different model behaviors: SigLIP2 implementation discrepancy vs Qwen3_5 infinite loop on a specific image." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Different tasks and failure modes; only broad ML-model regression similarity." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Unrelated: multimodal feature-length helper bug vs a flex_attention version check." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig validation and stale warning emission are different code paths." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "ONNX import failure and LayoutLMv3 error-message clarity are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Different bug classes: config propagation vs NaNs during checkout/init." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Both are tokenizer regressions, but they affect different loading/runtime behaviors and models." + }, + { + "left": "issue:44380", + "right": "issue:46077", + "accept": false, + "reason": "Different attention-path bugs in different models; not the same concrete issue." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "issue:45278 is a broad umbrella, but this is a specific missing import symbol and not clearly the same bug." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Backend packaging/install issue vs Python 3.14 load failure are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "A tokenizer mapping None bug and a flash_attention aux-state AttributeError are different failure modes." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but the reported symptoms and affected models differ." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 44, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42222", + "issue:42673", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43122", + "issue:43381", + "issue:43408", + "issue:43421", + "issue:43450", + "issue:43577", + "issue:43673", + "issue:43742", + "issue:43827", + "issue:43937", + "issue:43986", + "issue:44075", + "issue:44117", + "issue:44291", + "issue:44410", + "issue:44466", + "issue:44483", + "issue:44484", + "issue:44496", + "issue:44829", + "issue:44877", + "issue:44945", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45464", + "issue:45542", + "issue:45656", + "issue:46002", + "issue:46178", + "issue:46231", + "issue:46298", + "issue:46328" + ], + "soft_pairs": [ + "issue:43381|issue:44945", + "issue:43064|issue:43673", + "issue:43827|issue:45446", + "issue:43450|issue:43986", + "issue:43937|issue:44977", + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:42673|issue:45072", + "issue:44117|issue:45081", + "issue:43122|issue:46298", + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071", + "issue:42222|issue:46178", + "issue:38617|issue:41628", + "issue:39401|issue:43421", + "issue:43408|issue:43742", + "issue:44877|issue:46231", + "issue:44484|issue:45310", + "issue:43937|issue:44496", + "issue:43066|issue:43122", + "issue:44483|issue:45464", + "issue:44117|issue:46328", + "issue:44964|issue:45278", + "issue:44075|issue:45656", + "issue:42222|issue:45542", + "issue:43012|issue:43577" + ], + "prepared_review_unit_hash": "1b8cf87b5bca7d3847db6990b31018fafbc39c9b67cdbf42d221a37e6cfeebe4", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35813, + "estimated_input_tokens": 8954, + "estimated_eval_tokens": 18164 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous: tokenizer regressions, model-loading failures, training/optimizer bugs, video/vision issues, docs, and backend/dependency errors. I don\u2019t see any convincing duplicate pairs, so there is no strong canonical duplicate group here.", + "confidence": 0.86, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43122 is the best standalone issue to anchor on if one must choose: it is a concrete, user-visible tokenizer regression with clear behavioral impact and broader relevance than the more narrowly scoped or auxiliary reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Different failures: eval-mode checkpointing vs pipeline-parallel output corruption." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Unrelated training-state bug vs generation cache/chunked-prefill issue." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs cleanup about pipeline references is unrelated to a flex_attention import/version check." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batch video-shape bug vs missing-torchvision crash path; different code paths and symptoms." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "GenerationConfig validation failure is unrelated to Qwen3.5 flash-attention generation behavior." + }, + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Serialization/tied-weights issue is not the same as NaNs on checkout/init." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Release/version pinning complaint is unrelated to flex_attention backend import logic." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM is a different problem from dtype mismatches in inference." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping None handling is not the same as the Mistral regex patch crash." + }, + { + "left": "issue:43122", + "right": "issue:46298", + "accept": false, + "reason": "Tokenizer behavior regression is unrelated to a noisy logging message." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Missing projections in qwen3next layer 0 and Qwen3.5 from_pretrained failure are different bugs." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Flash-attention training degeneration is not the same as checkpoint serialization corruption." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights argument mismatch is unrelated to PretrainedConfig type-checking." + }, + { + "left": "issue:42222", + "right": "issue:46178", + "accept": false, + "reason": "VitPose breakage is not the same as the tensorflow_text backend mapping error." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Importing a removed helper from configuration_utils is a different import issue than AutoImageProcessor export failure." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Wrong offset_mapping in Qwen3 tokenizer is a different bug from runtime post-processor updates." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "sam3_video/sam3_tracker warning is unrelated to the MobileLLM config loading key error." + }, + { + "left": "issue:44877", + "right": "issue:46231", + "accept": false, + "reason": "Strict config loading for granite_speech is unrelated to a documentation parameter-name mismatch." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Shard-size default question is not the same as Qwen3.5 MoE loading failure." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Invalid GenerationConfig and unrecognized model/config.json are different loading/validation problems." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are tokenizer-v5 related, but one is decoder-type metadata and the other is a tokenization-output regression; not the same concrete bug." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Generic chat/completions request rejection is different from a Qwen3.5 streaming inference failure." + }, + { + "left": "issue:44117", + "right": "issue:46328", + "accept": false, + "reason": "Tokenizer mapping lookup bug is unrelated to SequenceFeatureExtractor.pad performance waste." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Phi-4 multimodal loading failure is too specific to be the same as a broad import-error report." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD args being ignored is a different optimizer bug from deepspeed double-step behavior." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage is not the same as missing-TensorFlow backend resolution." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Compile-time bfloat16 warning is not the same as model/qformer dtype staying float32 on load." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 45, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:38617", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43064", + "issue:43097", + "issue:43335", + "issue:43408", + "issue:43441", + "issue:43452", + "issue:43673", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44117", + "issue:44188", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44360", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44829", + "issue:44913", + "issue:44933", + "issue:44945", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45440", + "issue:45478", + "issue:45542", + "issue:45588", + "issue:46050", + "issue:46172", + "issue:46231", + "issue:46328" + ], + "soft_pairs": [ + "issue:44410|issue:45478", + "issue:42371|issue:44261", + "issue:44188|issue:46328", + "issue:44913|issue:46328", + "issue:42175|issue:42222", + "issue:38617|issue:44220", + "issue:43097|issue:44493", + "issue:41628|issue:45071", + "issue:43874|issue:44261", + "issue:44263|issue:44485", + "issue:45071|issue:45542", + "issue:42673|issue:44977", + "issue:42673|issue:43906", + "issue:43012|issue:43408", + "issue:44263|issue:46172", + "issue:44360|issue:46172", + "issue:44484|issue:45478", + "issue:43441|issue:44829", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:42371|issue:42831", + "issue:43097|issue:43452", + "issue:44933|issue:46231", + "issue:44117|issue:44987", + "issue:43408|issue:44368", + "issue:43874|issue:44263", + "issue:43673|issue:46328", + "issue:43976|issue:44945", + "issue:43986|issue:44484", + "issue:45440|issue:46172", + "issue:43097|issue:46050", + "issue:43097|issue:45588", + "issue:43064|issue:44315" + ], + "prepared_review_unit_hash": "395a1b1174bb924a40173848d443d777d712a6d7c6ba9b5836085a09dea12ad5", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37494, + "estimated_input_tokens": 9374, + "estimated_eval_tokens": 19004 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the issues span unrelated import errors, model-specific bugs, config regressions, backend/runtime warnings, and a few performance problems. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43097 is the clearest broad regression report in the set: it is version-scoped, user-facing, and has some inbound references, whereas the other issues are mostly narrow, unrelated bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different failures: qwen3next missing projections in one layer vs a Qwen3.5 MoE load-time error." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API/settings warning is unrelated to an MLA layernorm epsilon precision bug." + }, + { + "left": "issue:44188", + "right": "issue:46328", + "accept": false, + "reason": "torch.compile attention branching and feature-extractor padding performance are different code paths and symptoms." + }, + { + "left": "issue:44913", + "right": "issue:46328", + "accept": false, + "reason": "GPTNeoX config reload regression is unrelated to SequenceFeatureExtractor.pad list conversion overhead." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TensorFlow missing from a torch install and broken vitpose models are separate issues." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for layer_type_validation does not match an audio feature extraction bug." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder and unexpected position-id keys are distinct config regressions." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import failure is unrelated to PreTrainedConfig type checking breakage." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-processor method in GLM46V is unrelated to MLA q_a_layernorm epsilon handling." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "torch.split return-value handling in GlmMoeDsaIndexer does not match the GLM-5 RoPE implementation issue." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "Type-checking regression and tensorboard-without-TensorFlow backend error are different problems." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in multi-threaded dataloading and flash-attention generation failure are not the same bug." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "The reproduction of issue 38071 is not the same underlying defect as the Qwen3ForCausalLM VRAM leak." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "bfloat16 precision warning during compile and a sam3 model-type warning are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:46172", + "accept": false, + "reason": "GlmMoeDsaIndexer split handling and deepseek-v4 comb transpose are different model internals." + }, + { + "left": "issue:44360", + "right": "issue:46172", + "accept": false, + "reason": "Missing ReLU in the DSA indexer is unrelated to the deepseek-v4 transpose bug." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard-size semantics are unrelated to a Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Ministral-3 flash-attention failure and flash_attention_3 causing degenerate training are different failure modes." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-VL-Moe version breakage are separate load-time issues." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug is unrelated to PreTrainedConfig type checking." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 behavior settings and FineGrainedFP8 accuracy are not the same underlying defect." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "A removed config option and gguf_file load failures affect different APIs and code paths." + }, + { + "left": "issue:44933", + "right": "issue:46231", + "accept": false, + "reason": "Nonexistent image_utils import and a documentation parameter-name mismatch are unrelated." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping None handling and loading physical-intelligence/fast are separate loading failures." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "sam3 type warning and tie_word_embeddings warning are distinct config validation issues." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing GLM46V image-processor method and torch.split return handling are unrelated bugs." + }, + { + "left": "issue:43673", + "right": "issue:46328", + "accept": false, + "reason": "Missing generation cache in chunked_prefill is unrelated to padding performance in feature extraction." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python version compatibility failure and incorrect pipeline-parallel output are different regressions." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor crash without torchvision and max_shard_size documentation/question are unrelated." + }, + { + "left": "issue:45440", + "right": "issue:46172", + "accept": false, + "reason": "Native DeepseekV3MoE divergence and deepseek-v4 comb transpose are different model implementation issues." + }, + { + "left": "issue:43097", + "right": "issue:46050", + "accept": false, + "reason": "Removed tie_embeddings option and quantized save/load breakage are not the same bug." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "tie_embeddings removal and flash_attention s_aux=None crash are unrelated code paths." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state corruption and Liger Kernel not applied with model_init are different training issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 46, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:38617", + "issue:42617", + "issue:42673", + "issue:42757", + "issue:42890", + "issue:42907", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43502", + "issue:43550", + "issue:43792", + "issue:43825", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44162", + "issue:44261", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44938", + "issue:44964", + "issue:45103", + "issue:45200", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45561", + "issue:45588", + "issue:45712", + "issue:45753", + "issue:45859", + "issue:46123", + "issue:46172", + "issue:46178", + "issue:46298" + ], + "soft_pairs": [ + "issue:42673|issue:45200", + "issue:38617|issue:42757", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:42890|issue:46298", + "issue:44038|issue:44410", + "issue:43931|issue:44410", + "issue:43502|issue:43992", + "issue:45341|issue:45859", + "issue:38617|issue:44351", + "issue:43097|issue:43873", + "issue:44964|issue:45341", + "issue:44261|issue:44485", + "issue:44704|issue:45103", + "issue:43986|issue:44117", + "issue:42617|issue:45341", + "issue:43986|issue:45372", + "issue:43066|issue:43906", + "issue:43986|issue:45290", + "issue:45341|issue:45588", + "issue:45341|issue:45561", + "issue:43208|issue:43550", + "issue:43986|issue:45341", + "issue:43992|issue:44484", + "issue:43012|issue:43550", + "issue:43825|issue:44655", + "issue:43012|issue:44368", + "issue:45712|issue:46298", + "issue:42907|issue:44655", + "issue:42907|issue:45753", + "issue:43097|issue:46298", + "issue:44162|issue:46172", + "issue:43792|issue:46123", + "issue:44938|issue:46178" + ], + "prepared_review_unit_hash": "06eadb4b1ec78a7e11a2d53b03f2f6cf795748693643a6ba2265c06d4e4690a3", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37692, + "estimated_input_tokens": 9423, + "estimated_eval_tokens": 19102 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a single duplicate cluster; it is a grab bag of unrelated Transformers issues. I rejected all soft edges because each pair points to a different underlying bug or code path, even when the titles share a subsystem or model family.", + "confidence": 0.93, + "canonical_issue_reason": "No single canonical issue stands out: the items are mostly unrelated, with only weak thematic overlap among a few import/model-loading/Qwen3 reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43986 is the best representative issue: it is specific, reproducible, and tied to one concrete loading path with a clear environment dependency.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42673", + "right": "issue:45200", + "accept": false, + "reason": "Different failures: VRAM leak in Qwen3 CausalLM threading vs Gemma 4 text-only fine-tuning config default." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different missing symbols from different modules; not the same bug." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "Different tokenizer problems: AddedToken argument collision vs TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Both mention Qwen3 models, but one is missing attention projections and the other is a missing config field; distinct defects." + }, + { + "left": "issue:42890", + "right": "issue:46298", + "accept": false, + "reason": "Unrelated: flaky test seeding issue vs a noisy logging message." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Different model-path failures: Qwen3-VL-Moe compatibility issue vs missing layer projections in qwen3next." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Different concrete failures and model variants; one is a shape mismatch during load, the other is missing projections." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Different loading behaviors: network access despite local_files_only vs missing embed_tokens.weight on UMT5Encoder." + }, + { + "left": "issue:45341", + "right": "issue:45859", + "accept": false, + "reason": "Unrelated: testing utility bug vs CPU offload incompatibility in Qwen3_5Moe rotary embedding." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they concern different APIs and different missing exports." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Different concerns: removed config option documentation vs quantization offloading behavior." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "Completely different: multimodal model load failure vs a small testing utility bug." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Different model-specific math/config issues: MLA layernorm epsilon vs GLM-5 RoPE implementation." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Different code paths: AutoProcessor kwarg forwarding vs auto_docstring crashing on future annotations." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Different failures: video-model loading without torchvision vs tokenizer mapping assumptions." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: 3d_parallel.py runtime failure vs a testing helper bug." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Different missing-dependency/import problems affecting different processor/model-loading paths." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Too little evidence that these are the same bug; one is a tokenizer decoder type regression, the other is only a reproduction of an older issue." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Different crash locations: AutoProcessor video-model import path vs chat template handling of tool-call assistant messages." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Unrelated: testing utility bug vs flash_attention crash on sink-less models." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Unrelated: testing utility bug vs xdist race on captured_info.txt." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "Different issues: xLSTM training bugs vs Bamba torch.compile SDPA failure." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Unrelated: video-model loading crash vs testing utility bug." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Different behaviors: missing checkpoint weight vs question about the default shard size." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "Not the same bug: a warning during bfloat16 compilation vs an actual model failure with SDPA." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Different pipeline issues: misleading translation support message vs inability to save Pipeline objects." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Different surface areas: compile-time precision warning vs tie_word_embeddings warning in fine-tuning." + }, + { + "left": "issue:45712", + "right": "issue:46298", + "accept": false, + "reason": "Different problems: leftover dummy classes vs noisy logging." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Different bugs: failure saving dequantized models vs failure saving Pipeline objects." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Different symptoms and code paths: save/dequantization bug vs infinite loop on a specific image." + }, + { + "left": "issue:43097", + "right": "issue:46298", + "accept": false, + "reason": "Different issues: config removal/documentation concern vs noisy logging." + }, + { + "left": "issue:44162", + "right": "issue:46172", + "accept": false, + "reason": "Different model-specific failures: ESM2 breakage vs deepseek-v4 dtype/transpose bug." + }, + { + "left": "issue:43792", + "right": "issue:46123", + "accept": false, + "reason": "Different pipelines entirely: Whisper model run failure vs mask generation batch-finalization bug." + }, + { + "left": "issue:44938", + "right": "issue:46178", + "accept": false, + "reason": "Different environments and failures: Python 3.14 import/load issue vs an invalid backend mapping entry." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 47, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43611", + "issue:43618", + "issue:43673", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43881", + "issue:43901", + "issue:43937", + "issue:44038", + "issue:44222", + "issue:44230", + "issue:44242", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44625", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45276", + "issue:45290", + "issue:45478", + "issue:45600", + "issue:45698", + "issue:46077", + "issue:46082", + "issue:46123", + "issue:46172", + "issue:46209", + "issue:46298" + ], + "soft_pairs": [ + "issue:44483|issue:44514", + "issue:44222|issue:45478", + "issue:43208|issue:43526", + "issue:43012|issue:44683", + "issue:42490|issue:43012", + "issue:42757|issue:43824", + "issue:45600|issue:46298", + "issue:38617|issue:43502", + "issue:45698|issue:46172", + "issue:44038|issue:44230", + "issue:43673|issue:46123", + "issue:44483|issue:45290", + "issue:43064|issue:44380", + "issue:43618|issue:43761", + "issue:43299|issue:43867", + "issue:36683|issue:43475", + "issue:43066|issue:46209", + "issue:45276|issue:46077", + "issue:42994|issue:44655", + "issue:43901|issue:44655", + "issue:44625|issue:46077", + "issue:36010|issue:42757", + "issue:43611|issue:44655", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:46077|issue:46082", + "issue:43502|issue:44485", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:36683|issue:44242", + "issue:36683|issue:43881" + ], + "prepared_review_unit_hash": "eb4d45b58e6ea2c66027ace20af009cd0e22d6dedb7b85e5bb6d9da1ecc28519", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36510, + "estimated_input_tokens": 9128, + "estimated_eval_tokens": 18512 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a bundle of related-but-distinct Transformers regressions and API breakages, not a duplicate set. I rejected every soft edge because the paired issues target different code paths, models, or behaviors.", + "confidence": 0.97, + "canonical_issue_reason": "No clear canonical issue: the items span unrelated bugs (imports, loading/saving, generation, pipeline behavior, quantization, and model-specific regressions), so there is no single duplicate to represent the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative; the nearest matches still describe different concrete failures and should not be merged as one bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Different surfaces: `/v1/chat/completions` request handling vs batched `apply_chat_template` crash with `padding=False`." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Different directions and failures: FP8 `save_pretrained` bug vs Qwen3.5 MoE `from_pretrained` load error." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "Unrelated models/features: xLSTM training bugs vs BeitImageProcessorFast `reduce_labels` returning one label." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Both are compile-related, but one is a bfloat16 warning and the other is a torch>=2.9 flex_attention failure." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Local-path trailing-slash import warning is unrelated to bfloat16 compile warning behavior." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols from different modules (`is_offline_mode` vs `Qwen2_5_VLForConditionalGeneration`)." + }, + { + "left": "issue:45600", + "right": "issue:46298", + "accept": false, + "reason": "CI break from removed Sam3LiteText refs is unrelated to a noisy logging message." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Different offline/import problems: missing `layer_type_validation` import vs unwanted network requests with `local_files_only=True`." + }, + { + "left": "issue:45698", + "right": "issue:46172", + "accept": false, + "reason": "Custom-module reload after save is unrelated to a DeepSeek dtype/transpose bug." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Different Qwen/MoE FP8 issues: one is a v5 regression, the other is FP8 inference support." + }, + { + "left": "issue:43673", + "right": "issue:46123", + "accept": false, + "reason": "Generation cache regression is unrelated to MaskGenerationPipeline dropping final partial-batch results." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "API request acceptance problem is unrelated to chat-template tokenization crashing on tool-call assistant messages." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state bug is unrelated to GPT2 attention scaling being ignored under SDPA/FlashAttention." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both touch CLIP outputs, but one is missing attentions and the other is missing hidden states; not the same concrete bug." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL MoE loading breakage is unrelated to a state_dict-sorting load error." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config missing `vocab_size` is unrelated to SAM 3 Video missing `fpn_position_embeddings`." + }, + { + "left": "issue:43066", + "right": "issue:46209", + "accept": false, + "reason": "Wrong tokenizer decoder type and FP8 inference on B200 are different regressions." + }, + { + "left": "issue:45276", + "right": "issue:46077", + "accept": false, + "reason": "Gemma4 token embedding resize bug is unrelated to bidirectional attention still building causal masks." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model save failure and pipeline `save_pretrained` failure affect different objects and paths." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch for `return_all_scores` is unrelated to pipeline serialization failure." + }, + { + "left": "issue:44625", + "right": "issue:46077", + "accept": false, + "reason": "Qwen3.5 `num_labels` propagation bug is unrelated to Gemma4 attention-mask behavior." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Different missing imports from different modules; same broad symptom, different bug." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "Base-model-prefix loading regression is unrelated to pipeline save_pretrained failure." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "FlashAttention2 support error for Nemotron is unrelated to GLM-5 GenerationConfig validation." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Load failure with sorted state_dict and incorrect Qwen3.5 checkpoint saving are related only broadly to model I/O, not the same bug." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Gemma4 attention-mask regression is unrelated to LlamaConfig rejecting explicit `head_dim`." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "`local_files_only=True` still making requests is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Missing `vocab_size` in Gemma3Config is unrelated to Llama4Config missing `pad_token_id`." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP attentions regression is unrelated to Qwen3.5 checkpoint corruption on save_pretrained." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Gemma3Config attribute bug is unrelated to MoE load-balancing loss handling." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Gemma3Config missing attribute is unrelated to glm-4v-9b loading failure." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 48, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42890", + "issue:43064", + "issue:43097", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43502", + "issue:43575", + "issue:43576", + "issue:43618", + "issue:43867", + "issue:43906", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44112", + "issue:44117", + "issue:44222", + "issue:44246", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45125", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45600", + "issue:45753", + "issue:46132", + "issue:46202", + "issue:46285" + ], + "soft_pairs": [ + "issue:44380|issue:46132", + "issue:43906|issue:45753", + "issue:43299|issue:45753", + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:43441|issue:44380", + "issue:43352|issue:45478", + "issue:44355|issue:44855", + "issue:43867|issue:46202", + "issue:44380|issue:45479", + "issue:43352|issue:44380", + "issue:43867|issue:45375", + "issue:36683|issue:44117", + "issue:43618|issue:44380", + "issue:41669|issue:44246", + "issue:43097|issue:43352", + "issue:42890|issue:45561", + "issue:43064|issue:44492", + "issue:43976|issue:44938", + "issue:43867|issue:45357", + "issue:43992|issue:45478", + "issue:36296|issue:43575", + "issue:43064|issue:44655", + "issue:28282|issue:33453", + "issue:43618|issue:46285", + "issue:43618|issue:44857", + "issue:44655|issue:44938", + "issue:43618|issue:44977", + "issue:44360|issue:45440", + "issue:43502|issue:44062", + "issue:42890|issue:44964", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:44222|issue:45125", + "issue:43576|issue:46132" + ], + "prepared_review_unit_hash": "aaa841390cb083a09e808529813330706a5b779759182bfe7a0fcdc7febec37b", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37255, + "estimated_input_tokens": 9314, + "estimated_eval_tokens": 18884 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a grab bag of unrelated Transformers regression reports across different models, versions, and failure modes. The only plausible duplicate edge is the import-time slowdown pair (41669/44246); the rest should stay separate.", + "confidence": 0.87, + "canonical_issue_reason": "issue:41669 is the clearest root-cause report for the import-time slowdown and best matches the only likely duplicate subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best representative issue here because it describes the underlying import-performance problem rather than just the symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44380", + "right": "issue:46132", + "accept": false, + "reason": "Different bugs: GPT2 attention scaling under SDPA/FlashAttention vs AttentionInterface.register changing registered-function behavior." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "Unrelated regressions: an isolated reproduction of one issue versus a Qwen3.5 image-specific infinite loop." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Different model-loading failures on different Qwen variants; no shared concrete code-path." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Flash-Attention support/reporting issue vs Python version compatibility issue; not the same bug." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different Qwen/UMT5 loading problems with different missing fields and failure modes." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both involve attention backends, but they target different models and different broken behaviors." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Different model-specific failures: FlashAttention support for Nemotron vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both are import/load errors, but one is compiled-Python handling and the other is a torch.jit/script parsing issue in a specific model." + }, + { + "left": "issue:43867", + "right": "issue:46202", + "accept": false, + "reason": "Different problems: state_dict ordering sensitivity vs Gemma pipeline roundtrip on the \u2581 token." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention backend config regression vs classification-loss degeneracy; unrelated code paths." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Different attention-related issues with different models and failure symptoms." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Model-loading order issue vs missing vision-config field; not the same root cause." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Gemma config missing vocab_size vs tokenizer-mapping None handling; different assumptions and code paths." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIP attentions assignment regression vs GPT2 attention scaling under backends." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both describe the same import-time slowdown for `transformers`; 41669 gives the underlying cause, while 44246 reports the symptom." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "Embeddings/tie-weights API removal vs FlashAttention support; unrelated regressions." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "A SamHQ seeding problem in integration tests vs an xdist race on captured_info.txt." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "Distributed training optimizer-state corruption vs a cache-strategy typo." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Different Python-version compatibility reports with different symptoms and likely causes." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "State-dict ordering load failure vs Qwen3.5 visual-key save regression; different model paths." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "UMT5 missing embed_tokens weight vs Qwen3.5 MoE from_pretrained regression." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both mention tensor parallelism/OOM, but the model, failure mode, and root cause are different." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Wrong optimizer states under FSDP2/PEFT vs inability to save Pipeline objects." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "PyTorch-missing ImportError for AutoModel vs tokenizer-loading regression; unrelated." + }, + { + "left": "issue:43618", + "right": "issue:46285", + "accept": false, + "reason": "Different CLIP regressions affecting different classes and structures." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "CLIP attentions regression vs LwDetrImageLoss AMP crash; unrelated." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Pipeline save_pretrained issue vs Python 3.14 load failure; different code paths." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "CLIP output field regression vs Qwen3.5 flash-attention generation bug." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer ReLU omission vs DeepseekV3MoE divergence from remote implementation." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leak vs AddedToken keyword-argument error; not the same issue." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Test seeding flake vs multimodal model load failure." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Different test failures: missing set_seed coverage vs stale device override behavior on CI." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test flakiness vs auto_mappings referencing removed configs." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "Different MoE/tensor-parallel problems: FP8 save_pretrained vs missing _tp_plan." + }, + { + "left": "issue:43576", + "right": "issue:46132", + "accept": false, + "reason": "Broken `transformers env` CLI vs AttentionInterface.register behavior change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded in the packet and appropriately conservative. The summary fits the issue titles and the only accepted duplicate edge, 41669/44246, is well supported by the import-time slowdown theme. The remaining 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": 1, + "component_count": 18, + "review_unit_index": 49, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41628", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:43010", + "issue:43299", + "issue:43502", + "issue:43526", + "issue:43576", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:43901", + "issue:43976", + "issue:44222", + "issue:44230", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44556", + "issue:44623", + "issue:44655", + "issue:44749", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:45071", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45375", + "issue:45468", + "issue:45478", + "issue:45656", + "issue:45850", + "issue:46209" + ], + "soft_pairs": [ + "issue:42548|issue:44351", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:44387|issue:44556", + "issue:30333|issue:33453", + "issue:45125|issue:45375", + "issue:43010|issue:45278", + "issue:30990|issue:31795", + "issue:43723|issue:44556", + "issue:43502|issue:44222", + "issue:43010|issue:45850", + "issue:43010|issue:44368", + "issue:42831|issue:43874", + "issue:43502|issue:44961", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:43827|issue:44961", + "issue:44355|issue:44655", + "issue:44315|issue:44360", + "issue:33453|issue:34689", + "issue:43299|issue:44556", + "issue:33453|issue:36296", + "issue:42757|issue:43576", + "issue:43576|issue:45071", + "issue:43010|issue:45656", + "issue:43576|issue:43824", + "issue:31795|issue:38617", + "issue:44961|issue:45468", + "issue:44222|issue:44230", + "issue:43010|issue:43976", + "issue:43576|issue:44938", + "issue:44908|issue:44961", + "issue:44315|issue:46209", + "issue:41628|issue:42548", + "issue:36296|issue:43901", + "issue:36296|issue:43526", + "issue:44623|issue:45230" + ], + "prepared_review_unit_hash": "f57689b9ce12bd3b3205c1199d3c3a93edc29bc7987aaeaa41a46b9f2320641d", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 37, + "serialized_chars": 37616, + "estimated_input_tokens": 9404, + "estimated_eval_tokens": 19064 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are not a true duplicate cluster; they span many distinct Transformers v5 regressions, import errors, loading failures, docs issues, FP8 problems, and tensor-parallel bugs that only share a broad theme.", + "confidence": 0.92, + "canonical_issue_reason": "No single issue is a clear canonical duplicate target here; the set is too heterogeneous, with only a broad \u201cv5 broke many things\u201d theme in common.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the broadest umbrella title for the cluster, but it is too vague to serve as a precise canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols (PreTrainedModel vs HybridCache), so they are not the same bug." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "One reports errors with compiled Python files; the other reports a large slowdown after upgrade. Different failures." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Tensor-parallel `_tp_plan` support and a Qwen3.5 MoE `from_pretrained` load error are related in model family, but not the same concrete code-path bug." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 quantization memory/OOM regression is distinct from failure to reload a v4.57 checkpoint after upgrading to v5.2/v5.3." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow reporting on failed training jobs and tokenizer-loading regressions are unrelated." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "One is about missing tensor-parallel plan metadata; the other is about a missing config field silently dropped by strict serialization." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "A `no_grad` decoration bug on cache/layer updates is not the same as a broad set of import errors after version upgrade." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "A loading hang in Sentence Transformers is unrelated to documentation confusion about `input_ids` and `past_key_values`." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading in v5 and checkpoint reloading after upgrade are both load failures, but not the same specific defect." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "`local_files_only=True` still making API calls is a networking bug, not an FP8 `save_pretrained` bug." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "The cache/layer update bug is a concrete fixable path; the other is only a vague umbrella complaint about many models breaking." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "`@torch.no_grad` on update methods and a warning about `tie_word_embeddings` are different issues." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "An FP8 accuracy regression and a missing image-patch helper causing an AttributeError are unrelated." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "`local_files_only` network leakage is unrelated to the placeholder/garbled issue title." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLflow reporting on failure and tensor-parallel training behavior are different subsystems and failures." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file runtime errors are not the same as `PretrainedConfig` type-checking breakage." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still mentioning `pipeline()` is unrelated to the unrelated placeholder issue." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Running compiled Python files and saving pipeline objects are different code paths and problems." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application under `model_init` and a DSA indexer ReLU discussion are unrelated." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer-loading regression and Llama 3.2 Vision model-loading failure are different concrete bugs." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are loading regressions, but for different model families and different failure modes." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "A missing `huggingface_hub` symbol import is unrelated to the broken `transformers env` command." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "CLI/env command breakage and config type-checking are separate issues." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "The `env` command issue is not the same as an import error for `Qwen2_5_VLForConditionalGeneration`." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion and an import error from `configuration_utils` are not the same bug." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The placeholder issue title is unrelated to the Gemma-4 audio positional encoding bug." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "FP8 model save/load corruption and FP8 inference support for Qwen3-VL/Qwen3.5 MoE are different requests." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling is unrelated to the placeholder issue." + }, + { + "left": "issue:44315", + "right": "issue:46209", + "accept": false, + "reason": "Liger Kernel application under `model_init` is unrelated to FP8 inference failures on B200." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Different missing imports (`AutoImageProcessor` vs `PreTrainedModel`) indicate separate export regressions." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and pipeline docs mentioning `return_all_scores` are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training bug and BeitImageProcessorFast `reduce_labels` behavior are different problems." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files from `processor.save_pretrained(...)` is concrete; the other item is too vague to match any specific bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 50, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:31795", + "issue:33453", + "issue:41669", + "issue:42371", + "issue:42890", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43827", + "issue:43874", + "issue:43976", + "issue:44038", + "issue:44077", + "issue:44230", + "issue:44246", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44373", + "issue:44393", + "issue:44492", + "issue:44556", + "issue:44704", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45341", + "issue:45362", + "issue:45478", + "issue:45542", + "issue:45753", + "issue:45850", + "issue:46095", + "issue:46143", + "issue:46144", + "issue:46218" + ], + "soft_pairs": [ + "issue:44273|issue:45542", + "issue:44038|issue:45125", + "issue:44273|issue:45003", + "issue:44393|issue:45071", + "issue:44230|issue:46095", + "issue:44373|issue:44961", + "issue:44393|issue:45753", + "issue:43576|issue:44556", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:43572|issue:45850", + "issue:45362|issue:45850", + "issue:41669|issue:46218", + "issue:42890|issue:44908", + "issue:44246|issue:44273", + "issue:43408|issue:44315", + "issue:44704|issue:44908", + "issue:43352|issue:44393", + "issue:44297|issue:45230", + "issue:43976|issue:44393", + "issue:44295|issue:45230", + "issue:43576|issue:44908", + "issue:44908|issue:45071", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:45278|issue:45850", + "issue:43673|issue:44492", + "issue:46143|issue:46144", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43976|issue:46218", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:43576|issue:44273", + "issue:42371|issue:44492" + ], + "prepared_review_unit_hash": "b5d2487ef8d3ef667e3d173615602281197d5a0c6cc15d6e39b0b70e39895c6f", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 39, + "serialized_chars": 38789, + "estimated_input_tokens": 9698, + "estimated_eval_tokens": 19652 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of Transformers v5 regressions, model-specific failures, and a few docs/config issues. The strongest representative issue is the broad v5 breakage report, but the soft pairs mostly describe different concrete bugs and should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "issue:45850 is the broadest umbrella for the shared theme of v5 regressions breaking many models, so it best represents the cluster at a high level.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most actionable representative because it describes a concrete upgrade symptom (many import errors after moving to v5.5.0) while still matching the cluster\u2019s overall regression theme.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Both are import/runtime problems, but one is lazy-loading behavior and the other is a TensorBoard/TensorFlow backend error; different code paths." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Same broad Qwen3/MoE area, but one is a Qwen3-VL bug and the other is missing tensor-parallel metadata; not the same fix." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Import-related, but one is lazy loading and the other is unsafe sys.modules access; distinct underlying issues." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Different symptoms and subsystems: Qwen3-VL multimodal output issue vs a PretrainedConfig type-checking regression." + }, + { + "left": "issue:44230", + "right": "issue:46095", + "accept": false, + "reason": "A feature/support request for fp8 inference is not the same as asking for a weight conversion script." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "Unrelated: docstring typo for position_ids versus an unrelated placeholder issue." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Same model family, but one is bounding-box hallucination/error and the other is an infinite loop on a specific image; not the same bug." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Both are v5 regressions, but one breaks the transformers env command and the other breaks checkpoint reload after upgrade." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "A specific Llama4Config attribute bug is too different from the broad 'many models break' complaint." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-performance regression from import * usage is not the same as a missing GenerationMixin cache during chunked prefill." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both concern v5 upgrade incompatibilities, but they affect different model/loading paths and are not one concrete bug." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "Specific StableLmConfig attribute regression versus a broad v5 breakage report; too different to merge." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Qwen3.5 chat crash is a model-specific failure, not the same underlying issue as the generic v5 complaint." + }, + { + "left": "issue:41669", + "right": "issue:46218", + "accept": false, + "reason": "Both touch imports, but one is import-star performance and the other is a missing exported model symbol; different fixes." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing set_seed is unrelated to scheduler kwargs handling." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Importing transformers slowly and lazy loading not working properly are related at a high level but not the same concrete bug." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Different areas: model-type mismatch warning versus Liger Kernel not being applied with model_init." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "Both mention kwargs passing, but they are different APIs and code paths." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support error for Nemotron is unrelated to Qwen3-VL bounding-box behavior." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch is a specific serialization bug; the other issue is too vague to match it." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version compatibility regression is unrelated to the Qwen3-VL multimodal bug." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "position_ids buffer access error is a distinct model state/buffer bug, not the generic placeholder issue." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Broken env command and inverse_sqrt scheduler kwargs are unrelated subsystems." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs propagation and PretrainedConfig type checking are unrelated bugs." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star slowdown and missing HybridCache export are both import-related but not the same underlying problem." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Performance-heavy import behavior is unrelated to a small testing_utils bug." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Both are broad v5 complaints, but one is about import errors after upgrade and the other is a generic 'many models break' report; not one concrete bug." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Generation cache missing during chunked prefill is unrelated to a typo in cache strategy docs or code." + }, + { + "left": "issue:46143", + "right": "issue:46144", + "accept": false, + "reason": "Both involve RoFormer, but one is kwargs passthrough and the other is attention-interface usage; different fixes." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "A specific multimodal token-counting AttributeError is not the same as a broad v5 breakage report." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different models and symptoms: Qwen3-VL output bug versus Qwen3.5-Moe from_pretrained failure." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "PatchTSMixer post_init policy and tied-weight key AttributeError are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:46218", + "accept": false, + "reason": "Python 3.9 compatibility and a missing Qwen3_5ForCausalLM import are unrelated failures." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Documentation still referencing pipeline() is unrelated to scheduler kwargs behavior." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Doc confusion around input_ids/past_key_values does not match a tokenizer-loading regression." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star slowdown and a cache-strategy typo are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel not applied with model_init and degenerate training with flash_attention_3 are different training-path issues." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API guidance and a cache-strategy typo have no meaningful overlap." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 51, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:42936", + "issue:43066", + "issue:43298", + "issue:43352", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43606", + "issue:43668", + "issue:43704", + "issue:43717", + "issue:43827", + "issue:44031", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44351", + "issue:44360", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45468", + "issue:45850", + "issue:46018", + "issue:46095", + "issue:46144", + "issue:46172", + "issue:46218" + ], + "soft_pairs": [ + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43576|issue:46218", + "issue:43827|issue:44492", + "issue:46018|issue:46172", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31515|issue:31795", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:43298|issue:46095", + "issue:45850|issue:46218", + "issue:43502|issue:43519", + "issue:42371|issue:43704", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:43606|issue:45468", + "issue:44263|issue:45468", + "issue:44261|issue:45468", + "issue:44351|issue:46218", + "issue:43352|issue:46218", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43525|issue:44861", + "issue:43704|issue:44998", + "issue:43572|issue:44861", + "issue:41669|issue:44998", + "issue:43066|issue:44998", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:44998|issue:46218", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230", + "issue:43717|issue:46144", + "issue:42936|issue:46018", + "issue:43668|issue:44031" + ], + "prepared_review_unit_hash": "b9618afd4e36275691461d9b89f35ac4e9cd9c223ae110fac97b77c5a37af8f6", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 44, + "serialized_chars": 39952, + "estimated_input_tokens": 9988, + "estimated_eval_tokens": 20232 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly loose semantic similarity around Transformers v5, model-loading, and tokenizer/config regressions rather than true duplicates. I would not merge any soft pair; the safest representative issue is the broad v5-breakage umbrella report.", + "confidence": 0.31, + "canonical_issue_reason": "issue:45850 is the broadest umbrella in the set; it captures the general v5 regression theme that many of the other reports orbit, even though it is still too vague to be a perfect duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the best cluster representative because it is the most general user-facing report of widespread v5 breakage, which is the closest common thread across the candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Save-pretrained pipeline serialization and tied-weight-key attribute handling are different code paths and failures." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "A DSA indexer missing ReLU is unrelated to Gemma-4 audio positional encoding." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs a specific Qwen3.5 MoE from_pretrained regression; not the same issue." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading behavior and inverse_sqrt scheduler kwargs are unrelated subsystems." + }, + { + "left": "issue:43576", + "right": "issue:46218", + "accept": false, + "reason": "Broken env command and Qwen3_5 import failure are different failures with no shared code path." + }, + { + "left": "issue:43827", + "right": "issue:44492", + "accept": false, + "reason": "Pipeline-docs-after-v5-removals and a cache-strategy typo are not the same underlying bug." + }, + { + "left": "issue:46018", + "right": "issue:46172", + "accept": false, + "reason": "DeepSeek-V4 shared-expert gating and a tensor transpose issue are different model implementation problems." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are separate model-specific bugs." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp math and scheduler kwarg handling are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star cleanup/perf and a VRAM leak in multi-threaded loading are not the same bug." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion around forward args does not match a concrete model-loading regression." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Slow checkpoint loading and confusing forward documentation are different issues." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE and Gemma-4 audio positional encoding are unrelated model implementations." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leakage in dataloader threads is unrelated to a RoPE implementation bug." + }, + { + "left": "issue:43298", + "right": "issue:46095", + "accept": false, + "reason": "Audio model continuous batching support and DeepSeek-V4 weight conversion are different requests." + }, + { + "left": "issue:45850", + "right": "issue:46218", + "accept": false, + "reason": "Broad v5 breakage is too general to equate with a specific Qwen3_5 import error." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "Accidental network requests with local_files_only and Qwen3VL timestamp math are different failure modes." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API guidance and a VRAM leak are unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp calculation in a processor is not the same as missing files from processor.save_pretrained()." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Processor timestamp logic and dataloader-thread VRAM leak are distinct bugs." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch and Gemma-4 audio positional encoding are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return-value handling and audio positional encoding are different issues." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "Missing config.rms_norm_eps and Gemma-4 audio positional encoding are not the same code path." + }, + { + "left": "issue:44351", + "right": "issue:46218", + "accept": false, + "reason": "HybridCache import failure and Qwen3_5 import failure are both import-related but not the same symbol or fix." + }, + { + "left": "issue:43352", + "right": "issue:46218", + "accept": false, + "reason": "Flash Attention support gating and a module import error are different problems." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both mention tokenizer v5 changes, but one is broad behavior drift while the other is a specific decoder-type bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs being ignored is unrelated to the placeholder issue titled Unemployment." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weights helper crash and apply_chat_template tool-call crash are different code paths." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config does not match tied-weights-key list handling." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM and the unrelated placeholder issue are not duplicates." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Wrong tokenizer decoder type and the unrelated placeholder issue are not related." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading and a missing import symbol are different failures." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support for Qwen models and processor.save_pretrained missing files are unrelated." + }, + { + "left": "issue:44998", + "right": "issue:46218", + "accept": false, + "reason": "The placeholder issue has no meaningful relation to a Qwen3_5 import failure." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting on failed training jobs and slow from_pretrained checkpoint loading are unrelated." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint load slowness and tensor-parallel training bugs are different problems." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 support request and a Qwen3.5 MoE from_pretrained regression are not the same bug." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading and tokenizer-loading regression are only broadly similar, not the same issue." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching for audio models and FP8 inference support are separate feature requests." + }, + { + "left": "issue:43717", + "right": "issue:46144", + "accept": false, + "reason": "Mamba init_weights usage and RoFormer attention-interface usage are unrelated implementation concerns." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "Mask2Former ignore_value handling and DeepSeek-V4 shared-expert gating are different model bugs." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A type-hint mismatch in ModernBERTConfig is unrelated to tokenizer regex warnings." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 52, + "review_unit_count": 52, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-443", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031", + "issue:46144" + ], + "soft_pairs": [ + "issue:42936|issue:43240", + "issue:43240|issue:46144", + "issue:42936|issue:44031", + "issue:42936|issue:46144", + "issue:42936|issue:43813", + "issue:43240|issue:43668", + "issue:43668|issue:43813", + "issue:37934|issue:43668", + "issue:42936|issue:43668" + ], + "prepared_review_unit_hash": "dccbe49a0db64d8f40d9dda8ee189ba180a9d14519a66878d431e8821e532f2c", + "component_budget": { + "node_count": 443, + "item_count": 443, + "soft_pair_count": 1630, + "serialized_chars": 845090, + "estimated_input_tokens": 211273, + "estimated_eval_tokens": 422802 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 6639, + "estimated_input_tokens": 1660, + "estimated_eval_tokens": 3576 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are not duplicates; the cluster is heterogeneous across unrelated model bugs, config/type issues, a typo, and tokenizer warnings. No soft pair looks like the same underlying change or bug.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue cleanly represents this cluster because the topics are unrelated. If forced to pick the broadest functional bug, 43240 is the closest, but it is not a true canonical duplicate target.", + "canonical_pr_reason": null, + "best_issue_reason": "43240 is the strongest standalone issue for triage because it describes an actionable runtime bug in a core loss path, unlike the narrower config/typo/reporting items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Different bugs: Mask2Former ignore_value handling vs kwargs not forwarded to loss calculation. No shared codepath or concrete duplicate behavior." + }, + { + "left": "issue:43240", + "right": "issue:46144", + "accept": false, + "reason": "Loss-function kwargs forwarding is unrelated to RoFormer attention-interface usage." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "Mask2Former ignore_value handling and tokenizer regex warnings are unrelated subsystems with different failure modes." + }, + { + "left": "issue:42936", + "right": "issue:46144", + "accept": false, + "reason": "Different model components and symptoms; one is a loss/ignore_value bug, the other is an attention API integration issue." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Mask2Former loss handling and a typo in quantization_operation are unrelated." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "A kwargs-passing bug in loss calculation is not the same as an incorrect type hint in ModernBERTConfig." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "These are separate metadata/code-quality issues: type hint correctness vs a typo in a symbol name." + }, + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Llama4TextL2Norm/RMS norm behavior is a model-implementation question, not the ModernBERT norm_eps type hint issue." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Different concerns: a runtime ignore_value bug versus a type annotation mistake." + } + ] + }, + "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": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10519-3", + "nodes": [ + "issue:10519", + "issue:11005", + "issue:11307" + ], + "soft_pairs": [ + "issue:10519|issue:11307", + "issue:10519|issue:11005", + "issue:11005|issue:11307" + ], + "prepared_review_unit_hash": "11ba899bfd1988c607b44b0b9a82166bdc6163b147fea35b54917beccef74186", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2877, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2877, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster does not look like a duplicate set: the three issues cover unrelated topics (token truncation behavior, ReduceLROnPlateau-like scheduling, and Wav2Vec2 word time offsets). None of the soft pairs should be merged.", + "confidence": 0.96, + "canonical_issue_reason": "Issue #10519 is the clearest, most concrete feature request in the cluster and is the best anchor only in the sense of being the most well-scoped item; it is not actually a duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "#10519 is the strongest standalone issue: it has a specific, actionable request about truncation direction and clear parameter context. The other issues are unrelated and less suitable as a cluster representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:10519", + "right": "issue:11307", + "accept": false, + "reason": "Different problem domains: truncation strategy for token inputs versus extracting word time offsets from Wav2Vec2. No shared code-path or concrete bug overlap." + }, + { + "left": "issue:10519", + "right": "issue:11005", + "accept": false, + "reason": "Unrelated requests: text truncation direction versus ReduceLROnPlateau-like scheduler behavior. They do not describe the same underlying change." + }, + { + "left": "issue:11005", + "right": "issue:11307", + "accept": false, + "reason": "One is about learning-rate scheduling logic, the other about speech model alignment/time offsets. These are clearly distinct issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "034f022a674ebc0e0d160ef3eb5703ff90a6bfc2163dcbcafdadfaed3c4954e5", + "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 true duplicates. One is about Tapas tokenization behavior, one about the error message for private-model downloads without login, and one about failure to load bert-base-uncased. The latter is the broadest and most central, but the overlap is only superficial.", + "confidence": 0.72, + "canonical_issue_reason": "Issue #16618 is the broadest and most representative of the cluster because it describes a general model-loading failure, whereas the other two are about a specific tokenization mismatch and a specific auth/error-message case.", + "canonical_pr_reason": null, + "best_issue_reason": "#16618 is the best single issue to keep as the cluster anchor since it is the most general user-facing loading problem; the others are narrower and clearly refer to different failure modes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Tapas tokenization mismatch is a different bug from a model-loading failure; they do not appear to share the same underlying code path." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Private-model download auth/error-message behavior is a distinct scenario from failing to load bert-base-uncased, so these 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": 4, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "df54e4b1b59438a43e1aa75fea0e57ad0a4f77e70e4e54832bde72459e0a93dc", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate community contribution feature requests: one for Flash Attention 2 support across more architectures, and one for GGUF support across more architectures. They share only a broad theme and are not duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue #26350: Community contribution: Adding Flash Attention 2 support for more architectures", + "right": "issue #33260: Community contribution: Adding GGUF support for more architectures", + "accept": false, + "reason": "Different underlying feature requests targeting different code paths and integrations; the shared phrase 'more architectures' is too broad to treat as 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": 5, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-8", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:38435", + "issue:43834", + "issue:44365", + "issue:44370", + "issue:46222", + "issue:46226" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:38435", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:38435", + "issue:28936|issue:44370", + "issue:38435|issue:44370", + "issue:38435|issue:44365", + "issue:38435|issue:43834", + "issue:38435|issue:46222", + "issue:38435|issue:46226", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:43834|issue:46222", + "issue:43834|issue:46226", + "issue:44365|issue:44370", + "issue:44365|issue:46222", + "issue:44365|issue:46226", + "issue:44370|issue:46222", + "issue:44370|issue:46226", + "issue:46222|issue:46226" + ], + "prepared_review_unit_hash": "3e864c8cfdce97503f5162a1101a1ffdd593f94203bfe54d644813bcc595ab45", + "component_budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 24, + "serialized_chars": 13522, + "estimated_input_tokens": 3381, + "estimated_eval_tokens": 7018 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 24, + "serialized_chars": 13522, + "estimated_input_tokens": 3381, + "estimated_eval_tokens": 7018 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly separate i18n translation requests, but it contains two clear duplicate subgroups: three identical generic template issues and one exact Thai-title duplicate pair. I would not merge the language-specific issues with those subgroups.", + "confidence": 0.81, + "canonical_issue_reason": "issue:43834 is the earliest of the identical generic-template translation issues and is the cleanest representative of the only larger duplicate subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43834 is the strongest global issue representative because it is earliest, canonical-looking, and part of the most clearly duplicated set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different language-specific translation requests; only similar by template wording, not the same underlying issue." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Turkish vs. generic placeholder translation request; not the same concrete issue." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Turkish request and generic template issue are different translation tasks." + }, + { + "left": "issue:27088", + "right": "issue:38435", + "accept": false, + "reason": "Different target languages; these are separate translation requests, not duplicates." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Turkish and Spanish translation requests are distinct issues." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish request does not match the generic placeholder issue; different underlying task." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Different language-specific request vs. generic placeholder issue." + }, + { + "left": "issue:28936", + "right": "issue:38435", + "accept": false, + "reason": "Spanish and Romanian translation requests are separate issues." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Spanish request and generic placeholder request are not the same issue." + }, + { + "left": "issue:38435", + "right": "issue:44370", + "accept": false, + "reason": "Romanian translation request is distinct from the generic placeholder issues." + }, + { + "left": "issue:38435", + "right": "issue:44365", + "accept": false, + "reason": "Different translation request; similarity is only at the template level." + }, + { + "left": "issue:38435", + "right": "issue:43834", + "accept": false, + "reason": "Romanian request and generic placeholder issue are not the same underlying change." + }, + { + "left": "issue:38435", + "right": "issue:46222", + "accept": false, + "reason": "Different titles and different issue content; not enough to treat as the same request." + }, + { + "left": "issue:38435", + "right": "issue:46226", + "accept": false, + "reason": "Romanian docs translation and Thai-titled issue are unrelated." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": true, + "reason": "Same exact generic placeholder title and near-identical issue shape; looks like a duplicate submission of the same translation template." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": true, + "reason": "Identical title and highly similar body/template indicate the same underlying issue." + }, + { + "left": "issue:43834", + "right": "issue:46222", + "accept": false, + "reason": "Generic placeholder translation issue vs. Thai-titled issue; not clearly the same underlying request." + }, + { + "left": "issue:43834", + "right": "issue:46226", + "accept": false, + "reason": "Different titles and no concrete evidence they refer to the same issue." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": true, + "reason": "Exact same generic template title; these are duplicate issue submissions." + }, + { + "left": "issue:44365", + "right": "issue:46222", + "accept": false, + "reason": "No clear evidence the generic template issue and Thai-titled issue are the same." + }, + { + "left": "issue:44365", + "right": "issue:46226", + "accept": false, + "reason": "Different issue content; only superficial similarity." + }, + { + "left": "issue:44370", + "right": "issue:46222", + "accept": false, + "reason": "Generic placeholder translation issue and Thai-titled issue are not the same underlying bug/change." + }, + { + "left": "issue:44370", + "right": "issue:46226", + "accept": false, + "reason": "Different titles and no shared concrete target." + }, + { + "left": "issue:46222", + "right": "issue:46226", + "accept": true, + "reason": "Exact same Thai title and matching body size strongly indicate duplicate issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: the three generic placeholder issues share the exact same title, and the Thai-titled pair also has identical titles and body length. The non-duplicate verdicts between language-specific issues and these subgroups are conservative given the limited evidence. No obvious overstatement." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-16", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322", + "issue:46133" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177", + "issue:45322|issue:46133" + ], + "prepared_review_unit_hash": "678ebc2ecda6126d87bf4b4684ac63bfbffd6ad9b5546b154f656b90f5f9253e", + "component_budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21660, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a broad set of model-addition requests, not a duplicate set. The titles point to different concrete models or model families, so none of the soft edges look like the same underlying bug/change.", + "confidence": 0.11, + "canonical_issue_reason": "Issue 41115 is the broadest and most representative standalone request in the set, but there is no exact duplicate here.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 41115 is the best single representative because it is a clear, actionable model-architecture request with decent discussion activity; however, it should not be treated as a duplicate of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different requested models (EuroBert vs DEIMv2); same broad theme, but not the same change." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support and Qwen3-TTS support are unrelated model integrations." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert and RF-DETR are different model families and would require separate code paths." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are distinct models with separate implementation work." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "Object detection (RF-DETR) versus audio model support (LFM2.5 Audio) are not the same request." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR and OpenAI weight-sparse transformer support are different concrete architectures." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR and Qwen3-ASR are unrelated model additions." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR and Qwen3-TTS are different models and modalities." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR target different model families and implementation paths." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT and circuit-sparse transformer support are unrelated changes." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio are different model requests." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are separate model additions, not duplicates." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are distinct BERT-like families, but not the same model or bug." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are different model integrations." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 and the OpenAI weight-sparse transformer request are unrelated code changes." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are different model-specific requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral TTS support are separate model additions with different code paths." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are different model support requests." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are unrelated concrete model requests." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT and Qwen3-TTS are different model families." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT support and a generic RoPE-related BERT-like request are not the same underlying change." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "A generic BERT-like RoPE request and Voxtral TTS support are unrelated." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR share a prefix but are different modalities and separate implementations." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral-4B-TTS-2603 are different model-specific support requests." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated models." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support and a weight-sparse transformer request are different code-path problems." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are different audio model requests." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are unrelated model additions." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "Audio model support and SAM3-LiteText are different model families." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are separate audio-model requests." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Weight-sparse transformer support and EUPE are not the same implementation problem." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR support and the weight-sparse transformer request are unrelated." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral-4B-TTS-2603 are different model requests." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral TTS are unrelated model additions." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different models and code paths." + }, + { + "left": "issue:45322", + "right": "issue:46133", + "accept": false, + "reason": "EUPE and TIPSv2 are both vision-language related, but they are distinct model requests and not mergeable as one fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "9a4d98ec567b2bd946dc344a65723a5567aaf848c6fd3cc1b24db87f79179dce", + "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 is about enabling block decoding, while the other requests DeepSeek v3.2 support. They do not describe the same underlying bug or change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good canonical representative because they target different features/problems with no overlap in scope.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different requests: block decoding vs model support for DeepSeek v3.2. No shared code-path or concrete duplicate behavior is indicated." + } + ] + }, + "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": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "52e2e9669865109e3c88be0c3b2fe0ff9cef675dcc2ee70f71dbd5e5bd6c6308", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1583, + "estimated_input_tokens": 396, + "estimated_eval_tokens": 1048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are thematically related to Trainer customizability, but they describe different problems in different code paths: one about `remove_unused_column`, the other about FLOPS estimation for custom trainers. They should not be treated as duplicates.", + "confidence": 0.88, + "canonical_issue_reason": "If one must be chosen as the representative issue, #43598 is the better fit because it directly concerns Trainer behavior/customizability; however, it does not cover the FLOPS-estimation problem in #43600.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the more central/general issue in this small cluster, but it is still not a true superset of #43600.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Related by theme, but not the same underlying bug: #43598 is about `remove_unused_column` customizability, while #43600 is about estimating FLOPS for custom trainers." + } + ] + }, + "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": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "ea27712a6b42066d5e5989d6e97c7a1bbe56c66eddf1c559275abf7a58c198b7", + "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": "Related but distinct enhancement requests: one adds Qwen3-Omni registration to AutoModel/AutoModelForConditionalGeneration, the other requests AutoModelForSequenceClassification support for Qwen3.5. They target different model families and different auto-model heads.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the broader, higher-level registration request, but it is not a duplicate of 44405 because the model family and target auto-classes differ.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different underlying change: Qwen3-Omni auto-registration vs Qwen3.5 sequence-classification support. They touch different model/task code paths and should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "fede1aece86d0ce1cfac34cfb33df7d7740af5f5a8902cacd0a9efae6ac26052", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster appears to be low-information / likely spammy duplicate issues with generic titles. There is not enough concrete bug detail to safely merge any pair as the same underlying issue.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 43859 is the slightly best representative only because it has the most activity, but none of these issues contains enough real problem description to be a strong canonical choice.", + "canonical_pr_reason": null, + "best_issue_reason": "43859 is the most suitable issue to keep if one must be chosen, since it has discussion activity and is at least marginally more substantive than the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no shared issue details beyond weak similarity; no concrete evidence they describe the same bug." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no concrete body information tying them to the same underlying problem." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Generic title overlap is not enough; the issues do not provide a shared bug description or target." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": false, + "reason": "Even though the titles match, the bodies provide no concrete evidence of the same underlying issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": false, + "reason": "Same broad keyword only; insufficient detail to conclude these are duplicates of the same bug." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": false, + "reason": "Matching generic titles are not enough without a shared technical description or explicit target." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "626018c5d05aa92824ce938d7a51637ad3601d8e836cc93b173cc0eccf7fbf90", + "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": "These issues do not look like duplicates of one concrete bug or change; they are mostly spammy or generic placeholders with no body/detail evidence tying them together.", + "confidence": 0.95, + "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 only spam placeholders with no description or target; superficial title similarity is not enough to imply the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Same as above: generic spam titles with no concrete shared bug or change." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam-like and the other is a vague documentation suggestion; no evidence they refer to the same problem." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Completely different titles and no body detail; not enough to indicate a shared issue." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A documentation enhancement request is not the same underlying item as a spam placeholder." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation request vs. spam placeholder; no concrete overlap." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam placeholders, but there is no evidence they describe the same underlying bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "No shared concrete topic: spam placeholder versus a specific quoted-name title." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No meaningful evidence of the same underlying issue; titles 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": 12, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "d7f98b4ad2677b10270ff684761c8628b381de868a8ae32a3c11384e39079146", + "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 issues are highly similar and likely related, but the evidence is not strong enough to call them confirmed duplicates. #45145 is the better canonical issue because it was opened first and already has an inbound reference.", + "confidence": 0.84, + "canonical_issue_reason": "#45145 is the earlier issue and already has an inbound reference, so it is the best anchor for deduplication discussion.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the strongest issue representative for the cluster because it predates #45151 and has the existing linkage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The titles are identical and the bodies are moderately similar, but there are no explicit links, shared targets, or filenames; this supports a likely related/possible-duplicate relation rather than a confirmed same-underlying-issue duplicate." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The canonical-choice reasoning is grounded, but the cluster/soft-edge language is a bit too strong for the packet. The pair only has soft-similarity evidence with a moderate Jaccard score, so calling them \"near-certain duplicates\" and accepting the edge as same underlying issue overstates the evidence. A more conservative verdict would be that they are likely related or possible duplicates, not confirmed duplicates." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45672-2", + "nodes": [ + "issue:45672", + "issue:45674" + ], + "soft_pairs": [ + "issue:45672|issue:45674" + ], + "prepared_review_unit_hash": "33c9923270017b6566109b48727de562ca0ac1b30bbeaa25fc01ea45236b3f49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1671, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1671, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate 4-bit inference bugs, not duplicates: one is Gemma4/audio-module uint8 weight handling leading to a `torch.finfo()` TypeError, the other is a `BitsAndBytesConfig.llm_int8_skip_modules` regression that drops the default `lm_head` exclusion and triggers an AssertionError. They overlap only at a broad \u201c4-bit inference\u201d level.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "If a single issue had to represent the cluster, 45674 is the more general/config-level regression and is phrased more directly around the failing behavior; 45672 is model-specific and narrower.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Different failure modes and code paths: Gemma4 audio-module `torch.finfo()` on uint8 weights vs `BitsAndBytesConfig` skip-module handling removing the default `lm_head` exclusion. Same broad 4-bit context, but not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "6f195e32dfb7fd2498d40ebbc254b311ea9d89546bc1c548b623a2e8bee2bace", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two closed issues with superficially similar personal-name/date titles, but they refer to different individuals and do not describe the same bug or request. No PRs are present.", + "confidence": 0.95, + "canonical_issue_reason": "Neither issue is a meaningful canonical duplicate target; they are separate, non-technical, name-only reports with no shared underlying problem description.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to pick one, issue #45762 is marginally clearer only because it has a fuller name string, but it is not a good canonical issue overall.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Both are just different person-name/date titles and lack evidence of the same underlying bug or change; they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "2f37ca9f2afbbd031564320b9823ff02a9bca77a9e757a911f37122a5d294866", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1481, + "estimated_input_tokens": 371, + "estimated_eval_tokens": 998 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated standalone entries with different names/dates and no shared context, so this is not a duplicate cluster.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good canonical choice because there is no evidence they describe the same bug or request; both look like separate, unrelated tickets.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "Different subjects entirely; no shared description, targets, or repository context indicating the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 17, + "component_count": 18, + "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-45810-2", + "nodes": [ + "issue:45810", + "issue:46295" + ], + "soft_pairs": [ + "issue:45810|issue:46295" + ], + "prepared_review_unit_hash": "9b2e3a0937f7b1d00356dfccefe1cf8973ed98d9119e714ede3097ea61ed96a9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1542, + "estimated_input_tokens": 386, + "estimated_eval_tokens": 1028 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1542, + "estimated_input_tokens": 386, + "estimated_eval_tokens": 1028 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are unrelated: one requests a new Qwen3_5 token-classification/value-model feature, while the other asks for FP8 training support. They should not be clustered as duplicates or merged into a single canonical item.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45810", + "right": "issue:46295", + "accept": false, + "reason": "Different feature requests in different areas (model head support vs FP8 training); no shared code-path or concrete underlying bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 18, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45869-5", + "nodes": [ + "issue:45869", + "issue:45870", + "issue:45871", + "issue:45872", + "issue:45873" + ], + "soft_pairs": [ + "issue:45869|issue:45870", + "issue:45869|issue:45871", + "issue:45870|issue:45871", + "issue:45870|issue:45872", + "issue:45870|issue:45873", + "issue:45871|issue:45872", + "issue:45871|issue:45873", + "issue:45872|issue:45873" + ], + "prepared_review_unit_hash": "b3ea6e2aa179a13fa4c4365f7ee825ab3cca3e79291795d529fd4364f17c62e8", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5727, + "estimated_input_tokens": 1432, + "estimated_eval_tokens": 3120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster appears to split into one unrelated dataset item (45869), plus two likely duplicate pairs: 45870/45871 and 45872/45873. The duplicate evidence is fairly strong from identical titles and matching body sizes, but it is still only soft-similarity evidence, so the conclusion should remain tentative rather than exact.", + "confidence": 0.86, + "canonical_issue_reason": "45870 is a reasonable canonical issue for the DataForge example pair because it has the same title as 45871 and slightly more discussion activity, making it a better representative for that likely duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "45870 is the best issue to anchor deduping in this cluster: it sits in a likely duplicate pair with 45871, has slightly more activity than its twin, and 45869 is clearly separate while 45872/45873 form a second likely duplicate pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Both mention financial/DataForge topics, but 45869 is a dataset bundle/free sample while 45870 is an example about time series prediction; different underlying request." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Same as 45869 vs 45870: shared theme, but the artifacts describe different content and purpose." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Identical titles and matching body length make these look like the same issue submitted twice, even though the evidence is only soft-similarity based." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "45870 is an example post about prediction, while 45872 is a request about a time-series + scraping service; related domain, but not the same concrete issue." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Same as 45870 vs 45872: similar theme, but different request scope and title." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "The example-prediction issue and the service request are different underlying items despite both being DataForge-related." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Same reasoning as 45871 vs 45872: related theme, but not the same issue." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Identical titles and matching body length strongly suggest these are duplicate submissions of the same service-related request." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The summary is a bit too strong for the evidence in the packet. The identical titles for 45870/45871 and 45872/45873 do support likely duplication, but the packet only marks these as soft_similarity and every pair has deterministic_accept=false, so calling them \"clear duplicate pairs\"/\"exact duplicate\" overstates certainty. The 45869 split is grounded, but the duplicate-pair conclusions should be phrased more conservatively." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-15", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:46048", + "pull_request:46267", + "pull_request:46268" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:46267", + "pull_request:44827|pull_request:46048", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:46048|pull_request:46268", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "8edeccc0b4a0a62222a11427b9e67968bac6c33191f1365bfce6afb92809563f", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 20, + "serialized_chars": 40309, + "estimated_input_tokens": 10078, + "estimated_eval_tokens": 20412 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 20, + "serialized_chars": 40309, + "estimated_input_tokens": 10078, + "estimated_eval_tokens": 20412 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous false-positive similarity. The only true duplicate pair is the two fixed_cross_entropy PRs; the rest are unrelated model additions, docs, kernel routing, or test-only changes.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43254 is the clearest canonical representative of the only real duplicate pair: it directly adds supported kwargs to fixed_cross_entropy and cleanly captures the shared cross-entropy fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 43254 is the best overall PR candidate because it most directly represents the cluster\u2019s only genuine overlap; the other PRs are not the same underlying change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Videoprism model integration vs ExecuTorch export tests; unrelated changes." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer helper methods vs export/dynamic-shape testing; different code paths." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Mistral tokenizer methods vs adding a new MobileLLM model; no shared bug/change." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs new MobileLLM model implementation; unrelated." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Cross-entropy kwargs fix vs MobileLLM model addition; different subsystem." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Cross-entropy loss helper change vs Mistral4 test fixes; not the same code-path." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "ExecuTorch export test vs Mistral4 model/test changes; unrelated work." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Export dynamic-shape test vs model addition; no common underlying fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New model implementation vs config-resolution ordering fix; unrelated." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "New model addition vs Falcon refactor for output collection; different changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon output-interface refactor vs model-creation skill docs; not the same artifact." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon refactor vs Mistral4 test fixes; different models and problems." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes vs CLIP-family layernorm rename; unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46267", + "accept": false, + "reason": "Mistral4 fixes vs chat parsing/serve overhaul; unrelated code paths." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46048", + "accept": false, + "reason": "Mistral4 tests vs TDT loss kernel integration; different areas." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 tests vs config-resolution fix; unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Model test fixes vs skill/documentation PR; not a duplicate change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "Model implementation vs skill/docs; no shared underlying bug." + }, + { + "left": "pull_request:46048", + "right": "pull_request:46268", + "accept": false, + "reason": "TDT loss kernel integration vs ROCm AITER kernel routing; both kernel-related but different functionality." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs fix the same fixed_cross_entropy API gap by forwarding supported nn.functional.cross_entropy kwargs; they are alternate implementations of the same change." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative: it identifies the only explicitly supported duplicate pair (43251/43254) and treats the remaining soft matches as unrelated. The accepted pair is plausibly the same fixed_cross_entropy bugfix, and the rejected pairs do not look mergeable into a single PR for the same change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 31, + "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-40546-4", + "nodes": [ + "pull_request:40546", + "pull_request:42781", + "pull_request:46331", + "pull_request:46332" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781", + "pull_request:42781|pull_request:46331", + "pull_request:42781|pull_request:46332", + "pull_request:46331|pull_request:46332" + ], + "prepared_review_unit_hash": "a663a0e9fe475d8bd8bc056fbdd85d306283901f57193af8dcb24239578d9582", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 14484, + "estimated_input_tokens": 3621, + "estimated_eval_tokens": 7498 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 4, + "serialized_chars": 14484, + "estimated_input_tokens": 3621, + "estimated_eval_tokens": 7498 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are all in the audio/ASR model-registration area, but they add different models or variants (VibeVoice core, VibeVoice Realtime, Parakeet-RNNT, Nemotron ASR). The shared docs/auto-mapping edits are superficial; none are the same underlying change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the cluster contains separate feature additions for different models/variants rather than duplicates of one change.", + "best_issue_reason": null, + "best_pr_reason": "40546 is the broadest standalone implementation, but it is not a duplicate of the others and only serves as a weak cluster representative.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Same model family, but different changes: core VibeVoice implementation vs VibeVoice Realtime with additional tokenizer/generation work. Not one mergeable duplicate fix." + }, + { + "left": "pull_request:42781", + "right": "pull_request:46331", + "accept": false, + "reason": "Different models and code paths: VibeVoice Realtime vs Parakeet-RNNT. Shared auto-registration files are not enough to make them duplicates." + }, + { + "left": "pull_request:42781", + "right": "pull_request:46332", + "accept": false, + "reason": "Different model additions: VibeVoice Realtime vs Nemotron ASR Streaming. Similar framework plumbing, but not the same underlying change." + }, + { + "left": "pull_request:46331", + "right": "pull_request:46332", + "accept": false, + "reason": "Both are ASR-related PRs, but they add different models (Parakeet-RNNT vs Nemotron ASR) and cannot plausibly be merged as one duplicate change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 31, + "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": "8f53d817d5f4dba7dcdaaa1914200136989df6f0298c3a0d291bb707e574ce20", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4675, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are unrelated feature PRs in different model families: TimesFM covariate forecasting vs DINOv3 image classification support. They should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #41224 is the cleaner representative of the set: it is a focused, concrete model-support addition with code, docs, and tests, whereas PR #40755 is a separate TimesFM feature for an unrelated forecasting capability.", + "best_issue_reason": null, + "best_pr_reason": "PR #41224 is the best standalone representative because it is a narrower, well-scoped feature PR with substantial review activity and explicit implementation changes; PR #40755 addresses a different problem domain.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and different underlying changes: TimesFM covariate forecasting versus DINOv3 image classification support. They do not fix the same bug or implement the same feature 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": 4, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "b0bdeafd91ba55db087cae6f713b71e63db99fa56b30bc8197152f3c956a03db", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10436, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10436, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three unrelated model-addition pull requests (DeepSeek OCR, Isaac, and Kimi2-6). They share the same project-area patterns, but they do not appear to fix or implement the same underlying code path or change set.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR #45630 is the strongest single representative of the cluster because it is the most extensively reviewed and has the broadest integration surface among the three, but it is still not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Both are new-model addition PRs, but they target different models and different implementation details; this is shared scaffold, not the same underlying change." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "These PRs add different model families with distinct files and code paths. Similar auto-mapping/docs updates are not enough to treat them as one fix or one feature." + } + ] + }, + "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": 31, + "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": "c9b1f650c64e608ea683a0379e05eacc5e8a57556451853fce505f3ab1fdd305", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5935, + "estimated_input_tokens": 1484, + "estimated_eval_tokens": 3224 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs both update GitHub Actions versions, but they target different action families and different workflow failure modes: one is a Node 24 compatibility sweep for checkout/cache/upload-artifact, the other upgrades docker/build-push-action in Docker image workflows. They are related maintenance work, not duplicates.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the better canonical representative because it is the broader GitHub Actions compatibility sweep and explicitly addresses the Node 24 compatibility theme across many workflows.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the strongest overall representative of the cluster since it covers the most central workflow-action compatibility update and has the clearest overarching purpose.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Both are GitHub Actions upgrades, but they change different actions in different workflows (checkout/cache/upload-artifact vs docker/build-push-action) and do not look like the same underlying fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 31, + "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-42978-4", + "nodes": [ + "pull_request:42978", + "pull_request:43448", + "pull_request:43451", + "pull_request:45490" + ], + "soft_pairs": [ + "pull_request:42978|pull_request:43448", + "pull_request:42978|pull_request:43451", + "pull_request:42978|pull_request:45490", + "pull_request:43448|pull_request:43451", + "pull_request:43448|pull_request:45490", + "pull_request:43451|pull_request:45490" + ], + "prepared_review_unit_hash": "7949d6f072fd82a689b0201d531615e0fbf4a3544b51d0ee4233f4029c2e8692", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14184, + "estimated_input_tokens": 3546, + "estimated_eval_tokens": 7348 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14184, + "estimated_input_tokens": 3546, + "estimated_eval_tokens": 7348 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are four separate model-addition pull requests, not duplicates. They overlap only on shared infrastructure and docs registry files, but each introduces a different model family and distinct code paths.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43451 is the broadest and most active representative of the cluster, but it is still a distinct Molmo2 model-addition PR rather than a duplicate of the others.", + "best_issue_reason": null, + "best_pr_reason": "PR 43451 is the strongest single representative if one must be chosen: it has the most discussion, the widest set of model/processor/video files, and the clearest end-to-end model integration among the set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "ViT NEPA vs Molmo are different model families with different implementation files and tests; shared auto/docs files are boilerplate, not the same underlying change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA and Molmo2 are separate model integrations with different model code, configs, and test suites; they do not fix the same bug or add the same feature." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA and CTSM are unrelated model additions; the overlap is only in shared registry/documentation files." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are related in naming but are distinct model families with different files, processors, and support paths; not mergeable as one duplicate PR." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM target different models and different code paths, so this is only broad subsystem overlap." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are separate model additions with distinct implementation and test files; no shared concrete bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-3", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "564fe1b455a126729c3fc5afbca29d78ca15569bbe5e0d92f8a2479e5ffc1490", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 7093, + "estimated_input_tokens": 1774, + "estimated_eval_tokens": 3804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three PRs are not duplicates of one another: one is a Whisper tokenizer/test fix, one is a dummy test-only change, and one is a broader FP8/dequantization fix. The cluster is heterogeneous, so no soft edges should be merged.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:44815 is the strongest representative PR: it has a coherent production bug fix with supporting code changes and tests, whereas pull_request:43291 is a narrower Whisper-specific patch and pull_request:43665 is clearly not a real functional fix.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:44815 is the best standalone PR in the set because it addresses a concrete code-path problem with the most complete fix and validation coverage.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Different areas and different intent: Whisper tokenizer logic vs. placeholder test edits; they do not fix the same underlying bug." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Both are real fixes, but for unrelated code paths: Whisper decoding/tests vs. FP8 dequantization/model loading in Mistral/finegrained FP8." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Not the same change at all; 43665 is dummy test noise, while 44815 is a substantive dequantization 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": 9, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-5", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45932", + "pull_request:46100", + "pull_request:46114" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:46114", + "pull_request:43488|pull_request:43532", + "pull_request:43532|pull_request:46114", + "pull_request:45932|pull_request:46100", + "pull_request:46100|pull_request:46114" + ], + "prepared_review_unit_hash": "183a215021499e64644b8dec0adef24d227a15348e35c7e09d9158f329f1fd1b", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 12257, + "estimated_input_tokens": 3065, + "estimated_eval_tokens": 6386 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 12257, + "estimated_input_tokens": 3065, + "estimated_eval_tokens": 6386 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly synthetic \"do not merge\" PRs for CI/test-bot experimentation, but the changes are not duplicates of one another. The only high-overlap pair still edits different code paths and should not be merged together.", + "confidence": 0.78, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46114 is the most representative cluster member: it has the broadest synthetic test/CI footprint, touches multiple test files plus CI/config code, and links to the most other items via shared test-harness behavior.", + "best_issue_reason": null, + "best_pr_reason": "PR 46114 is the best overall representative because it is the most connected and widest-scoped example of the cluster\u2019s synthetic PRs.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:46114", + "accept": false, + "reason": "Both are synthetic test PRs, but they change different things: 43488 is a version/dependency tweak plus a ViT test file, while 46114 is a broader migration/OTEL test harness change." + }, + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "They only overlap on the ViT test file, but the actual changes are unrelated: 43488 adjusts packaging/versioning, while 43532 rewires workflow and test infrastructure for diff display." + }, + { + "left": "pull_request:43532", + "right": "pull_request:46114", + "accept": false, + "reason": "Both are CI/test harness experiments, but they target different code paths and purposes; they are not the same concrete fix/change." + }, + { + "left": "pull_request:45932", + "right": "pull_request:46100", + "accept": false, + "reason": "Even though both are synthetic test PRs, 45932 changes CI, model code, and multiple model files, while 46100 only adds failing assertions in ViT tests." + }, + { + "left": "pull_request:46100", + "right": "pull_request:46114", + "accept": false, + "reason": "Shared test-file overlap is not enough here: 46100 is a small ViT test migration, whereas 46114 is a much broader CI/test and utility 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": 10, + "component_count": 31, + "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": "5c641370d61b2db88083c5d3d3effe7dd3a22cc9875c0b1cc69de23443d36e04", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related segmentation feature PRs, but they are not duplicates: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation with different model integrations and tests. The overlap is mostly shared docs/registry plumbing.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR for a duplicate cluster: the two PRs target different pipeline features and different concrete code paths.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a good global duplicate representative because they solve different feature gaps; 43613 is broader, but it is still a separate change from 43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different underlying features and code paths: concept segmentation vs visual segmentation. Shared documentation and registry files are incidental and not enough to merge 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": 11, + "component_count": 31, + "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-43649-2", + "nodes": [ + "pull_request:43649", + "pull_request:46301" + ], + "soft_pairs": [ + "pull_request:43649|pull_request:46301" + ], + "prepared_review_unit_hash": "b2cd26ed2bdfdebe9a4cf51651b9622e1f26b00fde5f6d0b3482814eea5cd5d1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4652, + "estimated_input_tokens": 1163, + "estimated_eval_tokens": 2582 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4652, + "estimated_input_tokens": 1163, + "estimated_eval_tokens": 2582 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs are not duplicates: one updates failure-reporting/CI automation, while the other injects test failures and adjusts CircleCI test selection. They overlap on a ViT test file, but they do not appear to fix the same underlying bug or implement the same change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43649 is the better canonical representative because it has a clear, substantive failure-reporting/CI workflow change and broader scope; PR 46301 is a narrow test-injection/check change with different intent.", + "best_issue_reason": null, + "best_pr_reason": "PR 43649 is the strongest standalone PR in the cluster due to its clearer purpose, larger implementation footprint, and direct relation to CI/failure reporting rather than an isolated test modification.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43649", + "right": "pull_request:46301", + "accept": false, + "reason": "Reject: the shared ViT filename is incidental. 43649 changes self-comment/scheduled CI and failure-reporting utilities, while 46301 changes CircleCI markers and adds deliberate failing assertions in tests. They do not target the same concrete code-path problem and would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 31, + "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": "2dd7cc13e06264d55a5f0772c587ca6e1c63742190a7e49aa9161bdb187f69f9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two open PRs both touch `src/transformers/trainer.py`, but they address different trainer extensibility points: one changes gradient-accumulation loss scaling, the other adds a hook for signature-column filtering. They are not the same underlying change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: 43651 changes training loss scaling behavior, while 43663 changes input column filtering; they solve different problems in different code paths.", + "best_issue_reason": null, + "best_pr_reason": "If a single representative had to be chosen, 43651 is the more self-contained trainer behavior change, but it does not subsume 43663 and this cluster should not be collapsed around it.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different features in `Trainer`: 43651 adds a loss-scaling hook for gradient accumulation, while 43663 adds a signature-column override for dataset filtering. They are independently mergeable and 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": "pull_request", + "component_index": 13, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-2", + "nodes": [ + "pull_request:43656", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842" + ], + "prepared_review_unit_hash": "935460f30b107192d9f9dad46c09b25246c839951a4b849e9e3419cd6e9f7c85", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3663, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 3663, + "estimated_input_tokens": 916, + "estimated_eval_tokens": 2088 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two PRs in the same CLI module, but they target different TypeAdapter-related failure modes: one is a general NameError fix, the other is specifically about running without pydantic installed.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43656 is the more central representative: it is earlier, has more discussion, and directly targets the base TypeAdapter CLI NameError.", + "best_issue_reason": null, + "best_pr_reason": "PR 43656 is the best single representative for the cluster because it has the broader bug report and the stronger review/discussion signal.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Reject: same file and symbol, but different concrete bugs. 43656 fixes the CLI TypeAdapter NameError generally; 43842 fixes the pydantic-optional import path. They are not the same underlying change and shouldn\u2019t 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": 14, + "component_count": 31, + "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": 15, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44066|pull_request:44068", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44018|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44085", + "pull_request:44018|pull_request:44086", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:43997|pull_request:44073", + "pull_request:44071|pull_request:44086", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44018|pull_request:44059", + "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", + "pull_request:44059|pull_request:44068", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:43997|pull_request:44018", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44018|pull_request:44129", + "pull_request:44010|pull_request:44073", + "pull_request:43997|pull_request:44074", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43997|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "0c2182ac47925b7bf2946b5ac85860ff21144cc20914d95779c6b577b1df27c5", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84890, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75087, + "estimated_input_tokens": 18772, + "estimated_eval_tokens": 37800 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of model-specific refactors around the shared standardized output-tracing initiative tracked by #43979. Most PRs are parallel implementations for different architectures, not true duplicates; the only clear duplicate-like pairs are within the GPT-Neo and GPT-J refactor branches.", + "confidence": 0.88, + "canonical_issue_reason": "Issue #43979 is the common umbrella tracker explicitly referenced by many of the PRs and matches the shared standardized output-tracing refactor theme.", + "canonical_pr_reason": "PR #44722 is the strongest representative of the cluster: it explicitly targets #43979 and covers the same standardized output-tracing migration across the closely related GPT-J/CodeGen code paths.", + "best_issue_reason": "#43979 is the only clear shared issue target and best captures the underlying initiative that ties the cluster together.", + "best_pr_reason": "#44722 is the most complete and representative PR in the cluster, with explicit issue linkage and concrete changes to the core GPT-J/CodeGen tracing path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Same umbrella refactor theme, but CVT/FNet and GPT-J are different model code paths and not a single duplicate change." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different model families (CVT/FNet vs DeBERTaV2); too broad to treat as the same change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J output-tracing refactors on the same underlying code path; one is broader, but the GPT-J change is the same kind of fix." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet/ResNet and EfficientNet are separate implementations; same initiative, not the same bug/change." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated model paths despite sharing the umbrella issue." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen output tracing and EfficientNet output tracing are different concrete refactors." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTaV2 are separate model implementations; not a duplicate." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen vs MGP-STR are different architectures and cannot be merged as one concrete fix." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are different code paths; same theme only." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both PRs refactor the same GPT-Neo output-tracing code path, so they look like duplicate implementations of the same change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are different model families; not the same underlying change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen vs GPT-Neo are separate model refactors, not one duplicate PR." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated concrete code paths." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are different model implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are different architectures; same umbrella issue does not make them duplicates." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated model refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are separate code paths, so this is not a duplicate change." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are different model families; shared topic only." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are distinct concrete implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are separate refactors." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are different code paths and not mergeable as one PR." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo vs GPT-J are different model branches; not the same underlying change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are different concrete changes." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and XLM/Flaubert are separate model code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer and LongT5 are different models; same issue target is not enough to merge them." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "Segformer and VisualBERT are distinct implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", + "accept": false, + "reason": "RegNet and VisualBERT are unrelated concrete refactors." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44101", + "accept": false, + "reason": "MPNet and Flaubert are different model paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR are not the same bug/change." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44161", + "accept": false, + "reason": "ViLT and LongT5 are different model refactors." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-2 and MPT are separate code paths." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are different model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo and GPT-2 are distinct model families; not a duplicate." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44161", + "accept": false, + "reason": "VisualBERT and LongT5 are unrelated concrete changes." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44068", + "accept": false, + "reason": "MPNet and GPT-Neo are different model paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are separate refactors." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44071", + "accept": false, + "reason": "Segformer and MPT are unrelated model implementations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44086", + "accept": false, + "reason": "MPNet and MGP-STR are different concrete code paths." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBERT and Flaubert are separate model refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet and Segformer are different architectures; not duplicates." + }, + { + "left": "pull_request:44074", + "right": "pull_request:44101", + "accept": false, + "reason": "TextNet and Flaubert/XLM are different model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet and LongT5 are unrelated concrete refactors." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet and Segformer are different model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBERT and DeBERTaV2 are distinct model paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTaV2 and TextNet are unrelated concrete changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same underlying GPT-J/CodeGen standardized tracing refactor; the broader PR is a plausible superset of the same change." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both center on the GPT-J tracing refactor, and the changes are close enough to be merged into one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are different model families; shared issue target only." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "FNet/CVT and RegNet/ResNet are different model code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "FNet/CVT and SpeechT5 are unrelated concrete refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTaV2 and SpeechT5 are different implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTaV2 and ViTS are separate model paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: #43979 is the common umbrella issue, and #44722 is a reasonable canonical PR because it\u2019s the most complete GPT-J/CodeGen representative with explicit issue linkage. The soft-edge verdicts are conservative overall and the accepted pairs do look mergeable as single PRs for the same GPT-Neo / GPT-J-style output-tracing refactors." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 31, + "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": "efb78bb485eac13b17d9360a03914340d7d48cc06ac6624cea0a43064c6630fc", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84890, + "estimated_input_tokens": 21223, + "estimated_eval_tokens": 42702 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17124, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These PRs are thematically similar but are model-specific refactors for standardized output tracing/capture across different code paths. They are not duplicates and should not be merged together.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the clearest anchor for the cluster: it has an explicit issue link, a well-scoped standardized output-capture refactor, and a concrete model-specific code-path change.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the best representative of the overall theme because it is the most explicitly justified and most concrete standardized output tracing change among the set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are output-capture refactors, but for different models (FocalNet vs ImageGPT) with separate implementation paths; not the same underlying fix." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Both touch standardized output tracing, but one is VisualBert and the other is TextNet; these are distinct model-specific changes, not one shared bug." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet and VisualBert are different model implementations; the refactors follow the same pattern but do not fix the same concrete code-path problem." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Different models and different forward/output plumbing; similarity is only at the refactor pattern level, which is too broad for duplicate acceptance." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model code paths; both are output-tracing refactors, but not the same underlying change." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 are distinct implementations; the shared theme is standardized output capture, but the concrete fixes are not the same." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 31, + "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": "90fc77609ffb16de1cc52f2c35755d2f9a5a10755ad4cd667d1f450b6a00a3b1", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39786, + "estimated_input_tokens": 9947, + "estimated_eval_tokens": 20150 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39786, + "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 all share a broad \u201coutput tracing / can_return_tuple\u201d refactor theme, but they target different model implementations and code paths, so they are not duplicates. PR 44003 is the strongest representative because it spans two closely related mamba-family files and adds the most concrete tracing plumbing.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44003 is the most central and substantive representative: it updates both falcon_mamba and mamba, adds output-capture plumbing, and is broader than the single-model refactors.", + "best_issue_reason": null, + "best_pr_reason": "44003 is the best overall representative for the cluster because it is the broadest concrete implementation change rather than a narrow one-file refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Same refactor theme, but timm_backbone and UperNet are different model code paths." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Both are output-tracing refactors, but timm_backbone and vision_text_dual_encoder are unrelated implementations." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models and behavior: timm_backbone vs UnivNet." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems: timm_backbone refactor versus mamba/falcon_mamba tracing changes." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Both touch tracing helpers, but timm_backbone and rwkv are distinct model paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Different model families: MobileNetV1 vs UnivNet." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different code paths: MobileNetV1 versus UperNet." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "MobileNetV1 and Depth Anything are separate models; similar refactor only." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Different implementations: MobileNetV1 versus VisionEncoderDecoder." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different models and forward paths: MobileNetV1 vs SpeechEncoderDecoder." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Vision-text dual encoder and UnivNet are unrelated code paths." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models: vision-text dual encoder versus UperNet." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Same umbrella refactor idea, but vision-text dual encoder and mamba/falcon_mamba are different implementations." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families: vision-text dual encoder vs Depth Anything." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are different models and cannot be merged as one fix." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different concrete code paths: UnivNet versus mamba/falcon_mamba." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "Different models: UnivNet and Depth Anything." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are unrelated implementations; only the refactor pattern matches." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model code paths: UperNet versus mamba/falcon_mamba." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model families: mamba/falcon_mamba vs CodeGen." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "TimmBackbone and CodeGen are unrelated code paths despite similar tracing refactor wording." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen are different model implementations." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet and CodeGen are different subsystems with different forward logic." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Vision-text dual encoder and CodeGen do not fix the same underlying bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Different models: Depth Anything versus VisionEncoderDecoder." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model families: Depth Anything vs SpeechEncoderDecoder." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Depth Anything and SuperPoint are separate code paths." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models: Depth Anything versus RWKV." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Depth Anything and DPR are unrelated implementations." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are different code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are separate, non-duplicate refactors." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different models: VisionEncoderDecoder versus SuperPoint." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "VisionEncoderDecoder and DPR are unrelated model implementations." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are different model code paths." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models: SpeechEncoderDecoder versus RWKV." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "SpeechEncoderDecoder and DPR are unrelated." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are distinct implementations." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different code paths: SuperPoint versus DPR." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are different model families; similar tracing theme only." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 31, + "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": "81e130e1d0d80a0e23cc09526b303e7d61f7ac25ae42abe0cc92c7560b50b646", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS), not duplicates of the same change. They share the common Transformers boilerplate for adding a new model, but each targets a different architecture, fileset, and model-specific code path.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs are for different models and different implementations, so there is no single duplicate to anchor the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR 45075 is the strongest representative only in the sense that it is the most complete/established model-addition PR in the set, but it is not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL and Voxtral TTS are unrelated model additions with different model-specific files and code paths; shared Transformers registration/docs boilerplate is not enough to treat them as the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 add different models with distinct implementations, converters, and tests; they are not the same underlying bug or feature." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 and Voxtral TTS are separate model integrations touching different model directories and behavior, 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": 18, + "component_count": 31, + "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": "7e45a14750b2a56c0f3d28fa579dea054d27e60f3ba1393fccc13fd6d15d38d3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4407, + "estimated_input_tokens": 1102, + "estimated_eval_tokens": 2460 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related kernel/module-fusion efforts, but they are not the same change: #44979 introduces a generic Module Fusion API and supporting abstractions, while #45363 wires up n-to-1 kernel fusion through KernelConfig and integrations. They overlap in theme but target different code paths and could not reasonably be merged as one PR.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45363 is the more concrete, user-facing implementation of fusion behavior via KernelConfig and integration hooks; #44979 is a broader API scaffold. If one PR must represent the cluster, #45363 is the better anchor for the actual feature path.", + "best_issue_reason": null, + "best_pr_reason": "#45363 is the best representative of the cluster because it adds an end-to-end fusion workflow and touches the runtime integration points, whereas #44979 is mainly foundational API work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Both are about fusion, but they implement different layers: #44979 adds a generic Module Fusion API/module abstraction, while #45363 implements n-to-1 kernel fusion via KernelConfig and integration code. They do not appear to fix the same concrete bug or change the same code path, 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": 31, + "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": "ebf7b4fa2ca6f4c2abc01bb52a999585046cd198ccfc4a2d67569fbafbeb1579", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two PRs implement the same Mistral regex fix in the same file; the second is a broader version with tests, so they are duplicate/change-equivalent enough to cluster together.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45317 is the better canonical PR because it contains the same core fix plus test coverage, making it the more complete representation of the change.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45317 is the best PR overall: same concrete bug fix, same touched code path, and it adds tests, so it is the most complete candidate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Both PRs patch the same AttributeError in _patch_mistral_regex within tokenization_utils_tokenizers.py and are plausibly mergeable into one PR; the second mainly adds 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": 20, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "95eec3809039fb2b78fb1468e5aa03da069ada3c59c52ef68db7ca31a4785d20", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open NemotronH PRs overlap on the same model family, but they address different changes: one refactors the base NemotronH implementation/conversion mapping, while the other splits NemotronH into dense and sparse variants with docs and tests. They are related, but not duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the better canonical PR for the cluster because it is the broader, more complete architectural change: it introduces the dedicated nemotron_h_dense and nemotron_h_sparse implementations, updates auto-mapping/docs, and includes tests, making it the likely end-state of the model refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the full user-facing model restructuring, whereas #45115 is a narrower internal refactor focused mainly on inheritance and weight conversion mapping.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Both are about NemotronH, but #45115 is a conversion/inheritance refactor and #45569 is a model-splitting/docs/tests change. They do not appear to fix the same concrete code-path problem and would not be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 31, + "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": "8a3f292571f90166e20a75cb135db5dc387aeb86066b182decd0bb39832f974c", + "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": "Two related but distinct PRs: one adds heterogeneous per-layer configuration support, while the other adds heterogeneous model/cache/runtime support. They overlap in infrastructure files, but they are not the same concrete change.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45332 is the broader, more complete feature PR; it includes the model/runtime work and builds on the config plumbing, so it is the better representative for the cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR 45332 is the strongest standalone candidate because it covers the full heterogeneous-model feature rather than only the configuration layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related feature area, but different scopes: 45333 adds per-layer config support, while 45332 adds heterogeneous model/cache/runtime behavior. They are not the same underlying change and could be merged separately." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 31, + "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": "7aed025656c1f53c4a695c0b7892b5863e754e5d7768873eddb4c35ccaa18d96", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two separate typing-focused PRs: one is a broad repository-wide type checking sweep, and the other is a narrower typing/helper update around modeling_utils/PEFT. The shared files look incidental, not duplicate work.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45415 is the broader, more representative cluster item: it changes type-checking config and touches many transformers modules in one sweep.", + "best_issue_reason": null, + "best_pr_reason": "PR 45415 best represents the cluster because it is the largest and most central typing-related change, while 45425 is a narrower follow-up-style helper update.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "They overlap on typing-related files, but they do not appear to fix the same concrete code-path problem. 45415 is a broad type-checking pass across many modules plus pyproject config, while 45425 adds typing protocols/helpers for modeling_utils and PEFT-related code. Not mergeable as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45513-2", + "nodes": [ + "pull_request:45513", + "pull_request:46084" + ], + "soft_pairs": [ + "pull_request:45513|pull_request:46084" + ], + "prepared_review_unit_hash": "1129b193d63acb2335b696944d7bba2a433cb7ee8a225c4890fae36f7c9b8862", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4858, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4858, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: both are cache-related PRs, but they target different model families and different failure modes. PR #45513 fixes multi-token cached forward behavior in OLMo/Qwen3 variants for GDN linear attention, while PR #46084 fixes Mamba2 use_cache handling when seq_len > 1. They should be triaged separately.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #46084 is the cleaner representative: it has an explicit issue target, a narrowly scoped fix, and a direct code-path description for the seq_len > 1 cache bug.", + "best_issue_reason": null, + "best_pr_reason": "PR #46084 is the best standalone PR in this cluster because it is more specific, explicitly tied to issue #46032, and fixes one concrete cache path rather than spanning several model files.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Both are about cached forward execution, but they fix different model implementations and different underlying bugs. #45513 changes OLMo/Qwen3-family linear attention behavior for multi-token cached continuation; #46084 changes Mamba2 cache handling when seq_len > 1. They are not the same change and could not plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "a357636a21a7f9232be0aec2f8d4225a5f358197734f075610ecc8de397e6bef", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4507, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4507, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both EP-related PRs, but they address different bugs: #45548 fixes EP + DeepSpeed ZeRO-3 loading under `accelerate launch`, while #45662 fixes EP + FSDP2 expert parameters being overwritten by rank-0 broadcast. The overlap is mostly in subsystem and `modeling_utils.py`, not the same code-path failure.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45662 is the more concrete and narrowly defined fix, with direct changes in the loading/broadcast path tied to expert parameters; #45548 is a separate loading/serialization fix.", + "best_issue_reason": null, + "best_pr_reason": "#45662 best represents the cluster if one PR must be chosen because it targets the explicit expert-overwrite bug with clearer runtime impact and broader supporting code changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Different underlying failures: one is EP + ZeRO-3 loading via accelerate launch, the other is EP + FSDP2 expert parameters being overwritten by rank-0 broadcast. Shared EP context is not enough to merge them 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": 25, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "d12da6c2ce84ea7810dbdeb894e61fadece56367010137d6520ff1013636632d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4588, + "estimated_input_tokens": 1147, + "estimated_eval_tokens": 2550 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4588, + "estimated_input_tokens": 1147, + "estimated_eval_tokens": 2550 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist-related captured_info logging collision in transformers testing utilities; one is a narrower implementation, the other also updates CI log collection to handle split files.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:45645 is the more complete and representative fix: it changes the xdist-safe output path, updates tests, and adapts CI to consume multiple captured_info files.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:45645 best fits as the primary PR because it covers the full end-to-end behavior change, not just the internal file-writing fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying bug: xdist workers colliding on captured_info output. The fixes are directly related and could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 31, + "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-45670-2", + "nodes": [ + "pull_request:45670", + "pull_request:46320" + ], + "soft_pairs": [ + "pull_request:45670|pull_request:46320" + ], + "prepared_review_unit_hash": "a46a6d8021aae8239544f78305f4f944200d6d42d077182ca018b3af123b5a53", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4431, + "estimated_input_tokens": 1108, + "estimated_eval_tokens": 2472 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4431, + "estimated_input_tokens": 1108, + "estimated_eval_tokens": 2472 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two pull requests are unrelated: one adds AutoModel registry entries for glmasr/dia, the other implements RecurrentGemma attn_implementation dispatch plus supporting conversion/tests/docs. They should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 46320 is the more substantial and self-contained change, but it is not a duplicate of PR 45670; the two address different code paths and model families.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45670", + "right": "pull_request:46320", + "accept": false, + "reason": "Different targets and functionality: AutoModel mapping for glmasr/dia vs RecurrentGemma attention-implementation support. No shared concrete bug/change to merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 31, + "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-45720-2", + "nodes": [ + "pull_request:45720", + "pull_request:46259" + ], + "soft_pairs": [ + "pull_request:45720|pull_request:46259" + ], + "prepared_review_unit_hash": "54f5621e9bc1e55586d4aea04d84970e32831cc583f19a18b7ac5f97c8c572f7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7126, + "estimated_input_tokens": 1782, + "estimated_eval_tokens": 3820 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7126, + "estimated_input_tokens": 1782, + "estimated_eval_tokens": 3820 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: one PR implements a tuple-return linting behavior in model forward methods, while the other adds a new modeling rule about dead do_* flags in image/video processors. Different rule numbers, subsystems, and code paths.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45720 is the more concrete code-change PR: it updates model forward implementations to use can_return_tuple and removes explicit return_dict plumbing across several model files. That makes it a clearer anchor than the rule/docs-focused PR.", + "best_issue_reason": null, + "best_pr_reason": "PR #45720 is the better representative of the cluster because it contains the main runtime behavior changes across model forward paths, whereas PR #46259 is primarily a linter/rule-definition update with broader documentation and rule maintenance.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45720", + "right": "pull_request:46259", + "accept": false, + "reason": "Different underlying changes: TRF003 tuple-return handling in model forwards vs. TRF016 dead do_* flag detection in image/video processors. They do not fix the same bug and would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 28, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 29, + "component_count": 31, + "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-46073-4", + "nodes": [ + "pull_request:46073", + "pull_request:46154", + "pull_request:46196", + "pull_request:46317" + ], + "soft_pairs": [ + "pull_request:46073|pull_request:46154", + "pull_request:46073|pull_request:46196", + "pull_request:46073|pull_request:46317", + "pull_request:46154|pull_request:46196", + "pull_request:46154|pull_request:46317", + "pull_request:46196|pull_request:46317" + ], + "prepared_review_unit_hash": "f3703813ac6510d3757b744798b8e8271869ca7dec26a19ddb7e43d7b877f435", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 11166, + "estimated_input_tokens": 2792, + "estimated_eval_tokens": 5840 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 11166, + "estimated_input_tokens": 2792, + "estimated_eval_tokens": 5840 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are all about adding SDPA dispatch support, but each targets a different model family and implementation path, so they should not be merged as duplicates. The most representative PR is the broadest multi-model dispatch change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46196 is the most comprehensive representative: it covers multiple related model families (SeamlessM4T/v2 and wav2vec2 variants) plus tests, making it the broadest SDPA-dispatch change in the set.", + "best_issue_reason": null, + "best_pr_reason": "PR 46196 is the best cluster representative because it spans the widest scope among these similar dispatch-support PRs while still being a concrete, coherent change set.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46073", + "right": "pull_request:46154", + "accept": false, + "reason": "Different model implementations (CTRL vs T5); same high-level feature, but not the same underlying code-path bug or mergeable change." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46196", + "accept": false, + "reason": "CTRL SDPA dispatch and SeamlessM4T/wav2vec2 SDPA dispatch are separate model-specific fixes with different code paths." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46317", + "accept": false, + "reason": "CTRL attention dispatch and Zamba attention dispatch are distinct model changes, not the same concrete bug fix." + }, + { + "left": "pull_request:46154", + "right": "pull_request:46196", + "accept": false, + "reason": "T5 SDPA support and SeamlessM4T/wav2vec2 SDPA support affect different architectures and kernels; not a single duplicate PR." + }, + { + "left": "pull_request:46154", + "right": "pull_request:46317", + "accept": false, + "reason": "T5 and Zamba are different model code paths; shared theme alone is insufficient to treat them as duplicates." + }, + { + "left": "pull_request:46196", + "right": "pull_request:46317", + "accept": false, + "reason": "SeamlessM4T/wav2vec2 SDPA dispatch and Zamba dispatch are unrelated model-specific changes, even though both enable attention dispatch." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 30, + "component_count": 31, + "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-46126-2", + "nodes": [ + "pull_request:46126", + "pull_request:46269" + ], + "soft_pairs": [ + "pull_request:46126|pull_request:46269" + ], + "prepared_review_unit_hash": "d82301e5eb1a44226c09c6644ec60a60f607b07de823c27d364b8a1a795a372d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5571, + "estimated_input_tokens": 1393, + "estimated_eval_tokens": 3042 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5571, + "estimated_input_tokens": 1393, + "estimated_eval_tokens": 3042 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related distributed-training PRs, but they are not the same change: #46126 is a focused EP + Trainer integration, while #46269 is a much broader distributed branch base touching many subsystems. The shared files alone are not enough to treat them as duplicates.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "#46269 is the broader umbrella change and likely the better representative of the distributed branch work, while #46126 is a narrower follow-up/integration PR.", + "best_issue_reason": null, + "best_pr_reason": "#46269 is the most central artifact in this cluster because it spans the widest set of distributed changes and subsumes the shared files seen in #46126.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46126", + "right": "pull_request:46269", + "accept": false, + "reason": "Reject: the PRs target different scopes and likely different merge units. #46126 is specifically EP/Trainer integration, whereas #46269 is a large distributed base branch with many unrelated file changes; they do not look like the same concrete code-path fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 31, + "component_count": 31, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-46152-2", + "nodes": [ + "pull_request:46152", + "pull_request:46207" + ], + "soft_pairs": [ + "pull_request:46152|pull_request:46207" + ], + "prepared_review_unit_hash": "6f120d9bcabeb7262df6a965aa8aae9bf7fd2d14985e0f1b915491502717abbb", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4276, + "estimated_input_tokens": 1069, + "estimated_eval_tokens": 2394 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4276, + "estimated_input_tokens": 1069, + "estimated_eval_tokens": 2394 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs share a broad theme of avoiding direct file-open source inspection, but they target different code paths and different bugs, so they should not be merged as duplicates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #46207 is the cleaner representative of the cluster because it fixes a concrete source-reading heuristic in _can_set_attn_implementation and includes a corresponding test update.", + "best_issue_reason": null, + "best_pr_reason": "PR #46207 is the strongest standalone PR: it addresses a specific modeling_utils behavior, has clearer semantics, and is more directly tied to a single code-path fix than #46152.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46152", + "right": "pull_request:46207", + "accept": false, + "reason": "Reject: both are about avoiding file-open source inspection, but #46152 changes import_utils path resolution for traversables, while #46207 changes modeling_utils' attention-implementation capability check. Different modules, different behavior, and not the same concrete fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/manifest.json b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..e14b2503a84c32f1b8af0fcbcfa53f84f80d35c4 --- /dev/null +++ b/snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260601t180035z", + "artifacts": { + "hybrid": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-06-01T18:10:36Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260601T180035Z", + "variant": "hybrid" +} diff --git a/snapshots/20260601T180035Z/manifest.json b/snapshots/20260601T180035Z/manifest.json index 1f5a84daf77fb915b3ccd43bbd5bc2beb0728edf..a603a37cc48d6ef918d00fd9dd204659925e2b0d 100644 --- a/snapshots/20260601T180035Z/manifest.json +++ b/snapshots/20260601T180035Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 1340 }, "extracted_at": "2026-06-01T18:00:35Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260601t180035z", + "runs": { + "hybrid-model-20260601t180035z": { + "analysis_id": "hybrid-model-20260601t180035z", + "artifacts": { + "hybrid": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260601T180035Z/analysis-runs/hybrid-model-20260601t180035z/manifest.json", + "model": null, + "published_at": "2026-06-01T18:10:36Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260601T180035Z", "watermark": {