diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index f1bc176887333a98075b36e5cefaae3dcaef8545..e35068321c6d84015892e4eccd4b136145af972a 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": "20260519T180042Z", - "generated_at": "2026-05-19T18:16:46Z", + "snapshot_id": "20260520T000134Z", + "generated_at": "2026-05-20T00:12:11Z", "evidence_quality": "full", "llm_enrichment": true, "meta_bugs": [ diff --git a/analysis/current/analysis-report-hybrid.llm-reviews.json b/analysis/current/analysis-report-hybrid.llm-reviews.json index a2d6bda52d5b2e1dc0aeadfcb13ea14a6ec7d8e5..881320483e5692b2affcc16e9b8af6342faa26a7 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": "20260519T180042Z", - "generated_at": "2026-05-19T18:16:46Z", + "snapshot_id": "20260520T000134Z", + "generated_at": "2026-05-20T00:12:11Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -16,7 +16,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:24643", "issue:30277", @@ -107,8 +107,8 @@ "issue:43716|issue:45685", "issue:43541|issue:43716", "issue:43828|issue:44292", - "issue:43716|issue:44292", "issue:45507|issue:45685", + "issue:43716|issue:44292", "issue:44292|issue:44918", "issue:43039|issue:44918", "issue:41762|issue:43638", @@ -135,418 +135,436 @@ "issue:43854|issue:43866", "issue:41093|issue:43638" ], - "prepared_review_unit_hash": "f78e42176ae5137736e808b1a94c32b7d79eba3c2c64db605767ee887244ae64", + "prepared_review_unit_hash": "26530e3ae98fc71f92f8d02219f6d991942600bb64c8fd39ed84f60624c9e971", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 66, - "serialized_chars": 47567, - "estimated_input_tokens": 11892, - "estimated_eval_tokens": 24040 + "serialized_chars": 47563, + "estimated_input_tokens": 11891, + "estimated_eval_tokens": 24038 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "There is one strong duplicate issue pair around DeepSpeed ZeRO-3 + BertModel index-out-of-bounds; most other soft pairs are only broad topical overlaps and should stay separate.", - "confidence": 0.69, - "canonical_issue_reason": "issue:43596 is the clearest representative of the only strong duplicate family here: the same ZeRO-3/BertModel index-out-of-bounds crash as issue:43638, with a more precise title.", + "summary": "Mostly heterogeneous cluster with a few real duplicate subgroups: one around ZeRO-3 index-out-of-bounds model loading, one around Qwen3.5 MoE rotary-embedding/device materialization, and one around the v5 tokenizer regression.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43596 is the most generic and central report in the ZeRO-3 \"index 0 is out of bounds\" subgroup, and the other accepted reports are model variants of the same loading failure.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43596 is the best canonical issue because it states the concrete failing path clearly and matches the strongest duplicate counterpart in the set.", + "best_issue_reason": "Best single issue for this cluster because it anchors the largest coherent duplicate subgroup; the rest of the items are mostly unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44322", "right": "issue:45464", "accept": false, - "reason": "Different models and different failures; same general area only." + "reason": "Different Qwen3.5 failures with no clear shared code path from the titles alone." }, { "left": "issue:45237", "right": "issue:45685", "accept": false, - "reason": "Unrelated model/runtime problems; no shared code-path evidence." + "reason": "Different model and hardware/backend failures; not the same bug." }, { "left": "issue:43716", "right": "issue:45237", "accept": false, - "reason": "Different model-specific dtype vs GPU backend issues." + "reason": "Mistral dtype mismatch vs GPT-OSS AMD-GPU failure are unrelated." }, { "left": "issue:43828", "right": "issue:45237", "accept": false, - "reason": "Both are runtime/model bugs, but the concrete failure modes are unrelated." + "reason": "Different dtype/autocast bug and GPU backend issue." }, { "left": "issue:45237", "right": "issue:45507", "accept": false, - "reason": "Different model families and different symptoms." + "reason": "Different GPT-OSS/MoE issues; not the same concrete failure." }, { "left": "issue:44292", "right": "issue:45237", "accept": false, - "reason": "Separate model/runtime issues; not the same bug." + "reason": "Different model/runtime failures; no shared underlying bug." }, { "left": "issue:30277", "right": "issue:35545", "accept": false, - "reason": "DeepSpeed collective mismatch vs ONNX export error are unrelated." + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated." }, { "left": "issue:35545", "right": "issue:42915", "accept": false, - "reason": "Different model export/tokenizer problems with no shared failing path." + "reason": "ModernBERT ONNX export and Qwen3Moe FP8 failure are different bugs." }, { "left": "issue:35545", "right": "issue:41720", "accept": false, - "reason": "ONNX export and device-map CUDA assert are different failures." + "reason": "Different model/export vs device-map runtime failures." }, { "left": "issue:45901", "right": "issue:46015", "accept": false, - "reason": "Different user-facing features; no duplicate evidence." + "reason": "Runtime crash in table QA vs outdated RAG docs; unrelated." }, { "left": "issue:44509", "right": "issue:44512", "accept": false, - "reason": "Both are docs cleanups after v5 removals, but they reference different removed items and pages." + "reason": "Both are stale v5 docs, but they point to different removed features and are not clearly the same issue." }, { "left": "issue:35545", "right": "issue:36010", "accept": false, - "reason": "Export error vs import error; not the same underlying bug." + "reason": "ONNX export error and GenerationMixin import error are unrelated." }, { "left": "issue:44805", "right": "issue:45823", "accept": false, - "reason": "Mask/index shape mismatch vs device-mismatch during forward are unrelated." + "reason": "Both are mismatch errors, but different models and different failure mechanisms." }, { "left": "issue:43638", "right": "issue:44805", "accept": false, - "reason": "Different runtime signatures: zero3/Bert out-of-bounds vs mask/tensor shape mismatch." + "reason": "ZeRO-3 empty-index error vs mask/tensor shape mismatch are different bugs." }, { "left": "issue:43596", "right": "issue:44805", "accept": false, - "reason": "Different error classes and code paths." + "reason": "Same general error family but different code path and symptom; not clearly the same bug." }, { "left": "issue:44805", "right": "issue:45161", "accept": false, - "reason": "No common concrete failure; only both are model/runtime bugs." + "reason": "Shape-mask failure and GPT-OSS tensor-parallel issue are unrelated." }, { "left": "issue:44805", "right": "issue:44918", "accept": false, - "reason": "Different errors in different training stacks." + "reason": "Different shape/packing failures; not the same underlying issue." }, { "left": "issue:34634", "right": "issue:35545", "accept": false, - "reason": "Processor voice_preset bug is unrelated to ONNX export." + "reason": "BarkProcessor voice_preset and ModernBERT ONNX export are unrelated." }, { "left": "issue:30277", "right": "issue:43638", "accept": false, - "reason": "Different DeepSpeed-related failures and different model contexts." + "reason": "Different DeepSpeed failures: collective mismatch vs empty-index loading error." }, { "left": "issue:43596", "right": "issue:43638", "accept": true, - "reason": "Same ZeRO-3/BertModel index-0 out-of-bounds crash; the titles only differ in wording around pretrained vs non-pretrained BERT." + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; only the model context differs." }, { "left": "issue:43039", "right": "issue:45161", "accept": false, - "reason": "Liger Kernel cross-entropy call vs GPT-OSS MoE TP issue are unrelated." + "reason": "Liger cross-entropy routing and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:43975", "right": "issue:44457", "accept": false, - "reason": "Different tokenizer/LoRA behaviors with no shared failing path." + "reason": "Incorrect detokenization and LoRA merge/save mismatch are different bugs." }, { "left": "issue:44292", "right": "issue:44457", "accept": false, - "reason": "Different model/runtime problems; not duplicate evidence." + "reason": "Different model/runtime failure vs LoRA merge consistency bug." }, { "left": "issue:34928", "right": "issue:44805", "accept": false, - "reason": "Different distributed-training error classes and symptoms." + "reason": "FSDP activation-checkpoint shape recomputation and mask-index mismatch are different failures." }, { "left": "issue:24643", "right": "issue:30277", "accept": false, - "reason": "Both involve DeepSpeed, but the concrete RuntimeErrors are different." + "reason": "Both involve DeepSpeed, but the concrete errors and code paths are different." }, { "left": "issue:45859", "right": "issue:45902", - "accept": false, - "reason": "Same model class, but different device/materialization failures; not clearly the same bug." + "accept": true, + "reason": "Both point to the same Qwen3.5 MoE rotary-embedding state/device-materialization bug." }, { "left": "issue:43638", "right": "issue:45161", "accept": false, - "reason": "Zero3/Bert load failure vs GPT-OSS MoE tensor-parallel issue are unrelated." + "reason": "ZeRO-3 index error and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:34928", "right": "issue:36331", "accept": false, - "reason": "Activation-checkpointing/FSDP size mismatch vs Trainer API change are different issues." + "reason": "Activation-checkpoint/FSDP size mismatch vs trainer API signature break are unrelated." }, { "left": "issue:43596", "right": "issue:45161", "accept": false, - "reason": "Different models and different failure modes." + "reason": "Different model-loading and tensor-parallel issues." }, { "left": "issue:43716", "right": "issue:45507", "accept": false, - "reason": "Dtype mismatch in one model vs invalid method call in another." + "reason": "Different model-family dtype issue and invalid method call." }, { "left": "issue:39290", "right": "issue:45081", "accept": false, - "reason": "Different model/config errors; no shared bug." + "reason": "Gemma3 config attribute error and Mistral tokenizer regex patch crash are unrelated." }, { "left": "issue:45823", "right": "issue:45874", "accept": false, - "reason": "Device-mismatch during forward vs expensive reverse embedding lookup are different behaviors." + "reason": "Same model family, but device-map mismatch and inputs_embeds reverse-lookup are different code paths." }, { "left": "issue:43425", "right": "issue:44292", "accept": false, - "reason": "Torch version compatibility vs NVFP4 model runtime error are unrelated." + "reason": "Torch version compatibility and Qwen-3 NVFP4 runtime failure are unrelated." }, { "left": "issue:43828", "right": "issue:45161", "accept": false, - "reason": "Dtype/autocast issue vs GPT-OSS TP issue are not the same bug." + "reason": "Autocast dtype mismatch and GPT-OSS tensor-parallel failure are unrelated." }, { "left": "issue:34928", "right": "issue:41720", "accept": false, - "reason": "Different distributed/device failures." + "reason": "Different training-stack and device-map runtime failures." }, { "left": "issue:44918", "right": "issue:45161", "accept": false, - "reason": "Different training/inference paths and errors." + "reason": "Qwen3.5 SFT embedding unpacking and GPT-OSS TP failure are unrelated." }, { "left": "issue:43716", "right": "issue:45685", "accept": false, - "reason": "Different model-specific dtype/backend failures." + "reason": "Mistral dtype mismatch and MPS histogram int error are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing error and image-preprocessor dtype mismatch are unrelated." }, { "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different dtype mismatch and NVFP4 runtime failures." + }, + { + "left": "issue:45507", "right": "issue:45685", "accept": false, - "reason": "Different model/backend issues." + "reason": "Different MoE invalid-method and MPS backend errors." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model-family dtype and quantization/runtime failures." }, { "left": "issue:44292", "right": "issue:44918", "accept": false, - "reason": "NVFP4 runtime error vs SFT trainer unpacking issue are unrelated." + "reason": "Different Qwen model issues with no shared concrete bug." }, { "left": "issue:43039", "right": "issue:44918", "accept": false, - "reason": "Different training stack bugs." + "reason": "Liger kernel cross-entropy issue and SFT embedding unpacking are unrelated." }, { "left": "issue:41762", "right": "issue:43638", "accept": false, - "reason": "Both are zero3-related, but the models and failure signatures differ." + "reason": "Same ZeRO-3 context, but the titles point to different model-specific failures and not clearly one bug." }, { "left": "issue:43827", "right": "issue:44512", "accept": false, - "reason": "Both are docs regressions, but they cover different removed docs content." + "reason": "Both are stale docs in v5, but they reference different removed artifacts and are not clearly the same change." }, { "left": "issue:43716", "right": "issue:44560", "accept": false, - "reason": "Different model families and symptoms." + "reason": "Mistral image dtype mismatch and Qwen3-vl video StopIteration are unrelated." }, { "left": "issue:43828", "right": "issue:45685", "accept": false, - "reason": "Different model/runtime errors." + "reason": "Autocast dtype mismatch and MPS int histogram backend error are unrelated." }, { "left": "issue:44560", "right": "issue:45685", "accept": false, - "reason": "Video StopIteration vs MPS histogram error are unrelated." + "reason": "Different vision/video failure and MPS backend error." }, { "left": "issue:43039", "right": "issue:43828", "accept": false, - "reason": "Different code paths and failure classes." + "reason": "Liger kernel issue and autocast dtype mismatch are different bugs." }, { "left": "issue:30277", "right": "issue:36331", "accept": false, - "reason": "Collective mismatch vs trainer API signature mismatch are unrelated." + "reason": "Different DeepSpeed/trainer issues with no shared underlying code path." }, { "left": "issue:45237", - "right": "issue:46015", + "right": "issue:45901", "accept": false, - "reason": "GPU inference failure vs outdated RAG examples are unrelated." + "reason": "GPT-OSS AMD GPU failure and table-QA crash are unrelated." }, { "left": "issue:34928", "right": "issue:36010", "accept": false, - "reason": "FSDP checkpointing error vs import failure are unrelated." + "reason": "FSDP checkpointing mismatch and GenerationMixin import error are unrelated." }, { "left": "issue:43039", "right": "issue:44805", "accept": false, - "reason": "Different subsystems and error signatures." + "reason": "Liger kernel cross-entropy issue and mask-shape mismatch are unrelated." }, { "left": "issue:41762", "right": "issue:43596", - "accept": false, - "reason": "Both involve zero3 indexing issues, but the model contexts and errors do not match." + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; Gemma3 and BERT are variants of the same bug." }, { "left": "issue:43901", "right": "issue:44512", "accept": false, - "reason": "Different docs problems with different removed API mentions." + "reason": "Docs mentioning return_all_scores and docs mentioning the removed run command are different issues." }, { "left": "issue:39290", "right": "issue:41720", "accept": false, - "reason": "Gemma3/vLLM attribute error vs Qwen3 auto device-map CUDA assert are unrelated." + "reason": "Different model/config and device-map runtime failures." }, { "left": "issue:45237", "right": "issue:45901", "accept": false, - "reason": "Different model/runtime and task crashes." + "reason": "Different model/backend failure and table QA crash." }, { "left": "issue:44841", "right": "issue:45823", "accept": false, - "reason": "Processor loading failure vs device-mapping forward issue are not duplicates." + "reason": "Processor failure for Voxtral and Gemma4 device mismatch are unrelated." }, { "left": "issue:43039", "right": "issue:44560", "accept": false, - "reason": "Different model/backend issues." + "reason": "Different Liger-kernel and video-processing failures." }, { "left": "issue:43975", "right": "issue:46015", "accept": false, - "reason": "Tokenizer detokenization bug vs outdated RAG docs are unrelated." + "reason": "Incorrect detokenization and outdated RAG examples are unrelated." }, { "left": "issue:45812", "right": "issue:45920", - "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and are not clearly the same bug." + "accept": true, + "reason": "Same AutoTokenizer wrong-token-IDs v5 regression, with different affected model lists." }, { "left": "issue:44863", "right": "issue:46015", "accept": false, - "reason": "Checkpoint loading failure vs docs issue are unrelated." + "reason": "Checkpoint loading failure and outdated docs are unrelated." }, { "left": "issue:43866", "right": "issue:44863", "accept": false, - "reason": "Corrupted checkpoint report vs NemotronH load bug are different problems." + "reason": "Different checkpoint/model-loading problems." }, { "left": "issue:44292", "right": "issue:46015", "accept": false, - "reason": "Model execution error vs documentation cleanup are unrelated." + "reason": "Qwen NVFP4 runtime failure and outdated RAG docs are unrelated." }, { "left": "issue:43854", "right": "issue:43866", "accept": false, - "reason": "Different model-loading problems and different models." + "reason": "Unit-test model loading failure and corrupted checkpoint are different issues." }, { "left": "issue:41093", "right": "issue:43638", "accept": false, - "reason": "Mask/index shape mismatch vs zero3 Bert out-of-bounds are different failures." + "reason": "Mask-index mismatch and ZeRO-3 empty-index error are different failures." } ] }, "evaluator_result": { "accept": true, - "feedback": "The result is well grounded in the packet. The one accepted duplicate pair, issue:43596 and issue:43638, is supported by the titles and is the only clearly strong family here. The other soft-edge rejections stay appropriately conservative and do not overclaim duplicate evidence." + "feedback": "The summary is grounded in the packet and stays conservative about the soft edges. The three accepted duplicate subgroups (ZeRO-3 index-out-of-bounds loading, Qwen3.5 MoE rotary-embedding/materialization, and the v5 tokenizer regression) are all supported by the titles, while the rejected pairs are not overstated. " }, "evaluator_used": true, "retried": false, @@ -565,7 +583,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36010", "issue:39290", @@ -656,275 +674,278 @@ "issue:44530|issue:45005", "issue:42915|issue:45399" ], - "prepared_review_unit_hash": "c880125c686279e2b4bacc3f5404653f61180f7b1d7b592f2b2d5c0d1b28b33b", + "prepared_review_unit_hash": "a0eb7335a56c0e5e7a4ca609cc2e440f3d1c98f129590c57108094c2e5c27c76", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 39, - "serialized_chars": 38526, - "estimated_input_tokens": 9632, - "estimated_eval_tokens": 19520 + "serialized_chars": 38521, + "estimated_input_tokens": 9631, + "estimated_eval_tokens": 19518 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a loose cluster of distinct Transformers regressions and model-specific failures; the shared theme is broad compatibility/loading/runtime breakage, but the soft pairs do not look like true duplicates of the same concrete bug.", - "confidence": 0.34, - "canonical_issue_reason": "Issue 45020 is the broadest representative of the cluster\u2019s recurring \u2018recent Transformers versions break model loading/compatibility\u2019 theme, even though the rest of the items are largely separate bugs.", + "summary": "Heterogeneous cluster with two real duplicate subgroups: SigLIP2 output-regression reports and a separate remote_code/custom-module loading collision pair. The remaining soft edges are mostly false positives across unrelated bugs.", + "confidence": 0.89, + "canonical_issue_reason": "No single canonical issue spans the whole cluster because the accepted duplicates split into at least two distinct subgroups (SigLIP2 regression and remote_code/custom-module path collision), alongside many unrelated issues.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the best global issue candidate because it is the most umbrella-like and could plausibly anchor several of the version/regression reports, whereas the others are more model- or error-specific.", + "best_issue_reason": "No global best issue for the full cluster. If forced within the SigLIP2 subgroup, 43994 is the clearest representative, but it should not absorb the separate remote_code/custom-module pair.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39290", "right": "issue:43531", "accept": false, - "reason": "Both mention sliding-window behavior, but they affect different models and failures (Gemma3 config attr vs Qwen3-MoE sliding_window), so this is not clearly the same bug." + "reason": "Different models and config fields; both involve sliding_window, but not the same bug." }, { "left": "issue:43792", "right": "issue:45901", "accept": false, - "reason": "Whisper runtime failure and table-question-answering crash are unrelated code paths and models." + "reason": "Whisper inference failure and table QA crash are unrelated code paths." }, { "left": "issue:43425", "right": "issue:45070", "accept": false, - "reason": "Torch version incompatibility and a pydantic PretrainedConfig regression are different issues." + "reason": "Torch version compatibility and pydantic config breakage are different issues." }, { "left": "issue:43596", "right": "issue:45800", "accept": false, - "reason": "ZeRO-3/Bert index error and torch/transformers version incompatibility are distinct failure modes." + "reason": "DeepSpeed ZeRO-3 loading error is unrelated to torch/transformers version incompatibility." }, { "left": "issue:43975", "right": "issue:45901", "accept": false, - "reason": "Incorrect detokenization and table-qa crashing are unrelated." + "reason": "Incorrect detokenization and table-question-answering crash do not share a cause." }, { "left": "issue:43792", "right": "issue:45070", "accept": false, - "reason": "No shared model or code path; runtime crash vs config/pydantic breakage." + "reason": "Whisper runtime failure is not the same as a PretrainedConfig pydantic regression." }, { "left": "issue:45362", "right": "issue:45464", "accept": false, - "reason": "Both involve Qwen3.5 chat usage, but one is a general crash and the other is a streaming API failure; not enough evidence of one concrete bug." + "reason": "Both mention Qwen3.5, but one is a chat crash and the other is a streaming API failure." }, { "left": "issue:44292", "right": "issue:45901", "accept": false, - "reason": "init_empty_weights/_is_hf_initialized type error is unrelated to table-question-answering crashes." + "reason": "Qwen-3 NVFP4 loading error is unrelated to table QA task crashes." }, { "left": "issue:39290", "right": "issue:45823", "accept": false, - "reason": "Different Gemma models and different failures: missing sliding_window_pattern vs device mismatch." + "reason": "Gemma3 vLLM config error and Gemma4 device mismatch are different model bugs." }, { "left": "issue:43404", "right": "issue:43866", "accept": false, - "reason": "Tied lm_head weights in Mistral3 and a corrupted Ovis2 checkpoint are separate problems." + "reason": "Untied lm_head weights and a corrupted checkpoint are unrelated failures." }, { "left": "issue:45464", "right": "issue:45685", "accept": false, - "reason": "Streaming chat API failure and MPS histogram_mps integer error are unrelated." + "reason": "Qwen3.5 streaming API crash and MPS histogram kernel error are different subsystems." }, { "left": "issue:43541", "right": "issue:45685", "accept": false, - "reason": "Torch dynamo grouped_mm tracing error and MPS histogram implementation error are different code paths." + "reason": "Torch dynamo grouped_mm failure is not the same as the MPS MoE histogram issue." }, { "left": "issue:43541", "right": "issue:43828", "accept": false, - "reason": "Both are dtype-related, but one is grouped_mm tracing in Mixtral and the other is an autocast mismatch in Phi-tiny-MoE; not the same bug." + "reason": "Both are dtype/runtime problems, but they occur in different models and code paths." }, { "left": "issue:44841", "right": "issue:45084", "accept": false, - "reason": "Processor failure for Voxtral and template-node compilation error are unrelated." + "reason": "Processor failure for Voxtral is unrelated to a template-node compile error." }, { "left": "issue:36010", "right": "issue:39290", "accept": false, - "reason": "ImportError for GenerationMixin and Gemma3 sliding_window_pattern are unrelated regression types." + "reason": "ImportError for GenerationMixin is unrelated to Gemma3 sliding_window_pattern." }, { "left": "issue:45800", "right": "issue:45823", "accept": false, - "reason": "Torch/transformers compatibility and Gemma4 device-mapping mismatch are separate issues." + "reason": "Torch version incompatibility and Gemma4 device mismatch are different defects." }, { "left": "issue:41093", "right": "issue:41762", "accept": false, - "reason": "Both involve indexing errors, but the shapes, models, and trigger conditions differ too much to treat as one bug." + "reason": "Both are IndexErrors, but one is a mask-shape mismatch and the other is ZeRO-3 model loading." }, { "left": "issue:43296", "right": "issue:43366", "accept": false, - "reason": "PaddleOCR-VL loading in vLLM and GGUF gpt-oss architecture support are different model-support requests/problems." + "reason": "PaddleOCR-VL loading and GGUF gpt-oss support are unrelated model issues." }, { "left": "issue:43572", "right": "issue:45070", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig is not the same as the PretrainedConfig pydantic-field regression." + "reason": "Missing pad_token_idx and pydantic PretrainedConfig breakage are different config regressions." }, { "left": "issue:43541", "right": "issue:45161", "accept": false, - "reason": "Grouped_mm tracing failure and GPT-OSS tensor-parallel failure are different concrete paths." + "reason": "Mixtral tracing failure and GPT-OSS tensor-parallel issue are not the same bug." }, { "left": "issue:44387", "right": "issue:45005", "accept": false, - "reason": "Int4 CUDA memory growth and tied-weights translation model issues are unrelated." + "reason": "Int4 memory growth and tied-weights translation-model regressions are unrelated." }, { "left": "issue:43828", "right": "issue:45464", "accept": false, - "reason": "Autocast dtype mismatch and streaming chat API failure are not the same bug." + "reason": "Autocast dtype mismatch on Phi-tiny-MoE is unrelated to Qwen3.5 streaming inference." }, { "left": "issue:44291", "right": "issue:45070", "accept": false, - "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is a different regression from the pydantic PretrainedConfig field issue." + "reason": "Unexpected _is_hf_initialized arg and pydantic field breakage are different failures." }, { "left": "issue:43366", "right": "issue:45464", "accept": false, - "reason": "GGUF gpt-oss architecture support and Qwen3.5 streaming chat failure are unrelated." + "reason": "GGUF gpt-oss support and Qwen3.5 streaming API failure do not match." }, { "left": "issue:45020", "right": "issue:45800", "accept": false, - "reason": "Remote_code breakage and torch/transformers version incompatibility are different classes of failures." + "reason": "Remote-code loading breakage is unrelated to torch/transformers incompatibility." }, { "left": "issue:43531", "right": "issue:45070", "accept": false, - "reason": "Qwen3-MoE sliding_window bug and PretrainedConfig pydantic regression are unrelated." + "reason": "Qwen3-MoE sliding_window and PretrainedConfig pydantic issues are unrelated." }, { "left": "issue:43541", "right": "issue:44589", "accept": false, - "reason": "Grouped_mm tracing error and missing Float8 storage object are different low-level failures." + "reason": "Grouped_mm tracing failure and missing Float8 storage are different runtime problems." }, { "left": "issue:41093", "right": "issue:43596", "accept": false, - "reason": "Both are index errors, but they occur in different models and mechanisms; no evidence of the same root cause." + "reason": "Two IndexErrors, but the tensor shapes and triggering paths are unrelated." }, { "left": "issue:43054", "right": "issue:43994", - "accept": false, - "reason": "Both concern Siglip2 output quality, but one is a comparative embedding complaint and the other is a nonsensical-results report; too little evidence they are the same concrete bug." + "accept": true, + "reason": "Both report SigLIP2 producing bad embeddings/results; same underlying regression." }, { "left": "issue:45542", "right": "issue:45800", "accept": false, - "reason": "Undefined tf backend from tensorboard-only install is unrelated to torch/transformers incompatibility." + "reason": "TensorBoard-without-TF backend error is unrelated to torch/transformers compatibility." }, { "left": "issue:45759", "right": "issue:45902", "accept": false, - "reason": "Custom multimodal config unwrapping and Qwen3.5 MoE uninitialized-memory issues are distinct." + "reason": "Composite Qwen config unwrapping and uninitialized rotary embedding are different bugs." }, { "left": "issue:43716", "right": "issue:44918", "accept": false, - "reason": "Mistral-3 image preprocessor dtype mismatch and Qwen3.5 embedding unpacking in trl are different bugs." + "reason": "Mistral image preprocessor dtype mismatch and Qwen3.5 SFT embedding unpacking are unrelated." }, { "left": "issue:44918", "right": "issue:45685", "accept": false, - "reason": "Unpacking embeddings with trl and MPS histogram_mps integer error do not share a concrete code path." + "reason": "TRL embedding unpacking failure and MPS MoE histogram error are unrelated." }, { "left": "issue:45632", "right": "issue:45698", - "accept": false, - "reason": "Both involve custom-module loading, but one is a cache-path collision and the other is loading the wrong module after save_pretrained; not the same bug." + "accept": true, + "reason": "Both describe remote_code/custom-module loading picking the wrong module due to a path/cache collision." }, { "left": "issue:43404", "right": "issue:45005", "accept": false, - "reason": "Un-tied lm_head weights in Mistral3 and translation-model tied-weight issues are related only by theme, not by a shared concrete fix." + "reason": "Untied lm_head in one model and tied-weights issues in translation models are not the same bug." }, { "left": "issue:43645", "right": "issue:45399", "accept": false, - "reason": "Custom model init in Jupyter and flash-attn2 fallback blocking are unrelated." + "reason": "Custom model initialization in notebooks and flash-attn fallback blocking are unrelated." }, { "left": "issue:40990", "right": "issue:44960", "accept": false, - "reason": "GPT-OSS perplexity anomaly and GLM5 issue are different model-specific reports." + "reason": "High perplexity on gpt-oss and the GLM5 issue are different model regressions." }, { "left": "issue:44530", "right": "issue:45005", "accept": false, - "reason": "PagedAttentionCache linear_attention crash and tied-weights translation issues are unrelated." + "reason": "PagedAttentionCache linear_attention failure and tied-weights translation issues are unrelated." }, { "left": "issue:42915", "right": "issue:45399", "accept": false, - "reason": "FineGrainedFP8Config failure in Qwen3Moe and flash-attn2 fallback gating are different problems." + "reason": "Qwen3Moe FP8 failure and flash-attn fallback gating are different concerns." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports a heterogeneous cluster, but the summary is too strong in claiming SigLIP2 is the only clear duplicate subgroup. The evidence also shows a separate accepted duplicate pair for remote_code/custom-module loading collisions (`issue:45632` \u2194 `issue:45698`). Because the cluster contains at least these two soft-duplicate subgroups, the canonical/best-issue rationale is not fully grounded as written. The individual soft-edge rejections are mostly conservative, but the high-level cluster summary overstates the evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -939,7 +960,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36331", "issue:38175", @@ -1012,8 +1033,8 @@ "issue:43054|issue:45701", "issue:44910|issue:45859", "issue:45663|issue:45902", - "issue:42947|issue:44387", "issue:41553|issue:43881", + "issue:42947|issue:44387", "issue:44403|issue:44451", "issue:43054|issue:43493", "issue:43643|issue:45020", @@ -1024,238 +1045,244 @@ "issue:45685|issue:45823", "issue:43881|issue:43883" ], - "prepared_review_unit_hash": "5787801d306a43f15829b6f15f186341a3aaa6ece6ac67fce0f646018ce9e022", + "prepared_review_unit_hash": "d58ccd8d21b64e0cd156ba31802f8d74a756fe186a59ed0aadf54bce60bf431d", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 33, - "serialized_chars": 36660, - "estimated_input_tokens": 9165, - "estimated_eval_tokens": 18586 + "serialized_chars": 36663, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous and over-grouped. Only a few pairs look like true duplicates: the v5 non-persistent buffer corruption reports, and the SigLIP2 HF-vs-JAX discrepancy reports. Most other pairs are different bugs that only share a broad subsystem like loading, quantization, or MoE training.", - "confidence": 0.84, - "canonical_issue_reason": "issue:43950 is the clearest representative of the strongest duplicate subcluster: a v5 regression where non-persistent buffers are corrupted/junk-filled during from_pretrained/load. It is specific, regression-oriented, and has direct near-duplicates.", + "summary": "This cluster is mostly a loose collection of Transformers v5/model-loading regressions, but only one pair is a clear duplicate: the non-persistent buffer corruption reports. Most other soft pairs are related only at the subsystem or model-family level and should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 43950 is the strongest canonical issue: it states the broad underlying v5 regression around non-persistent buffers being corrupted, and it has a near-identical later duplicate in 44534. It is more general than the model-specific follow-up reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43950 is the best single issue to anchor the cluster because it states the underlying bug crisply and matches the closest accepted duplicates.", + "best_issue_reason": "43950 is the best overall issue to anchor the cluster because it describes a concrete, reusable bug pattern rather than a single model symptom, and it most clearly matches a duplicate report in the set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44360", "right": "issue:44512", "accept": false, - "reason": "DSA indexer/ReLU discussion is unrelated to a docs note about a removed run command." + "reason": "DSA indexer/ReLU discussion vs docs mentioning a removed run command; unrelated topics." }, { "left": "issue:39186", "right": "issue:44918", "accept": false, - "reason": "Different failures: FSDP 2-D weight error vs Qwen3.5 embedding unpacking in TRL SFT trainer." + "reason": "FSDP weight-shape RuntimeError vs TRL SFT input-embedding unpacking failure; different code paths." }, { "left": "issue:43873", "right": "issue:45005", "accept": false, - "reason": "Quantization/offload behavior and tied-weights handling are different bugs." + "reason": "Quantization/offloading behavior vs tied-weights translation-model issue; not the same bug." }, { "left": "issue:44863", "right": "issue:45005", "accept": false, - "reason": "NemotronH checkpoint loading failure is unrelated to tied-weights regression in translation models." + "reason": "NemotronH checkpoint loading failure vs translation-model tied-weights regression; unrelated." }, { "left": "issue:44492", "right": "issue:44512", "accept": false, - "reason": "A typo in cache strategies is unrelated to stale docs about a removed command." + "reason": "Cache-strategies typo vs docs still referencing removed run command; both docs, but different changes." }, { "left": "issue:44918", "right": "issue:45507", "accept": false, - "reason": "Different model/code paths: TRL embedding unpacking vs GraniteMoEHybrid invalid method call." + "reason": "Qwen3.5 embedding unpacking issue vs GraniteMoEHybrid invalid-method call; different models and failures." }, { "left": "issue:43975", "right": "issue:44292", "accept": false, - "reason": "DeepSeek detokenization bug is unrelated to Qwen-3 NVFP4 runtime error." + "reason": "Detokenization bug vs Qwen-3-8B-NVFP4 runtime error; not the same underlying issue." }, { "left": "issue:44292", "right": "issue:45507", "accept": false, - "reason": "Unrelated model/runtime issues; no shared concrete bug." + "reason": "Qwen-3-8B-NVFP4 loading/runtime error vs GraniteMoEHybrid invalid-method call; unrelated." }, { "left": "issue:43950", "right": "issue:44534", "accept": true, - "reason": "Both report the same v5 non-persistent buffer corruption/junk-filling regression in loading/from_pretrained behavior." + "reason": "These are the same underlying regression: non-persistent buffers get corrupted/junked in v5 during model loading/materialization." }, { "left": "issue:39692", "right": "issue:43054", "accept": false, - "reason": "Both involve SigLIP2, but one is a docs/example issue and the other is a model-quality complaint; not the same concrete bug." + "reason": "SigLIP2 docs/example errors vs poor text-embedding quality; different problem class." }, { - "left": "issue:43644", + "left": "issue:43643", "right": "issue:43950", - "accept": true, - "reason": "Same underlying v5 bug: non-persistent buffers get filled with junk/corrupted during load or from_pretrained." + "accept": false, + "reason": "AutoConfig trust_remote_code missing-fields bug vs non-persistent buffer corruption; unrelated." }, { "left": "issue:43828", "right": "issue:44928", "accept": false, - "reason": "Autocast dtype mismatch and Qwen3.5 gradient explosion from 3D position_ids are different issues." + "reason": "Autocast dtype mismatch vs Qwen3.5 gradient explosion/NaN; same model family, but not the same concrete bug." }, { "left": "issue:36331", "right": "issue:41762", "accept": false, - "reason": "Unexpected trainer kwarg and Gemma3 ZeRO-3 load failure are unrelated." + "reason": "CustomTrainer compute_loss signature mismatch vs Gemma3 ZeRO-3 loading error; unrelated." }, { "left": "issue:41628", "right": "issue:45800", "accept": false, - "reason": "AutoImageProcessor import failure and torch/transformers incompatibility are only broadly environment-related, not the same bug." + "reason": "AutoImageProcessor import failure vs torch/transformers incompatibility; not the same bug." }, { "left": "issue:43866", "right": "issue:44403", "accept": false, - "reason": "Corrupted Ovis2 checkpoint and noisy transformer loading are different problems." + "reason": "Corrupted Ovis2 checkpoint vs generic loading noise; unrelated." }, { "left": "issue:43950", "right": "issue:45902", "accept": false, - "reason": "Both mention loading/memory state, but one is non-persistent buffer corruption while the other is a Qwen3.5 MoE rotary embedding uninitialized-memory bug." + "reason": "Both mention non-persistent buffers, but 45902 is a specific Qwen3_5MoeTextRotaryEmbedding materialization bug and is not clearly the same report as the broader from_pretrained regression." }, { "left": "issue:43872", "right": "issue:44589", "accept": false, - "reason": "Bitsandbytes __new__ API mismatch and missing Float8 storage are unrelated quantization/runtime errors." + "reason": "bitsandbytes kwarg incompatibility vs missing Float8 storage type; different compatibility issues." }, { "left": "issue:38175", "right": "issue:43054", "accept": false, - "reason": "Both are SigLIP2 complaints, but the reports are not the same concrete failure mode." + "reason": "Unexpected zero probabilities vs degraded text embeddings; both SigLIP2-related, but not the same bug." }, { "left": "issue:41553", "right": "issue:43883", "accept": false, - "reason": "Bad AutoTokenizer error message for Voxtral and Molmo tied-weights attribute failure are unrelated." + "reason": "AutoTokenizer loading error for Voxtral vs Molmo tied-weights attribute error; unrelated." }, { "left": "issue:43054", "right": "issue:45701", "accept": false, - "reason": "SigLIP2 embedding quality and version-dependent tokenization changes are different bugs." + "reason": "SigLIP2 embedding quality issue vs tokenization changed across versions; different symptoms and likely different causes." }, { "left": "issue:44910", "right": "issue:45859", "accept": false, - "reason": "Flash-Attention packed-sequence misinterpretation and CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding are different code-path issues." + "reason": "Both touch Qwen3.5/MoE rotary code, but one is a Flash Attention position_ids crash and the other is CPU-offload compatibility; not the same bug." }, { "left": "issue:45663", "right": "issue:45902", "accept": false, - "reason": "Gemma4 shared_kv_states/FSDP2 error is unrelated to Qwen3_5MoeTextRotaryEmbedding uninitialized-memory read." + "reason": "Gemma4 FSDP2 shared_kv_states KeyError vs Qwen3_5Moe rotary buffer initialization issue; unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral tokenizer loading error vs glm-4v-9b loading failure; different models and failure modes." }, { "left": "issue:42947", "right": "issue:44387", "accept": false, - "reason": "Gradient checkpointing ineffectiveness and int4 quantization OOM are both memory-related but not the same bug." + "reason": "Gradient checkpointing ineffectiveness with LoRA vs int4 reserved-memory/OOM regression; different mechanisms." }, { - "left": "issue:41553", - "right": "issue:43881", + "left": "issue:44403", + "right": "issue:44451", "accept": false, - "reason": "Voxtral tokenizer loading error and glm-4v-9b loading failure are unrelated." + "reason": "Generic loading noise vs inability to load ScandiBERT; the titles are too broad and do not indicate the same concrete bug." }, { "left": "issue:44403", - "right": "issue:44451", + "right": "issue:44488", "accept": false, - "reason": "Generic loading noise and inability to load a specific model are not the same concrete issue." + "reason": "Generic loading noise vs inability to load cjvt/sleng-bert; not the same issue." }, { "left": "issue:43054", "right": "issue:43493", - "accept": true, - "reason": "Both point to the same SigLIP2 implementation discrepancy versus the original JAX model, likely causing the observed embedding-quality regression." + "accept": false, + "reason": "SigLIP2 embedding quality vs HF/JAX implementation discrepancy; related model family, but not the same concrete bug." }, { "left": "issue:43643", "right": "issue:45020", "accept": false, - "reason": "Both involve remote_code/trust_remote_code, but one is missing fields in AutoConfig output and the other is a broader compatibility report." + "reason": "AutoConfig missing fields with trust_remote_code vs broader recent remote_code breakage; related area, but too broad to merge as one bug." }, { "left": "issue:43975", "right": "issue:45520", "accept": false, - "reason": "Detokenization regression and a Python 3.13 flash_attn import KeyError are unrelated." + "reason": "Detokenization bug vs flash_attn import failure on Python 3.13; unrelated." }, { "left": "issue:44403", "right": "issue:44488", "accept": false, - "reason": "Both mention loading models, but they are different model-specific failures." + "reason": "Generic loading noise vs another model loading failure; not the same underlying bug." }, { "left": "issue:42947", "right": "issue:43856", "accept": false, - "reason": "LoRA checkpointing inefficiency and Qwen3 MoE memory usage are different training-memory issues." + "reason": "LoRA checkpointing inefficiency vs Qwen3 MoE memory usage; both about memory, but different issues." }, { "left": "issue:41762", "right": "issue:42915", "accept": false, - "reason": "Gemma3 ZeRO-3 index error and Qwen3 MoE fine-grained FP8 failure are unrelated." + "reason": "Gemma3 ZeRO-3 loading failure vs Qwen3 MoE FineGrainedFP8Config failure; different models and code paths." }, { "left": "issue:45685", "right": "issue:45823", "accept": false, - "reason": "MPS histogram for Int and Gemma4 PLE device mismatch are different device/runtime bugs." + "reason": "MPS histogram Int error vs Gemma4 PLE device mismatch; unrelated." }, { "left": "issue:43881", "right": "issue:43883", "accept": false, - "reason": "glm-4v-9b loading failure and Molmo tied-weights attribute error are unrelated loading bugs." + "reason": "glm-4v-9b loading failure vs Molmo missing all_tied_weights_keys; different bugs." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet, and the soft-edge verdicts are generally conservative. The accepted pairs are plausible duplicate links based on the issue titles and framing, especially the v5 non-persistent-buffer regression cluster around issue:43950." + "feedback": "The assessment is grounded in the packet and stays conservative. The chosen anchor/canonical issue, 43950, is well supported by the title overlap with 44534, and the summary appropriately avoids over-claiming duplicate status for the other soft pairs. I don\u2019t see any soft-edge verdicts that overstate the evidence." }, "evaluator_used": true, "retried": false, @@ -1274,7 +1301,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:24643", "issue:30064", @@ -1358,226 +1385,226 @@ "issue:24643|issue:30064", "issue:43366|issue:43828" ], - "prepared_review_unit_hash": "1d8c58a91588502401ebf3b0713936858d888cf9f9a47308d69c81a6d05fb77d", + "prepared_review_unit_hash": "529422a86c5f61d4179fec144aec4cbb80e53a7a5c7f34d03497e0e6801dbce6", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 37045, - "estimated_input_tokens": 9262, - "estimated_eval_tokens": 18780 + "serialized_chars": 37041, + "estimated_input_tokens": 9261, + "estimated_eval_tokens": 18778 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous, but there are a few true duplicate subgroups: docs about removed pipeline tasks, the same mask-shape IndexError, the `_is_hf_initialized` model-loading regression, and likely the Qwen3 video-input regression. Most other pairs are clearly different bugs or too broad to merge.", - "confidence": 0.69, - "canonical_issue_reason": "No single cluster-wide canonical issue: the set splits into several unrelated bug families. If a representative is needed, issue 43827 is the cleanest early anchor for the docs-removal subgroup.", + "summary": "Mostly a heterogeneous cluster of transformer regressions, tokenizer/model-loading issues, and a few docs/video/audio bugs. There is no strong single canonical issue for the whole set; 45020 is only the broadest representative of the loading/regression subgroup. Only a few soft pairs look like true duplicates.", + "confidence": 0.88, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "No single global best issue for the whole cluster for the same reason; 43827 is the strongest representative only for the docs-cleanup subgroup.", + "best_issue_reason": "issue:45020 is the broadest representative of the recent model-loading/regression subgroup, but it still doesn't cover the unrelated training/docs/audio/video reports in this cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42491", "right": "issue:44368", "accept": false, - "reason": "Related Qwen3/MoE/LoRA context, but these are different problems: version compatibility vs a warning about tie_word_embeddings." + "reason": "Related to Qwen3/LoRA, but one is a hf4.x\u2192hf5.x compatibility break and the other is a tie_word_embeddings warning; not the same bug." }, { "left": "issue:43824", "right": "issue:43872", "accept": false, - "reason": "Different failures: Qwen2.5-VL import error vs bitsandbytes `_is_hf_initialized` constructor incompatibility." + "reason": "Missing Qwen2.5-VL import vs bitsandbytes `_is_hf_initialized` incompatibility are different failure modes." }, { "left": "issue:45020", "right": "issue:45823", "accept": false, - "reason": "Both are recent model-loading/runtime regressions, but the concrete bugs differ: remote_code handling vs Gemma4 PLE device placement." + "reason": "Generic remote_code breakage vs Gemma4 device_map/PLE forward mismatch; different code paths." }, { "left": "issue:44661", "right": "issue:45020", "accept": false, - "reason": "Tokenizer-mapping helper failure is not the same as the broader remote_code regression." + "reason": "Tokenizer-mapping edge case is too specific to merge with broad remote_code regressions." }, { "left": "issue:44991", "right": "issue:45399", "accept": false, - "reason": "Tokenizer loading for a specific model is unrelated to the flash-attn fallback gating bug." + "reason": "Tokenizer loading failure for a specific model vs flash-attn2 fallback gating; unrelated bugs." }, { "left": "issue:43828", "right": "issue:45823", "accept": false, - "reason": "Different concrete code paths: autocast dtype mismatch in Phi MoE vs Gemma4 PLE device mismatch." + "reason": "Autocast dtype mismatch and device placement mismatch are separate model execution issues." }, { "left": "issue:43782", "right": "issue:44960", "accept": false, - "reason": "Different model families and error modes; no clear shared underlying bug." + "reason": "Different models and symptoms; no clear shared code-path bug from the titles alone." }, { "left": "issue:45081", "right": "issue:45399", "accept": false, - "reason": "Mistral tokenizer regex crash is unrelated to the flash-attn fallback checks." + "reason": "Mistral regex patch crash vs flash-attn fallback checks; distinct tokenizer vs attention-path problems." }, { "left": "issue:43827", "right": "issue:44509", "accept": true, - "reason": "Same docs cleanup: both report stale references to removed pipeline tasks in v5." + "reason": "Both report docs still referencing removed pipeline tasks after v5 removals; same documentation issue." }, { "left": "issue:45020", "right": "issue:45356", "accept": false, - "reason": "General remote_code breakage is not the same as the Kimi-K2.5 tokenizer regression." + "reason": "Remote_code model-loading regressions are not the same as the Kimi-K2.5 tokenizer codec/regression report." }, { "left": "issue:43404", "right": "issue:43950", "accept": false, - "reason": "Different bugs: tied lm_head in Mistral3 vs silent corruption of non-persistent buffers." + "reason": "Untied lm_head in Mistral3 is unrelated to non-persistent buffer corruption during from_pretrained()." }, { "left": "issue:43742", "right": "issue:45399", "accept": false, - "reason": "MobileLLM loading key error is unrelated to flash-attn fallback gating." + "reason": "MobileLLM key error and flash-attn fallback gating are different loading/runtime problems." }, { "left": "issue:42915", "right": "issue:45020", "accept": false, - "reason": "Both touch loading/runtime behavior, but the Qwen3 MoE weight-conversion issue is distinct from the remote_code regression." + "reason": "LoRA qwen3_moe hf4/hf5 incompatibility is model/version-specific and not the same as the broad remote_code regressions." }, { "left": "issue:43638", "right": "issue:45823", "accept": false, - "reason": "Zero-3 index-out-of-bounds in BERT is unrelated to Gemma4 PLE device placement." + "reason": "Zero3 index error with a non-pretrained Bert model is unrelated to Gemma4 device placement mismatch." }, { "left": "issue:43792", "right": "issue:44220", "accept": false, - "reason": "Whisper runtime failure and `_torch_extract_fbank_features()` are plausibly related, but the titles do not show the same concrete bug." + "reason": "Whisper can't-run report and `_torch_extract_fbank_features()` are too underspecified to treat as the same bug." }, { "left": "issue:43257", "right": "issue:43866", "accept": false, - "reason": "Qwen3 MoE weight-loading failure and Ovis2 checkpoint corruption are different issues." + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed vs Ovis2 checkpoint corruption are unrelated." }, { "left": "issue:43872", "right": "issue:44291", "accept": true, - "reason": "Same unexpected `_is_hf_initialized` keyword regression during model loading / empty-weights initialization." + "reason": "Both describe the same `_is_hf_initialized` argument regression during model loading/init-empty-weights flows." }, { "left": "issue:42915", "right": "issue:43872", "accept": false, - "reason": "Both involve loading regressions, but they are different concrete failures and would not be fixed by one PR." + "reason": "LoRA model compatibility issue vs bitsandbytes constructor-kwarg incompatibility; not the same problem." }, { "left": "issue:43940", "right": "issue:45313", "accept": false, - "reason": "Qwen3-Next ZeRO-3 missing weights and Qwen3.5 ZeRO-3 language_model loading failure are related themes but not the same bug." + "reason": "Both are ZeRO-3 weight-loading failures, but the model families and reported failure modes differ enough to avoid merging." }, { "left": "issue:43854", "right": "issue:44863", "accept": false, - "reason": "GLM-4.7 test-load issue and NemotronH checkpoint loading are different model-specific problems." + "reason": "GLM-4.7 test-loading problem and NemotronH checkpoint loading failure are different model-specific issues." }, { "left": "issue:41553", "right": "issue:44991", "accept": false, - "reason": "Bad tokenizer error message for Voxtral is not the same as a hard tokenizer-loading failure for est-roberta." + "reason": "Bad Voxtral error message vs est-roberta tokenizer load failure; only loosely related as tokenizer issues." }, { "left": "issue:42947", "right": "issue:45923", "accept": false, - "reason": "Gradient checkpointing not taking effect in PEFT LoRA is different from a missing supports_gradient_checkpointing flag on a remote-code model." + "reason": "Gradient checkpointing ineffective with PEFT LoRA is not the same as a missing supports_gradient_checkpointing flag." }, { "left": "issue:36331", "right": "issue:41093", "accept": false, - "reason": "Unexpected compute_loss kwarg is unrelated to the mask-shape IndexError." + "reason": "Trainer compute_loss signature mismatch vs tensor/mask shape mismatch are unrelated." }, { "left": "issue:44928", "right": "issue:45588", "accept": false, - "reason": "RLHF gradient explosion from 3D position ids is unrelated to the flash-attention s_aux=None crash." + "reason": "RLHF NaN/SDPA fallback problem vs flash_attention `s_aux=None` crash are different attention-path failures." }, { "left": "issue:43257", "right": "issue:45305", "accept": false, - "reason": "Both involve Qwen3 and DeepSpeed, but one is weight conversion/loading and the other is gradient averaging with loss kwargs." + "reason": "DeepSpeed weight conversion bug vs gradient averaging-by-GAS bug; different training issues." }, { "left": "issue:43872", "right": "issue:45538", "accept": false, - "reason": "Unexpected `_is_hf_initialized` loading error is unrelated to CLIPTokenizer's max-length sentinel value." + "reason": "_is_hf_initialized incompatibility has nothing to do with CLIPTokenizer model_max_length." }, { "left": "issue:41093", "right": "issue:44805", "accept": true, - "reason": "Same IndexError shape-mismatch symptom; these look like duplicate reports of the same underlying indexing bug." + "reason": "These are the same mask/index shape-mismatch error pattern, just with different example sizes and wording." }, { "left": "issue:44479", "right": "issue:44560", "accept": true, - "reason": "Both describe the 5.3.0 video-input regression in Qwen3-family VLMs, with one being a specific manifestation." + "reason": "Both point to the same Qwen3/Qwen3.5 video-input regression in v5.3.0 affecting video handling paths." }, { "left": "issue:41553", "right": "issue:44488", "accept": false, - "reason": "Different tokenizer-loading complaints for different models; not the same bug." + "reason": "Voxtral tokenizer error message and sleng-bert loading failure are unrelated tokenizer-specific issues." }, { "left": "issue:24643", "right": "issue:30064", "accept": false, - "reason": "DeepSpeed training weight-dimension error and void segmentation-map processing are unrelated." + "reason": "DeepSpeed training weight-dimension error vs void segmentation map processing are clearly unrelated." }, { "left": "issue:43366", "right": "issue:43828", "accept": false, - "reason": "GGUF architecture support and an autocast dtype mismatch are unrelated." + "reason": "GGUF gpt-oss support and autocast dtype mismatch are different model-format vs execution-dtype problems." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is conservative and grounded in the packet. The accepted soft pairs are plausible duplicates or near-duplicates, and the rejected pairs are mostly clearly different bug families. No obvious overstatement of evidence." + "feedback": "The summary stays conservative and matches the packet: the cluster is heterogeneous, 45020 is only a broad representative, and the accepted soft pairs are plausibly duplicates based on the issue titles. No pair is overstated beyond the evidence available here." }, "evaluator_used": true, "retried": false, @@ -1596,7 +1623,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36010", "issue:38175", @@ -1680,226 +1707,226 @@ "issue:42491|issue:45276", "issue:43708|issue:44075" ], - "prepared_review_unit_hash": "53ca2baa3b9458c317ed2f4626d796ce3c2fcc185e9c9e46d8fc18b08e536ff4", + "prepared_review_unit_hash": "98967f62b2644af3142ee146f00c3785924b2889b39e21ecfbb259a13b7eedf9", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36979, - "estimated_input_tokens": 9245, - "estimated_eval_tokens": 18746 + "serialized_chars": 36974, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a mix of unrelated issue groups. The only clear duplicate sets are around custom model initialization, non-persistent buffer regression, a BERT model-loading regression, and a couple of model-specific loading/output regressions.", - "confidence": 0.78, - "canonical_issue_reason": "issue:43646 is the clearest broad regression title and best represents the custom-model initialization duplicate set; it is more general than the notebook-specific wording in issue:43645.", + "summary": "Most items are unrelated model- or feature-specific bugs. Only three soft pairs look like true duplicates: the Transformers v5 custom-init regression, the SigLIP2 bad-output regression, and the non-persistent-buffer junk-fill regression.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 44534 is the clearest general wording of the exact Transformers v5 non-persistent-buffer regression, and it cleanly subsumes the matching 43644 report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the strongest standalone issue candidate because it states the underlying bug most generally and cleanly.", + "best_issue_reason": "Issue 44534 is the strongest standalone representative in this set: concise, specific, and an exact duplicate of 43644.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45325", "right": "issue:45902", "accept": false, - "reason": "Different models and different bugs: Qwen2.5-VL rope indexing vs Qwen3.5-MoE rotary embedding initialization." + "reason": "Different models and different failure modes; both are rotary-embedding related at most, but not the same concrete bug." }, { "left": "issue:45663", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma-4, but one is an FSDP2 KeyError and the other is a device_map forward mismatch; not the same bug." + "reason": "Same Gemma4 family, but one is an FSDP2 KeyError in shared_kv_states and the other is a device_map forwarding mismatch." }, { "left": "issue:43366", "right": "issue:43531", "accept": false, - "reason": "GGUF/gpt-oss support and Qwen3-MoE sliding_window are unrelated changes." + "reason": "Unrelated issues: GGUF/gpt-oss support versus a Qwen3-MoE sliding_window bug." }, { "left": "issue:43950", "right": "issue:45834", "accept": false, - "reason": "Non-persistent buffer corruption and Kosmos2.5 long-OCR indexing are different failure modes." + "reason": "Different subsystems and symptoms; non-persistent buffer corruption is unrelated to Kosmos2.5 OCR indexing." }, { "left": "issue:43550", "right": "issue:44910", "accept": false, - "reason": "Different code paths: Bamba torch.compile+SDPA vs Qwen3.5 FlashAttention position_ids handling." + "reason": "Different models and different code paths: Bamba torch.compile/SDPA versus Qwen3.5 flash-attention position_ids handling." }, { "left": "issue:43366", "right": "issue:44589", "accept": false, - "reason": "Architecture support for gpt-oss and a Float8 storage TypeError are not the same issue." + "reason": "No concrete overlap; GGUF support and Float8 storage loading are separate problems." }, { "left": "issue:43645", "right": "issue:43646", "accept": true, - "reason": "Same underlying regression: custom model initialization breaks in Transformers 5.0.0; the notebook wording is just a narrower variant." + "reason": "These describe the same Transformers v5 custom-model initialization regression; the notebook mention is just a repro variant." }, { "left": "issue:44560", "right": "issue:44918", "accept": false, - "reason": "Qwen3-vl video StopIteration and Qwen3.5 embedding unpacking in TRL are different bugs." + "reason": "Both involve Qwen-family models, but the failures are different: video StopIteration versus TRL unpacking embeddings." }, { "left": "issue:42915", "right": "issue:43957", "accept": false, - "reason": "Qwen3Moe FP8 failure and meta-device loading failures are unrelated." + "reason": "Different regressions: FineGrainedFP8Config on Qwen3Moe versus meta-device loading issues across other models." }, { "left": "issue:43824", "right": "issue:43957", "accept": false, - "reason": "An import error for Qwen2.5-VL is not the same as a meta-device loading regression." + "reason": "ImportError for a missing Qwen2.5-VL class is unrelated to meta-device loading regressions." }, { "left": "issue:42617", "right": "issue:43366", "accept": false, - "reason": "3D parallel execution failure and GGUF model support are unrelated." + "reason": "Unrelated: running 3d_parallel.py versus GGUF gpt-oss support." }, { "left": "issue:36010", "right": "issue:42915", "accept": false, - "reason": "GenerationMixin import breakage and Qwen3Moe FP8 failure are different problems." + "reason": "Different bugs entirely: GenerationMixin import path versus Qwen3Moe FP8 loading." }, { "left": "issue:44661", "right": "issue:45823", "accept": false, - "reason": "Tokenizer-mapping failure and Gemma4 device mismatch are separate bugs." + "reason": "Tokenizer mapping/add-new-model-like behavior is unrelated to Gemma4 PLE device mismatch." }, { "left": "issue:38175", "right": "issue:43994", "accept": true, - "reason": "Same underlying SigLIP2 bad-output regression for the same model; the titles describe the same symptom in different words." + "reason": "Same SigLIP2 base model and same bad-output symptom; zero probabilities and nonsensical outputs are likely the same underlying regression." }, { "left": "issue:43632", "right": "issue:45834", "accept": false, - "reason": "_is_hf_initialized flag regression and Kosmos2.5 OCR indexing are unrelated." + "reason": "Transformers v5 _is_hf_initialized regression is unrelated to Kosmos2.5 long-OCR index errors." }, { "left": "issue:44560", "right": "issue:44805", "accept": false, - "reason": "Different symptoms and code paths: video StopIteration vs mask/tensor shape mismatch." + "reason": "Different failure modes and likely different code paths: video StopIteration versus mask-shape IndexError." }, { "left": "issue:44155", "right": "issue:45584", "accept": false, - "reason": "AudioFlamingo3 batched-track leakage and Whisper empty-transcription handling are not the same bug." + "reason": "AudioFlamingo3 batched-track leakage is unrelated to Whisper empty-transcription handling." }, { "left": "issue:43638", "right": "issue:44661", "accept": false, - "reason": "Deepspeed zero3 Bert initialization and add-new-model-like/tokenizer mapping are unrelated." + "reason": "Zero3/BertModel initialization and tokenizer-mapping model registration are different bugs." }, { "left": "issue:43596", "right": "issue:44661", "accept": false, - "reason": "Same as above: a zero3/Bert IndexError is not the tokenizer-mapping failure." + "reason": "Different concrete failures: deepspeed zero3/BertModel indexing versus add-new-model-like tokenizer mapping logic." }, { "left": "issue:44661", "right": "issue:44805", "accept": false, - "reason": "Tokenizer-mapping error and mask shape mismatch are different issues." + "reason": "No shared underlying bug; tokenizer-mapping model registration is unrelated to a tensor mask-shape mismatch." }, { "left": "issue:44877", "right": "issue:45030", - "accept": true, - "reason": "Both report stricter config validation preventing model/config loading; they look like the same regression expressed with different example configs." + "accept": false, + "reason": "Both are config-loading regressions, but they concern different models and different validation failures." }, { "left": "issue:43317", "right": "issue:44756", "accept": false, - "reason": "Device-map offload loading and mmap OOM on Strix Halo are different problems." + "reason": "Different problem areas: dequantized model offload loading versus mmap/OOM on Strix Halo." }, { "left": "issue:38175", "right": "issue:39692", "accept": false, - "reason": "Both mention SigLIP2, but one is an output regression and the other is a docs/example problem with model/processor mismatch plus quantization failure." + "reason": "Same SigLIP2 area, but the bugs are not clearly the same concrete issue: one is bad probabilities, the other is docs/example mismatch and quantization failure." }, { "left": "issue:42491", "right": "issue:43720", "accept": false, - "reason": "Qwen3-MoE LoRA compatibility and BitNet packed-weight loading are unrelated." + "reason": "Qwen3-MoE LoRA compatibility across HF versions is unrelated to BitNet packed-weight loading." }, { "left": "issue:44960", "right": "issue:44977", "accept": false, - "reason": "GLM5 and Qwen3.5 flash-attention failures are different model-specific bugs." + "reason": "Different models and failures: GLM5 versus Qwen3.5 flash-attention generation." }, { "left": "issue:45313", "right": "issue:45357", "accept": false, - "reason": "ZeRO-3 weight loading for language_model and save_pretrained visual-key corruption are different code paths." + "reason": "Different parts of Qwen3.5 and different operations: ZeRO-3 language_model loading versus save_pretrained visual-encoder key handling." }, { "left": "issue:44451", "right": "issue:44488", - "accept": true, - "reason": "Both are model-loading regressions for different BERT checkpoints and appear to stem from the same underlying loading bug." + "accept": false, + "reason": "Both are model-loading failures, but they target different BERT models and there is not enough evidence they are the same bug." }, { "left": "issue:43644", "right": "issue:44534", "accept": true, - "reason": "These are the same non-persistent-buffer corruption regression; the titles are near-paraphrases." + "reason": "Exact same Transformers v5 non-persistent-buffer junk-fill regression; only the version wording differs." }, { "left": "issue:41720", "right": "issue:42915", "accept": false, - "reason": "Auto device mapping cuda assert and FineGrainedFP8Config failure are unrelated." + "reason": "Different Qwen3 issues with different triggers: auto device mapping cudaErrorAssert versus FineGrainedFP8Config." }, { "left": "issue:42491", "right": "issue:45276", "accept": false, - "reason": "Qwen3-MoE LoRA compatibility and Gemma4 resize_token_embeddings behavior are different bugs." + "reason": "Unrelated: Qwen3-MoE LoRA compatibility versus Gemma4 resize_token_embeddings behavior." }, { "left": "issue:43708", "right": "issue:44075", "accept": false, - "reason": "Checkpoint resume max_steps math and SGD args not being used are unrelated trainer/optimizer issues." + "reason": "Trainer resume/max_steps logic is unrelated to SGD optimizer arguments being ignored." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays mostly conservative. The accepted duplicate pairs are plausible from the titles alone, and the rejected pairs are appropriately cautious. Canonicalizing issue:43646 over issue:43645 is also reasonable because it is the broader title." + "feedback": "The summary is grounded in the packet, and the only positive soft-edge calls are stated conservatively enough. The canonical/best issue choice for the non-persistent-buffer regression is well supported by the titles, and the other pairwise rejections stay within the evidence shown." }, "evaluator_used": true, "retried": false, @@ -1918,7 +1945,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36010", "issue:39404", @@ -1994,8 +2021,8 @@ "issue:45663|issue:45759", "issue:43335|issue:45663", "issue:45663|issue:45859", - "issue:43873|issue:44387", "issue:44155|issue:45823", + "issue:43873|issue:44387", "issue:44291|issue:44756", "issue:44960|issue:46050", "issue:44292|issue:44912", @@ -2004,14 +2031,14 @@ "issue:45276|issue:45292", "issue:45684|issue:45698" ], - "prepared_review_unit_hash": "31da5553bf7546f0369397bb0f7d36b8328e025d5cf6d029296bb4e5d23c5287", + "prepared_review_unit_hash": "b314310e515c24e48a901e5d506201e7460d2b59cde7f81c3807e6e22a3d867f", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, @@ -2026,217 +2053,214 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose thematic bucket of Transformers regressions (model loading, tokenizer handling, quantization, save/load, offloading), not a set of true duplicates. None of the soft pairs look close enough to merge into one issue or one PR.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "Mostly unrelated closed issues about different regressions. The only clear duplicate family is the resize_token_embeddings/output_embeddings reports; the rest are distinct bugs or model-specific failures.", + "confidence": 0.81, + "canonical_issue_reason": "issue:45292 is the broadest, most model-agnostic report of the resize_token_embeddings/output_embeddings regression, so it best serves as the umbrella issue for the related model-specific reports.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:45292 is the best global representative because it states the core API-level symptom without narrowing to one architecture, while the others in that family are narrower manifestations.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43854", "right": "issue:43931", "accept": false, - "reason": "Both are load failures, but they involve different models and different symptoms (unit-test loading vs weight-shape mismatch)." + "reason": "Different models and different loading failures; no shared concrete bug path." }, { "left": "issue:42915", "right": "issue:44756", "accept": false, - "reason": "One is Qwen3Moe FP8 config failure; the other is a Strix Halo mmap/OOM workaround. Only broad memory/infra overlap." + "reason": "Qwen3 MoE FP8 conversion failure vs Strix Halo mmap/OOM workaround; unrelated causes." }, { "left": "issue:45488", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different model families and different tokenizer paths." + "reason": "Both are tokenizer regressions, but the affected models and failure modes differ too much to be the same bug." }, { "left": "issue:39692", "right": "issue:43994", "accept": false, - "reason": "Same SigLIP2 family, but one is a broken docs example and the other is bad model/pipeline outputs; not the same bug." + "reason": "Doc/example errors for SigLIP2 vs nonsensical inference results; not the same underlying issue." }, { "left": "issue:43257", "right": "issue:43854", "accept": false, - "reason": "Different models and different failure modes; only a broad loading/compatibility theme." + "reason": "Qwen3 MoE deepspeed/accelerate weight conversion issue is unrelated to GLM-4.7 Flash model loading." }, { "left": "issue:43856", "right": "issue:43873", "accept": false, - "reason": "Both mention memory/quantization, but one is training-memory inefficiency and the other is offloading misbehavior." + "reason": "Separate memory-related problems: training memory usage vs quantization/offload behavior." }, { "left": "issue:42491", "right": "issue:43931", "accept": false, - "reason": "Different Qwen-related issues: LoRA compatibility across versions vs a specific VL model loading mismatch." + "reason": "LoRA checkpoint compatibility on hf4.x/hf5.x is unrelated to the Qwen3-VL weight-shape mismatch." }, { "left": "issue:43644", "right": "issue:43645", "accept": false, - "reason": "Both are Transformers 5.0 regressions, but one is non-persistent buffer initialization and the other is Jupyter custom-model initialization." + "reason": "Different regressions in 5.0.0: buffer initialization vs Jupyter custom model initialization." }, { "left": "issue:43856", "right": "issue:44387", "accept": false, - "reason": "Both concern memory, but one is Qwen3 MoE training efficiency and the other is int4 quantization reserved-memory growth." + "reason": "Both mention memory, but one is Qwen3 MoE training memory and the other is int4 reserved-memory/OOM behavior." }, { "left": "issue:44910", "right": "issue:45588", "accept": false, - "reason": "Both involve flash attention, but one is a Qwen3.5 packed-sequence crash and the other is an AttributeError on sink-less models." + "reason": "Flash-attention crash from misread 3D position_ids is a different code path than the s_aux=None AttributeError." }, { "left": "issue:42491", "right": "issue:45292", "accept": false, - "reason": "Different problems: LoRA model portability across branches versus resize_token_embeddings not updating outputs." + "reason": "Qwen3 MoE hf4.x/hf5.x compatibility is unrelated to resize_token_embeddings not updating output_embeddings." }, { "left": "issue:45362", "right": "issue:45406", "accept": false, - "reason": "Different components and failures: chat crash on Qwen3.5-35B vs Gemma4Processor missing _tokenizer in serve." + "reason": "Different models and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer." }, { "left": "issue:44488", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer/model-load complaints, but they hit different models and likely different tokenizer metadata issues." + "reason": "Two tokenizer-loading failures on different models; no evidence of the same root cause." }, { "left": "issue:45276", "right": "issue:45335", - "accept": false, - "reason": "Very similar wording, but the affected architectures and embedding targets differ; not enough evidence of one shared root bug." + "accept": true, + "reason": "Both describe the same resize_token_embeddings regression failing to propagate to nested output/decoder embeddings in composite model classes." }, { "left": "issue:36010", "right": "issue:39404", "accept": false, - "reason": "ImportError for GenerationMixin is unrelated to the Whisper return_language pipeline regression." + "reason": "An import error for GenerationMixin is unrelated to Whisper pipeline return_language behavior." }, { "left": "issue:44164", "right": "issue:44291", "accept": false, - "reason": "Both touch model loading/saving, but extra_state handling and init_empty_weights/_is_hf_initialized are distinct code paths." + "reason": "save/from_pretrained extra_state handling and init_empty_weights argument handling are separate serialization/loading bugs." }, { "left": "issue:43404", "right": "issue:43454", "accept": false, - "reason": "Both are weight-tying bugs, but in different model classes and with different breakage surfaces." + "reason": "Both are untied lm_head reports, but they target different model implementations and no concrete shared code path is evident." }, { "left": "issue:43425", "right": "issue:43957", "accept": false, - "reason": "Torch version incompatibility and meta-device loading breakage are separate regressions." + "reason": "Torch 2.10 compatibility and meta-device loading regressions are different issues." }, { "left": "issue:44402", "right": "issue:44488", "accept": false, - "reason": "Tokenizer vocab inconsistency is not the same as a model failing to load in current version." + "reason": "Tokenizer vocab-size mismatch in one model is not the same as sleng-bert failing to load." }, { "left": "issue:39692", "right": "issue:44960", "accept": false, - "reason": "SigLIP2 docs/model issues are unrelated to the generic GLM5 issue." + "reason": "SigLIP2 example/runtime issues are unrelated to the GLM5 report." }, { "left": "issue:42947", "right": "issue:45704", "accept": false, - "reason": "Gradient checkpointing with LoRA and an apex RMSNorm memory leak are unrelated." + "reason": "Gradient checkpointing with PEFT LoRA is a different bug than T5's apex.FusedRMSNorm memory leak." }, { "left": "issue:45663", "right": "issue:45759", "accept": false, - "reason": "Different composite-model bugs: FSDP2 attention state vs from_config not unwrapping text_config." + "reason": "Gemma4 FSDP2 shared_kv_states bug and Qwen multimodal config unwrapping are distinct code paths." }, { "left": "issue:43335", "right": "issue:45663", "accept": false, - "reason": "Sparse-layer creation in SwitchTransformers is unrelated to Gemma4 FSDP2 attention state handling." + "reason": "SwitchTransformers sparse-layer config bug is unrelated to the Gemma4 attention KeyError." }, { "left": "issue:45663", "right": "issue:45859", "accept": false, - "reason": "Different Gemma/Qwen offload bugs with different failing functions and causes." + "reason": "FSDP2 attention-state rebuilding and CPU-offload rotary embedding compatibility are separate issues." }, { - "left": "issue:43873", - "right": "issue:44387", + "left": "issue:44155", + "right": "issue:45823", "accept": false, - "reason": "Both involve offloading/quantization performance, but one is generic offloading behavior and the other is a reserved-memory/OOM regression." + "reason": "AudioFlamingo3 batched inference leakage is unrelated to Gemma4 PLE device mismatch." }, { - "left": "issue:44155", - "right": "issue:45823", + "left": "issue:43873", + "right": "issue:44387", "accept": false, - "reason": "AudioFlamingo3 batched inference leak is unrelated to Gemma4 PLE device placement." + "reason": "Quantization offloading behavior and increased reserved memory/OOM are not the same bug." }, { "left": "issue:44291", "right": "issue:44756", "accept": false, - "reason": "Unexpected init arg during meta loading and disabling mmap for Strix Halo are unrelated fixes." + "reason": "init_empty_weights argument handling is unrelated to disabling mmap on Strix Halo." }, { "left": "issue:44960", "right": "issue:46050", "accept": false, - "reason": "Different models and different persistence bugs; one is GLM5, the other is sinq quantized save/load." + "reason": "GLM5 is a model-specific report; sinq save/load corruption is a different serialization bug." }, { "left": "issue:44292", "right": "issue:44912", "accept": false, - "reason": "Both are quantization issues, but NVFP4 load failure and MXFP4 fallback to bf16 are not the same bug." + "reason": "NVFP4 load failure and MXFP4 fallback are distinct quantization-format problems." }, { "left": "issue:43854", "right": "issue:45216", "accept": false, - "reason": "Both are model correctness/load regressions, but they concern different models and different APIs." + "reason": "GLM-4.7 Flash unit-test loading failure is unrelated to the Qwen3.5 save_pretrained regression." }, { "left": "issue:44387", "right": "issue:44756", "accept": false, - "reason": "OOM under int4 quantization and disabling mmap on Strix Halo are different memory issues." + "reason": "Int4 reserved-memory OOM and Strix Halo mmap OOM have different triggers and fixes." }, { "left": "issue:45276", "right": "issue:45292", - "accept": false, - "reason": "Closely related wording, but the model-specific embedding targets differ and there is no clear shared failing code path." - }, - { - "left": "issue:45684", - "right": "issue:45698", - "accept": false, - "reason": "Both are save_pretrained-related, but one is file permission propagation and the other is wrong custom-module loading after save/load." + "accept": true, + "reason": "Both report the same resize_token_embeddings regression; 45292 is the generic output_embeddings case and 45276 is the Gemma4-specific manifestation." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The packet supports 45292 as the broad resize_token_embeddings/output_embeddings umbrella issue, with 45276 and 45335 as model-specific manifestations. The other soft-edge rejections stay conservative by leaning on distinct models/failure modes rather than claiming exact causality." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -2251,7 +2275,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36032", "issue:39404", @@ -2322,8 +2346,8 @@ "issue:43425|issue:45823", "issue:43906|issue:44530", "issue:43425|issue:43716", - "issue:43611|issue:43645", "issue:39404|issue:45701", + "issue:43611|issue:43645", "issue:44530|issue:45084", "issue:43901|issue:44509", "issue:44265|issue:44898", @@ -2333,24 +2357,24 @@ "issue:44589|issue:45084", "issue:43299|issue:43931", "issue:43596|issue:44683", - "issue:44164|issue:45759", "issue:43994|issue:44079", + "issue:44164|issue:45759", "issue:36032|issue:43452" ], - "prepared_review_unit_hash": "4696607f846c4c52879baddee89bafacd6faca021eaec703c22cef37578d92f7", + "prepared_review_unit_hash": "09c00895000605ec566f40ee6fedafd4ac2cb89fc6a32d1055a49568b35e19e3", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37722, + "serialized_chars": 37721, "estimated_input_tokens": 9431, "estimated_eval_tokens": 19118 }, @@ -2359,96 +2383,96 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab-bag of unrelated Transformers regressions. The only clear duplicate pair is the resize_token_embeddings/output-embedding bug (generic vs t5gemma-specific). No PRs are present.", - "confidence": 0.69, - "canonical_issue_reason": "issue:45292 is the best canonical issue because it states the broad, underlying bug generically: resize_token_embeddings does not propagate to output embeddings. issue:45335 looks like a narrower model-specific instance of the same problem.", + "summary": "The cluster is mostly a set of unrelated Transformers issues with one clear duplicate pair around `resize_token_embeddings` not propagating to downstream embeddings. No PRs are present.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45292 is the broadest, most general statement of the duplicate bug (`resize_token_embeddings` not updating output embeddings); issue:45335 looks like a model-specific instance of the same propagation problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45292 is the strongest representative of the only true duplicate pair in the cluster and is broader than the t5gemma-specific report.", + "best_issue_reason": "issue:45292 is the best cluster representative because it describes the underlying bug in generic terms rather than a single model variant.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43381", "right": "issue:44928", "accept": false, - "reason": "Both mention gradient checkpointing/Qwen3.5, but the failures are different: eval-mode restriction vs RLHF NaN from 3D position_ids/SDPA fallback." + "reason": "Both mention training/gradient behavior, but one is about gradient checkpointing in eval mode and the other about NaNs from Qwen3.5 SDPA fallback; different failure modes." }, { "left": "issue:42947", "right": "issue:43381", "accept": false, - "reason": "Related theme, but one is LoRA + gradient checkpointing being ineffective and the other is gradient checkpointing being disallowed in eval mode; different bugs." + "reason": "Both involve gradient checkpointing, but one is about ineffective LoRA checkpointing and the other about eval-mode misuse; not the same bug." }, { "left": "issue:44164", "right": "issue:44756", "accept": false, - "reason": "save/from_pretrained extra_state handling and disabling mmap for Strix Halo OOM are unrelated issues." + "reason": "`save/from_pretrained` extra_state handling and Strix Halo mmap OOM are unrelated issues." }, { "left": "issue:44479", "right": "issue:44877", "accept": false, - "reason": "Qwen video-input regression and granite_speech strict-config loading are different subsystems and symptoms." + "reason": "Different regressions: video input behavior for Qwen VL models vs strict config loading for granite_speech." }, { "left": "issue:41720", "right": "issue:44155", "accept": false, - "reason": "Qwen3 auto device-map cuda assert is unrelated to AudioFlamingo3 embedding/token leakage across tracks." + "reason": "Qwen3 auto device mapping CUDA assert and AudioFlamingo3 batched inference token/embedding leakage are unrelated." }, { "left": "issue:45588", "right": "issue:45663", "accept": false, - "reason": "flash_attention s_aux=None crash and Gemma4 FSDP2 shared_kv_states KeyError are different code paths." + "reason": "Both touch attention-related code, but one is a flash_attention sinkless-model crash and the other is a Gemma4 FSDP2 shared_kv_states bug." }, { "left": "issue:43957", "right": "issue:44756", "accept": false, - "reason": "meta-device loading breakage and Strix Halo mmap OOM are distinct problems." + "reason": "Meta-device loading failures and mmap/OOM on Strix Halo are different problems with different triggers." }, { "left": "issue:43646", "right": "issue:43708", "accept": false, - "reason": "Custom model initialization in Transformers 5.0 and Trainer resume_from_checkpoint max_steps calculation are unrelated." + "reason": "Custom model initialization and Trainer resume/max_steps calculation are unrelated." }, { "left": "issue:45292", "right": "issue:45335", "accept": true, - "reason": "Same underlying bug: resize_token_embeddings does not update the model's output embeddings, with 45335 being a t5gemma-specific instance." + "reason": "Same underlying bug: `resize_token_embeddings` does not propagate to the model's output embeddings; 45335 is the t5gemma-specific manifestation." }, { "left": "issue:43828", "right": "issue:43957", "accept": false, - "reason": "Autocast dtype mismatch for Phi-tiny-MoE is unrelated to meta-device loading failures." + "reason": "Both are dtype/device-ish loading issues, but one is autocast on Phi-tiny-MoE and the other is meta-device loading breakage; not the same root cause." }, { "left": "issue:44402", "right": "issue:44451", "accept": false, - "reason": "Tokenizer vocab-size mismatch and failure to load ScandiBERT are different model-loading issues." + "reason": "Different tokenizer/model-loading problems for different checkpoints; no clear shared code-path." }, { "left": "issue:43645", "right": "issue:44164", "accept": false, - "reason": "Notebook custom-model initialization and extra_state save/load failure are not the same underlying bug." + "reason": "Jupyter/custom-model initialization is unrelated to save/from_pretrained extra_state handling." }, { "left": "issue:43425", "right": "issue:43828", "accept": false, - "reason": "Torch 2.10 incompatibility is too broad and distinct from the Phi-tiny-MoE autocast dtype mismatch." + "reason": "Torch version incompatibility and autocast dtype mismatch are different issues." }, { "left": "issue:43257", "right": "issue:44863", "accept": false, - "reason": "Qwen3 MOE conversion with accelerate+deepspeed and NemotronH checkpoint loading are different failures." + "reason": "Both concern model loading, but one is Qwen3 MOE conversion with accelerate+deepspeed and the other is NemotronH checkpoint loading; too different." }, { "left": "issue:44683", @@ -2460,115 +2484,115 @@ "left": "issue:44589", "right": "issue:44756", "accept": false, - "reason": "Float8 storage deserialization and Strix Halo mmap OOM do not describe the same bug." + "reason": "Float8 storage lookup and Strix Halo mmap OOM are different low-level failures." }, { "left": "issue:43425", "right": "issue:45823", "accept": false, - "reason": "A general Torch 2.10 incompatibility is not the same as Gemma4 PLE's device_map=\"auto\" forward mismatch." + "reason": "Torch 2.10 incompatibility and Gemma4 PLE device-map forward mismatch are not the same bug." }, { "left": "issue:43906", "right": "issue:44530", "accept": false, - "reason": "An isolated reproduction of another issue is not enough to merge with a PagedAttentionCache linear_attention crash; the underlying bug is unclear." + "reason": "An isolated reproduction of an older issue and a Qwen3.5 PagedAttentionCache crash are unrelated." }, { "left": "issue:43425", "right": "issue:43716", "accept": false, - "reason": "Torch version incompatibility and Mistral-3 image-preprocessor/model dtype mismatch are different problems." + "reason": "Generic torch incompatibility versus Mistral-3 image preprocessor/model dtype mismatch; different symptoms and code paths." }, { - "left": "issue:43611", - "right": "issue:43645", + "left": "issue:39404", + "right": "issue:45701", "accept": false, - "reason": "base_model_prefix loading failure and Jupyter notebook custom-model initialization differ in trigger and failure mode." + "reason": "Whisper pipeline `return_language` regression and generic tokenization changes across versions are not the same issue." }, { - "left": "issue:39404", - "right": "issue:45701", + "left": "issue:43611", + "right": "issue:43645", "accept": false, - "reason": "Whisper return_language pipeline regression and tokenization changes across versions are not the same issue." + "reason": "`base_model_prefix` loading and custom model initialization in notebooks are different model-construction failures." }, { "left": "issue:44530", "right": "issue:45084", "accept": false, - "reason": "PagedAttentionCache invalid group type linear_attention is unrelated to the non-template-nodes compile error." + "reason": "Qwen3.5 PagedAttentionCache crash and non-template-node compilation error are unrelated." }, { "left": "issue:43901", "right": "issue:44509", "accept": false, - "reason": "Both touch docs/pipeline wording, but they concern different removed/renamed tasks and behaviors." + "reason": "Both are docs-related, but they concern different pipeline API removals/behavior changes." }, { "left": "issue:44265", "right": "issue:44898", "accept": false, - "reason": "torch.export/export with torch_compilable_check and Perceiver non-default-resolution failure are different bugs." + "reason": "`torch.export.export` with `torch_compilable_check` and Perceiver interpolation failure are different model/export issues." }, { "left": "issue:39404", "right": "issue:44912", "accept": false, - "reason": "Whisper pipeline return_language and MXFP4 quantization fallback on git-oss-20b are unrelated." + "reason": "Whisper pipeline `return_language` regression and MXFP4 quantization fallback are unrelated." }, { "left": "issue:44479", "right": "issue:44805", "accept": false, - "reason": "A Qwen video-input regression and a generic mask shape IndexError are too different to treat as duplicates." + "reason": "Video-input regression for VL models and a mask shape IndexError are different bugs." }, { "left": "issue:43425", "right": "issue:44918", "accept": false, - "reason": "Torch 2.10 incompatibility is not the same as Qwen3.5 input-embedding unpacking failure with TRL SFT trainer." + "reason": "Torch version incompatibility and Qwen3.5 SFT embedding unpacking are unrelated." }, { "left": "issue:44589", "right": "issue:45084", "accept": false, - "reason": "Float8 storage lookup failure and compile-time non-template-node error are unrelated." + "reason": "Float8 storage lookup failure and template-node compilation error are not the same issue." }, { "left": "issue:43299", "right": "issue:43931", "accept": false, - "reason": "Both are Qwen3-VL loading failures, but one is a dev0 regression and the other is a specific weight-shape mismatch; not enough evidence they are the same bug." + "reason": "Both are Qwen3-VL loading problems, but one is a broad 5.0.0.dev0 regression and the other is a specific weight-shape mismatch; not enough evidence of one root cause." }, { "left": "issue:43596", "right": "issue:44683", "accept": false, - "reason": "ZeRO-3/BertModel index error and compiled flex_attention on newer torch versions are unrelated." + "reason": "Deepspeed zero3/BertModel index error and compiled flex_attention failure are unrelated." }, { - "left": "issue:44164", - "right": "issue:45759", + "left": "issue:43994", + "right": "issue:44079", "accept": false, - "reason": "extra_state save/load and unwrap text_config in from_config are different model-loading/saving problems." + "reason": "Siglip2 nonsensical outputs and ModelOutput key assignment bug are different problem classes." }, { - "left": "issue:43994", - "right": "issue:44079", + "left": "issue:44164", + "right": "issue:45759", "accept": false, - "reason": "Siglip2 nonsensical outputs and ModelOutput key assignment are different behaviors with no clear shared cause." + "reason": "`extra_state` save/load handling and `from_config` not unwrapping `text_config` are separate model-serialization issues." }, { "left": "issue:36032", "right": "issue:43452", "accept": false, - "reason": "Tokenizer method-name conflict during T5 loading and gguf_file from_pretrained breakage are separate loading issues." + "reason": "T5Tokenizer `add_special_tokens` conflict and gguf_file loading breakage are unrelated tokenizer/loading problems." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate pair, issue:45292 vs issue:45335, is strongly supported by near-identical resize_token_embeddings wording, and the remaining soft-edge pairs are reasonably rejected as different bugs. No PRs are present, so the canonical-pr fields being null is appropriate." + "feedback": "The summary is grounded in the packet: all items are issues, no PRs are present, and the only clearly supported duplicate pair is 45292/45335. The soft-edge verdicts are conservative overall and do not overstate evidence." }, "evaluator_used": true, "retried": false, @@ -2587,7 +2611,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:32090", "issue:34567", @@ -2660,25 +2684,25 @@ "issue:44811|issue:45584", "issue:43883|issue:44488", "issue:44451|issue:44987", - "issue:44464|issue:45987", "issue:43452|issue:43482", + "issue:44464|issue:45987", "issue:43541|issue:45084", - "issue:43644|issue:43646", "issue:42915|issue:44530", + "issue:43644|issue:43646", "issue:43317|issue:43482", "issue:44849|issue:45325", "issue:36032|issue:43645", "issue:45084|issue:45507", "issue:43262|issue:43377" ], - "prepared_review_unit_hash": "c4c498b8c2d1438521f7b4d8a916dd8b5d1d14a6a28a153822e43e7c47fa02d3", + "prepared_review_unit_hash": "4c9688ded8c9c32783ebbfbf6902f62ed98daedbd1667a764c990fd0812ae46b", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, @@ -2693,186 +2717,204 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: many items are unrelated model-/feature-specific regressions, with only a couple of likely duplicate subpairs. The strongest coherent subcluster is around Transformers v5 custom model initialization, but there is no single perfect canonical across the whole set.", - "confidence": 0.34, - "canonical_issue_reason": "Use issue 43646 as the representative issue: it is the broadest, most generic v5 regression in the set and best fits the custom-model-initialization subcluster that also includes nearby reports.", + "summary": "The set is mostly heterogeneous across unrelated model, tokenizer, audio, cache, and training regressions. I only see one likely duplicate pair: the GGUF loading regression in issue:43452 and issue:43482.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43452 is the broader, more generic GGUF/from_pretrained loading regression; issue 43482 looks like a model-specific manifestation of the same failure.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43646 is the best overall representative for the largest coherent subcluster; its title is generic enough to cover the related v5 initialization regressions better than the narrower symptom reports.", + "best_issue_reason": "Issue 43452 is the best representative issue because it describes the underlying loader breakage in a general way and can subsume the more specific Qwen2.5-GGUF report.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39404", "right": "issue:44671", "accept": false, - "reason": "Different bugs and code paths: Whisper pipeline return_language behavior vs CamemBERT masked-LM prediction quality." + "reason": "Different models and failures: Whisper pipeline return_language vs CamemBERT masked-LM predictions." }, { "left": "issue:43856", "right": "issue:44756", "accept": false, - "reason": "Both mention performance/memory, but one is Qwen3 MoE training inefficiency and the other is Strix Halo mmap OOM; not the same bug." + "reason": "Both involve performance/memory, but one is Qwen3 MoE training inefficiency and the other is Strix Halo mmap OOM." }, { "left": "issue:44991", "right": "issue:45081", "accept": false, - "reason": "Both are loading failures, but one is tokenizer loading for EMBEDDIA/est-roberta and the other is a Mistral regex patch crash; different root causes." + "reason": "Both are tokenizer-related regressions, but they hit different code paths and different models." }, { "left": "issue:44671", "right": "issue:44991", "accept": false, - "reason": "One is incorrect MLM predictions, the other is tokenizer loading failure; no shared underlying change is evident." + "reason": "Both are v5 tokenizer/model-loading complaints, but the concrete bug and affected model differ." }, { "left": "issue:44737", "right": "issue:45859", "accept": false, - "reason": "Different device-placement bugs in different models: XLNet CPU arange regression vs Qwen3.5 MoE CPU-offload incompatibility." + "reason": "Both mention device/offload behavior, but XLNet CPU arange vs Qwen3.5Moe rotary embedding are separate bugs." }, { "left": "issue:32090", "right": "issue:39404", "accept": false, - "reason": "Trainer GPU broadcast TypeError is unrelated to Whisper pipeline return_language regression." + "reason": "Trainer broadcast NoneType error is unrelated to Whisper pipeline return_language behavior." }, { "left": "issue:44164", "right": "issue:44479", "accept": false, - "reason": "save/from_pretrained extra_state handling and video-input regression are unrelated." + "reason": "save/from_pretrained extra_state handling is unrelated to the Qwen video-input regression." }, { "left": "issue:44661", "right": "issue:44683", "accept": false, - "reason": "Tokenizer mapping feature bug vs compiled flex_attention failure on torch>=2.9; different subsystems and fixes." + "reason": "Tokenizer mapping/new-model registration is unrelated to compiled flex_attention failing on torch >= 2.9." }, { "left": "issue:44488", "right": "issue:45081", "accept": false, - "reason": "Both are model-loading complaints, but they target different models and different failure modes; too broad to call duplicates." + "reason": "Different model-loading failures: BERT tokenizer load vs Mistral regex patch crash." }, { "left": "issue:43582", "right": "issue:43632", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError is unrelated to the _is_hf_initialized regression." + "reason": "AppleSilicon allocator warmup TypeError and _is_hf_initialized regression are different initialization bugs." }, { "left": "issue:43611", "right": "issue:43644", "accept": false, - "reason": "base_model_prefix loading regression and non-persistent buffer junk are different initialization/loading issues." + "reason": "base_model_prefix loading breaks vs non-persistent buffers being junk are distinct v5 regressions." }, { "left": "issue:40990", "right": "issue:43421", "accept": false, - "reason": "Perplexity regression on a model/dataset pair is unrelated to runtime special-token post-processor updates." + "reason": "High perplexity on gpt-oss is unrelated to runtime post-processor updates in TokenizersBackend." }, { "left": "issue:43716", "right": "issue:45084", "accept": false, - "reason": "Image preprocessor dtype mismatch and template-node compilation failure are different code paths." + "reason": "Mistral-3 dtype mismatch in the image preprocessor is unrelated to template-node compilation errors." }, { "left": "issue:44206", "right": "issue:44220", - "accept": true, - "reason": "These look like the same audio feature-extraction bug: the feature extractor/helper path crashes around the unsupported center argument in fbank extraction." + "accept": false, + "reason": "Both are audio-feature issues, but one is an unsupported center argument and the other is a different fbank-extraction problem." }, { - "left": "issue:44451", + "left": "issue:44488", "right": "issue:44987", "accept": false, - "reason": "Both are loading regressions, but for different models and different symptoms; no evidence of a shared underlying bug." + "reason": "Both are model load failures, but they affect different models and appear to stem from different regressions." }, { - "left": "issue:44464", - "right": "issue:45987", + "left": "issue:43643", + "right": "issue:44530", "accept": false, - "reason": "Chunked-generation inconsistency under compiled forward is unrelated to StaticCache.get_seq_length returning a tensor instead of int." + "reason": "AutoConfig missing fields with trust_remote_code is unrelated to PagedAttentionCache linear_attention group handling." }, { - "left": "issue:43452", - "right": "issue:43482", - "accept": true, - "reason": "Both point to the same GGUF/from_pretrained loading regression in Transformers v5, affecting tokenizer/model loading through the gguf_file path." + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and Qwen2.5-VL multi-image IterableDataset failures are unrelated." }, { - "left": "issue:43317", - "right": "issue:43482", + "left": "issue:36032", + "right": "issue:42915", "accept": false, - "reason": "device_map gpu+cpu offload dequantization failure is a different problem from GGUF loading failure." + "reason": "T5 tokenizer method conflict is unrelated to Qwen3Moe FineGrainedFP8Config failure." }, { - "left": "issue:44849", - "right": "issue:45325", + "left": "issue:44811", + "right": "issue:45584", "accept": false, - "reason": "Qwen3.5 hidden-states bug and Qwen2.5-VL rope-index scaling bug are distinct model behaviors." + "reason": "Both are Whisper issues, but batch_decode skip_special_tokens and empty-transcription generation after align_special_tokens are different bugs." }, { - "left": "issue:36032", - "right": "issue:43645", + "left": "issue:43883", + "right": "issue:44488", "accept": false, - "reason": "Tokenizer method-name conflict and Jupyter custom-model initialization breakage are not the same bug." + "reason": "Molmo tied-weights metadata error is unrelated to the sleng-bert loading failure." }, { - "left": "issue:45084", - "right": "issue:45507", + "left": "issue:44451", + "right": "issue:44987", "accept": false, - "reason": "Can't compile non-template nodes is unrelated to GraniteMoEHybrid calling an invalid method." + "reason": "Different models and different failure modes: loading physical-intelligence/fast vs tokenizer loading for EMBEDDIA/est-roberta." }, { - "left": "issue:43644", - "right": "issue:43646", + "left": "issue:43452", + "right": "issue:43482", + "accept": true, + "reason": "Both point to the same GGUF loading regression in transformers v5; 43482 is a specific instance of the broader 43452 bug." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is not the same as StaticCache.get_seq_length returning the wrong type." + }, + { + "left": "issue:43541", + "right": "issue:45084", "accept": false, - "reason": "Related v5 initialization area, but one is specifically about non-persistent buffers being filled with junk while the other is a broader custom-model-init failure; not enough to merge as the same bug." + "reason": "Mixtral grouped_mm tracing errors and non-template-node compilation errors are different compiler failures." }, { "left": "issue:42915", "right": "issue:44530", "accept": false, - "reason": "FineGrainedFP8Config failure in Qwen3Moe training and PagedAttentionCache linear_attention crash are different issues." + "reason": "Qwen3Moe FP8 config failure and Qwen3.5 PagedAttentionCache linear_attention crash are separate issues." }, { - "left": "issue:43643", - "right": "issue:44530", + "left": "issue:43644", + "right": "issue:43646", "accept": false, - "reason": "trust_remote_code missing fields and PagedAttentionCache group-type crash are unrelated." + "reason": "Both are v5 custom-model regressions, but non-persistent-buffer corruption is not the same bug as custom model initialization breaking." }, { - "left": "issue:34567", - "right": "issue:40444", + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "GPU+CPU offload dequantized-model loading and GGUF loading failure are different loader paths." + }, + { + "left": "issue:44849", + "right": "issue:45325", "accept": false, - "reason": "TrainerState token counting and Qwen2.5-VL iterable-dataset multi-image finetuning are different bugs." + "reason": "Qwen3.5 hidden-state output bug is unrelated to Qwen2.5-VL rope index scaling." }, { "left": "issue:36032", - "right": "issue:42915", + "right": "issue:43645", "accept": false, - "reason": "T5 tokenizer special-token method conflict is unrelated to Qwen3Moe FineGrainedFP8Config failure." + "reason": "Tokenizer special-token method conflict is unrelated to Jupyter custom-model initialization breakage." }, { - "left": "issue:44811", - "right": "issue:45584", + "left": "issue:45084", + "right": "issue:45507", "accept": false, - "reason": "Whisper batch_decode skip_special_tokens behavior and empty-transcription generation after align_special_tokens are not the same underlying bug." + "reason": "TypeError compiling non-template nodes is unrelated to GraniteMoEHybrid calling an invalid method." }, { - "left": "issue:43883", - "right": "issue:44488", + "left": "issue:43262", + "right": "issue:43377", "accept": false, - "reason": "Missing all_tied_weights_keys and loading failure for cjvt/sleng-bert are different model-loading regressions." + "reason": "Default 16 kHz sampling-rate behavior is unrelated to MIMI encoder padding-mask differences between batched and single inputs." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded and conservative overall. The summary correctly treats the set as mostly heterogeneous, and the two accepted soft pairs look like plausible same-bug duplicates from the packet titles/descriptions. The representative-issue choice for 43646 is a reasonable, cautious canonicalization for the custom-model-initialization subcluster." + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, issue:43452 and issue:43482, is plausibly the same GGUF/from_pretrained loading regression at different specificity levels. The other rejections are appropriately cautious given the differing models, code paths, or failure modes." }, "evaluator_used": true, "retried": false, @@ -2891,7 +2933,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36032", "issue:40990", @@ -2955,8 +2997,8 @@ "issue:42915|issue:45084", "issue:44265|issue:44610", "issue:43645|issue:44534", - "issue:44451|issue:45081", "issue:44220|issue:44683", + "issue:44451|issue:45081", "issue:44987|issue:45081", "issue:45216|issue:45357", "issue:43404|issue:45127", @@ -2967,244 +3009,244 @@ "issue:42915|issue:44589", "issue:43296|issue:43531", "issue:43531|issue:44877", - "issue:43611|issue:44534", "issue:43425|issue:44403", + "issue:43611|issue:44534", "issue:44479|issue:45325", "issue:36032|issue:41720", "issue:42175|issue:45542", - "issue:40990|issue:44811", "issue:43792|issue:44589", + "issue:40990|issue:44811", "issue:44683|issue:45020" ], - "prepared_review_unit_hash": "146035a3b65a31aaaa0a84c885d83089462d41aa5ee67b31a000e91ef663881b", + "prepared_review_unit_hash": "d7489c19b3c0a91abeb8ce834fa41852b906dcb3e969c7cd2ea8eb0a26510f30", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37219, - "estimated_input_tokens": 9305, - "estimated_eval_tokens": 18866 + "serialized_chars": 37214, + "estimated_input_tokens": 9304, + "estimated_eval_tokens": 18864 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a mixed cluster of unrelated Transformers v5/v5.x regressions with only one clearly grounded duplicate pair. The Qwen3.5 save_pretrained pair is solid, but the Qwen video-temporal pair is too broad to merge as a duplicate from the packet alone.", - "confidence": 0.58, - "canonical_issue_reason": "Best canonical anchor is issue:45216 because it has the clearest duplicate-style match in the packet (issue:45357) and cleanly represents the Qwen3.5 save_pretrained checkpoint-serialization regression.", + "summary": "This cluster is mostly a family of Transformers v5/v5.x loading and serialization regressions across different models and code paths. Most soft pairs are related thematically but not true duplicates; only the Qwen3.5 save_pretrained regressions look like the same underlying bug.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45020 is the broadest umbrella: it frames the recent-version regressions as a general breakage of model loading/remote_code behavior, which matches the cluster\u2019s dominant theme.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45216 is the strongest representative issue in the cluster: it has a plausible same-bug counterpart, a concrete v5.4+ regression description, and clearer duplicate evidence than the broader thematic issues.", + "best_issue_reason": "issue:45020 is the best tracker candidate because it is general, user-facing, and central to the cluster of v5 loading/serialization regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43404", "right": "issue:44466", "accept": false, - "reason": "Both involve tied weights, but they describe different code paths: model definition vs. save_pretrained serialization." + "reason": "Both involve tied-weights behavior, but one is a missing tie in a specific model class and the other is device-dependent save_pretrained serialization; different bugs." }, { "left": "issue:43089", "right": "issue:45987", "accept": false, - "reason": "Unrelated performance overhead vs. seq-length contract bug." + "reason": "Generation performance/sync overhead is unrelated to the StaticCache return-type contract bug." }, { "left": "issue:43883", "right": "issue:44991", "accept": false, - "reason": "Different models and different failures; no same underlying bug is evident." + "reason": "Different failures: missing all_tied_weights_keys vs tokenizer loading for a specific checkpoint." }, { "left": "issue:44987", "right": "issue:44991", "accept": false, - "reason": "Both are load failures, but they appear to be separate model-specific regressions with different symptoms." + "reason": "Both are model-loading failures, but they concern different checkpoints and likely different root causes." }, { "left": "issue:43994", "right": "issue:44610", "accept": false, - "reason": "Vision-related, but one is nonsensical outputs and the other is an image-size preprocessing mismatch." + "reason": "Different multimodal regression types: bad results from a model/pipeline path vs processor image-size mismatch." }, { "left": "issue:43646", "right": "issue:44534", "accept": false, - "reason": "Separate v5 regressions with different mechanisms: custom model init vs. buffer initialization." + "reason": "Custom model init breakage and junk-filled buffers are separate v5 regressions." }, { "left": "issue:43322", "right": "issue:43540", "accept": false, - "reason": "Different multimodal models and different failure modes." + "reason": "Segfault while loading Llava Next is not the same as the Qwen3OmniMoe video-processing ValueError." }, { "left": "issue:44403", "right": "issue:45081", "accept": false, - "reason": "Logging/noise during loading is not the same bug as the tokenizer regex crash." + "reason": "Noise/logging during load and a tokenizer patch crash are different code-path problems." }, { "left": "issue:43377", "right": "issue:43819", "accept": false, - "reason": "Both are correctness mismatches, but they affect different architectures and forward paths." + "reason": "Both are output mismatches, but they affect different models and mechanisms (padding mask vs missing STE)." }, { "left": "issue:42915", "right": "issue:45084", "accept": false, - "reason": "Unrelated failures: FP8 config handling vs. template compilation error." + "reason": "FineGrainedFP8Config failure and template-node compilation errors are unrelated." }, { "left": "issue:44265", "right": "issue:44610", "accept": false, - "reason": "Different subsystems: exportability vs. processor image resolution." + "reason": "torch.export compatibility is unrelated to OmDet-Turbo processor resolution mismatch." }, { "left": "issue:43645", "right": "issue:44534", "accept": false, - "reason": "Notebook custom-model init breakage and junk-filled buffers are separate regressions." + "reason": "Notebook custom-model initialization and non-persistent buffer corruption are different failures." }, { - "left": "issue:44451", - "right": "issue:45081", + "left": "issue:44220", + "right": "issue:44683", "accept": false, - "reason": "Different model/tokenizer load failures with no shared code path shown." + "reason": "Audio feature extraction and compiled flex_attention failures are unrelated." }, { - "left": "issue:44220", - "right": "issue:44683", + "left": "issue:44451", + "right": "issue:45081", "accept": false, - "reason": "Audio feature extraction bug versus flex_attention compatibility bug." + "reason": "Different tokenizer/model loading failures with no clear shared code-path." }, { "left": "issue:44987", "right": "issue:45081", "accept": false, - "reason": "Separate loading failures affecting different components." + "reason": "Both are load-time failures, but for different models and different tokenizer/model code paths." }, { "left": "issue:45216", "right": "issue:45357", "accept": true, - "reason": "Same Qwen3.5 save_pretrained regression: both report incorrect checkpoint / visual-encoder key serialization on the same v5.x path." + "reason": "Both report Qwen3.5 save_pretrained regressions producing incorrect checkpoints/keys; same underlying serialization bug." }, { "left": "issue:43404", "right": "issue:45127", "accept": false, - "reason": "Both mention tied weights, but one is a tie bug and the other is LoRA merge collapse after vocab extension." + "reason": "Tied lm_head weights in a model class is different from LoRA merge collapse with extended vocabulary." }, { "left": "issue:42915", "right": "issue:44291", "accept": false, - "reason": "Both are v5-era failures, but they concern different mechanisms and models." + "reason": "FP8 config failure and init_empty_weights/_is_hf_initialized constructor breakage are separate regressions." }, { "left": "issue:43632", "right": "issue:44756", "accept": false, - "reason": "HF initialization flag regression is unrelated to the mmap/OOM workaround." + "reason": "_is_hf_initialized initialization issues are unrelated to the Strix Halo mmap/OOM mitigation request." }, { "left": "issue:36032", "right": "issue:43742", "accept": false, - "reason": "Tokenizer special-token conflict and MobileLLM key error are different load failures." + "reason": "Tokenizer add_special_tokens conflict and MobileLLM key error are different load failures." }, { "left": "issue:44062", "right": "issue:44987", "accept": false, - "reason": "Tokenizer AddedToken argument conflict is not the same as the separate model-load failure." + "reason": "AddedToken argument duplication is unrelated to the physical-intelligence/fast loading issue." }, { "left": "issue:42915", "right": "issue:44589", "accept": false, - "reason": "Different failures and code paths: FP8 config handling vs. missing Float8 storage type." + "reason": "FP8 config failure and missing Float8 storage are different low-level issues." }, { "left": "issue:43296", "right": "issue:43531", "accept": false, - "reason": "PaddleOCR-VL loading and Qwen3-MoE sliding_window behavior are unrelated." + "reason": "PaddleOCR-VL load failure in vLLM and Qwen3-MoE sliding_window behavior are unrelated." }, { "left": "issue:43531", "right": "issue:44877", "accept": false, - "reason": "Different models and problems: sliding_window behavior vs. strict config loading." + "reason": "Sliding-window behavior and strict config loading are distinct model/config regressions." }, { - "left": "issue:43611", - "right": "issue:44534", + "left": "issue:43425", + "right": "issue:44403", "accept": false, - "reason": "Broad v5 regressions, but not the same concrete bug." + "reason": "Torch version incompatibility is not the same as noisy model loading." }, { - "left": "issue:43425", - "right": "issue:44403", + "left": "issue:43611", + "right": "issue:44534", "accept": false, - "reason": "Torch version incompatibility is unrelated to loading-noise behavior." + "reason": "base_model_prefix loading breakage and non-persistent buffer junk are different v5 regressions." }, { "left": "issue:44479", "right": "issue:45325", "accept": false, - "reason": "Too broad to treat as duplicates: a general video-input regression across several models vs. a specific still-image temporal position-id scaling bug." + "reason": "The broad video-input regression and the specific still-image rope-index scaling bug are related only at a high level, not enough to merge." }, { "left": "issue:36032", "right": "issue:41720", "accept": false, - "reason": "Tokenizer load conflict and auto device-mapping CUDA assert are unrelated." + "reason": "T5 tokenizer load conflict and Qwen3 auto device-map cudaErrorAssert are unrelated." }, { "left": "issue:42175", "right": "issue:45542", "accept": false, - "reason": "Packaging/backend dependency theme is similar, but the packet does not ground them as the same bug." + "reason": "Both touch TF/backend packaging, but one is missing TensorFlow in a torch install and the other is a tensorboard-without-TF backend error." }, { - "left": "issue:40990", - "right": "issue:44811", + "left": "issue:43792", + "right": "issue:44589", "accept": false, - "reason": "High perplexity evaluation issue and Whisper batch_decode behavior are unrelated." + "reason": "Whisper runtime failure and missing Float8 storage are unrelated." }, { - "left": "issue:43792", - "right": "issue:44589", + "left": "issue:40990", + "right": "issue:44811", "accept": false, - "reason": "Whisper runtime failure and missing Float8 storage support are separate issues." + "reason": "High perplexity on gpt-oss-20b is unrelated to Whisper batch_decode skip_special_tokens behavior." }, { "left": "issue:44683", "right": "issue:45020", "accept": false, - "reason": "Compiled flex_attention torch-version breakage is unrelated to remote_code loading regressions." + "reason": "Compiled flex_attention on torch>=2.9 is a specific backend incompatibility, not the broad remote_code loading regression." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The summary is mostly grounded, but one soft-edge acceptance is too aggressive for a conservative cluster evaluation. `issue:44479` and `issue:45325` are both in the Qwen VL/video-temporal area, but the packet only shows a broad thematic relationship: one is a general video-input regression across several models, while the other is a specific still-image `tokens_per_second` / `get_rope_index` position-id bug. That is not enough evidence that they are the same bug or mergeable into one fix. The `issue:45216` / `issue:45357` match looks plausible, but the cluster should be rejected because not every accepted pair is sufficiently grounded in the packet." + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:45216 vs issue:45357, is plausibly the same Qwen3.5 save_pretrained serialization regression and looks mergeable into one fix. The other pairs are appropriately rejected as model-, checkpoint-, or code-path-specific rather than clear duplicates. issue:45020 is a reasonable broad umbrella for the cluster." }, "evaluator_used": true, - "retried": true, + "retried": false, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -3220,7 +3262,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:33666", "issue:40444", @@ -3290,227 +3332,227 @@ "issue:43377|issue:45491", "issue:41720|issue:45081", "issue:44265|issue:45072", - "issue:43531|issue:44291", "issue:42175|issue:43296", + "issue:43531|issue:44291", "issue:43994|issue:44898", "issue:43611|issue:43646", "issue:43632|issue:45072", "issue:43792|issue:43957", - "issue:45325|issue:45834", "issue:44079|issue:44534", + "issue:45325|issue:45834", "issue:43454|issue:44466", "issue:42915|issue:43482", "issue:40444|issue:45381", "issue:45325|issue:45381" ], - "prepared_review_unit_hash": "58892eda8ec8f05662b355a7a1a2c467c5880f7ee56161b69632737baea3df05", + "prepared_review_unit_hash": "53d8a06899054f3aa2f3426ae3f4d8a61878e1516a02e8c4f778d23d48eb1c08", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36989, - "estimated_input_tokens": 9248, - "estimated_eval_tokens": 18752 + "serialized_chars": 36999, + "estimated_input_tokens": 9250, + "estimated_eval_tokens": 18756 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "All soft edges look like false positives. The cluster is a heterogeneous mix of unrelated loading, tokenizer, model-init, attention, training, and packaging bugs; only a few issues share a broad Transformers v5 / model-initialization theme.", - "confidence": 0.95, - "canonical_issue_reason": "No single true duplicate stands out; issue 43646 is only the broadest umbrella because it covers the widest v5 model-initialization/loading regression surface.", + "summary": "This cluster is heterogeneous: it mixes unrelated model-loading, tokenizer, vision-language, and training regressions. None of the soft-edge pairs are safe duplicates, so all were rejected.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43611 is the broadest representative of the cluster\u2019s dominant theme (Transformers v5 loading/init regressions), but it is only a loose anchor because the cluster is not a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "43646 is the best representative issue because it is the broadest and most central v5 initialization regression among the set, but it still does not unify the cluster into one bug.", + "best_issue_reason": "issue:43611 is the best global issue anchor among the items, since it captures the common v5 model-loading breakage theme more cleanly than the others; however, it is still not a strong duplicate center for this mixed cluster.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43818", "right": "issue:45357", "accept": false, - "reason": "Different bugs: Video-LLaVA missing temporal attention/weight sharing vs Qwen3.5 save_pretrained visual-key regression." + "reason": "Different models and different bugs: Video-LLaVA temporal-attention/weight-sharing vs Qwen3.5 visual-encoder key serialization." }, { "left": "issue:43421", "right": "issue:44568", "accept": false, - "reason": "Both involve tokenizer special tokens, but one is runtime post-processor updates and the other is BOS/EOS insertion behavior in a specific tokenizer." + "reason": "Both involve tokenizers, but one is about runtime post-processor updates and the other is a tokenizer-specific BOS/EOS failure; different root causes." }, { "left": "issue:44403", "right": "issue:44991", "accept": false, - "reason": "Generic loading noise vs a specific tokenizer-loading failure for EMBEDDIA/est-roberta; not the same bug." + "reason": "One is about reducing noisy load messages, the other is a concrete tokenizer loading failure for a specific model." }, { "left": "issue:43632", "right": "issue:44534", "accept": false, - "reason": "_is_hf_initialized init regression is unrelated to non-persistent buffers being filled with junk." + "reason": "Unrelated v5 regressions: one is `_is_hf_initialized` handling, the other is non-persistent buffer initialization." }, { "left": "issue:41553", "right": "issue:43582", "accept": false, - "reason": "Bad AutoTokenizer error messaging vs Apple Silicon TypeError in caching_allocator_warmup; different code paths." + "reason": "Completely different areas: AutoTokenizer error messaging vs Apple Silicon allocator warmup TypeError." }, { "left": "issue:33666", "right": "issue:40444", "accept": false, - "reason": "Both are Qwen2-VL-related, but multi-GPU training and iterable-dataset multi-image finetuning failures are distinct issues." + "reason": "Both Qwen VL training issues, but different versions and different failure modes; not the same concrete bug." }, { "left": "issue:44462", "right": "issue:45812", "accept": false, - "reason": "Tokenizer repository-file selection vs wrong token IDs for Granite models; both are tokenizer regressions but not the same underlying defect." + "reason": "Both are tokenizer regressions, but one ignores `tokenizer.json` while the other produces wrong Granite token IDs; too different to merge." }, { "left": "issue:44079", "right": "issue:45663", "accept": false, - "reason": "ModelOutput key assignment bug vs Gemma-4 shared_kv_states FSDP2 failure; unrelated failures." + "reason": "Different bugs in different code paths: `ModelOutput` key assignment vs Gemma-4 FSDP attention state rebuilding." }, { "left": "issue:43482", "right": "issue:45538", "accept": false, - "reason": "Qwen2.5-GGUF loading failure and CLIPTokenizer max-length misuse are unrelated." + "reason": "Both touch tokenizer/loading behavior, but GGUF loading failure and `model_max_length` misuse are unrelated." }, { "left": "issue:43317", "right": "issue:43856", "accept": false, - "reason": "device_map/offload dequantization failure vs Qwen3 MoE training memory inefficiency; different problems." + "reason": "One is device-map/offload loading failure; the other is Qwen3 MoE memory inefficiency during training." }, { "left": "issue:44829", "right": "issue:45479", "accept": false, - "reason": "flash_attention_3 training degeneration is not the same as the num_labels=1 zero-loss classification bug." + "reason": "Both affect training, but the causes differ: flash-attention-3 degeneration vs classification loss handling for `num_labels=1`." }, { "left": "issue:43381", "right": "issue:45923", "accept": false, - "reason": "Gradient checkpointing in eval mode vs missing supports_gradient_checkpointing flag; related area, different bug." + "reason": "Gradient checkpointing appears in both, but one is eval-mode incompatibility and the other is a missing capability flag on a trust-remote-code model." }, { "left": "issue:40444", "right": "issue:45325", "accept": false, - "reason": "Both are Qwen2.5-VL, but iterable-dataset multi-image finetuning and still-image position_ids scaling are separate regressions." + "reason": "Same model family, but different bugs: iterable-dataset multi-image finetuning vs wrong still-image position scaling." }, { "left": "issue:44291", "right": "issue:44589", "accept": false, - "reason": "Unexpected _is_hf_initialized argument during init_empty_weights is unrelated to missing Float8 storage handling." + "reason": "Both are loading regressions in v5, but the concrete failures are different: unexpected `_is_hf_initialized` arg vs missing float8 storage type." }, { "left": "issue:43482", "right": "issue:43525", "accept": false, - "reason": "Qwen2.5-GGUF loading and Llama4Config missing pad_token_id are different model/config issues." + "reason": "Both are loading failures, but one is a GGUF/transformers v5 compatibility issue and the other is a missing config attribute." }, { "left": "issue:43377", "right": "issue:45491", "accept": false, - "reason": "MIMI padding-mask inconsistency and Gemma3 NaN embeddings from sliding-window attention are different bugs." + "reason": "Different architectures and root causes: MIMI padding-mask batching bug vs Gemma3 sliding-window/all-padding NaNs." }, { "left": "issue:41720", "right": "issue:45081", "accept": false, - "reason": "Qwen3 auto device mapping cuda assert and Mistral regex patch crash have no shared code path." + "reason": "Unrelated failures: Qwen3 auto device mapping CUDA assert vs Mistral regex patch crashing on tokenizer backend access." }, { "left": "issue:44265", "right": "issue:45072", "accept": false, - "reason": "torch.export + torch_compilable_check is unrelated to bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "Different systems and symptoms: `torch.export` with `torch_compilable_check` vs dtype mismatch in bfloat16 inference." }, { - "left": "issue:43531", - "right": "issue:44291", + "left": "issue:42175", + "right": "issue:43296", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights/_is_hf_initialized are distinct regressions." + "reason": "Packaging/backend selection issue vs a model loading failure in vLLM; no shared bug path." }, { - "left": "issue:42175", - "right": "issue:43296", + "left": "issue:43531", + "right": "issue:44291", "accept": false, - "reason": "Packaging/backends install issue vs PaddleOCR-VL load failure in vLLM; not the same underlying bug." + "reason": "One is a sliding-window issue in Qwen3-MoE, the other is an `init_empty_weights` argument regression; unrelated." }, { "left": "issue:43994", "right": "issue:44898", "accept": false, - "reason": "Siglip2 nonsensical outputs and Perceiver non-default-resolution failure are unrelated model-specific bugs." + "reason": "Both are vision model inference bugs, but different models and different code paths." }, { "left": "issue:43611", "right": "issue:43646", "accept": false, - "reason": "Both are v5 loading/init regressions, but base_model_prefix loading and custom model initialization are separate concrete failures." + "reason": "Both are broad v5 initialization regressions, but one is about `base_model_prefix` loading and the other about custom model initialization; not the same bug." }, { "left": "issue:43632", "right": "issue:45072", "accept": false, - "reason": "_is_hf_initialized regression is not the same as bf16 dtype mismatch during inference." + "reason": "Different regressions: `_is_hf_initialized` breakage vs dtype mismatches in bfloat16 inference." }, { "left": "issue:43792", "right": "issue:43957", "accept": false, - "reason": "Whisper model runtime failure and meta-device loading breakage are different loading paths and causes." + "reason": "Different loading/runtime issues: Whisper model cannot run vs `torch.device('meta')` loading breakage." }, { - "left": "issue:45325", - "right": "issue:45834", + "left": "issue:44079", + "right": "issue:44534", "accept": false, - "reason": "Qwen2.5-VL rope-index bug and Kosmos2.5 long-OCR index error are distinct multimodal failures." + "reason": "`ModelOutput` key bookkeeping is unrelated to junk-filled non-persistent buffers." }, { - "left": "issue:44079", - "right": "issue:44534", + "left": "issue:45325", + "right": "issue:45834", "accept": false, - "reason": "ModelOutput key assignment and junk-filled non-persistent buffers are unrelated runtime/serialization issues." + "reason": "Both are multimodal long-input issues, but Qwen2.5-VL position-id scaling and Kosmos2.5 OCR index errors are different bugs." }, { "left": "issue:43454", "right": "issue:44466", "accept": false, - "reason": "Tied lm_head weights not being set and device-dependent serialization inconsistency are related only at a very high level, not the same bug." + "reason": "AyaVision weight-tying bug and serialization inconsistency in `lm_head.weight` are related only at a very high level, not the same underlying issue." }, { "left": "issue:42915", "right": "issue:43482", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen2.5-GGUF loading failure are unrelated." + "reason": "Qwen3MoE FP8 config failure vs Qwen2.5-GGUF loading failure; different model families and different failure modes." }, { "left": "issue:40444", "right": "issue:45381", "accept": false, - "reason": "IterableDataset multi-image finetuning failure and video vision_position_ids bug are separate Qwen2.5-VL regressions." + "reason": "Both Qwen2.5-VL issues, but one is dataset/multi-image finetuning failure and the other is video position-id regression." }, { "left": "issue:45325", "right": "issue:45381", "accept": false, - "reason": "Both are Qwen2.5-VL position-id bugs, but still-image temporal scaling and video-input position_ids are different code paths and symptoms." + "reason": "Same model family and nearby symptoms, but still-image vs video position-id handling are distinct code paths." } ] }, @@ -3532,7 +3574,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:35707", "issue:39692", @@ -3615,33 +3657,33 @@ "issue:43296|issue:44877", "issue:43873|issue:45701" ], - "prepared_review_unit_hash": "1f5c80b34ba1ce3953f816f6506441e92738849ec964bd882679def859c9c7c3", + "prepared_review_unit_hash": "3d268d08262a5d832b5866f425826a3122ea85168143ccdf5ecbafca6a5ebab1", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36923, - "estimated_input_tokens": 9231, - "estimated_eval_tokens": 18718 + "serialized_chars": 36927, + "estimated_input_tokens": 9232, + "estimated_eval_tokens": 18720 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous: most items are distinct model/config/tokenizer/loading regressions rather than duplicates. No soft pair looks like the same underlying bug/change, so all soft edges are rejected.", - "confidence": 0.79, - "canonical_issue_reason": "issue:43873 is the broadest, most central open report in the set and several nearby items are offloading/device-map/quantization-adjacent, so it is the best umbrella issue for triage even though the cluster is not a true duplicate group.", + "summary": "These issues are mostly unrelated regressions across loading, quantization/offload, tokenization, multimodal inputs, and model-specific config bugs. I did not find any soft pair that clearly looks like the same concrete underlying bug, so all proposed merges are rejected.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43873 is the least-bad anchor: it is open, has the most activity among the broadly related loading/offloading reports, and is general enough to represent the cluster better than the very model-specific bugs.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the most suitable global issue anchor: active discussion, inbound references, and a broad offloading/quantization scope that can subsume some neighboring reports better than the more model-specific issues.", + "best_issue_reason": "issue:43873 is the best overall issue to anchor on, but only because the cluster is heterogeneous; it has broad offloading/quantization scope and the most discussion/inbound refs among the active candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ { @@ -3654,175 +3696,175 @@ "left": "issue:43749", "right": "issue:44079", "accept": false, - "reason": "FSDP CPU RAM-efficient loading vs ModelOutput key behavior; different bugs." + "reason": "FSDP CPU RAM efficient loading vs ModelOutput key handling; unrelated." }, { "left": "issue:43296", "right": "issue:45800", "accept": false, - "reason": "PaddleOCR-VL loading failure in vLLM vs torch/transformers version incompatibility; not the same issue." + "reason": "Specific PaddleOCR-VL/vLLM load failure vs broad torch/transformers incompatibility; not the same bug." }, { "left": "issue:44479", "right": "issue:45823", "accept": false, - "reason": "Qwen VL video regression vs Gemma4 PLE device mismatch; different models and failure modes." + "reason": "Different multimodal regressions: video-input path vs device mismatch during forward." }, { "left": "issue:35707", "right": "issue:40444", "accept": false, - "reason": "Generation with inputs_embeds/past_key_values vs Qwen2.5-VL iterable-dataset multi-image finetuning; unrelated." + "reason": "Progressive generation with inputs_embeds/past_key_values vs VL finetuning on IterableDataset; unrelated." }, { "left": "issue:43606", "right": "issue:44265", "accept": false, - "reason": "CPU offload device mismatch vs torch.export/torch_compilable_check export failure; different concrete problems." + "reason": "CPU offload device mismatch vs torch.export/check-wrapper export failure; different failures." }, { "left": "issue:44291", "right": "issue:44877", "accept": false, - "reason": "Unexpected _is_hf_initialized arg in init_empty_weights vs strict config blocking granite_speech loading; distinct loading bugs." + "reason": "Unexpected _is_hf_initialized arg vs strict config loading; different load-time issues." }, { "left": "issue:44387", "right": "issue:44617", "accept": false, - "reason": "int4 quantization OOM vs Sam3Video OOM; same symptom class, but different cause and path." + "reason": "Int4 reserved-memory/OOM regression vs SAM3Video OOM; not the same cause." }, { "left": "issue:44568", "right": "issue:45920", "accept": false, - "reason": "mDeBERTa special-token insertion bug vs broad AutoTokenizer regression; related area but not the same fix." + "reason": "Single tokenizer missing BOS/EOS vs broad wrong-token-IDs regression; related area only, not same bug." }, { "left": "issue:43881", "right": "issue:44488", "accept": false, - "reason": "glm-4v-9b load failure vs cjvt/sleng-bert load failure; different model-specific issues." + "reason": "Two separate model-loading failures for different models." }, { "left": "issue:43701", "right": "issue:45325", "accept": false, - "reason": "resume_from_checkpoint key mismatch vs Qwen2.5-VL rope index scaling; unrelated bugs." + "reason": "Checkpoint key mismatch vs rope/position-id scaling bug; unrelated." }, { "left": "issue:44186", "right": "issue:44265", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash vs torch.export failure with torch_compilable_check; different subsystems." + "reason": "Tokenizer padding/truncation crash vs torch.export failure; unrelated." }, { "left": "issue:43606", "right": "issue:43819", "accept": false, - "reason": "Bark CPU-offload mismatch vs DAC.from_latents/STE mismatch; unrelated failures." + "reason": "Device mismatch on CPU offload vs DAC.from_latents/STE mismatch; unrelated." }, { "left": "issue:41720", "right": "issue:45823", "accept": false, - "reason": "Qwen3 auto device-map cuda assert vs Gemma4 PLE device mismatch; different models and code paths." + "reason": "Different models and failures: Qwen3 auto device map assert vs Gemma4 PLE mismatch." }, { "left": "issue:43454", "right": "issue:43550", "accept": false, - "reason": "lm_head tying/garbage generation vs torch.compile SDPA failure; no shared underlying bug." + "reason": "Weight tying/garbage text vs torch.compile+SDPA failure; unrelated." }, { "left": "issue:43262", "right": "issue:43746", "accept": false, - "reason": "Audio chat-template sampling-rate default vs GraniteSpeech PEFT local-checkpoint loading; different issues." + "reason": "Audio chat-template sample-rate default vs PEFT local checkpoint loading; unrelated." }, { "left": "issue:43377", "right": "issue:44610", "accept": false, - "reason": "Missing padding-mask support in MIMI encoder vs OmDet-Turbo processor/model size mismatch; unrelated." + "reason": "Padding-mask batch inconsistency vs processor/model image-size mismatch; unrelated." }, { "left": "issue:43317", "right": "issue:43873", "accept": false, - "reason": "Both concern offloading/quantization, but one is dequantized-model loading on cpu/gpu offload and the other is a broader offloading complaint; not clearly the same bug." + "reason": "Both mention offloading/quantization, but one is dequantized loading with device_map=auto and the other is generic offloading behavior; too broad to merge." }, { "left": "issue:39692", "right": "issue:40444", "accept": false, - "reason": "SigLIP2 documentation errors vs Qwen2.5-VL multi-image finetuning failure; unrelated." + "reason": "SigLIP2 documentation errors vs Qwen2.5-VL IterableDataset finetuning failure; unrelated." }, { "left": "issue:43572", "right": "issue:45759", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig vs composite Qwen config unwrap issue; different config bugs." + "reason": "Missing pad_token_idx vs from_config not unwrapping text_config; unrelated." }, { "left": "issue:43454", "right": "issue:45072", "accept": false, - "reason": "Weight tying/serialization bug vs dtype mismatch in bfloat16 inference; unrelated." + "reason": "Weight tying bug vs bfloat16 dtype mismatch in wrappers; unrelated." }, { "left": "issue:43257", "right": "issue:45923", "accept": false, - "reason": "Qwen3 MOE weight conversion/loading problem vs missing supports_gradient_checkpointing flag; different model-load fixes." + "reason": "Qwen3 MoE weight conversion/loading vs missing gradient-checkpointing flag; unrelated." }, { "left": "issue:43377", "right": "issue:44898", "accept": false, - "reason": "MIMI padding-mask issue vs Perceiver resolution/interpolate_pos_encoding bug; different code paths." + "reason": "MIMI padding-mask bug vs Perceiver non-default-resolution failure; unrelated." }, { "left": "issue:40990", "right": "issue:45584", "accept": false, - "reason": "High perplexity on gpt-oss-20b vs Whisper empty-transcription generation failure; unrelated." + "reason": "GPT-OSS perplexity regression vs Whisper empty-transcription generation; unrelated." }, { "left": "issue:40990", "right": "issue:42947", "accept": false, - "reason": "Perplexity regression vs gradient-checkpointing ineffectiveness; different underlying problems." + "reason": "Perplexity regression vs LoRA gradient checkpointing ineffective; unrelated." }, { "left": "issue:44466", "right": "issue:45357", "accept": false, - "reason": "lm_head serialization inconsistency vs Qwen3.5 visual-encoder key serialization regression; different save_pretrained bugs." + "reason": "lm_head serialization inconsistency vs visual-encoder key saving regression; only broadly about saving, not same bug." }, { "left": "issue:43454", "right": "issue:43720", "accept": false, - "reason": "Weight-tying generation bug vs BitNet packed-weight loading bug; unrelated." + "reason": "Weight tying bug vs packed-weights not unpacked during accelerate loading; unrelated." }, { "left": "issue:43526", "right": "issue:43883", "accept": false, - "reason": "BEiT reduce_labels returns only one label vs Molmo missing all_tied_weights_keys; different issues." + "reason": "BeitImageProcessorFast label reduction bug vs Molmo tied-weights attribute error; unrelated." }, { "left": "issue:43296", "right": "issue:44877", "accept": false, - "reason": "PaddleOCR-VL load failure vs strict granite_speech config loading failure; unrelated." + "reason": "PaddleOCR-VL load failure vs strict config loading for granite_speech; unrelated." }, { "left": "issue:43873", "right": "issue:45701", "accept": false, - "reason": "Offloading/quantization regression vs tokenization changing across versions; not the same bug." + "reason": "Quantization/offloading issue vs tokenization regression; unrelated." } ] }, @@ -3844,7 +3886,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:34634", "issue:35707", @@ -3928,226 +3970,226 @@ "issue:45081|issue:45812", "issue:41720|issue:42617" ], - "prepared_review_unit_hash": "0d4953e35e0a427fc046a41e8bdbbb94f4e9d3496e41af535373b6826f279b84", + "prepared_review_unit_hash": "13df3b4c15783efee13cc6ba42d82a6fb1dc2eef573ec53aee9b0da30f61814a", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 32, - "serialized_chars": 36782, - "estimated_input_tokens": 9196, - "estimated_eval_tokens": 18648 + "serialized_chars": 36776, + "estimated_input_tokens": 9194, + "estimated_eval_tokens": 18644 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is highly heterogeneous: most items are model-specific regressions or unrelated bugs around tokenization, loading, quantization, offload, or trainer behavior. None of the soft pairs look like the same concrete bug/change, so I reject all duplicate candidates.", - "confidence": 0.78, - "canonical_issue_reason": "#43873 is the broadest and most active loading/offloading regression in the set, with inbound references and discussion; if a single anchor is needed, it best represents the recurring quantization/offload theme.", + "summary": "The cluster is highly heterogeneous: the soft-similarity links mostly connect unrelated bugs across tokenization, loading, quantization/offload, trainer behavior, and multimodal processing. I do not see any pair that clearly shares the same underlying defect, so all soft edges are rejected.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 45701 is the broadest, most externally referenced item in this set and the best anchor for the mixed regression/tokenization subgroup, though it still does not duplicate the other issues.", "canonical_pr_reason": null, - "best_issue_reason": "#43873 is the most central/general issue among otherwise unrelated reports, but the cluster does not really form a true duplicate group.", + "best_issue_reason": "Issue 45701 is the most representative high-signal issue to anchor this cluster, but the cluster is too mixed for a true dedupe canonical to cover the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43881", "right": "issue:44991", "accept": false, - "reason": "Different models and different failure modes: model loading failure vs tokenizer loading regression." + "reason": "Both involve loading/tokenizer failures, but they affect different models and different failure modes." }, { "left": "issue:41720", "right": "issue:44977", "accept": false, - "reason": "Both mention Qwen3-family models, but one is a device-mapping CUDA assert and the other is a flash-attention generation bug; not the same underlying issue." + "reason": "Auto device-mapping CUDA assert and flash-attention generation failure are different code paths." }, { "left": "issue:44008", "right": "issue:45823", "accept": false, - "reason": "Gemma3n forward variable-name collision is unrelated to Gemma4 PLE device mismatch." + "reason": "Gemma3n forward variable collision and Gemma4 PLE device mismatch are unrelated bugs." }, { "left": "issue:43404", "right": "issue:45357", "accept": false, - "reason": "Both are multimodal model regressions, but the concrete bugs differ: weight tying in Mistral3 vs incorrect visual encoder keys in Qwen3.5 save_pretrained." + "reason": "Both touch image-text models, but one is tied weights and the other is save_pretrained key handling." }, { "left": "issue:45632", "right": "issue:45684", "accept": false, - "reason": "Cache-path collision and read-only permission propagation are separate save/load filesystem issues." + "reason": "Cache-path collision and read-only permission propagation are distinct save_pretrained issues." }, { "left": "issue:34634", "right": "issue:35707", "accept": false, - "reason": "Bark voice_preset handling and progressive generation with inputs_embeds/past_key_values are unrelated." + "reason": "Bark voice preset loading and progressive generation with inputs_embeds are unrelated." }, { "left": "issue:43577", "right": "issue:43708", "accept": false, - "reason": "Blip2 dtype propagation bug and Trainer max_steps resume calculation bug are unrelated subsystems." + "reason": "A dtype initialization bug and a Trainer resume/max_steps bug are different subsystems." }, { "left": "issue:35707", "right": "issue:41720", "accept": false, - "reason": "Progressive generation with embeddings is unrelated to Qwen3 device-mapping CUDA failure." + "reason": "Progressive generation with embeddings and Qwen3 device-mapping CUDA asserts are not the same defect." }, { "left": "issue:42617", "right": "issue:42915", "accept": false, - "reason": "A 3D parallel script failure and a Qwen3Moe FP8 loading issue are different problems." + "reason": "3d_parallel.py execution failure and Qwen3Moe FP8 loading failure are unrelated." }, { "left": "issue:44186", "right": "issue:45072", "accept": false, - "reason": "Tokenizer crash on NER/padding is unrelated to bf16 dtype mismatches in model inference." + "reason": "Tokenizer crashes for LayoutLMv2 and dtype mismatches in inference are different problems." }, { "left": "issue:44423", "right": "issue:45406", "accept": false, - "reason": "Both crash in serving contexts, but the concrete processor/attribute failures are different." + "reason": "Continuous-batching multimodal crash and missing Gemma4Processor tokenizer attr are separate serve bugs." }, { "left": "issue:44877", "right": "issue:44991", "accept": false, - "reason": "Strict config rejection for granite_speech is unrelated to tokenizer loading for EMBEDDIA/est-roberta." + "reason": "Strict config handling for granite_speech and tokenizer loading for est-roberta are unrelated." }, { "left": "issue:43550", "right": "issue:43720", "accept": false, - "reason": "torch.compile SDPA failure and packed-weight unpacking during accelerate loading are different code paths." + "reason": "torch.compile/SDPA failure and packed-weight unpacking failure are different code paths." }, { "left": "issue:36331", "right": "issue:42915", "accept": false, - "reason": "Trainer compute_loss signature breakage is unrelated to Qwen3Moe FP8 loading." + "reason": "CustomTrainer compute_loss signature mismatch and Qwen3Moe FP8 failure are unrelated." }, { "left": "issue:43450", "right": "issue:45701", "accept": false, - "reason": "Batched video-shape bug and tokenization behavior change are not the same issue." + "reason": "Video batch-shape handling and tokenization version regression are different domains." }, { "left": "issue:43749", "right": "issue:44534", "accept": false, - "reason": "FSDP CPU-efficient loading regression and non-persistent buffer junk fill are separate Transformer internals issues." + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer corruption are not the same bug." }, { "left": "issue:44610", "right": "issue:44898", "accept": false, - "reason": "OmDet-Turbo processor image-size mismatch is unrelated to Perceiver non-default-resolution failure." + "reason": "Processor image-size mismatch and Perceiver non-default-resolution failure are similar only at a high level, not the same issue." }, { "left": "issue:36331", "right": "issue:42617", "accept": false, - "reason": "Unexpected compute_loss kwarg and 3d_parallel.py failure do not share a concrete root cause." + "reason": "Trainer loss signature error and 3d_parallel.py failure are unrelated." }, { "left": "issue:43873", "right": "issue:44756", "accept": false, - "reason": "Quantization/offload behavior and Strix Halo mmap OOM are both memory-related but not the same bug." + "reason": "Quantization offload problems and Strix Halo mmap OOM are different memory-management issues." }, { "left": "issue:44186", "right": "issue:44610", "accept": false, - "reason": "Tokenizer crash on batched padding/truncation and processor output-size mismatch are different preprocessing bugs." + "reason": "Tokenizer crashes on batched padding and OmDet processor resolution mismatch are unrelated." }, { "left": "issue:43550", "right": "issue:43606", "accept": false, - "reason": "Both involve offload/compute behavior, but one is SDPA compile failure and the other is a CPU-offload device mismatch for Bark-small." + "reason": "Bamba torch.compile/SDPA and Bark-small CPU-offload device mismatch are different model/runtime failures." }, { "left": "issue:43322", "right": "issue:46050", "accept": false, - "reason": "Llava Next loading segfault and sinq save/load breakage are unrelated model-loading problems." + "reason": "Llava Next loading segfault and sinq save/load breakage are separate quantization/loading bugs." }, { "left": "issue:44479", "right": "issue:44918", "accept": false, - "reason": "Video-input regression in Qwen VL models and Qwen3.5 input-embedding unpacking with TRL are different bugs." + "reason": "Video-input regression and SFT input-embedding unpacking failure affect different paths." }, { "left": "issue:44387", "right": "issue:45704", "accept": false, - "reason": "int4 quantization memory growth and apex FusedRMSNorm leak are different memory issues in different models." + "reason": "Int4 quantization OOM and T5 apex RMSNorm memory leak are both memory-related but not the same defect." }, { "left": "issue:42915", "right": "issue:43317", "accept": false, - "reason": "Qwen3Moe FP8 failure and dequantized-model gpu/cpu offload loading failure are distinct quantization/offload paths." + "reason": "Qwen3Moe FP8 failure and dequantized model offload loading failure are different quantization/loading bugs." }, { "left": "issue:43316", "right": "issue:44913", "accept": false, - "reason": "Gemma3TextConfig API discrepancy and GPTNeoX rotary_pct reload regression are unrelated config bugs." + "reason": "Gemma3TextConfig API mismatch and GPTNeoXConfig rotary_pct reload regression are unrelated config bugs." }, { "left": "issue:41720", "right": "issue:43322", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert and Llava Next segfault are different models and failure modes." + "reason": "Qwen3 device-mapping crash and Llava Next segfault are different failure modes." }, { "left": "issue:43295", "right": "issue:45701", "accept": false, - "reason": "Processor.tokenizer API regression and tokenization-output changes are related only at a very broad level; not the same concrete bug." + "reason": "Processor/tokenizer API regression and tokenization-output regression are related only broadly, not the same bug." }, { "left": "issue:40990", "right": "issue:45701", "accept": false, - "reason": "Perplexity anomaly on gpt-oss-20b is not the same as generic tokenization changes." + "reason": "High perplexity on GPT-OSS and tokenization changes are not the same underlying issue." }, { "left": "issue:41720", "right": "issue:45161", "accept": false, - "reason": "Qwen3 auto device-map crash and GPT-OSS MoE tensor-parallel issue are different model/runtime failures." + "reason": "CUDA assert on auto device mapping and GPT-OSS MoE tensor-parallel failure are distinct." }, { "left": "issue:45081", "right": "issue:45812", "accept": false, - "reason": "Mistral tokenizer regex patch crash and Granite tokenizer wrong IDs are both tokenizer bugs, but with different models and distinct root causes." + "reason": "Mistral regex patch crash and Granite token-ID regression are different tokenizer bugs." }, { "left": "issue:41720", "right": "issue:42617", "accept": false, - "reason": "Qwen3 CUDA assert under auto device mapping and failure to run 3d_parallel.py are unrelated." + "reason": "Qwen3 device-mapping crash and 3d_parallel.py failure are unrelated." } ] }, @@ -4169,7 +4211,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:29159", "issue:30064", @@ -4231,8 +4273,8 @@ "issue:29159|issue:36032", "issue:43606|issue:43720", "issue:30064|issue:34634", - "issue:43550|issue:43653", "issue:44492|issue:44509", + "issue:43550|issue:43653", "issue:43421|issue:45701", "issue:42915|issue:43322", "issue:43388|issue:45059", @@ -4247,196 +4289,196 @@ "issue:44898|issue:45072", "issue:41720|issue:43746" ], - "prepared_review_unit_hash": "5cf3870bc7035d6e655597199bc5502998edd050126a22987cc669992d1b23a4", + "prepared_review_unit_hash": "192006d3ebc5e5a9fb96acbf0d335f1dd085d8ea7fcf3b6d659e41f1ae036aab", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 26, - "serialized_chars": 35066, - "estimated_input_tokens": 8767, - "estimated_eval_tokens": 17790 + "serialized_chars": 35063, + "estimated_input_tokens": 8766, + "estimated_eval_tokens": 17788 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: nearly all soft pairs are distinct bugs or regressions that only share a broad subsystem. The only clear duplicate is the pair of identical Qwen2_5_VLProcessor batched padding crashes.", - "confidence": 0.89, - "canonical_issue_reason": "issue:44514 is the best canonical issue because it is an exact duplicate of issue:44545 (same title, same batched `apply_chat_template` crash with `padding=False`), and it is the earlier report.", + "summary": "The cluster is mostly a set of unrelated issue reports with only one clear duplicate pair: the two identical Qwen2_5_VLProcessor.apply_chat_template crash reports. The rest are broad tokenizer/model-loading regressions that share themes but not the same concrete bug path.", + "confidence": 0.92, + "canonical_issue_reason": "issue:44545 is the strongest canonical representative because it is an exact duplicate of issue:44514, has the same title/root crash, and has slightly more inbound references indicating it is the more central report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44514 is the strongest representative of the cluster\u2019s only true duplicate pair; it has the clearest one-to-one duplicate relationship and can anchor triage for that bug.", + "best_issue_reason": "issue:44545 is the best overall issue in this set because it cleanly represents the only confirmed duplicate pair and is the most reference-central standalone bug report here.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43531", "right": "issue:43572", "accept": false, - "reason": "Both are model/config-related, but they describe different problems on different models: `sliding_window` behavior in Qwen3-MoE versus missing `pad_token_idx` in StableLmConfig." + "reason": "Different bugs: one is a Qwen3-MoE sliding_window behavior issue, the other is a StableLmConfig pad_token_idx regression." }, { "left": "issue:43526", "right": "issue:43881", "accept": false, - "reason": "One is a Beit image processor label-reduction bug; the other is a glm-4v model loading failure. No same code path." + "reason": "Different subsystems and failures: BeitImageProcessorFast label reduction vs a GLM-4V model loading failure." }, { "left": "issue:43540", "right": "issue:43782", "accept": false, - "reason": "Both involve Qwen multimodal models, but one fails on video input processing and the other fails in `from_pretrained` with `weight_only=True`. Different concrete bugs." + "reason": "Both involve Qwen3 multimodal models, but one is a video-input processing ValueError and the other is a from_pretrained/load-time weight_only error; not the same code path." }, { "left": "issue:36010", "right": "issue:42617", "accept": false, - "reason": "An import error for `GenerationMixin` is unrelated to a `3d_parallel.py` runtime failure." + "reason": "Unrelated: GenerationMixin import error vs a script execution problem for 3d_parallel.py." }, { "left": "issue:44671", "right": "issue:44743", "accept": false, - "reason": "CamemBERT masked-LM prediction regression and Qwen3.5 recurrent-state reset are unrelated model bugs." + "reason": "Both are model-specific regressions, but CamemBERT MLM predictions and Qwen3.5 recurrent-state caching are different bugs." }, { "left": "issue:43421", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer-related, but one is about updating the post-processor after runtime special-token changes while the other is a Granite token-ID regression during `AutoTokenizer` loading." + "reason": "Tokenizer-related, but one is runtime post-processor updates after special-token edits while the other is wrong Granite token IDs; distinct issues." }, { "left": "issue:44186", "right": "issue:44361", "accept": false, - "reason": "Different tokenizer classes and different failure modes; these do not look like the same underlying bug." + "reason": "Both tokenizer issues, but LayoutLMv2 NER/padding crashes and MLuke task AttributeErrors are different failure modes and code paths." }, { "left": "issue:45406", "right": "issue:45464", "accept": false, - "reason": "Gemma4Processor missing `_tokenizer` in transformers serve is a different path from Qwen3.5 streaming inference failures." + "reason": "Different products and failures: Gemma4Processor serve-time missing _tokenizer vs Qwen3.5 streaming inference failure." }, { "left": "issue:29159", "right": "issue:36032", "accept": false, - "reason": "Slow-vs-fast tokenizer inconsistency is not the same as T5 tokenizer loading breaking on an `add_special_tokens` method conflict." + "reason": "Not the same bug: slow/fast tokenizer inconsistency vs a T5Tokenizer add_special_tokens load conflict." }, { "left": "issue:43606", "right": "issue:43720", "accept": false, - "reason": "Both are loading/offload-related, but one is a CPU offload device mismatch for Bark and the other is packed-weight unpacking for BitNet. Different fixes." + "reason": "Both are loading/offload related, but device mismatch on CPU offload and packed-weight unpacking during accelerate loading are different concrete problems." }, { "left": "issue:30064", "right": "issue:34634", "accept": false, - "reason": "Image segmentation-map processing and Bark voice preset handling are unrelated." + "reason": "Completely different areas: image processor void segmentation handling vs BarkProcessor voice_preset behavior." }, { - "left": "issue:43550", - "right": "issue:43653", + "left": "issue:44492", + "right": "issue:44509", "accept": false, - "reason": "A `torch.compile`/SDPA failure for Bamba is not the same bug as BigBirdTokenizer mask-token registration and empty decode output." + "reason": "A typo fix in cache strategies is unrelated to documentation about removed pipeline tasks." }, { - "left": "issue:44492", - "right": "issue:44509", + "left": "issue:43550", + "right": "issue:43653", "accept": false, - "reason": "A typo in cache strategy docs is unrelated to docs still mentioning removed pipeline tasks." + "reason": "Different bugs: Bamba torch.compile/SDPA failure vs BigBirdTokenizer mask-token registration/decoding issue." }, { "left": "issue:43421", "right": "issue:45701", "accept": false, - "reason": "Runtime post-processor synchronization after token changes is different from a broad version-dependent tokenization change report." + "reason": "Both mention tokenization, but one is a backend post-processor update bug and the other is a broad version-dependent tokenization change report." }, { "left": "issue:42915", "right": "issue:43322", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure and Llava Next segmentation fault are different model-specific crashes." + "reason": "Unrelated model/runtime failures: Qwen3Moe FineGrainedFP8Config vs Llava Next loading segfault." }, { "left": "issue:43388", "right": "issue:45059", "accept": false, - "reason": "A metrics-gathering bug that drops tuple label elements is not the same as SAM3 text/bounding-box weird behavior." + "reason": "Different issues in different paths: evaluation metric gathering drops tuple labels vs SAM3 text/bbox processing weirdness." }, { "left": "issue:43606", "right": "issue:43653", "accept": false, - "reason": "CPU offload device mismatch and tokenizer special-token registration are unrelated." + "reason": "Both mention CI regressions, but device mismatch on CPU offload and tokenizer mask-token registration are unrelated." }, { "left": "issue:44514", "right": "issue:44545", "accept": true, - "reason": "Exact duplicate: same title, same Qwen2_5_VLProcessor batched `apply_chat_template` crash when `padding=False`." + "reason": "Exact duplicate reports of the same Qwen2_5_VLProcessor.apply_chat_template batched-padding=False crash." }, { "left": "issue:43531", "right": "issue:45759", "accept": false, - "reason": "`sliding_window` behavior in Qwen3-MoE is a different issue from `AutoModelForCausalLM.from_config` not unwrapping `text_config` in multimodal configs." + "reason": "Both touch Qwen3-family model behavior, but sliding_window on Qwen3-MoE and AutoModelForCausalLM config unwrapping are different bugs." }, { "left": "issue:34567", "right": "issue:35707", "accept": false, - "reason": "TrainerState token-count tracking and progressive generation with `inputs_embeds`/`past_key_values` are different bugs." + "reason": "TrainerState token accounting and progressive generation with inputs_embeds/past_key_values are unrelated." }, { "left": "issue:43421", "right": "issue:43927", "accept": false, - "reason": "Post-processor updates for modified special tokens are distinct from DiaConfig losing custom token IDs on save/load." + "reason": "Related to token IDs, but one is runtime post-processor updates and the other is save/load preserving custom DiaConfig token IDs." }, { "left": "issue:44368", "right": "issue:45357", "accept": false, - "reason": "A warning about `tie_word_embeddings` is unrelated to saving incorrect visual-encoder keys." + "reason": "A warning about tie_word_embeddings is unrelated to incorrect visual encoder keys being saved." }, { "left": "issue:44451", "right": "issue:44991", "accept": false, - "reason": "Both are tokenizer-loading regressions, but they reference different models and no shared concrete code path is evident." + "reason": "Both are tokenizer/model-loading complaints, but for different models and different failure mechanisms." }, { "left": "issue:42490", "right": "issue:43329", "accept": false, - "reason": "A local-path trailing-slash import warning is unrelated to an undefined-variable bug in the video branch of `_get_num_multimodal_tokens`." + "reason": "A local-path import warning is unrelated to a multimodal video token counting bug." }, { "left": "issue:44898", "right": "issue:45072", "accept": false, - "reason": "Perceiver non-default-resolution failure with position interpolation is unrelated to bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + "reason": "Different model/runtime problems: Perceiver interpolation failure vs dtype mismatch in bfloat16 inference." }, { "left": "issue:41720", "right": "issue:43746", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert and GraniteSpeech PEFT local-checkpoint loading are different failures with different code paths." + "reason": "Different loading/runtime failures on different models: Qwen3 auto device mapping cudaErrorAssert vs GraniteSpeech PEFT checkpoint loading." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative on the soft-edge pairs. The only clear duplicate identified in the cluster is the Qwen2_5_VLProcessor batched padding crash pair (44514/44545), and the remaining verdicts are appropriately cautious given the available evidence." + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:44514/issue:44545, is supported by nearly identical titles and the duplicate verdict is reasonable. The canonical choice of issue:44545 is also justified by its slightly higher inbound references. No overstatement stands out." }, "evaluator_used": true, "retried": false, @@ -4455,7 +4497,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:30064", "issue:33666", @@ -4509,9 +4551,9 @@ "issue:44987|issue:45042", "issue:43873|issue:45704", "issue:43531|issue:44589", - "issue:45759|issue:45859", "issue:44062|issue:44451", "issue:33666|issue:35707", + "issue:45759|issue:45859", "issue:39692|issue:44610", "issue:45704|issue:45923", "issue:45588|issue:45759", @@ -4536,20 +4578,20 @@ "issue:43540|issue:44008", "issue:30064|issue:36010" ], - "prepared_review_unit_hash": "ac3b496cd01d0a8e89a5212b05e3b5d2c94973590943350804dad241e7306ca6", + "prepared_review_unit_hash": "3e3d3dafae71da15ff0ba8d34a0195b825cdcb5ec19028ac55489519f9c7bf6a", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36048, + "serialized_chars": 36047, "estimated_input_tokens": 9012, "estimated_eval_tokens": 18280 }, @@ -4558,192 +4600,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous soft-similarity noise across unrelated issues. The only clear duplicate-style match is the offline tokenizer/cache regression pair; the rest differ in model, subsystem, or root cause.", - "confidence": 0.77, - "canonical_issue_reason": "44843 is the clearest root-cause report: it names `_patch_mistral_regex`, the unconditional `model_info()` call, and the HF_HUB_OFFLINE failure path directly.", + "summary": "Mostly a heterogeneous cluster of unrelated model/processor/training bugs. The only strong duplicate-style overlap is the HF_HUB_OFFLINE tokenizer regression pair; the rest are broad-theme similarities but not the same concrete bug.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 44843 is the clearest, most specific report: it names the exact failing code path (_patch_mistral_regex/model_info) and the offline regression, making it the best anchor for the only likely duplicate subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "44843 is the most actionable and code-path-specific issue here, making it the best canonical representative for the accepted duplicate pair.", + "best_issue_reason": "Issue 44843 is the strongest representative issue in this set because it has an explicit root cause, a reproducible failure mode, and a clear fix target.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44987", "right": "issue:45042", "accept": false, - "reason": "Different failures: model loading regression vs PIL image processor torchvision dependency." + "reason": "Different problems: one is a model-loading regression, the other is an image-processor torchvision dependency issue." }, { "left": "issue:43873", "right": "issue:45704", "accept": false, - "reason": "Unrelated areas: quantization/offloading behavior vs T5 RMSNorm memory leak." + "reason": "Both mention training/runtime behavior, but one is quantization/offloading and the other is a T5 RMSNorm memory leak; not the same bug." }, { "left": "issue:43531", "right": "issue:44589", "accept": false, - "reason": "Different subsystems and symptoms: Qwen3-MoE sliding window vs Float8 storage loading." - }, - { - "left": "issue:45759", - "right": "issue:45859", - "accept": false, - "reason": "Both involve Qwen, but one is config unwrapping and the other is CPU-offload incompatibility in rotary embedding; not the same bug." + "reason": "Qwen3-MoE sliding-window behavior is unrelated to the Float8 storage import/runtime error." }, { "left": "issue:44062", "right": "issue:44451", "accept": false, - "reason": "Tokenizer error vs a model-specific load failure; no clear shared root cause." + "reason": "Both are tokenizer-loading related, but one is an AddedToken argument collision and the other is a model-specific load failure; too little evidence of the same root cause." }, { "left": "issue:33666", "right": "issue:35707", "accept": false, - "reason": "Multi-GPU training and progressive generation are different problems." + "reason": "Multi-GPU Qwen2-VL training and progressive generation with embeds/past key values are different code paths." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Both concern Qwen 3.5, but one is config unwrapping and the other is CPU-offload incompatibility in rotary embedding; not the same bug." }, { "left": "issue:39692", "right": "issue:44610", "accept": false, - "reason": "Both touch vision docs/processors, but the concrete failures and models differ." + "reason": "Both are model/processor mismatches, but they involve different models and different failure modes." }, { "left": "issue:45704", "right": "issue:45923", "accept": false, - "reason": "Memory leak in apex RMSNorm is unrelated to a missing capability flag on a trust_remote_code model." + "reason": "T5 RMSNorm leak and a missing supports_gradient_checkpointing flag are unrelated." }, { "left": "issue:45588", "right": "issue:45759", "accept": false, - "reason": "Flash-attention sink handling vs Qwen multimodal config unwrapping are different code paths." + "reason": "Flash-attention sink handling and Qwen multimodal config unwrapping are different issues." }, { "left": "issue:42886", "right": "issue:44843", "accept": true, - "reason": "Same offline tokenizer-load bug: both point to HF_HUB_OFFLINE failures in the tokenizer loading path, and 44843 identifies the root cause in `_patch_mistral_regex`." + "reason": "Both describe the same offline tokenizer regression; 44843 gives the concrete root cause in _patch_mistral_regex/model_info, while 42886 is the broader symptom." }, { "left": "issue:45663", "right": "issue:45923", "accept": false, - "reason": "Gemma-4 FSDP2 attention bug is unrelated to Nemotron gradient-checkpointing support." + "reason": "Gemma-4 FSDP2 shared_kv_states KeyError is unrelated to a missing gradient-checkpointing flag." }, { "left": "issue:43421", "right": "issue:43653", "accept": false, - "reason": "Both mention special tokens, but one is runtime post-processor updating and the other is BigBird mask-token registration." + "reason": "Both involve special tokens, but one is runtime post-processor refresh and the other is BigBird mask-token registration; not the same concrete bug." }, { "left": "issue:44918", "right": "issue:44936", "accept": false, - "reason": "TRL SFT embedding unpacking and trainer evaluate-after-train behavior are distinct trainer issues." + "reason": "Different trainer failures: unpacking input embeddings in SFT versus evaluate() failing after train()." }, { "left": "issue:43381", "right": "issue:43844", "accept": false, - "reason": "Gradient checkpointing eval-mode restriction is unrelated to ZeRO-3 gradient growth." + "reason": "Gradient checkpointing eval-mode handling is unrelated to the ZeRO-3 gradient explosion report." }, { "left": "issue:43421", "right": "issue:44186", "accept": false, - "reason": "Post-processor refresh for special tokens is not the same as LayoutLMv2 NER/padding crashes." + "reason": "Tokenizer post-processor refresh and LayoutLMv2 NER/padding crashes are different failures." }, { "left": "issue:43525", "right": "issue:43531", "accept": false, - "reason": "A missing `pad_token_id` attribute and a sliding-window Qwen3-MoE bug are different failures." + "reason": "Missing pad_token_id on Llama4Config is unrelated to Qwen3-MoE sliding_window behavior." }, { "left": "issue:43782", "right": "issue:45381", "accept": false, - "reason": "Qwen3VL weight-only loading error and Qwen2.5-VL video position-id bug are different issues." + "reason": "Both are Qwen VL issues, but one is a weight_only loading error and the other is a video vision_position_ids bug." }, { "left": "issue:45704", "right": "issue:45859", "accept": false, - "reason": "Same broad family only; the RMSNorm leak and CPU-offload rotary issue do not share a concrete code-path bug." + "reason": "RMSNorm memory leak and CPU-offload rotary embedding incompatibility are distinct code paths." }, { "left": "issue:45081", "right": "issue:45356", "accept": false, - "reason": "Both involve `fix_mistral_regex`, but one is a tokenizer crash and the other is a Kimi-K2.5 regression with codec/warning issues; not clearly the same bug." + "reason": "Both touch fix_mistral_regex, but one is a backend_tokenizer crash and the other is a Kimi-K2.5 codec-handling regression; too different to merge as one bug." }, { "left": "issue:34634", "right": "issue:41720", "accept": false, - "reason": "BarkProcessor voice preset and Qwen3 auto device mapping failures are unrelated." + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping cudaErrorAssert are unrelated." }, { "left": "issue:45356", "right": "issue:45907", "accept": false, - "reason": "Tokenizer regression in `fix_mistral_regex` is unrelated to `list_repo_files` revision forwarding." + "reason": "Tokenizer regex regression and list_repo_files revision forwarding are completely unrelated." }, { "left": "issue:44625", "right": "issue:45479", "accept": false, - "reason": "Config propagation for Qwen3.5 and single-label zero-loss classification are different problems." + "reason": "A Qwen3.5 config propagation bug and a generic single-label classification zero-loss issue are not the same defect." }, { "left": "issue:39692", "right": "issue:43873", "accept": false, - "reason": "SigLIP2 example issues and quantization offloading are different failure modes." + "reason": "SigLIP2 docs/model mismatch is unrelated to quantization offloading behavior." }, { "left": "issue:43994", "right": "issue:44671", "accept": false, - "reason": "Different models and symptoms: SigLIP2 nonsense outputs vs CamemBERT masked-LM regression." + "reason": "Both are model-output regressions, but they affect different models and likely different causes." }, { "left": "issue:43596", "right": "issue:44220", "accept": false, - "reason": "DeepSpeed zero3 initialization crash and fbank feature extraction bug are unrelated." + "reason": "Zero3/BertModel indexing and _torch_extract_fbank_features are unrelated." }, { "left": "issue:44220", "right": "issue:44661", "accept": false, - "reason": "Audio feature extraction and tokenizer mapping registration are different code paths." + "reason": "Audio feature extraction and add-new-model-like/tokenizer-mapping logic are unrelated." }, { "left": "issue:43720", "right": "issue:43819", "accept": false, - "reason": "BitNet packed-weight loading and DAC latent conversion/STE mismatch are unrelated." + "reason": "BitNet packed-weight loading and DAC.from_latents STE mismatch are different code paths." }, { "left": "issue:43540", "right": "issue:44008", "accept": false, - "reason": "Video-input validation in Qwen3OmniMoe is unrelated to Gemma3n's audio mask variable collision." + "reason": "Qwen3OmniMoe video input processing and Gemma 3n variable-name collision are unrelated." }, { "left": "issue:30064", "right": "issue:36010", "accept": false, - "reason": "Void segmentation map processing and GenerationMixin import failure are unrelated." + "reason": "Void segmentation map processing and a GenerationMixin import error are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. Most pair rejections are well supported by distinct titles/subsystems. The one accepted duplicate-style match, 42886 \u2194 44843, is plausibly the same offline tokenizer/cache regression based on the explicit HF_HUB_OFFLINE and tokenizer-loading wording. No obvious overstatement beyond the evidence provided." + "feedback": "The assessment is grounded in the packet and stays conservative. The 42886/44843 pair is well-supported as the only clear duplicate-style overlap, and the other soft-edge rejections do not overclaim same-root-cause evidence." }, "evaluator_used": true, "retried": false, @@ -4762,7 +4804,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:30064", "issue:36331", @@ -4821,8 +4863,8 @@ "issue:45183|issue:45479", "issue:44077|issue:44625", "issue:43335|issue:43756", - "issue:42915|issue:43746", "issue:43716|issue:44008", + "issue:42915|issue:43746", "issue:43550|issue:45072", "issue:43295|issue:45834", "issue:43550|issue:43819", @@ -4837,25 +4879,25 @@ "issue:43531|issue:43643", "issue:43782|issue:44977", "issue:43577|issue:43818", - "issue:44448|issue:44671", "issue:43421|issue:44811", - "issue:44561|issue:45020", - "issue:30064|issue:36331" + "issue:44448|issue:44671", + "issue:30064|issue:36331", + "issue:44561|issue:45020" ], - "prepared_review_unit_hash": "418541aee0561ca3a67cc45f64ab36d44883aa08cc3b4d9476d0b0aa68c5f72b", + "prepared_review_unit_hash": "c7b7d97ffe51005f67351b210bcc20890ac3a2b16c71d290b8de8044697a928d", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 36283, + "serialized_chars": 36284, "estimated_input_tokens": 9071, "estimated_eval_tokens": 18398 }, @@ -4864,174 +4906,174 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of unrelated Transformers regressions across loading, tokenization, multimodal preprocessing, quantization, and model-specific inference bugs. None of the proposed soft pairs look like the same underlying defect, so I would not merge any of them.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 45020 is the broadest representative of the cluster\u2019s dominant theme: recent-version regressions that break remote_code / from_pretrained model loading paths. It best captures the general load-time regression surface, even though the cluster is heterogeneous overall.", + "summary": "This cluster is mostly a loose set of unrelated Transformers bug reports. A few items share broad themes like model loading, tokenizers, or remote_code regressions, but none of the soft pairs look like the same concrete bug/change under a strict duplicate standard.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 45020 is the broadest umbrella candidate for the cluster's recurring recent-version / remote_code loading regressions, though the set is heterogeneous and not a clean duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45020 is the best single issue to anchor the cluster because it is the most umbrella-like and likely to absorb several of the other load/regression reports conceptually. It is still not a true duplicate of most others, just the most representative.", + "best_issue_reason": "Issue 45020 is the best global representative because it is the most umbrella-like report and matches the dominant load/regression theme better than the more narrowly scoped issues.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43746", "right": "issue:46050", "accept": false, - "reason": "Both are loading-related, but one is PEFT adapter local checkpoint loading and the other is quantized save_pretrained/from_pretrained corruption. Different failure modes and code paths." + "reason": "Different failure modes: PEFT adapter local checkpoint loading vs quantized model save/load corruption." }, { "left": "issue:43618", "right": "issue:43697", "accept": false, - "reason": "CLIPOutput attentions missing is a field/serialization regression; RTDetrV2 differing outputs is a model inference change. Unrelated bugs." + "reason": "Different models and bugs: missing CLIP attentions vs RTDetrV2 output drift in v5." }, { "left": "issue:43653", "right": "issue:43720", "accept": false, - "reason": "Tokenizer special-token registration versus BitNet packed-weight unpacking during accelerate loading are different subsystems and defects." + "reason": "Tokenizer special-token registration bug is unrelated to BitNet packed-weight unpacking during accelerate loading." }, { "left": "issue:43388", "right": "issue:46032", "accept": false, - "reason": "Metric-gathering label truncation and Mamba2 use_cache correctness are separate runtime paths with no shared underlying bug." + "reason": "Different code paths: gather_for_metrics label truncation vs Mamba2 cache correctness with seq_len > 1." }, { "left": "issue:45183", "right": "issue:45479", "accept": false, - "reason": "Input validation/error-message logic is not the same issue as degenerate zero loss from problem_type/num_labels handling." + "reason": "Both concern model input/loss logic, but one is an input validation XOR bug and the other is a degenerate loss from num_labels=1 classification setup." }, { "left": "issue:44077", "right": "issue:44625", "accept": false, - "reason": "PatchTSMixer post_init policy and Qwen3.5 num_labels propagation are different configuration bugs." + "reason": "Unrelated issues: patchtsmixer post_init policy vs Qwen3.5 num_labels propagation." }, { "left": "issue:43335", "right": "issue:43756", "accept": false, - "reason": "SwitchTransformers layer construction with zero sparse layers and Smollm3 RoPE-layer dropping are distinct model-setup errors." + "reason": "Different model internals and symptoms: sparse layer creation bug vs RoPE-layer dropping in Smollm3." }, { - "left": "issue:42915", - "right": "issue:43746", + "left": "issue:43716", + "right": "issue:44008", "accept": false, - "reason": "Qwen3Moe FP8 loading failure and GraniteSpeech PEFT checkpoint loading are unrelated model/loading problems." + "reason": "One is a dtype mismatch in image preprocessing/model loading; the other is a variable name collision in Gemma3n forward." }, { - "left": "issue:43716", - "right": "issue:44008", + "left": "issue:42915", + "right": "issue:43746", "accept": false, - "reason": "Mistral-3 dtype mismatch in preprocessing is not the same as Gemma3n variable-name collision in forward()." + "reason": "Different subsystems and models: Qwen3Moe FP8 config failure vs GraniteSpeech PEFT checkpoint loading." }, { "left": "issue:43550", "right": "issue:45072", "accept": false, - "reason": "Bamba SDPA torch.compile failure and SwitchTransformers/TimmWrapper bf16 dtype mismatch are different model and path issues." + "reason": "Both mention dtype/compile issues, but they affect different models and concrete paths; not the same bug." }, { "left": "issue:43295", "right": "issue:45834", "accept": false, - "reason": "Processor.tokenizer regression with image inputs is not the same bug as Kosmos2.5 long-OCR index errors." + "reason": "Different regressions: processor.tokenizer access in v4.57.5 vs Kosmos2.5 OCR long-input index error." }, { "left": "issue:43550", "right": "issue:43819", "accept": false, - "reason": "Bamba torch.compile/SDPA and DAC.from_latents vs forward mismatch are unrelated concrete bugs." + "reason": "Completely different failures: torch.compile + SDPA in Bamba vs DAC.from_latents missing STE consistency." }, { "left": "issue:43746", "right": "issue:43873", "accept": false, - "reason": "PEFT checkpoint loading and quantization offloading behavior are different code paths; no evidence of the same defect." + "reason": "Adapter loading from local checkpoints is unrelated to quantization offloading behavior." }, { "left": "issue:43950", "right": "issue:45987", "accept": false, - "reason": "Non-persistent buffer corruption in from_pretrained and StaticCache.get_seq_length returning a tensor are unrelated issues." + "reason": "Non-persistent buffer corruption in from_pretrained is unrelated to StaticCache.get_seq_length return type." }, { "left": "issue:44186", "right": "issue:44898", "accept": false, - "reason": "Tokenizer padding/truncation crash and Perceiver image-resolution failure are different model/component bugs." + "reason": "Different tokenizer/image-classification failures with no shared concrete code path." }, { "left": "issue:44843", "right": "issue:45081", "accept": false, - "reason": "Both touch mistral regex helpers, but one is offline model_info calls and the other is missing backend_tokenizer access. Same area, different concrete failures." + "reason": "Both touch Mistral tokenizer patching, but one is offline model_info access and the other is backend_tokenizer attribute handling; too different to merge." }, { "left": "issue:44062", "right": "issue:44488", "accept": false, - "reason": "AddedToken constructor duplication and failure to load cjvt/sleng-bert are not the same bug." + "reason": "Token AddedToken construction error is not the same as a model not loading; only broad tokenizer area overlaps." }, { "left": "issue:43653", "right": "issue:43819", "accept": false, - "reason": "Tokenizer special-token registration and DAC latent reconstruction mismatch are unrelated." + "reason": "Mask-token special registration in tokenizers is unrelated to DAC latent decoding consistency." }, { "left": "issue:43643", "right": "issue:44877", "accept": false, - "reason": "trust_remote_code missing fields and strict config rejecting granite_speech config are both config-loading issues, but not the same underlying bug." + "reason": "Both are config-loading problems, but one is missing fields with trust_remote_code and the other is strict config rejection of granite_speech." }, { "left": "issue:43540", "right": "issue:45381", "accept": false, - "reason": "Qwen3OmniMoe video-input failure and qwen2.5-vl vision_position_ids wrong are different multimodal bugs." + "reason": "Both involve video inputs in Qwen-family models, but they are different models and different bugs." }, { "left": "issue:43531", "right": "issue:43643", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and trust_remote_code config field loss are unrelated." + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to AutoConfig trust_remote_code field loss." }, { "left": "issue:43782", "right": "issue:44977", "accept": false, - "reason": "Qwen3VL weight_only loading error and Qwen3.5 flash-attention generation failure are distinct issues." + "reason": "Different Qwen models and different inference paths: weight_only load error vs flash-attention generation issue." }, { "left": "issue:43577", "right": "issue:43818", "accept": false, - "reason": "BLIP2 dtype loading mismatch and Video-LLaVA temporal-attention/weight-sharing problems are unrelated." - }, - { - "left": "issue:44448", - "right": "issue:44671", - "accept": false, - "reason": "These are both v5 behavior regressions, but they affect different models and different output paths." + "reason": "Different model families and bugs: BLIP2 dtype handling vs Video-LLaVA temporal-attention/weight-sharing issue." }, { "left": "issue:43421", "right": "issue:44811", "accept": false, - "reason": "Runtime post-processor updates for special tokens and Whisper skip_special_tokens decoding are separate tokenizer/processor behaviors." + "reason": "Both are tokenizer-related, but one is runtime post-processor updates and the other is Whisper batch_decode skip_special_tokens handling." }, { - "left": "issue:44561", - "right": "issue:45020", + "left": "issue:44448", + "right": "issue:44671", "accept": false, - "reason": "Removal of is_torch_fx_available breaking trust_remote_code is related to remote_code regressions, but it is a different specific breakage and code path than the broad umbrella issue." + "reason": "Both are v4-v5 behavioral regressions, but they are distinct models and distinct outputs, not the same underlying bug." }, { "left": "issue:30064", "right": "issue:36331", "accept": false, - "reason": "Image processor void segmentation maps and CustomTrainer compute_loss keyword mismatch are entirely unrelated." + "reason": "Image processor segmentation-map handling and CustomTrainer compute_loss signature are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Close in theme, but 44561 is one specific remote_code breakage cause while 45020 is a broader umbrella report; not enough evidence they are the same concrete bug." } ] }, @@ -5053,7 +5095,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28218", "issue:29159", @@ -5070,9 +5112,9 @@ "issue:43582", "issue:43606", "issue:43650", + "issue:43653", "issue:43697", "issue:43720", - "issue:43742", "issue:43782", "issue:43819", "issue:43825", @@ -5091,9 +5133,9 @@ "issue:44805", "issue:44821", "issue:44857", + "issue:44912", "issue:44936", "issue:44991", - "issue:45020", "issue:45072", "issue:45081", "issue:45084", @@ -5107,9 +5149,9 @@ "soft_pairs": [ "issue:43825|issue:43994", "issue:44821|issue:45084", + "issue:44485|issue:44509", "issue:39692|issue:45834", "issue:45584|issue:45834", - "issue:44485|issue:44509", "issue:43322|issue:45685", "issue:44479|issue:45834", "issue:43606|issue:45072", @@ -5126,217 +5168,220 @@ "issue:43404|issue:43782", "issue:45081|issue:45406", "issue:43650|issue:43906", - "issue:44671|issue:45701", "issue:43582|issue:44857", + "issue:44671|issue:45701", "issue:44060|issue:44368", "issue:43262|issue:43819", "issue:43526|issue:43697", "issue:45084|issue:45538", - "issue:43742|issue:45020" + "issue:43653|issue:44912" ], - "prepared_review_unit_hash": "b212b1a24b67fc4ce0d44b9842c0c4c4c7c26f7c26ab09067ad97636503bdb10", + "prepared_review_unit_hash": "fae9706c52964baef1fd5a9fc1e6121c9f1a88cd373135f680fb1329e73c4ab5", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36187, - "estimated_input_tokens": 9047, - "estimated_eval_tokens": 18350 + "serialized_chars": 36249, + "estimated_input_tokens": 9063, + "estimated_eval_tokens": 18382 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No strong duplicate clusters emerge from these soft pairs; most are adjacent regressions in the same library areas but describe different concrete failures. The best representative issue is the broad tokenizer-regression report, not because it duplicates the others, but because it is the most central anchor among this set.", - "confidence": 0.77, - "canonical_issue_reason": "issue:45701 is the broadest and most central report in this set, with multiple inbound references and an active discussion, so it is the best representative anchor if one issue must be chosen.", + "summary": "The cluster is mostly a grab-bag of unrelated tokenizer, multimodal, loading, and docs issues. Only one soft edge looks like a likely duplicate pair: the added-token spacing regression and the slow/fast tokenizer inconsistency report.", + "confidence": 0.58, + "canonical_issue_reason": "issue:28218 is the most concrete statement of the underlying tokenizer bug (an extra space after an added token), while issue:29159 reads like the broader symptom report of the same inconsistency.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45701 is the most general issue here and the closest thing to a cluster hub; the other issues are narrower, model-specific, or unrelated symptoms.", + "best_issue_reason": "issue:28218 is the clearest and most actionable representative of the duplicate pair because it names the concrete failure mode directly.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43825", "right": "issue:43994", "accept": false, - "reason": "Different problems: a v5 pipeline error-message regression versus a SigLIP2 model/pipeline quality issue." + "reason": "Different problems: a v5 pipeline error-message issue versus a SigLIP2 docs/example failure." }, { "left": "issue:44821", "right": "issue:45084", "accept": false, - "reason": "Unrelated failures: loading AutoImageProcessor from URL versus a Jinja/template compilation TypeError." + "reason": "No shared underlying bug; loading an image processor from URL is unrelated to a template compilation TypeError." }, { - "left": "issue:39692", - "right": "issue:45834", + "left": "issue:44485", + "right": "issue:44509", "accept": false, - "reason": "SigLIP2 doc/example mistakes are not the same bug as Kosmos2.5's long-OCR input index error." + "reason": "GLM-5 RoPE implementation discussion is unrelated to docs still mentioning removed pipeline tasks." }, { - "left": "issue:45584", + "left": "issue:39692", "right": "issue:45834", "accept": false, - "reason": "Whisper empty-transcription/alignment bug is unrelated to the Kosmos2.5 OCR index error." + "reason": "Different models and failures: SigLIP2 docs example errors versus Kosmos2.5 OCR index error." }, { - "left": "issue:44485", - "right": "issue:44509", + "left": "issue:45584", + "right": "issue:45834", "accept": false, - "reason": "RoPE implementation discussion and docs mentioning removed pipeline tasks are different issues." + "reason": "Whisper empty-transcription generation failure is unrelated to the Kosmos2.5 long-input OCR issue." }, { "left": "issue:43322", "right": "issue:45685", "accept": false, - "reason": "A Llava Next loading segfault and an MPS int-histogram error in moe are not the same code-path bug." + "reason": "A Llava Next loading segfault and an MPS int histogram limitation are distinct bugs." }, { "left": "issue:44479", "right": "issue:45834", "accept": false, - "reason": "Qwen video-input regression and Kosmos OCR index error are unrelated model-specific failures." + "reason": "Video-input regression in Qwen VL models is not the same as Kosmos2.5 OCR indexing." }, { "left": "issue:43606", "right": "issue:45072", "accept": false, - "reason": "Bark CPU-offload device mismatch is not the same as the dtype mismatch in SwitchTransformers/TimmWrapperModel." + "reason": "CPU offload device mismatch in Bark-small is unrelated to bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel." }, { "left": "issue:43825", "right": "issue:43827", "accept": false, - "reason": "They share the v5 pipeline-removal theme, but one is a runtime error-message issue and the other is docs cleanup; not the same concrete bug." + "reason": "Both involve v5 pipeline removal, but one is a runtime error message and the other is documentation drift; not the same concrete bug." }, { "left": "issue:44186", "right": "issue:44442", "accept": false, - "reason": "LayoutLMv2Tokenizer NER/padding crash and FastSpeech2ConformerTokenizer loading failure are different tokenizer bugs." + "reason": "Different tokenizer failures on different models; no evidence they share one root cause." }, { "left": "issue:34634", "right": "issue:36010", "accept": false, - "reason": "BarkProcessor voice_preset failure is unrelated to the GenerationMixin import-path ImportError." + "reason": "BarkProcessor voice_preset behavior and a GenerationMixin import error are unrelated." }, { "left": "issue:44805", "right": "issue:44936", "accept": false, - "reason": "Mask/tensor shape IndexError versus trainer.evaluate() failing after train are different failures." + "reason": "Mask-shape IndexError is a different failure from trainer.evaluate() breaking after training." }, { "left": "issue:43577", "right": "issue:43582", "accept": false, - "reason": "Blip2 dtype-loading bug and AppleSilicon warmup TypeError do not share the same underlying cause." + "reason": "Blip2 dtype loading and AppleSilicon allocator warmup TypeError are separate issues." }, { "left": "issue:43452", "right": "issue:44991", "accept": false, - "reason": "Both concern loading, but gguf_file breaking from_pretrained and a specific tokenizer load failure in v5 are not the same issue." + "reason": "Both involve loading/tokenizers, but the gguf_file regression and EMBEDDIA tokenizer-loading failure do not appear to be the same bug." }, { "left": "issue:28218", "right": "issue:29159", - "accept": false, - "reason": "The added-token spacing bug may be one symptom, but 29159 is broader inconsistent slow/fast tokenizer behavior and not clearly the same concrete defect." + "accept": true, + "reason": "Both describe the same tokenizer regression around added tokens producing inconsistent spacing/behavior between slow and fast tokenizers." }, { "left": "issue:44610", "right": "issue:45072", "accept": false, - "reason": "Processor/model image-size mismatch is unrelated to the dtype mismatch reported here." + "reason": "Processor image-size mismatch and bf16 dtype mismatch are unrelated." }, { "left": "issue:42175", "right": "issue:45081", "accept": false, - "reason": "Missing TensorFlow in torch extras and a Mistral regex patch crash are unrelated." + "reason": "Dependency/back-end packaging and a Mistral regex patch crash are different problems." }, { "left": "issue:43720", "right": "issue:45072", "accept": false, - "reason": "Packed-weights unpacking during accelerate loading is a different bug from a dtype mismatch in other models." + "reason": "Packed-weight loading in BitNet is unrelated to bf16 dtype mismatch behavior." }, { "left": "issue:43404", "right": "issue:43782", "accept": false, - "reason": "Mistral3 tied-weights warning bug and Qwen3VL weight_only loading error are different model/load-path failures." + "reason": "Weight-tying bug in Mistral3 and Qwen3VL weight_only loading error are different model-specific issues." }, { "left": "issue:45081", "right": "issue:45406", "accept": false, - "reason": "Both are AttributeErrors during loading, but they involve different missing attributes and different processor/tokenizer paths." + "reason": "Mistral tokenizer regex patch crash and Gemma4Processor missing _tokenizer are distinct failures." }, { "left": "issue:43650", "right": "issue:43906", "accept": false, - "reason": "'ADD THE DATA' is not a concrete bug report and is not the same as the isolated reproduction issue." + "reason": "The titles are unrelated; no duplicate relationship is apparent." }, { - "left": "issue:44671", - "right": "issue:45701", + "left": "issue:43582", + "right": "issue:44857", "accept": false, - "reason": "CamemBERT masked-LM regression and a broad tokenizer-version-change report are related only at a high level, not the same bug." + "reason": "Apple Silicon warmup TypeError and CUDA float16 AMP crash are different environment-specific bugs." }, { - "left": "issue:43582", - "right": "issue:44857", + "left": "issue:44671", + "right": "issue:45701", "accept": false, - "reason": "AppleSilicon warmup TypeError and CUDA float16 AMP crash are different platform-specific issues." + "reason": "A CamemBERT masked-LM regression and a generic tokenization-version change report are not the same concrete bug." }, { "left": "issue:44060", "right": "issue:44368", "accept": false, - "reason": "Both mention tied-weights warnings, but they are different model families and symptoms; not one concrete bug." + "reason": "Both mention tied-weights warnings, but they concern different Qwen models and different symptoms." }, { "left": "issue:43262", "right": "issue:43819", "accept": false, - "reason": "Audio apply_chat_template sampling-rate defaulting and DAC.from_latents vs forward mismatch are unrelated." + "reason": "Audio chat-template sampling-rate defaulting and DAC latent/forward mismatch are unrelated audio bugs." }, { "left": "issue:43526", "right": "issue:43697", "accept": false, - "reason": "reduce_labels returning one label and RTDetrV2 output divergence are different model/processor bugs." + "reason": "BEiT label reduction and RT-DETRv2 output differences are different vision issues." }, { "left": "issue:45084", "right": "issue:45538", "accept": false, - "reason": "Template compilation errors and CLIPTokenizer model_max_length behavior are unrelated tokenizer/template issues." + "reason": "Template compilation TypeError and CLIPTokenizer model_max_length behavior are unrelated." }, { - "left": "issue:43742", - "right": "issue:45020", + "left": "issue:43653", + "right": "issue:44912", "accept": false, - "reason": "A key error for one model is not the same as the broad remote_code regression." + "reason": "BigBirdTokenizer special-token registration and MXFP4 quantization fallback are not the same issue." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays mostly conservative. The one accepted soft edge, issue:28218 vs issue:29159, is plausible from the titles and similarity signal, and the other non-duplicates are reasonably rejected. No mergeability concerns apply here since there are no PR pairs." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -5351,7 +5396,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:34567", "issue:34634", @@ -5375,8 +5420,8 @@ "issue:43643", "issue:43644", "issue:43645", - "issue:43653", "issue:43720", + "issue:43742", "issue:43746", "issue:43749", "issue:43819", @@ -5392,6 +5437,7 @@ "issue:44912", "issue:44936", "issue:44977", + "issue:45020", "issue:45042", "issue:45356", "issue:45459", @@ -5402,11 +5448,11 @@ "issue:45859" ], "soft_pairs": [ - "issue:43653|issue:44912", + "issue:43742|issue:45020", "issue:43329|issue:45600", "issue:45459|issue:45803", - "issue:43644|issue:43749", "issue:43638|issue:44936", + "issue:43644|issue:43749", "issue:44589|issue:45042", "issue:43746|issue:44811", "issue:38175|issue:44610", @@ -5422,234 +5468,231 @@ "issue:43749|issue:44291", "issue:43531|issue:45042", "issue:43257|issue:43329", - "issue:43262|issue:44811", "issue:36010|issue:36331", + "issue:43262|issue:44811", "issue:44568|issue:45356", "issue:42490|issue:43257", "issue:43643|issue:45759", "issue:43329|issue:44479", - "issue:43329|issue:43450", "issue:44568|issue:45488", + "issue:43329|issue:43450", "issue:34567|issue:40990", "issue:43606|issue:45859" ], - "prepared_review_unit_hash": "29b51eb2730e5621659141944018aa06e6fbe1a8b5c20ec40f50080b6198689b", + "prepared_review_unit_hash": "f23a09b0473772fd249c9ffb1dc56d120ba9038eb44bd6f802256d78229b6a88", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 47, - "item_count": 47, + "node_count": 48, + "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36589, - "estimated_input_tokens": 9148, - "estimated_eval_tokens": 18552 + "serialized_chars": 37109, + "estimated_input_tokens": 9278, + "estimated_eval_tokens": 18812 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "All soft-edge pairs should be rejected on the evidence provided. The Qwen video issues are related in subsystem, but issue:43329 is a specific multimodal token-counting bug while issue:44479 is a broader video-input regression, which is not enough to prove the same underlying bug or code path.", - "confidence": 0.83, - "canonical_issue_reason": "issue:44479 is the best canonical issue candidate because it is the broadest, most user-facing report in the cluster and names the full affected Qwen VL family; issue:43329 is narrower and looks more root-cause-specific, but not strong enough to merge them as duplicates.", + "summary": "This batch is mostly a collection of unrelated bugs, not a tight duplicate cluster. I rejected all soft-edge duplicate candidates because they point to different code paths, models, or failure modes. If one issue must serve as a representative, #45020 is the broadest regression-style report, but it is not a true duplicate umbrella for the rest.", + "confidence": 0.92, + "canonical_issue_reason": "#45020 is the broadest, most general regression report in the set (remote_code-related loading breakage), so it is the closest thing to a representative issue; however, the batch does not form a real duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the strongest representative issue for the cluster because it captures the widest scope and clearest regression framing, while the other issues are either unrelated or too weakly connected to be treated as duplicates.", + "best_issue_reason": "#45020 is the best global representative because it is the least model-specific and most likely to subsume adjacent loading regressions, even though the other issues are still distinct.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43653", - "right": "issue:44912", + "left": "issue:43742", + "right": "issue:45020", "accept": false, - "reason": "Different failure modes and components: tokenizer special-token decoding vs quantization/load fallback." + "reason": "Different failures: MobileLLM loading key error vs a broad remote_code regression; not the same code path." }, { "left": "issue:43329", "right": "issue:45600", "accept": false, - "reason": "Same broad multimodal area, but one is a video-token counting bug and the other is a stale auto-mapping reference; not the same bug." + "reason": "Video token counting bug vs stale auto_mappings references; unrelated problems." }, { "left": "issue:45459", "right": "issue:45803", "accept": false, - "reason": "Both involve error handling, but they affect different tokenizer/feature code paths and different concrete failures." + "reason": "Tokenizer protobuf error handling vs bare-except swallowing errors in Fuyu tensor conversion; different functions and bugs." }, { - "left": "issue:43644", - "right": "issue:43749", + "left": "issue:43638", + "right": "issue:44936", "accept": false, - "reason": "Both are loading-related, but the actual bugs differ: non-persistent buffer init vs FSDP RAM-efficient loading regression." + "reason": "DeepSpeed ZeRO-3 index error during Bert training vs trainer evaluate-after-train failure; distinct trainer behaviors." }, { - "left": "issue:43638", - "right": "issue:44936", + "left": "issue:43644", + "right": "issue:43749", "accept": false, - "reason": "Different training/evaluation failures with no shared underlying code path shown." + "reason": "Non-persistent buffer initialization junk vs FSDP CPU RAM efficient loading; different loading issues." }, { "left": "issue:44589", "right": "issue:45042", "accept": false, - "reason": "Unrelated problems: float8 storage lookup error vs PIL backend requiring torchvision." + "reason": "Float8 storage deserialization error vs PIL backend torchvision dependency regression; unrelated." }, { "left": "issue:43746", "right": "issue:44811", "accept": false, - "reason": "Different models and APIs: PEFT/local checkpoint loading vs Whisper batch decoding behavior." + "reason": "PEFT checkpoint loading for GraniteSpeech vs Whisper batch_decode skip_special_tokens; different processor/model paths." }, { "left": "issue:38175", "right": "issue:44610", "accept": false, - "reason": "Different model families and symptoms: zero probabilities vs processor input-size mismatch." + "reason": "SigLIP2 zero probabilities vs OmDet-Turbo image size mismatch; different symptoms and code paths." }, { "left": "issue:43819", "right": "issue:43927", "accept": false, - "reason": "Different bugs in different components: DAC latent conversion vs config token IDs after save/load." + "reason": "DAC latent conversion mismatch vs DiaConfig token ID persistence bug; not the same underlying defect." }, { "left": "issue:39692", "right": "issue:44912", "accept": false, - "reason": "Documentation/example cleanup and quantization fallback are separate issues." + "reason": "SigLIP2 doc/example errors vs MXFP4 quantization falling back to bf16; different problems." }, { "left": "issue:43854", "right": "issue:44977", "accept": false, - "reason": "Different model-loading/runtime failures with no shared concrete code path indicated." + "reason": "GLM-4.7-Flash load issue vs Qwen3.5 flash-attention generation bug; different models and code paths." }, { "left": "issue:36010", "right": "issue:43645", "accept": false, - "reason": "Both involve import/model initialization, but they are different APIs and failure mechanisms." + "reason": "GenerationMixin import failure vs Jupyter custom-model initialization breakage; related only at a very high level." }, { "left": "issue:43550", "right": "issue:44912", "accept": false, - "reason": "A torch.compile + SDPA issue is not the same as an MXFP4 quantization load fallback." + "reason": "torch.compile SDPA failure vs quantization fallback to bf16; different concrete bugs." }, { "left": "issue:43526", "right": "issue:44554", "accept": false, - "reason": "Different components and bugs: BEiT label reduction vs MPS attention correctness." + "reason": "BEiT reduce_labels bug vs MPS attention correctness issue; unrelated." }, { "left": "issue:34634", "right": "issue:36331", "accept": false, - "reason": "No shared underlying bug; Bark voice preset handling is unrelated to a CustomTrainer signature change." + "reason": "BarkProcessor voice_preset bug vs CustomTrainer compute_loss signature mismatch; different areas entirely." }, { "left": "issue:43720", "right": "issue:44610", "accept": false, - "reason": "Packed-weight loading in BitNet is unrelated to OmDet-Turbo processor output shape/size." + "reason": "Packed-weight unpacking during accelerate loading vs processor output shape mismatch; not the same change." }, { "left": "issue:43454", "right": "issue:43577", "accept": false, - "reason": "Different model-specific issues: weight tying in AyaVision vs dtype propagation in BLIP2." + "reason": "AyaVision weight tying bug vs BLIP-2 dtype propagation bug; distinct model-init issues." }, { "left": "issue:43749", "right": "issue:44291", "accept": false, - "reason": "Both are loading-related, but one is an FSDP-efficient-loading regression and the other is an init_empty_weights argument mismatch." + "reason": "FSDP loading regression vs unexpected _is_hf_initialized arg in init_empty_weights; different compatibility failures." }, { "left": "issue:43531", "right": "issue:45042", "accept": false, - "reason": "A Qwen3-MoE sliding-window issue is unrelated to PIL backend torchvision requirements." + "reason": "Qwen3-MoE sliding_window issue vs PIL backend requiring torchvision; unrelated subsystems." }, { "left": "issue:43257", "right": "issue:43329", "accept": false, - "reason": "Accelerate+DeepSpeed weight conversion is unrelated to multimodal video token counting." + "reason": "Qwen3 MoE weight conversion/loading bug vs undefined video helper usage in multimodal token counting; different bugs." }, { - "left": "issue:43262", - "right": "issue:44811", + "left": "issue:36010", + "right": "issue:36331", "accept": false, - "reason": "Audio chat-template sample-rate defaults and Whisper decode skipping are different processor behaviors." + "reason": "Importing GenerationMixin vs CustomTrainer.compute_loss kwargs; unrelated." }, { - "left": "issue:36010", - "right": "issue:36331", + "left": "issue:43262", + "right": "issue:44811", "accept": false, - "reason": "ImportError for GenerationMixin and compute_loss signature mismatch are unrelated trainer/runtime problems." + "reason": "Audio chat-template sampling-rate default bug vs Whisper batch_decode special-token handling; different processor bugs." }, { "left": "issue:44568", "right": "issue:45356", "accept": false, - "reason": "Different tokenizer regressions affecting different tokenizer classes and root causes." + "reason": "mdeberta special-token regression vs Kimi tokenizer codec/regression warning; different tokenizer paths." }, { "left": "issue:42490", "right": "issue:43257", "accept": false, - "reason": "Local-path import warning is unrelated to Qwen3 MoE weight conversion during accelerate/deepspeed loading." + "reason": "Trailing-slash local-model import warning vs Qwen3 MoE accelerate/deepspeed conversion issue; unrelated." }, { "left": "issue:43643", "right": "issue:45759", "accept": false, - "reason": "Different config-handling bugs: missing fields from trust_remote_code vs text_config unwrapping for composite multimodal configs." + "reason": "Missing fields from AutoConfig with trust_remote_code vs not unwrapping text_config in AutoModelForCausalLM.from_config; different config-loading bugs." }, { "left": "issue:43329", "right": "issue:44479", "accept": false, - "reason": "Related in scope, but the evidence only shows a broad video/VLM overlap; it does not establish the same broken code path or same bug." + "reason": "Both involve video VLM behavior, but one is a specific undefined-helper bug and the other is a broader regression; not the same concrete defect." }, { - "left": "issue:43329", - "right": "issue:43450", + "left": "issue:44568", + "right": "issue:45488", "accept": false, - "reason": "One is a multimodal token-counting bug; the other is a batched video processor shape bug." + "reason": "add_special_tokens regression vs LlamaTokenizer overriding ByteLevel with Metaspace; related to tokenizers but not the same bug." }, { - "left": "issue:44568", - "right": "issue:45488", + "left": "issue:43329", + "right": "issue:43450", "accept": false, - "reason": "Different tokenizer regressions affecting different tokenizer classes and different behavior." + "reason": "Multimodal token counting video branch bug vs batched video processor output shape bug; different stages of processing." }, { "left": "issue:34567", "right": "issue:40990", "accept": false, - "reason": "Trainer token-count tracking and perplexity on gpt-oss are unrelated." + "reason": "Trainer num_input_tokens_seen not updating vs high perplexity on gpt-oss; unrelated." }, { "left": "issue:43606", "right": "issue:45859", "accept": false, - "reason": "Both mention CPU offload, but they affect different models and different failing code paths." + "reason": "Bark CPU offload device mismatch vs Qwen3_MoeTextRotaryEmbedding CPU offload incompatibility; different models and code paths." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The negative soft-edge verdicts are generally conservative, but the one accepted pair is too strong for the evidence in the packet. From titles alone, issue:43329 is a specific multimodal token-counting bug in a video branch, while issue:44479 is a broader video-input regression across several Qwen VL variants. That supports broad similarity, but not that they are the same broken code path or the same bug. The summary also overstates this by calling it the only plausible duplicate-looking pair. Please downgrade that pair to a tentative/uncertain match or reject it." - }, - "evaluator_used": true, - "retried": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -5665,7 +5708,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:24643", "issue:29159", @@ -5722,8 +5765,8 @@ "issue:29159|issue:34567", "issue:43257|issue:43931", "issue:44291|issue:45042", - "issue:42915|issue:43742", "issue:43452|issue:43582", + "issue:42915|issue:43742", "issue:41720|issue:43540", "issue:33357|issue:34567", "issue:42915|issue:44821", @@ -5738,12 +5781,12 @@ "issue:38175|issue:44898", "issue:43404|issue:45987", "issue:43577|issue:45072", + "issue:24643|issue:29159", "issue:45137|issue:45405", "issue:43257|issue:43756", - "issue:24643|issue:29159", "issue:43742|issue:44291", - "issue:44062|issue:44991", "issue:44737|issue:45588", + "issue:44062|issue:44991", "issue:43540|issue:45823", "issue:43257|issue:43696", "issue:43906|issue:45381", @@ -5751,20 +5794,20 @@ "issue:34567|issue:36331", "issue:43646|issue:43749" ], - "prepared_review_unit_hash": "02d9766c4c35a24d9253b4dd6027683264a48b912f64b12e040be3df849a4fb4", + "prepared_review_unit_hash": "04a260264fa20c3b763abe26d401ade2afcb2032445de4747b603df9c91f19de", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 33, - "serialized_chars": 37603, + "serialized_chars": 37601, "estimated_input_tokens": 9401, "estimated_eval_tokens": 19058 }, @@ -5773,66 +5816,66 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "Mostly a heterogeneous set of closed issues with a small Qwen video-input regression subcluster. The only clear near-duplicate here is the v5.3.0 Qwen video-input regression pair (44479/45381); the rest are too model- or subsystem-specific to merge.", - "confidence": 0.77, - "canonical_issue_reason": "issue:44479 is the best representative because it states the broad v5.3.0 video-input regression affecting multiple Qwen VL variants and subsumes the narrower 45381 report.", + "summary": "This cluster is mostly heterogeneous false positives. The only clear duplicate pair is the Qwen2.5-VL video-input regression reports; all other soft pairs describe different bugs, models, or code paths.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44479 is the best canonical issue because it describes the broad v5.3.0 video-input regression across Qwen VL variants; issue:45381 is a narrower reproduction of the same problem.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44479 is the strongest cluster representative: broad scope, explicit regression framing, and it aligns with the only accepted soft duplicate pair.", + "best_issue_reason": "issue:44479 is the strongest global representative of the only true duplicate area in this set, since it captures the broader regression rather than a single model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44849", "right": "issue:45701", "accept": false, - "reason": "Different problems: Qwen3.5 hidden-state behavior vs. tokenizer/version-dependent tokenization changes." + "reason": "Different problems: Qwen3.5 hidden-state behavior vs a general tokenization-version change." }, { "left": "issue:43697", "right": "issue:45357", "accept": false, - "reason": "Different code paths and symptoms: RTDetrV2 forward outputs vs. Qwen3.5 save_pretrained key serialization." + "reason": "Unrelated failures: RTDetrV2 output differences vs Qwen3.5 visual-encoder key saving." }, { "left": "issue:29159", "right": "issue:34567", "accept": false, - "reason": "Tokenizer slow/fast inconsistency and TrainerState token counters are unrelated." + "reason": "Tokenizer slow/fast inconsistency is unrelated to TrainerState token counting." }, { "left": "issue:43257", "right": "issue:43931", "accept": false, - "reason": "Both touch Qwen3 loading, but one is MOE weight conversion with accelerate+deepspeed and the other is a Qwen3-VL shape mismatch; not the same bug." + "reason": "Different loading bugs: Qwen3 MOE weight conversion vs Qwen3-VL weight-shape mismatch." }, { "left": "issue:44291", "right": "issue:45042", "accept": false, - "reason": "Init_empty_weights/_is_hf_initialized and PIL image processor torchvision requirements are unrelated." + "reason": "Init-empty-weights argument handling is unrelated to PIL image processor torchvision requirements." }, { - "left": "issue:42915", - "right": "issue:43742", + "left": "issue:43452", + "right": "issue:43582", "accept": false, - "reason": "Different failures: FineGrainedFP8Config on Qwen3Moe vs. a MobileLLM-125M key error." + "reason": "Tokenizer/gguf loading issue and Apple Silicon allocator TypeError are unrelated." }, { - "left": "issue:43452", - "right": "issue:43582", + "left": "issue:42915", + "right": "issue:43742", "accept": false, - "reason": "Tokenizer/AutoModel gguf loading and AppleSilicon allocator warmup TypeError are unrelated." + "reason": "Qwen3Moe FineGrainedFP8 loading and MobileLLM key errors are different model-loading failures." }, { "left": "issue:41720", "right": "issue:43540", "accept": false, - "reason": "Both are Qwen family issues, but one is device-mapping cuda assert and the other is video-input parsing; not the same concrete bug." + "reason": "CUDA assert with auto device mapping is unrelated to Qwen3OmniMoe video-input ValueError." }, { "left": "issue:33357", "right": "issue:34567", "accept": false, - "reason": "CLIP Mac bus error and TrainerState token tracking are unrelated." + "reason": "MacOS bus error on CLIP loading is unrelated to TrainerState token counting." }, { "left": "issue:42915", @@ -5844,109 +5887,109 @@ "left": "issue:43927", "right": "issue:44912", "accept": false, - "reason": "DiaConfig token IDs vs. git-oss MXFP4 quantization fallback are unrelated." + "reason": "DiaConfig save/load token IDs and GPT-oss quantization fallback are different bugs." }, { "left": "issue:44479", "right": "issue:45381", "accept": true, - "reason": "Both describe the same Qwen VL video-input regression in transformers v5.3.0; 45381 is a narrower manifestation of the broader 44479 report." + "reason": "Both describe the same Qwen VL video-input regression/incorrect vision position ids in transformers 5.3.0." }, { "left": "issue:44987", "right": "issue:45907", "accept": false, - "reason": "Tokenizer/model loading failure and list_repo_files revision forwarding are unrelated." + "reason": "Model loading on physical-intelligence/fast is unrelated to list_repo_files revision forwarding." }, { "left": "issue:44987", "right": "issue:45538", "accept": false, - "reason": "Model-specific tokenizer loading failure vs. CLIPTokenizer model_max_length bug." + "reason": "General model loading failure and CLIPTokenizer max_length bug are unrelated." }, { "left": "issue:42915", "right": "issue:45538", "accept": false, - "reason": "FP8 Qwen3Moe load failure and CLIPTokenizer max-length issue are unrelated." + "reason": "Qwen3Moe quantization loading and CLIPTokenizer model_max_length are unrelated." }, { "left": "issue:43540", "right": "issue:44560", "accept": false, - "reason": "Different video-input bugs in different Qwen multimodal models; not clearly the same underlying defect." + "reason": "Different video bugs in different model families; not the same concrete code path." }, { "left": "issue:43540", "right": "issue:44479", "accept": false, - "reason": "Both are video-related, but the affected models and reported failures differ enough that they do not look like the same bug." + "reason": "Both are video-related, but they affect different Qwen model families and error paths." }, { "left": "issue:43317", "right": "issue:45538", "accept": false, - "reason": "Dequantized model offload loading and CLIPTokenizer max-length are unrelated." + "reason": "device_map/offload loading failure is unrelated to tokenizer max_length." }, { "left": "issue:38175", "right": "issue:44898", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 and Perceiver interpolation failures are unrelated vision bugs." + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to Perceiver non-default-resolution failure." }, { "left": "issue:43404", "right": "issue:45987", "accept": false, - "reason": "lm_head tying in Mistral3 and StaticCache sequence-length return type are unrelated." + "reason": "Mistral3 lm_head tying bug is unrelated to StaticCache sequence-length return type." }, { "left": "issue:43577", "right": "issue:45072", "accept": false, - "reason": "Both involve dtype issues, but on different models and code paths; not the same concrete bug." + "reason": "BLIP2 dtype loading and SwitchTransformers/TimmWrapper bfloat16 mismatches are different issues." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "DeepSpeed weight-dimension runtime error is unrelated to tokenizer inconsistency." }, { "left": "issue:45137", "right": "issue:45405", "accept": false, - "reason": "DeepSpeed ZeRO3 deque error and a PEFT version bump are unrelated." + "reason": "DeepSpeed ZeRO3 deque error and MIN_PEFT_VERSION bump are unrelated." }, { "left": "issue:43257", "right": "issue:43756", "accept": false, - "reason": "Qwen3 MOE weight conversion and Smollm3 RoPE-layer count are unrelated." - }, - { - "left": "issue:24643", - "right": "issue:29159", - "accept": false, - "reason": "DeepSpeed weight-dimension error and tokenizer slow/fast inconsistency are unrelated." + "reason": "Qwen3 MOE weight conversion and Smollm3 RoPE-layer mismatch are different model bugs." }, { "left": "issue:43742", "right": "issue:44291", "accept": false, - "reason": "MobileLLM key error and init_empty_weights unexpected argument are unrelated load-time failures." + "reason": "MobileLLM load error and init_empty_weights unexpected-arg failure are unrelated." }, { - "left": "issue:44062", - "right": "issue:44991", + "left": "issue:44737", + "right": "issue:45588", "accept": false, - "reason": "Both are tokenizer-load failures, but the models and specific failure modes are too different to treat as the same bug from the available evidence." + "reason": "XLNet CPU arange bug is unrelated to flash_attention s_aux=None crash." }, { - "left": "issue:44737", - "right": "issue:45588", + "left": "issue:44062", + "right": "issue:44991", "accept": false, - "reason": "XLNet CPU arange bug and flash_attention sinkless-model AttributeError are unrelated." + "reason": "AddedToken special-argument duplication and EMBEDDIA tokenizer loading failure are not the same concrete bug." }, { "left": "issue:43540", "right": "issue:45823", "accept": false, - "reason": "Different models and different device-mapping/video-input failures; not the same bug." + "reason": "Qwen3OmniMoe video input error and Gemma4 PLE device mismatch are unrelated." }, { "left": "issue:43257", @@ -5958,31 +6001,31 @@ "left": "issue:43906", "right": "issue:45381", "accept": false, - "reason": "No clear linkage: one is an isolated reproduction of another issue, the other is a Qwen VL video-input regression." + "reason": "Reproduction of issue 38071 is unrelated to the Qwen2.5-VL video-position-id regression." }, { "left": "issue:44062", "right": "issue:45081", "accept": false, - "reason": "AddedToken special-argument duplication and Mistral regex/backend_tokenizer failure are different tokenizer issues." + "reason": "AddedToken special duplication and Mistral regex patch AttributeError are different tokenizer bugs." }, { "left": "issue:34567", "right": "issue:36331", "accept": false, - "reason": "TrainerState token counting and compute_loss signature change are unrelated training API issues." + "reason": "TrainerState token counter not updating is unrelated to CustomTrainer compute_loss signature mismatch." }, { "left": "issue:43646", "right": "issue:43749", "accept": false, - "reason": "Custom model init breakage and FSDP CPU RAM efficient loading failure are different problems despite both involving loading." + "reason": "Custom model initialization breakage and FSDP CPU RAM-efficient loading are unrelated." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted near-duplicate pair, 44479/45381, is well-supported as the same Qwen VL video-input regression family, and the rest of the soft-edge rejections are appropriately cautious given the differing models, subsystems, or failure modes. No mergeability issue is apparent for the accepted pair." + "feedback": "The summary is well grounded in the packet and stays conservative: the single accepted duplicate pair is the only one that clearly matches in the provided titles, and the other soft-edge rejections are supported by the issue descriptions. No obvious overstatement or mergeability issue." }, "evaluator_used": true, "retried": false, @@ -6001,7 +6044,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28282", "issue:29127", @@ -6059,8 +6102,8 @@ "issue:42175|issue:43824", "issue:45357|issue:45920", "issue:44291|issue:44821", - "issue:43643|issue:45375", "issue:43452|issue:44488", + "issue:43643|issue:45375", "issue:44792|issue:44964", "issue:45042|issue:45081", "issue:28282|issue:34689", @@ -6070,214 +6113,217 @@ "issue:45405|issue:45600", "issue:43531|issue:44821", "issue:43697|issue:45216", - "issue:28282|issue:29127", "issue:44514|issue:45381", + "issue:28282|issue:29127", "issue:43720|issue:44898", "issue:43582|issue:44977", - "issue:42175|issue:44938", "issue:44484|issue:44704", "issue:41762|issue:44936", + "issue:42175|issue:44938", "issue:44625|issue:44877", "issue:43452|issue:43577", "issue:43452|issue:44843" ], - "prepared_review_unit_hash": "498be8b0073004fa785366fb531538c3ab59a44808b8bb1855365d00a41096b8", + "prepared_review_unit_hash": "dec4a574a0b70bb5c8e7e9c8ddc28f895df5325c1db61578f2753255d7c3badb", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 36124, - "estimated_input_tokens": 9031, - "estimated_eval_tokens": 18318 + "serialized_chars": 36127, + "estimated_input_tokens": 9032, + "estimated_eval_tokens": 18320 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The soft pairs are mostly false positives: they share broad themes like model loading, config handling, or tokenizer regressions, but they do not look like the same concrete bug or fixable change. No clear duplicate cluster emerges from these issues.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "This cluster is mostly heterogeneous: many unrelated model-loading, config, and backend issues. I found one plausible duplicate pair around SigLIP2 correctness, but the rest do not look like the same underlying bug/change.", + "confidence": 0.69, + "canonical_issue_reason": "issue:43493 is the best root-cause-style report in the only believable duplicate pair: it describes the SigLIP2 implementation discrepancy directly, while the other report is a downstream symptom (bad outputs).", "canonical_pr_reason": null, - "best_issue_reason": "issue:45920 is the strongest representative because it describes a broad, active AutoTokenizer regression affecting multiple model families, with clear user impact and a concrete loading/token-ID code path.", + "best_issue_reason": "issue:43493 is the strongest global representative because it is concrete, model-specific, and framed around the likely underlying correctness bug rather than just a user-facing failure mode.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43493", "right": "issue:43994", - "accept": false, - "reason": "Both are about SigLIP2, but one is an HF-vs-JAX implementation discrepancy and the other is a nonsensical-results report; they do not clearly point to the same concrete defect." + "accept": true, + "reason": "Same model family (SigLIP2) and same underlying symptom class: HF vs reference discrepancy leading to incorrect/nonsensical outputs. These could plausibly be one bug." }, { "left": "issue:43749", "right": "issue:44756", "accept": false, - "reason": "These are unrelated failures: FSDP CPU RAM-efficient loading vs disabling mmap on Strix Halo to avoid OOM." + "reason": "Different failures and environments: FSDP CPU RAM-efficient loading versus mmap/OOM on Strix Halo." }, { "left": "issue:36010", "right": "issue:42175", "accept": false, - "reason": "GenerationMixin import failure and missing TensorFlow backend packaging are different problems with different code paths." + "reason": "Unrelated: missing GenerationMixin import versus TensorFlow backend packaging omission." }, { "left": "issue:42175", "right": "issue:43824", "accept": false, - "reason": "A packaging/backend omission is not the same as the Qwen2.5-VL import error." + "reason": "Unrelated install/backend packaging issue versus Qwen2.5-VL import error." }, { "left": "issue:45357", "right": "issue:45920", "accept": false, - "reason": "Both involve Qwen3.5/serialization or tokenization regressions, but they concern different failures: save_pretrained key handling vs wrong token IDs at inference." + "reason": "Both are regressions, but they concern different code paths: save_pretrained serialization versus tokenizer ID generation." }, { "left": "issue:44291", "right": "issue:44821", "accept": false, - "reason": "init_empty_weights TypeError and loading AutoImageProcessor from URL are unrelated bugs." + "reason": "Different areas: init_empty_weights/_is_hf_initialized argument handling versus loading AutoImageProcessor from URL." }, { - "left": "issue:43643", - "right": "issue:45375", + "left": "issue:43452", + "right": "issue:44488", "accept": false, - "reason": "Both mention config fields being dropped, but one is a generic trust_remote_code loading issue while the other is a specific Qwen3_5MoeVisionConfig field omission." + "reason": "Both involve model loading, but the concrete bugs differ: gguf_file handling versus a specific model load failure." }, { - "left": "issue:43452", - "right": "issue:44488", + "left": "issue:43643", + "right": "issue:45375", "accept": false, - "reason": "General gguf_file loading breakage and a specific model load failure are not the same underlying issue." + "reason": "Related only loosely through missing config fields; the reported causes and affected models are different." }, { "left": "issue:44792", "right": "issue:44964", "accept": false, - "reason": "Both are multimodal/model-loading reports, but they target different models and failure modes." + "reason": "Different models and failures: janus image-generation test versus Phi-4 multimodal loading." }, { "left": "issue:45042", "right": "issue:45081", "accept": false, - "reason": "Image-processor torchvision dependency handling is unrelated to the Mistral regex patch crash." + "reason": "Completely different subsystems: image processor torchvision dependency versus Mistral regex/tokenizer crash." }, { "left": "issue:28282", "right": "issue:34689", "accept": false, - "reason": "A missing PyTorch ImportError and a Llama 3.2 vision model-loading breakage are distinct issues." + "reason": "Different issues: missing PyTorch dependency import error versus Llama 3.2 Vision loading breakage." }, { "left": "issue:43526", "right": "issue:45479", "accept": false, - "reason": "One is a BeitImageProcessorFast label reduction bug; the other is a sequence-classification zero-loss problem across models." + "reason": "Different bug classes: BEiT image processor label reduction versus sequence-classification loss degeneracy." }, { "left": "issue:43742", "right": "issue:44589", "accept": false, - "reason": "KeyError while loading MobileLLM-125M and a Float8 storage lookup TypeError are unrelated." + "reason": "Different concrete failures: MobileLLM key error versus Float8 storage lookup TypeError." }, { "left": "issue:43756", "right": "issue:45325", "accept": false, - "reason": "Both are RoPE-related, but they affect different models and different position-index calculations." + "reason": "Both mention positional/RoPE logic, but they are different models and different incorrect computations." }, { "left": "issue:45405", "right": "issue:45600", "accept": false, - "reason": "PEFT minimum-version bump and stale auto_mappings references are separate maintenance issues." + "reason": "Unrelated: dependency version bump issue versus removed config references breaking CI." }, { "left": "issue:43531", "right": "issue:44821", "accept": false, - "reason": "Qwen3-MoE sliding_window behavior and AutoImageProcessor URL loading are unrelated." + "reason": "Unrelated: Qwen3-MoE sliding-window behavior versus AutoImageProcessor URL loading." }, { "left": "issue:43697", "right": "issue:45216", "accept": false, - "reason": "RTDetrV2 output differences in v5 and Qwen3.5 save_pretrained regression are different code paths." + "reason": "Different regressions and paths: RTDetrV2 output mismatch versus Qwen3.5 checkpoint saving." }, { - "left": "issue:28282", - "right": "issue:29127", + "left": "issue:44514", + "right": "issue:45381", "accept": false, - "reason": "Missing PyTorch import and LayoutLMv3 box-validation error are not the same bug." + "reason": "Same model family, but different bugs: batching/padding crash versus wrong video vision_position_ids." }, { - "left": "issue:44514", - "right": "issue:45381", + "left": "issue:28282", + "right": "issue:29127", "accept": false, - "reason": "Both involve Qwen2.5-VL processing, but one is batched chat-template padding behavior and the other is video vision_position_ids correctness." + "reason": "Unrelated: PyTorch missing import error versus LayoutLMv3 error-message clarity." }, { "left": "issue:43720", "right": "issue:44898", "accept": false, - "reason": "BitNet packed-weight loading and Perceiver interpolation failure are unrelated." + "reason": "Different models and code paths: BitNet packed-weight loading versus Perceiver interpolation failure." }, { "left": "issue:43582", "right": "issue:44977", "accept": false, - "reason": "Apple Silicon allocator warmup TypeError and Qwen3.5 flash-attention generation issues do not share the same fix." - }, - { - "left": "issue:42175", - "right": "issue:44938", - "accept": false, - "reason": "A packaging/backend issue and a Python 3.14 load failure are different failures." + "reason": "Different platforms and bugs: Apple Silicon allocator TypeError versus Qwen3.5 flash-attention generation." }, { "left": "issue:44484", "right": "issue:44704", "accept": false, - "reason": "save_pretrained shard-size behavior and AutoProcessor cached_file kwargs passing are unrelated." + "reason": "Different concerns: save_pretrained shard size policy versus passing kwargs to cached_file." }, { "left": "issue:41762", "right": "issue:44936", "accept": false, - "reason": "DeepSpeed ZeRO-3 loading failure and trainer.evaluate after train are separate runtime issues." + "reason": "Different failures: DeepSpeed ZeRO-3 load index error versus trainer.evaluate() after train()." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Unrelated: backend packaging versus Python 3.14 load failure." }, { "left": "issue:44625", "right": "issue:44877", "accept": false, - "reason": "Qwen3.5 num_labels propagation and granite_speech strict-config loading are different config bugs." + "reason": "Both are config-related, but one is num_labels propagation and the other is strict config blocking a model load." }, { "left": "issue:43452", "right": "issue:43577", "accept": false, - "reason": "gguf_file loading breakage and BLIP2 dtype remaining float32 are unrelated." + "reason": "Different loading issues: gguf_file/pretrained loading versus Blip2 dtype propagation." }, { "left": "issue:43452", "right": "issue:44843", "accept": false, - "reason": "gguf_file loading and offline model_info calls in mistral regex patch are different loading regressions." + "reason": "Both touch loading, but one is gguf_file support and the other is an offline Mistral regex/network call bug." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The only accepted soft pair, issue:43493 with issue:43994, is plausible based on shared SigLIP2/model-correctness framing, and the rest of the pairwise rejections are cautious rather than overstated." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -6292,7 +6338,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:24643", "issue:29127", @@ -6375,224 +6421,209 @@ "issue:32090|issue:34567", "issue:43504|issue:44610" ], - "prepared_review_unit_hash": "fcbf8f3be6d54ad2fb83fcca24a1e8034eb5fcfdbb7478fe690d2bcdf77596a3", + "prepared_review_unit_hash": "2576aedff65917ba2862fe730f97315bee94c275d2ed92a8ffabc8f985e62408", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 30, - "serialized_chars": 36842, - "estimated_input_tokens": 9211, - "estimated_eval_tokens": 18678 + "serialized_chars": 36847, + "estimated_input_tokens": 9212, + "estimated_eval_tokens": 18680 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is mostly heterogeneous. I only see two plausible duplicate islands: the apply_chat_template crash around assistant tool-call messages, and the v5 tied-weights serialization issue. Everything else looks model- or symptom-specific enough to keep separate.", - "confidence": 0.84, - "canonical_issue_reason": "No single canonical spans the whole set; issue 45290 is the cleanest anchor for the apply_chat_template crash duplicate pair.", + "summary": "No safe duplicate consolidation: the set is a heterogeneous mix of unrelated tokenizer, trainer, vision, generation, and MoE issues. None of the soft pairs look like the same concrete bug/change.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a reliable canonical target; the cluster spans many unrelated failure modes and model families.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45290 is the best representative because it states the core failure mode most generally, without the extra model-specific narrowing.", + "best_issue_reason": "No clear global best issue for deduping this cluster, since the items do not describe one underlying problem.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44514", "right": "issue:45290", - "accept": true, - "reason": "Same underlying crash in apply_chat_template with assistant tool-call messages/no content; the Qwen2_5_VLProcessor report is a narrower instance of the generic bug." + "accept": false, + "reason": "Both mention apply_chat_template crashes, but the triggers differ (batched padding vs assistant tool-call messages), so this is not the same bug." }, { "left": "issue:43295", "right": "issue:45356", "accept": false, - "reason": "Different regressions: processor.tokenizer/image-passing breakage vs Kimi codec handling and a misleading warning." + "reason": "Both are tokenizer regressions, but one is about processor.tokenizer/image passthrough and the other about codec handling plus a misleading warning; different code paths." }, { "left": "issue:44466", "right": "issue:45005", - "accept": true, - "reason": "Both describe the same v5 tied-weights serialization problem around lm_head.weight/model device." + "accept": false, + "reason": "Both touch tied weights, but one is device-dependent lm_head serialization and the other is translation-model v5 weight tying; not enough to be the same defect." }, { "left": "issue:24643", "right": "issue:29127", "accept": false, - "reason": "Unrelated DeepSpeed shape error vs LayoutLMv3 box-validation messaging." + "reason": "Completely different bugs: DeepSpeed training weight shape error vs LayoutLMv3 box-validation messaging." }, { "left": "issue:43819", "right": "issue:44811", "accept": false, - "reason": "Different code paths: DAC forward mismatch vs Whisper batch_decode special-token handling." + "reason": "Different subsystems and failures: DAC latent reconstruction mismatch vs Whisper batch_decode skip_special_tokens behavior." }, { "left": "issue:44936", "right": "issue:45823", "accept": false, - "reason": "Trainer evaluate-after-train bug vs Gemma4 PLE device-map mismatch." + "reason": "Trainer evaluate-after-train failure is unrelated to Gemma4 device-map forward device mismatch." }, { "left": "issue:30064", "right": "issue:33666", "accept": false, - "reason": "Void segmentation-map preprocessing vs Qwen2-VL multi-GPU training; no shared bug." + "reason": "Image processor segmentation-map handling and Qwen2-VL multi-GPU training are unrelated." }, { "left": "issue:43653", "right": "issue:44361", "accept": false, - "reason": "Different tokenizer failures on different models and symptoms." + "reason": "Both are tokenizer issues, but one is BigBird special-token registration and the other is MLuke task-time AttributeError; different bugs." }, { "left": "issue:38175", "right": "issue:43295", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to the processor.tokenizer regression." + "reason": "Unrelated: SigLIP2 zero probabilities versus tokenizer/processor regression in v4.57.5." }, { "left": "issue:44361", "right": "issue:44442", "accept": false, - "reason": "MLuke tokenizer AttributeError vs FastSpeech2Conformer tokenizer loading failure." + "reason": "Both involve tokenizers, but the models and failure modes differ: MLuke AttributeError vs AutoTokenizer failing to load FastSpeech2ConformerTokenizer." }, { "left": "issue:43653", "right": "issue:44568", "accept": false, - "reason": "Both concern tokenizer special tokens, but they are different models and different failure modes." + "reason": "Similar theme of special tokens, but BigBird mask-token decode failure and mDeBERTa add_special_tokens BOS/EOS omission are different code paths and symptoms." }, { "left": "issue:43577", "right": "issue:43697", "accept": false, - "reason": "BLIP2 dtype retention and RTDetrV2 output drift are unrelated." + "reason": "Different problems: BLIP2 dtype propagation vs RTDetrV2 output drift in v5." }, { "left": "issue:43643", "right": "issue:44561", "accept": false, - "reason": "AutoConfig missing fields vs trust_remote_code breakage from removing is_torch_fx_available." + "reason": "Both mention trust_remote_code, but one is missing fields in AutoConfig and the other is a v5 API removal breaking remote-code models; not the same issue." }, { "left": "issue:44843", "right": "issue:44991", "accept": false, - "reason": "Offline model_info call in a regex patch vs a tokenizer-loading regression for a specific model." + "reason": "Different tokenizer-loading failures: offline model_info call in _patch_mistral_regex vs est-roberta tokenizer loading regression." }, { "left": "issue:44464", "right": "issue:44743", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency vs Qwen3_5 recurrent-state reset are different concrete bugs." + "reason": "Both concern generation state, but one is chunked generation with compiled forward and the other is Qwen3.5 modular recurrent-state reset; not clearly the same bug." }, { "left": "issue:41720", "right": "issue:43906", "accept": false, - "reason": "CUDA assert with auto device mapping vs an isolated reproduction of another issue." + "reason": "Qwen3 auto device-map cudaErrorAssert is unrelated to an isolated reproduction issue with no matching failure described here." }, { "left": "issue:44493", "right": "issue:46050", "accept": false, - "reason": "Unexpected position-id keys vs quantized save/load failure are not the same defect." + "reason": "Unexpected position-id keys on load and sinq quantized save/load breakage are different loading problems." }, { "left": "issue:29159", "right": "issue:33357", "accept": false, - "reason": "Tokenizer inconsistency vs MacOS CLIP bus error; no concrete overlap." + "reason": "Tokenizer slow/fast inconsistency is unrelated to the MacOS bus error on CLIP." }, { "left": "issue:43653", "right": "issue:43927", "accept": false, - "reason": "BigBird decode/special-token bug vs DiaConfig custom token IDs lost on save/load." + "reason": "BigBird special-token decoding and DiaConfig losing custom token IDs are different token/config persistence bugs." }, { "left": "issue:45491", "right": "issue:46002", "accept": false, - "reason": "Different NaN symptoms in different model paths; not the same bug." + "reason": "Both mention NaNs, but one is sliding-window attention on mixed-length batching and the other is classification-head NaNs after checkout/init; different causes." }, { "left": "issue:43531", "right": "issue:43742", "accept": false, - "reason": "Qwen3-MoE sliding-window issue vs MobileLLM load key error." + "reason": "Qwen3-MoE sliding_window behavior and MobileLLM-125M load key error are unrelated." }, { "left": "issue:43550", "right": "issue:43927", "accept": false, - "reason": "torch.compile+SDPA failure vs config save/load token-ID loss." + "reason": "torch.compile+SDPA failure in Bamba is unrelated to DiaConfig save/load token ID loss." }, { "left": "issue:43688", "right": "issue:45440", "accept": false, - "reason": "MoE auxiliary-loss normalization bug vs native/remote DeepSeekV3 divergence are related only at a very broad subsystem level." + "reason": "Both are MoE-related, but auxiliary-loss normalization and DeepSeekV3 remote-vs-native divergence are not the same concrete bug." }, { "left": "issue:44464", "right": "issue:44977", "accept": false, - "reason": "Chunked generation with compiled forward vs flash-attention generation failure are not the same code-path problem." - }, - { - "left": "issue:43550", - "right": "issue:44361", - "accept": false, - "reason": "Different model-specific failures with no shared underlying defect." - }, - { - "left": "issue:43577", - "right": "issue:45588", - "accept": false, - "reason": "BLIP2 dtype bug vs flash_attention sink-less-model crash are unrelated." + "reason": "Both affect generation, but compiled-forward chunking and flash-attention on Qwen3.5 are distinct failure modes." }, { "left": "issue:43504", "right": "issue:43550", "accept": false, - "reason": "Legacy-field load failure vs torch.compile/SDPA failure." + "reason": "BEiT legacy-field loading and Bamba torch.compile/SDPA failure are unrelated." }, { "left": "issue:43504", "right": "issue:43720", "accept": false, - "reason": "Legacy-field load failure vs packed-weight loading failure." + "reason": "Different loading issues: legacy preset field in BEiT vs packed-weight unpacking in BitNet accelerate loading." }, { "left": "issue:32090", "right": "issue:34567", "accept": false, - "reason": "Trainer _gpu_broadcast_one NoneType error vs TrainerState token counter not updating." + "reason": "Trainer broadcast NoneType error and TrainerState token counter not updating are separate trainer bugs." }, { "left": "issue:43504", "right": "issue:44610", "accept": false, - "reason": "Legacy-field load failure vs processor/model image-size mismatch." + "reason": "BEiT model-preset loading and OmDet-Turbo processor output-size mismatch are unrelated." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is appropriately conservative and grounded in the packet. It only elevates two plausible duplicate clusters, and the rest of the pair verdicts stay model/symptom-specific without overclaiming. The chosen representative issues are reasonable given the titles and soft-similarity signals." - }, - "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 }, @@ -6607,7 +6638,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28282", "issue:32090", @@ -6689,202 +6720,202 @@ "issue:45803|issue:45987", "issue:43688|issue:45704" ], - "prepared_review_unit_hash": "48737c71935802e5e80404f1be8dc83183e624ed813249d41b80edf63861165f", + "prepared_review_unit_hash": "66c188c5f510a146f9d409984573a6fb2c14b940d53a0a259cb0f4361d99c001", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36562, - "estimated_input_tokens": 9141, - "estimated_eval_tokens": 18538 + "serialized_chars": 36560, + "estimated_input_tokens": 9140, + "estimated_eval_tokens": 18536 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is not a single duplicate cluster: the issues span unrelated bugs across tokenization, multimodal loading, training, configs, and serialization. None of the soft pairs look like the same underlying bug or change, so all soft edges should be rejected.", - "confidence": 0.96, - "canonical_issue_reason": "If forced to pick one representative, issue:46050 is the most concrete and actionable save/load regression, but the set is too heterogeneous for any issue to be a true canonical duplicate target.", + "summary": "This cluster is mostly heterogeneous; the items share at most broad subsystems (tokenizers, configs, loading, multimodal models) rather than the same underlying defect. I would not merge any of the soft pairs as duplicates based on the available evidence.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 45812 is the strongest single representative: it describes a concrete, reproducible regression with broad impact across all Granite models and has multiple inbound references.", "canonical_pr_reason": null, - "best_issue_reason": "issue:46050 is the strongest standalone issue in the set: it has a clear failure mode, a focused save/pretrained reproduction path, and is still open. It does not, however, subsume the rest of the cluster.", + "best_issue_reason": "Issue 45812 is the best issue candidate for triage because it is specific, high-impact, and more broadly applicable than the narrower model-specific reports in this set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43122", "right": "issue:43906", "accept": false, - "reason": "Different problems: tokenization drift across versions vs an isolated reproduction of a different upstream issue." + "reason": "43906 is a reproduction of another issue, but the shared root cause is not explicit enough to treat it as the same bug as 43122." }, { "left": "issue:44466", "right": "issue:46050", "accept": false, - "reason": "Both involve serialization/loading, but one is tied-weights/device-dependent serialization while the other is a quantized save/load breakage; different code paths." + "reason": "Both concern save/load behavior, but one is tied-weight serialization by device and the other is quantized-model reload failure." }, { "left": "issue:28282", "right": "issue:35141", "accept": false, - "reason": "ImportError due to missing PyTorch vs token-embedding resize reinitialization; unrelated failures." + "reason": "Unrelated failures: missing PyTorch import vs embedding resize causing post_init reinitialization." }, { "left": "issue:43452", "right": "issue:44451", "accept": false, - "reason": "Both are load failures, but one is gguf/AutoTokenizer/AutoModel handling and the other is a specific model load regression; no shared underlying bug is evident." + "reason": "Both are loading problems, but they point to different mechanisms and no shared concrete code path is shown." }, { "left": "issue:32090", "right": "issue:33666", "accept": false, - "reason": "Trainer NoneType GPU broadcast error vs Qwen2-VL multi-GPU training issue; different symptoms and likely different fixes." + "reason": "Generic distributed broadcast type error vs Qwen2-VL multi-GPU training issue; too broad to call the same bug." }, { "left": "issue:43742", "right": "issue:44821", "accept": false, - "reason": "KeyError when loading a model vs AutoImageProcessor URL loading; separate loading paths." + "reason": "Different loading surfaces: MobileLLM key error vs AutoImageProcessor URL loading." }, { "left": "issue:45823", "right": "issue:46050", "accept": false, - "reason": "Gemma4 device mismatch in forward with auto device map is not the same as quantized model save/load breakage." + "reason": "Device-map forward mismatch and quantized save/load breakage are different failure modes." }, { "left": "issue:41720", "right": "issue:44464", "accept": false, - "reason": "CUDA assert under auto device mapping vs inconsistent outputs with compiled forward/chunked generation; different execution paths." + "reason": "Qwen3 auto device-map assert and chunked-generation compiled-forward inconsistency are unrelated." }, { "left": "issue:33666", "right": "issue:36010", "accept": false, - "reason": "Multi-GPU Qwen2-VL training vs GenerationMixin import error; unrelated." + "reason": "Multi-GPU training behavior vs GenerationMixin import error are not the same defect." }, { "left": "issue:43606", "right": "issue:43927", "accept": false, - "reason": "CPU offload device mismatch vs DiaConfig losing custom token IDs on save/load; different root causes." + "reason": "CPU offload device mismatch and DiaConfig save/load token-ID corruption are unrelated." }, { "left": "issue:43493", "right": "issue:43825", "accept": false, - "reason": "SigLIP2 HF/JAX discrepancy vs pipeline error message for translation tasks; not the same bug." + "reason": "SigLIP2 implementation discrepancy vs pipeline error-message wording regression do not share a concrete bug." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "BitNet packed-weight loading bug vs MLukeTokenizer task AttributeError; unrelated." + "reason": "BitNet accelerate-loading unpacking bug and MLukeTokenizer task AttributeError are distinct." }, { "left": "issue:44849", "right": "issue:45357", "accept": false, - "reason": "Qwen3.5 hidden-states bug vs incorrect visual encoder keys in save_pretrained; separate regressions." + "reason": "Both involve Qwen3.5, but one is hidden-states output behavior and the other is save_pretrained key serialization." }, { "left": "issue:43525", "right": "issue:43572", "accept": false, - "reason": "Both mention missing pad-token-related attributes, but they affect different config classes and attribute names; too weak to treat as the same bug." + "reason": "Both are pad-token-related, but they affect different config classes and attributes, so they are not clearly the same bug." }, { "left": "issue:43756", "right": "issue:44913", "accept": false, - "reason": "RoPE-layer mismatch in Smollm3 vs GPTNeoX rotary_pct reverting on reload; related theme, different bug." + "reason": "Smollm3 RoPE-layer dropping and GPTNeoX rotary_pct reload reset are different configuration/architecture issues." }, { "left": "issue:44568", "right": "issue:45812", "accept": false, - "reason": "Tokenizer special-token behavior for mdeberta-v3-base vs Granite token ID regression; different models and failure modes." + "reason": "Both are tokenizer regressions in v5, but the model families and symptoms differ enough that they do not look like one bug." }, { "left": "issue:43262", "right": "issue:43295", "accept": false, - "reason": "Audio chat-template sampling-rate default vs processor/tokenizer image-passing regression; different multimodal processor issues." + "reason": "Audio chat-template sampling-rate default and processor.tokenizer/image handling regression are different processor-path bugs." }, { "left": "issue:28282", "right": "issue:33357", "accept": false, - "reason": "Missing PyTorch ImportError vs MacOS bus error on a CLIP community model; unrelated." + "reason": "Missing PyTorch import and Mac bus error in CLIP are unrelated." }, { "left": "issue:43688", "right": "issue:43749", "accept": false, - "reason": "Auxiliary-loss normalization vs broken FSDP CPU RAM efficient loading; different subsystems." + "reason": "Auxiliary-loss normalization and FSDP CPU RAM-efficient loading are unrelated training issues." }, { "left": "issue:28282", "right": "issue:32090", "accept": false, - "reason": "PyTorch missing ImportError vs custom Trainer GPU broadcast NoneType TypeError; unrelated." + "reason": "ImportError on model class vs distributed GPU broadcast type error are unrelated." }, { "left": "issue:43720", "right": "issue:44361", "accept": false, - "reason": "Packed-weight loading bug vs tokenizer AttributeError; no shared code-path problem." + "reason": "Packed-weight loading bug and tokenizer task AttributeError are different code paths." }, { "left": "issue:43577", "right": "issue:44554", "accept": false, - "reason": "Blip2 dtype propagation bug vs MPS attention correctness issue; not the same defect." + "reason": "Loading dtype propagation for Blip2 is unrelated to the MPS attention correctness issue." }, { "left": "issue:39692", "right": "issue:43493", "accept": false, - "reason": "Docs example/model mismatch plus quantization failure vs core SigLIP2 implementation discrepancy; one is documentation/example-specific, the other is an implementation issue." + "reason": "Same model family, but doc-example mistakes and HF-vs-JAX implementation discrepancy are not the same underlying problem." }, { "left": "issue:43540", "right": "issue:44977", "accept": false, - "reason": "Video-input processing error in Qwen3OmniMoe vs flash-attention generation problem in Qwen3.5; different failures." + "reason": "Both are Qwen-family video/vision reports, but the concrete failures differ and do not indicate a shared root cause." }, { "left": "issue:44964", "right": "issue:45405", "accept": false, - "reason": "Model loading regression vs unrelated PEFT minimum-version bump." + "reason": "Model loading failure vs dependency-version bump are not duplicate symptoms." }, { "left": "issue:44479", "right": "issue:44625", "accept": false, - "reason": "Video-input regression across Qwen variants vs num_labels propagation in Qwen3.5 config; different code paths." + "reason": "Video-input regression and num_labels propagation bug are separate Qwen3.5 issues." }, { "left": "issue:45803", "right": "issue:45987", "accept": false, - "reason": "Bare except in Fuyu tensor conversion vs StaticCache sequence-length contract mismatch; unrelated." + "reason": "Bare-except error swallowing in Fuyu and StaticCache return-type contract violation are unrelated." }, { "left": "issue:43688", "right": "issue:45704", "accept": false, - "reason": "Aux-loss normalization bug vs T5 using a leaking apex RMSNorm; separate issues." + "reason": "Aux-loss normalization bug and T5 apex RMSNorm memory leak are different defects." } ] }, @@ -6906,7 +6937,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:29942", "issue:30333", @@ -6935,10 +6966,10 @@ "issue:44291", "issue:44361", "issue:44423", - "issue:44464", "issue:44466", "issue:44488", "issue:44493", + "issue:44521", "issue:44589", "issue:44625", "issue:44734", @@ -6947,9 +6978,9 @@ "issue:45083", "issue:45200", "issue:45229", + "issue:45290", "issue:45405", "issue:45520", - "issue:45584", "issue:45588", "issue:45701", "issue:45759", @@ -6960,20 +6991,20 @@ "issue:43334|issue:43572", "issue:43756|issue:45083", "issue:44488|issue:44843", - "issue:43493|issue:43844", "issue:43334|issue:45759", "issue:45200|issue:45229", + "issue:43493|issue:43844", "issue:43257|issue:43299", - "issue:39692|issue:43295", "issue:43824|issue:44589", + "issue:39692|issue:43295", "issue:43646|issue:44466", - "issue:43504|issue:43606", "issue:43278|issue:43844", + "issue:43504|issue:43606", "issue:45229|issue:45823", "issue:43572|issue:44291", "issue:44589|issue:45520", - "issue:43927|issue:44361", "issue:33357|issue:33666", + "issue:43927|issue:44361", "issue:43688|issue:45701", "issue:43504|issue:43653", "issue:44423|issue:44734", @@ -6984,204 +7015,204 @@ "issue:45588|issue:46050", "issue:43994|issue:44493", "issue:29942|issue:30333", - "issue:44464|issue:45584" + "issue:44521|issue:45290" ], - "prepared_review_unit_hash": "13ea93df2c4bac1aa473bd648b7c3de2a4d3b7e3c53b4a9d5d31ea8ca6160782", + "prepared_review_unit_hash": "c3b767b2e5d655aa459ad9b584f2c5dc20821cf765821710d1a1aba35c3c7d8a", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 28, - "serialized_chars": 35674, - "estimated_input_tokens": 8919, - "estimated_eval_tokens": 18094 + "serialized_chars": 35693, + "estimated_input_tokens": 8924, + "estimated_eval_tokens": 18104 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is very heterogeneous: most items are unrelated model-specific regressions, config mismatches, tokenizer issues, or load-time failures. None of the soft edges look like true duplicates or mergeable PR-equivalents.", - "confidence": 0.91, - "canonical_issue_reason": "If forced to pick one issue, issue:45701 is the broadest open report, but it is still not a real umbrella for the rest of the cluster.", + "summary": "This cluster is a grab bag of unrelated Transformers bugs and regressions. All suggested soft duplicate pairs are false positives; they share broad themes like configs, multimodal models, or serving, but not the same concrete underlying defect.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items span many different models, APIs, and failure modes, so there is no single underlying bug to anchor the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "Issue:45701 is the closest thing to a representative anchor because it is broad and open, but the set is too diverse for a meaningful single canonical issue.", + "best_issue_reason": "No single issue is a strong cluster representative; 44521 is the most active/open item, but it is still unrelated to most others and should not be treated as a canonical duplicate target.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43334", "right": "issue:43572", "accept": false, - "reason": "Both are version-era config errors, but they affect different models and different missing fields (`pad_token_id` vs `pad_token_idx`)." + "reason": "Both are config/token-id regressions, but they affect different models and different missing fields, so they are not the same bug." }, { "left": "issue:43756", "right": "issue:45083", "accept": false, - "reason": "Different model families and different bugs: RoPE layer mismatch vs a helper-function behavior issue." + "reason": "Both mention feature-extraction/ROPE behavior, but one is a model-specific RoPE-layer issue and the other is a helper-function bug in qwen3_omni_moe." }, { "left": "issue:44488", "right": "issue:44843", "accept": false, - "reason": "Both involve model loading, but one is a specific model failing to load and the other is an HF_HUB_OFFLINE regression in tokenizer patching." - }, - { - "left": "issue:43493", - "right": "issue:43844", - "accept": false, - "reason": "Unrelated problems: SigLIP2 implementation mismatch vs DeepSpeed/ZeRO-3 gradient growth." + "reason": "One is a model load failure for cjvt/sleng-bert; the other is an offline-mode tokenizer patch bug. Different code paths." }, { "left": "issue:43334", "right": "issue:45759", "accept": false, - "reason": "Both touch Qwen multimodal configs, but one is a missing config field and the other is from_config unwrapping behavior." + "reason": "Both involve Qwen multimodal configs, but one is a missing pad token field and the other is AutoModelForCausalLM not unwrapping text_config." }, { "left": "issue:45200", "right": "issue:45229", "accept": false, - "reason": "Different symptom and scope: fine-tuning token-type defaults vs multi-GPU inference OOM." + "reason": "One is a required token-type default bug; the other is a multi-GPU CUDA OOM. Not the same issue." }, { - "left": "issue:43257", - "right": "issue:43299", + "left": "issue:43493", + "right": "issue:43844", "accept": false, - "reason": "Both mention Qwen3 MoE loading, but one is accelerate+deepspeed conversion and the other is a dev-version loading regression." + "reason": "SigLIP2 is the only commonality; one is implementation discrepancy, the other is a DeepSpeed/init gradient anomaly." }, { - "left": "issue:39692", - "right": "issue:43295", + "left": "issue:43257", + "right": "issue:43299", "accept": false, - "reason": "Documentation-example errors are not the same bug as the processor/tokenizer regression in custom model code." + "reason": "Both are Qwen3 MoE loading regressions, but they fail in different places and involve different fixes." }, { "left": "issue:43824", "right": "issue:44589", "accept": false, - "reason": "Different failure modes: missing import for a model class vs missing Float8 storage support." + "reason": "An import error and a float8 storage lookup error are unrelated runtime failures." }, { - "left": "issue:43646", - "right": "issue:44466", + "left": "issue:39692", + "right": "issue:43295", "accept": false, - "reason": "Custom model initialization breakage is unrelated to device-dependent serialization of `lm_head.weight`." + "reason": "One is a doc-example/model-processor mismatch; the other is a custom-model regression in v4.57.5." }, { - "left": "issue:43504", - "right": "issue:43606", + "left": "issue:43646", + "right": "issue:44466", "accept": false, - "reason": "Different models and different root causes: legacy preset field vs CPU offload device mismatch." + "reason": "Custom model init breakage and lm_head serialization differences are separate code paths." }, { "left": "issue:43278", "right": "issue:43844", "accept": false, - "reason": "Embedding dtype drift is not the same bug as ZeRO-3 gradient inflation." + "reason": "Embedding dtype mismatch during eval is unrelated to gradient growth under ZeRO-3." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading for BEiT is unrelated to a CPU-offload device mismatch in Bark." }, { "left": "issue:45229", "right": "issue:45823", "accept": false, - "reason": "Both are Gemma4-related, but one is OOM and the other is a forward device mismatch." + "reason": "Both are Gemma4 issues, but one is OOM and the other is a forward-time device mismatch." }, { "left": "issue:43572", "right": "issue:44291", "accept": false, - "reason": "Both are 5.0 load-time regressions, but the missing config field and the unexpected `_is_hf_initialized` arg are different code paths." + "reason": "Missing pad_token_idx and an unexpected init_empty_weights argument are different compatibility bugs." }, { "left": "issue:44589", "right": "issue:45520", "accept": false, - "reason": "Unrelated import/runtime failures: float8 storage lookup vs flash_attn import key error on Python 3.13." + "reason": "A missing Float8 storage type and a flash_attn import KeyError on Python 3.13 are distinct failures." }, { - "left": "issue:43927", - "right": "issue:44361", + "left": "issue:33357", + "right": "issue:33666", "accept": false, - "reason": "Both are model/tokenizer errors, but they concern different artifacts and different exception paths." + "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are unrelated." }, { - "left": "issue:33357", - "right": "issue:33666", + "left": "issue:43927", + "right": "issue:44361", "accept": false, - "reason": "Completely different models and issues: MacOS CLIP bus error vs Qwen2-VL multi-GPU training." + "reason": "Different tokenizer/config errors with different models and symptoms." }, { "left": "issue:43688", "right": "issue:45701", "accept": false, - "reason": "Aux-loss normalization and tokenization changes are different bug classes." + "reason": "Aux-loss normalization and tokenization changes are unrelated issues." }, { "left": "issue:43504", "right": "issue:43653", "accept": false, - "reason": "A pretrained preset load failure is unrelated to a tokenizer special-token registration bug." + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token registration are separate bugs." }, { "left": "issue:44423", "right": "issue:44734", "accept": false, - "reason": "Both affect serving, but they crash in different code paths with different root causes." + "reason": "Both are serve crashes, but they occur in different endpoints and code paths." }, { "left": "issue:43606", "right": "issue:44112", "accept": false, - "reason": "A real runtime device mismatch is not the same as a stale CI test." + "reason": "A real device-mismatch bug and a stale CI test are not duplicates." }, { "left": "issue:43575", "right": "issue:45405", "accept": false, - "reason": "OOM when loading a model is unrelated to an unmet dependency version bump." + "reason": "TP OOM on a Qwen model and an unreleased dependency version bump are unrelated." }, { "left": "issue:44792", "right": "issue:45405", "accept": false, - "reason": "A Janus generation test failure is not the same issue as the PEFT version pin problem." + "reason": "Janus test failure and PEFT version pinning are unrelated." }, { "left": "issue:44625", "right": "issue:45759", "accept": false, - "reason": "Both involve Qwen3.5/3.6 config plumbing, but one is num_labels propagation and the other is text_config unwrapping." + "reason": "Both touch Qwen3.5 multimodal configs, but one is num_labels propagation and the other is config unwrapping in model construction." }, { "left": "issue:45588", "right": "issue:46050", "accept": false, - "reason": "Flash-attention sinkless-model crash and sinq quantization save/load breakage are unrelated." + "reason": "A flash_attention sink-less crash and a sinq save/load quantization bug are different problems." }, { "left": "issue:43994", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 inference nonsense and position-id key warnings are different symptoms with different likely causes." + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are not the same defect." }, { "left": "issue:29942", "right": "issue:30333", "accept": false, - "reason": "Flash Attention test failures have no overlap with MLFlow reporting after training failure." + "reason": "Flash Attention 2 test failures and MLflow reporting on failed jobs are unrelated." }, { - "left": "issue:44464", - "right": "issue:45584", + "left": "issue:44521", + "right": "issue:45290", "accept": false, - "reason": "Compiled-forward chunked generation inconsistency is unrelated to Whisper empty-transcription generation failure." + "reason": "Both involve chat templates, but one is assistant-mask generation and the other is tool-call tokenization failure." } ] }, @@ -7203,7 +7234,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:15354", "issue:28218", @@ -7231,8 +7262,8 @@ "issue:43957", "issue:43975", "issue:44315", + "issue:44464", "issue:44466", - "issue:44521", "issue:44554", "issue:44610", "issue:44849", @@ -7244,23 +7275,23 @@ "issue:45127", "issue:45198", "issue:45200", - "issue:45290", "issue:45325", "issue:45356", "issue:45412", "issue:45446", "issue:45520", + "issue:45584", "issue:45823", "issue:46050" ], "soft_pairs": [ - "issue:44521|issue:45290", + "issue:44464|issue:45584", "issue:43844|issue:44964", "issue:44554|issue:45446", "issue:28218|issue:34567", "issue:43688|issue:43873", - "issue:45084|issue:45520", "issue:43540|issue:45200", + "issue:45084|issue:45520", "issue:29159|issue:32090", "issue:15354|issue:38175", "issue:43232|issue:44849", @@ -7270,236 +7301,230 @@ "issue:43278|issue:43701", "issue:44315|issue:44849", "issue:44554|issue:45356", - "issue:43295|issue:44610", "issue:28218|issue:33357", + "issue:43295|issue:44610", "issue:44898|issue:45412", "issue:43572|issue:44987", + "issue:43572|issue:43957", "issue:43493|issue:43701", "issue:44466|issue:45127", - "issue:43572|issue:43957", "issue:45200|issue:45325", "issue:37428|issue:43957", - "issue:43295|issue:43450", "issue:43550|issue:43844", + "issue:43295|issue:43450", "issue:43334|issue:43525", "issue:43824|issue:43975", "issue:43295|issue:43873", "issue:38175|issue:45412" ], - "prepared_review_unit_hash": "d2113b111b7d4b13eb7b10d30a4742a08a61b43b07a7d5e63b969e9acbdaa0c0", + "prepared_review_unit_hash": "164fcb0b857254b1321b6afe9f88c6bcd5973cd8336565222aa06b9d9c4205b1", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 31, - "serialized_chars": 36595, - "estimated_input_tokens": 9149, - "estimated_eval_tokens": 18554 + "serialized_chars": 36571, + "estimated_input_tokens": 9143, + "estimated_eval_tokens": 18542 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is highly heterogeneous: tokenizer, multimodal processing, loading/config, training, quantization, and attention bugs are mixed together. None of the soft pairs look like true duplicates or the same fixable code-path change, so I reject all soft edges and see no clear global canonical issue.", - "confidence": 0.93, - "canonical_issue_reason": null, + "summary": "These candidates are mostly false-positive similarity matches across unrelated bugs. I would not merge any of the proposed soft edges.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue emerges here: the proposed pairs span different subsystems and failure modes, so there is no clear duplicate cluster to anchor.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "If one issue must be chosen as the most representative standalone report, issue:43873 is the strongest candidate because it is active, has inbound references, and describes a concrete reproducible problem.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44521", - "right": "issue:45290", + "left": "issue:44464", + "right": "issue:45584", "accept": false, - "reason": "Both involve apply_chat_template, but one is about all-zero assistant masks for multimodal inputs and the other is a crash on tool-call assistant messages; different failure modes." + "reason": "Both are generation bugs, but one is about compiled forward output drift and the other about Whisper/align_special_tokens; different code paths." }, { "left": "issue:43844", "right": "issue:44964", "accept": false, - "reason": "Unrelated bugs: DeepSpeed/ZeRO-3 gradient growth versus a model-loading import failure for Phi-4 multimodal." + "reason": "ZeRO-3 gradient growth and a model-loading ImportError are unrelated failures." }, { "left": "issue:44554", "right": "issue:45446", "accept": false, - "reason": "Both touch attention/flex_attention, but one is an MPS correctness issue and the other is a bad PyTorch version check on import; not the same bug." + "reason": "Attention correctness on MPS with mismatched head dims is not the same as a flex_attention import-version check." }, { "left": "issue:28218", "right": "issue:34567", "accept": false, - "reason": "Tokenizer spacing behavior and TrainerState token-count tracking are unrelated." + "reason": "Tokenizer spacing behavior and TrainerState token-count tracking are different issues." }, { "left": "issue:43688", "right": "issue:43873", "accept": false, - "reason": "Different areas and symptoms: auxiliary-loss normalization versus quantization/offloading behavior." + "reason": "Aux-loss normalization in MoE models is unrelated to quantization/offloading behavior." }, { - "left": "issue:45084", - "right": "issue:45520", + "left": "issue:43540", + "right": "issue:45200", "accept": false, - "reason": "A compile/template-node TypeError is unrelated to a flash_attn import key error on Python 3.13." + "reason": "Video input processing in Qwen3OmniMoe is not the same as Gemma4 text-only mm_token_type_ids handling." }, { - "left": "issue:43540", - "right": "issue:45200", + "left": "issue:45084", + "right": "issue:45520", "accept": false, - "reason": "Both are multimodal-model issues, but one is video processing in Qwen3OmniMoe and the other is Gemma 4 text-only fine-tuning token-type defaults." + "reason": "A compile-time template-node error and a Python 3.13 flash_attn import error are different root causes." }, { "left": "issue:29159", "right": "issue:32090", "accept": false, - "reason": "Tokenizer inconsistency versus Trainer distributed broadcast NoneType error; no shared underlying bug." + "reason": "Tokenizer slow/fast inconsistency is unrelated to a Trainer distributed broadcast NoneType error." }, { "left": "issue:15354", "right": "issue:38175", "accept": false, - "reason": "TorchScript generator-expression export error and SigLIP2 zero probabilities are unrelated." + "reason": "TorchScript GeneratorExp export failure and SIGLIP2 zero-probability behavior are distinct problems." }, { "left": "issue:43232", "right": "issue:44849", "accept": false, - "reason": "Generation kwargs after sync_gpus and Qwen3.5 hidden-state handling are different code paths and symptoms." + "reason": "Generation kwargs syncing and hidden-states output in Qwen3.5 do not share the same bug." }, { "left": "issue:45200", "right": "issue:45823", "accept": false, - "reason": "Both mention Gemma4, but one is missing mm_token_type_ids defaults and the other is a device-map forward mismatch; different fixes." + "reason": "Both mention Gemma4, but one is missing token-type defaults and the other is a device-map forward mismatch." }, { "left": "issue:45072", "right": "issue:45198", "accept": false, - "reason": "Bfloat16 dtype mismatches in inference are unrelated to Wav2Vec2 save/tokenization failures." + "reason": "BF16 dtype mismatches during inference are unrelated to Wav2Vec2 save/tokenization failures." }, { "left": "issue:43873", "right": "issue:46050", "accept": false, - "reason": "Quantization/offloading not working is not the same as sinq save_pretrained/from_pretrained breakage." + "reason": "Quantization/offloading misbehavior is not the same as a sinq save/load regression." }, { "left": "issue:43278", "right": "issue:43701", "accept": false, - "reason": "Embedding dtype drift in eval and resume_from_checkpoint key mismatch are unrelated." + "reason": "A BF16-to-FP32 evaluation dtype change is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:44315", "right": "issue:44849", "accept": false, - "reason": "Liger Kernel application failure in model_init is unrelated to Qwen3.5 output_hidden_states behavior." + "reason": "Liger Kernel not applying with model_init and a Qwen3.5 hidden_states bug are different issues." }, { "left": "issue:44554", "right": "issue:45356", "accept": false, - "reason": "MPS attention correctness and Kimi tokenizer codec/regression issues are different bugs." + "reason": "MPS attention correctness and Kimi-K2.5 tokenizer regression do not describe the same defect." }, { - "left": "issue:43295", - "right": "issue:44610", + "left": "issue:28218", + "right": "issue:33357", "accept": false, - "reason": "Both involve processors, but one is processor/tokenizer API regression and the other is an image-size mismatch in OmDet-Turbo." + "reason": "Added-token spacing and a MacOS bus error in CLIP are unrelated." }, { - "left": "issue:28218", - "right": "issue:33357", + "left": "issue:43295", + "right": "issue:44610", "accept": false, - "reason": "Tokenizer spacing bug and MacOS bus error in CLIP are unrelated." + "reason": "Processor.tokenizer regression and OmDet-Turbo image-size mismatch are separate processor bugs." }, { "left": "issue:44898", "right": "issue:45412", "accept": false, - "reason": "Perceiver interpolation failure and RT-DETR memory release are different classes of issue." + "reason": "Perceiver resolution handling and RT-DETR memory release are unrelated." }, { "left": "issue:43572", "right": "issue:44987", "accept": false, - "reason": "A missing config attribute after 5.0 update is not the same as a model-loading failure for a specific repo on 5.1.0." + "reason": "Missing pad_token_idx in StableLmConfig and a load failure for physical-intelligence/fast are different model/config issues." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Both involve loading, but one is a config attribute regression and the other is meta-device loading breakage." }, { "left": "issue:43493", "right": "issue:43701", "accept": false, - "reason": "SigLIP2 implementation discrepancy and checkpoint resume key mismatch are unrelated." + "reason": "SigLIP2 implementation discrepancy is unrelated to checkpoint resume key mismatch." }, { "left": "issue:44466", "right": "issue:45127", "accept": false, - "reason": "Serialization of tied lm_head weights by device is not the same as LoRA merge collapse with extended vocabulary." + "reason": "Tied-weight serialization inconsistency and LoRA merge collapse are different failure modes." }, { - "left": "issue:43572", + "left": "issue:37428", "right": "issue:43957", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig and meta-device loading failures are different root causes." + "reason": "A flash_attention_utils import error and meta-device model loading are not the same bug." }, { - "left": "issue:45200", - "right": "issue:45325", - "accept": false, - "reason": "Gemma4 token-type defaults and Qwen2.5-VL rope indexing are unrelated multimodal bugs." - }, - { - "left": "issue:37428", - "right": "issue:43957", + "left": "issue:43550", + "right": "issue:43844", "accept": false, - "reason": "Flash-attention import error and meta-device model-loading breakage do not share the same underlying problem." + "reason": "torch.compile/SDPA failure in Bamba is unrelated to DeepSpeed ZeRO-3 gradient growth." }, { "left": "issue:43295", "right": "issue:43450", "accept": false, - "reason": "Processor/tokenizer regression and batched video shape bug are different failures." - }, - { - "left": "issue:43550", - "right": "issue:43844", - "accept": false, - "reason": "A torch.compile SDPA failure in Bamba is unrelated to DeepSpeed/ZeRO-3 gradient inflation." + "reason": "The former is about processor.tokenizer access with images; the latter is a batched video-shape bug." }, { "left": "issue:43334", "right": "issue:43525", "accept": false, - "reason": "Both are missing pad_token_id-style errors, but they affect different config classes and model families; not the same concrete bug." + "reason": "Both are missing pad_token_id errors, but they affect different config classes and model families." }, { "left": "issue:43824", "right": "issue:43975", "accept": false, - "reason": "An import error for a missing Qwen2.5-VL class is unrelated to a tokenizer detokenization regression." + "reason": "A model import error and a tokenizer detokenization regression are unrelated." }, { "left": "issue:43295", "right": "issue:43873", "accept": false, - "reason": "Processor API regression and quantization offloading malfunction are not the same issue." + "reason": "Processor API regression and quantization/offloading behavior do not share a code path." }, { "left": "issue:38175", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 zero probabilities and RT-DETR memory not being released are unrelated." + "reason": "SIGLIP2 zero probabilities and RT-DETR memory leaks are unrelated." } ] }, @@ -7521,7 +7546,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:37428", "issue:38175", @@ -7576,19 +7601,19 @@ "issue:42490|issue:43696", "issue:42915|issue:43824", "issue:37428|issue:43824", - "issue:38175|issue:43493", "issue:44514|issue:44521", + "issue:38175|issue:43493", "issue:43653|issue:44112", "issue:44442|issue:45198", "issue:43278|issue:43856", - "issue:43827|issue:43901", "issue:43450|issue:43575", + "issue:43827|issue:43901", "issue:42490|issue:43493", "issue:43819|issue:45083", "issue:43819|issue:44112", "issue:43262|issue:43450", - "issue:44610|issue:44857", "issue:45127|issue:45245", + "issue:44610|issue:44857", "issue:44206|issue:45584", "issue:37428|issue:43425", "issue:44792|issue:45563", @@ -7601,224 +7626,231 @@ "issue:43278|issue:43825", "issue:37428|issue:44351", "issue:44206|issue:45823", - "issue:43611|issue:43931", "issue:44360|issue:44561", - "issue:43335|issue:43653" + "issue:43611|issue:43931", + "issue:43335|issue:43653", + "issue:43550|issue:44112" ], - "prepared_review_unit_hash": "639fd5bf5c05e6c637c43f1ed7f3f22250f20015ef3c63044306553b7a7014f6", + "prepared_review_unit_hash": "f35192beef8112b7404cf8e2e765568aedcbdcf3d9bdd43ee6f4afcb7d199036", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36929, - "estimated_input_tokens": 9233, - "estimated_eval_tokens": 18722 + "soft_pair_count": 32, + "serialized_chars": 37227, + "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 mixed bag of unrelated Transformers bug reports across different models, processors, and regression types. The soft-similarity pairs mostly share only a broad subsystem/theme, not the same concrete failure, so none should be merged as duplicates.", - "confidence": 0.97, - "canonical_issue_reason": "issue:43824 is the strongest single anchor here: it has the highest discussion/inbound signal among the closed issues and describes a crisp, user-facing import failure with a concrete missing symbol.", + "summary": "This cluster is heterogeneous: it mixes import/load regressions, chat-template/processor bugs, model-specific correctness issues, docs/deprecation problems, and CI/test flakes. I don\u2019t see one true canonical issue or PR for the whole set; the soft pairs are mostly near-theme matches rather than duplicates.", + "confidence": 0.44, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster. The items split into multiple unrelated bug families, so a canonical issue would be misleading.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43824 is also the best representative issue overall for triage because it is well-scoped, high-signal, and easy to understand; none of the other items appear to be duplicates of it.", + "best_issue_reason": "If forced to choose one issue as the least-bad representative, issue 44521 is the most active and broadly discussion-heavy, but it still only covers one processor/chat-template regression thread and not the full set.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42490", "right": "issue:43696", "accept": false, - "reason": "Different failures: local-path trailing-slash warning vs CUDA OOM on GPT-oss-20b." + "reason": "Import-warning-on-path-slash and CUDA OOM on GPT-oss-20b are unrelated failures." }, { "left": "issue:42915", "right": "issue:43824", "accept": false, - "reason": "Both are import/runtime breakages, but they affect different models and different missing symbols/code paths." + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-VL import error are different models and code paths." }, { "left": "issue:37428", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different absent names and unrelated internal modules." + "reason": "Different missing-symbol import errors in different modules; not the same bug." }, { - "left": "issue:38175", - "right": "issue:43493", + "left": "issue:44514", + "right": "issue:44521", "accept": false, - "reason": "Same model family, but one is zero probabilities in a specific model while the other is a broader HF-vs-JAX discrepancy; not the same concrete bug." + "reason": "Both involve apply_chat_template, but one is a batched padding=False crash and the other is zero assistant masks." }, { - "left": "issue:44514", - "right": "issue:44521", + "left": "issue:38175", + "right": "issue:43493", "accept": false, - "reason": "Both involve apply_chat_template, but one crashes on batched padding=False input while the other returns all-zero assistant masks; different bugs." + "reason": "Same model family, but one is zero probabilities and the other is a broader HF-vs-JAX discrepancy." }, { "left": "issue:43653", "right": "issue:44112", "accept": false, - "reason": "Tokenizer special-token registration bug vs a GraniteSpeech CI device-override regression; unrelated." + "reason": "Tokenizer special-token registration bug vs GraniteSpeech CI device override failure." }, { "left": "issue:44442", "right": "issue:45198", "accept": false, - "reason": "Different tokenizer/model-loading failures on different architectures and failure modes." + "reason": "Different tokenizers/models and different failure modes." }, { "left": "issue:43278", "right": "issue:43856", "accept": false, - "reason": "Training/eval dtype mismatch is unrelated to Qwen3 MoE memory usage." + "reason": "Eval dtype regression and MoE training memory inefficiency are unrelated." }, { - "left": "issue:43827", - "right": "issue:43901", + "left": "issue:43450", + "right": "issue:43575", "accept": false, - "reason": "Both are docs regressions, but they target different API surfaces and different corrective changes." + "reason": "Video batching shape bug and tensor-parallel OOM are unrelated." }, { - "left": "issue:43450", - "right": "issue:43575", + "left": "issue:43827", + "right": "issue:43901", "accept": false, - "reason": "Video-processor shape bug vs tensor-parallel OOM while loading a large model; not the same issue." + "reason": "Both are docs around pipelines, but they describe different deprecations and behaviors." }, { "left": "issue:42490", "right": "issue:43493", "accept": false, - "reason": "Local model import warning is unrelated to the SigLIP2 implementation discrepancy." + "reason": "Local-path import warning and SigLIP2 output discrepancy are unrelated." }, { "left": "issue:43819", "right": "issue:45083", "accept": false, - "reason": "Different model internals and different helper-function behavior; not one shared defect." + "reason": "DAC latent mismatch and qwen3_omni_moe feature-length behavior are different code paths." }, { "left": "issue:43819", "right": "issue:44112", "accept": false, - "reason": "DAC forward/from_latents mismatch is unrelated to a GraniteSpeech test/device override failure." + "reason": "DAC inference bug and GraniteSpeech CI flake are unrelated." }, { "left": "issue:43262", "right": "issue:43450", "accept": false, - "reason": "Audio chat-template sampling-rate bug vs batched video processor shape bug; different modalities and code paths." + "reason": "Audio chat-template sampling-rate bug and batched video-shape bug are different processors." }, { - "left": "issue:44610", - "right": "issue:44857", + "left": "issue:45127", + "right": "issue:45245", "accept": false, - "reason": "Processor output-size mismatch vs AMP/CUDA crash in a loss module; separate problems." + "reason": "LoRA/tied-embedding collapse and category-count runtime limit are unrelated." }, { - "left": "issue:45127", - "right": "issue:45245", + "left": "issue:44610", + "right": "issue:44857", "accept": false, - "reason": "LoRA merge/tied-embeddings collapse is unrelated to the category-cardinality runtime limit." + "reason": "Processor image-size mismatch and AMP CUDA loss crash are unrelated." }, { "left": "issue:44206", "right": "issue:45584", "accept": false, - "reason": "Feature-extractor argument regression vs Whisper empty-transcription failure after token alignment; distinct bugs." + "reason": "Unsupported center arg in feature extractor and Whisper empty-transcription failure are unrelated." }, { "left": "issue:37428", "right": "issue:43425", "accept": false, - "reason": "ImportError for a missing flash-attention helper is not the same as a Torch 2.10 compatibility issue." + "reason": "Flash-attention import error and Torch 2.10 compatibility issue are not the same bug." }, { "left": "issue:44792", "right": "issue:45563", "accept": false, - "reason": "Failed image-generation test for Janus vs a stale warning in paged generate(); different behaviors." + "reason": "Janus image-generation test failure and stale generate() warning are different issues." }, { "left": "issue:43335", "right": "issue:43550", "accept": false, - "reason": "SwitchTransformers sparse-layer construction bug vs Bamba torch.compile+SDPA failure; unrelated code paths." + "reason": "Sparse-layer config bug and Bamba torch.compile SDPA bug are unrelated." }, { "left": "issue:43606", "right": "issue:45083", "accept": false, - "reason": "CPU-offload device mismatch in bark-small is unrelated to qwen3_omni_moe feature-length helper behavior." + "reason": "CPU offload device mismatch and helper-length behavior are different problems." }, { "left": "issue:45290", "right": "issue:45381", "accept": false, - "reason": "Tool-call chat-template crash and Qwen2.5-VL video vision_position_ids bug are different symptoms and fixes." + "reason": "Tool-call chat-template crash and video vision_position_ids bug are distinct." }, { "left": "issue:44857", "right": "issue:45593", "accept": false, - "reason": "AMP/CUDA loss crash vs missing auxiliary losses when denoising is off; not the same underlying defect." + "reason": "AMP CUDA crash in a loss and missing auxiliary losses are unrelated." }, { "left": "issue:44448", "right": "issue:44743", "accept": false, - "reason": "Pegasus v4/v5 output change is unrelated to Qwen3.5 recurrent-state reset under cache." + "reason": "Pegasus v4/v5 output difference and recurrent-state reset in qwen3_5 are unrelated." }, { "left": "issue:45200", "right": "issue:45588", "accept": false, - "reason": "Gemma4 token-type defaulting issue is unrelated to a flash-attention AttributeError on sink-less models." + "reason": "Gemma4 mm_token_type_ids defaulting and flash_attention s_aux handling are different code paths." }, { "left": "issue:43278", "right": "issue:43825", "accept": false, - "reason": "Embedding dtype drift is unrelated to the pipeline deprecation/error-message regression." + "reason": "Embedding dtype regression and pipeline error-message/docs issue are unrelated." }, { "left": "issue:37428", "right": "issue:44351", "accept": false, - "reason": "Different import failures for different missing symbols; same broad area, but not the same bug." + "reason": "They are both import errors, but for different missing symbols and modules." }, { "left": "issue:44206", "right": "issue:45823", "accept": false, - "reason": "Both mention device mismatches, but they affect different models and different forward paths." + "reason": "Feature-extractor center-arg crash and Gemma4 device mismatch are unrelated." }, { - "left": "issue:43611", - "right": "issue:43931", + "left": "issue:44360", + "right": "issue:44561", "accept": false, - "reason": "Base_model_prefix loading regression and Qwen3-VL weight-shape mismatch are separate model-loading failures." + "reason": "DSA indexer discussion and removal of is_torch_fx_available are unrelated." }, { - "left": "issue:44360", - "right": "issue:44561", + "left": "issue:43611", + "right": "issue:43931", "accept": false, - "reason": "DSA indexer activation bug is unrelated to removal of is_torch_fx_available breaking trust_remote_code models." + "reason": "base_model_prefix loading breakage and Qwen3-VL shape mismatch are different failures." }, { "left": "issue:43335", "right": "issue:43653", "accept": false, - "reason": "Sparse-layer config bug vs tokenizer special-token registration bug; no shared underlying code path." + "reason": "Sparse-layer creation bug and BigBirdTokenizer special-token bug are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA compile failure and GraniteSpeech CI flake are unrelated." } ] }, @@ -7840,7 +7872,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28218", "issue:29127", @@ -7892,11 +7924,10 @@ ], "soft_pairs": [ "issue:39692|issue:43526", - "issue:43550|issue:44112", "issue:43388|issue:43526", + "issue:44855|issue:45083", "issue:45310|issue:45478", "issue:43335|issue:43504", - "issue:44855|issue:45083", "issue:43819|issue:44493", "issue:43335|issue:45083", "issue:45588|issue:45859", @@ -7917,10 +7948,10 @@ "issue:44857|issue:45072", "issue:44448|issue:44977", "issue:43701|issue:45083", - "issue:43927|issue:45698", "issue:43550|issue:45083", - "issue:44568|issue:45491", + "issue:43927|issue:45698", "issue:34689|issue:35141", + "issue:44568|issue:45491", "issue:29127|issue:32090", "issue:40444|issue:43526", "issue:45372|issue:45588", @@ -7928,256 +7959,250 @@ "issue:45198|issue:45803", "issue:43412|issue:45588" ], - "prepared_review_unit_hash": "69f8fa5f1d6fff8b99ae23e8118b9db0ad64af13d78368bf5bfeb1047dc57674", + "prepared_review_unit_hash": "3d3b6106d1050bcd8f1c670093c0f4e096613f98eef3b654d3d8c91a4eea21ec", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 36, - "serialized_chars": 38139, - "estimated_input_tokens": 9535, - "estimated_eval_tokens": 19326 + "soft_pair_count": 35, + "serialized_chars": 37839, + "estimated_input_tokens": 9460, + "estimated_eval_tokens": 19176 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is mostly a loose mix of unrelated Transformers issues. One pair, `issue:45310`/`issue:45478`, is a likely near-duplicate for the same Qwen3.5 MoE `from_pretrained` regression, but the packet only supports that from strong title/body similarity rather than an explicit duplicate link.", - "confidence": 0.93, - "canonical_issue_reason": "`issue:45310` is the better canonical issue for the shared Qwen3.5 MoE `from_pretrained` bug: it is the earlier report and appears to be the broader anchor for the same failure mode as `issue:45478`.", + "summary": "Most pairs are unrelated despite broad surface similarity. The only accepted duplicate is the Qwen3.5 MoE from_pretrained regression: issue:45310 and issue:45478.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45310 is the canonical issue because it is the earlier report and the two issues have the same title and near-identical Qwen3.5 MoE from_pretrained failure description.", "canonical_pr_reason": null, - "best_issue_reason": "`issue:45310` is the best issue anchor here because it is the earliest and strongest match for the shared Qwen3.5 MoE `from_pretrained` regression, with the later issue looking like a near-duplicate.", + "best_issue_reason": "issue:45310 is the best representative of the only accepted duplicate pair, mainly because it is the older report with the clearest matching bug description.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:39692", "right": "issue:43526", "accept": false, - "reason": "Docs/example errors in SigLIP2 are unrelated to BeitImageProcessorFast `reduce_labels` behavior." + "reason": "Different components and failures: SigLIP2 docs/model-processor mismatch vs BeitImageProcessorFast label reduction." }, { - "left": "issue:43550", - "right": "issue:44112", + "left": "issue:43388", + "right": "issue:43526", "accept": false, - "reason": "Bamba SDPA/compile failure and GraniteSpeech CI device-override test are different code paths." + "reason": "Different bugs: gather_for_metrics dropping labels in the last batch vs BeitImageProcessorFast returning only one label." }, { - "left": "issue:43388", - "right": "issue:43526", + "left": "issue:44855", + "right": "issue:45083", "accept": false, - "reason": "`gather_for_metrics` label truncation is unrelated to BeitImageProcessorFast `reduce_labels`." + "reason": "Unrelated failures: DebertaV2 import/JIT parse error vs qwen3_omni_moe helper behavior." }, { "left": "issue:45310", "right": "issue:45478", "accept": true, - "reason": "Likely the same Qwen3.5 MoE `from_pretrained` regression; the titles match exactly and the reports appear to describe the same failure mode, though there is no explicit duplicate link in the packet." + "reason": "Same underlying regression: both describe the transformers>=5.4.0 Qwen3.5 Moe from_pretrained error." }, { "left": "issue:43335", "right": "issue:43504", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug and BEiT legacy-field loading bug are unrelated." - }, - { - "left": "issue:44855", - "right": "issue:45083", - "accept": false, - "reason": "DebertaV2 import parsing error and qwen3_omni_moe feature-length helper issue are different bugs." + "reason": "Different subsystems and symptoms: SwitchTransformers sparse-layer config bug vs BEiT semantic segmentation legacy-field loading bug." }, { "left": "issue:43819", "right": "issue:44493", "accept": false, - "reason": "DAC latent decoding mismatch is unrelated to the position-id key warning regression." + "reason": "Different code paths: DAC.from_latents/STE mismatch vs unexpected position-id key warnings across models." }, { "left": "issue:43335", "right": "issue:45083", "accept": false, - "reason": "Different models and failures: SwitchTransformers config vs qwen3_omni_moe helper behavior." + "reason": "Only broad model-family overlap; not the same defect." }, { "left": "issue:45588", "right": "issue:45859", "accept": false, - "reason": "flash_attention `s_aux=None` crash and Qwen rotary embedding CPU-offload incompatibility are separate issues." + "reason": "Different failures in different layers: flash_attention s_aux handling vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." }, { "left": "issue:39692", "right": "issue:44493", "accept": false, - "reason": "SigLIP2 docs/example problems are unrelated to the position-id key issue." + "reason": "Docs/example errors are unrelated to the position-id key regression." }, { "left": "issue:29942", "right": "issue:32090", "accept": false, - "reason": "Flash Attention 2 test failures and Trainer `_gpu_broadcast_one` TypeError are unrelated." + "reason": "Different issues: Flash Attention 2 test failures vs Trainer/_gpu_broadcast_one NoneType TypeError." }, { "left": "issue:43335", "right": "issue:45072", "accept": false, - "reason": "SwitchTransformers config creation and bfloat16 dtype mismatch are different bugs." + "reason": "Different bugs: SwitchTransformers sparse-layer config vs dtype mismatches in bfloat16 inference." }, { "left": "issue:43720", "right": "issue:44112", "accept": false, - "reason": "BitNet packed-weight loading and GraniteSpeech stale CI test do not share the same root cause." + "reason": "Different CI/runtime problems: BitNet packed-weight loading vs GraniteSpeech stale device-override test." }, { "left": "issue:43335", "right": "issue:44112", "accept": false, - "reason": "SwitchTransformers config bug and GraniteSpeech CI failure are unrelated." + "reason": "No shared underlying bug; config-layer issue and CI test failure are distinct." }, { "left": "issue:44448", "right": "issue:44779", "accept": false, - "reason": "Both are v5 regressions, but they affect different models and failure modes, so not the same bug." + "reason": "Both are version-related output changes, but they affect different models and likely different code paths." }, { "left": "issue:38175", "right": "issue:44493", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to the unexpected position-id key warning." + "reason": "Different symptom and model: unexpected zero probabilities in SigLIP2 vs position-id key warnings." }, { "left": "issue:44292", "right": "issue:45520", "accept": false, - "reason": "Qwen-3-8B-NVFP4 runtime failure and Python 3.13 `flash_attn` import error are different issues." + "reason": "Different runtime errors: Qwen-3-8B-NVFP4 run failure vs flash_attn import KeyError on Python 3.13." }, { "left": "issue:28218", "right": "issue:35141", "accept": false, - "reason": "Tokenizer spacing after added tokens and embedding reinitialization after resize are unrelated." + "reason": "Tokenizer spacing after added token is unrelated to embedding reinitialization during post_init." }, { "left": "issue:44977", "right": "issue:45229", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and Gemma4 multi-GPU OOM are different problems." + "reason": "Different models and failures: flash-attention generation issue vs multi-GPU CUDA OOM." }, { "left": "issue:42490", "right": "issue:43854", "accept": false, - "reason": "Trailing-slash local path warning and GLM-4.7-Flash test loading failure are unrelated." + "reason": "Different loading problems: trailing-slash import warning vs GLM-4.7-Flash unit-test load failure." }, { "left": "issue:44561", "right": "issue:44779", "accept": false, - "reason": "Removal of `is_torch_fx_available` affects trust-remote-code loading; Deepseek tokenizer regression is a different bug." + "reason": "Different regressions: removal of is_torch_fx_available impacting trust_remote_code vs Deepseek tokenizer output changes." }, { "left": "issue:44462", "right": "issue:44561", "accept": false, - "reason": "AutoTokenizer ignoring `tokenizer.json` is unrelated to the `is_torch_fx_available` removal breakage." + "reason": "AutoTokenizer ignoring tokenizer.json and the v5 trust_remote_code breakage are separate issues." }, { "left": "issue:43606", "right": "issue:44857", "accept": false, - "reason": "CPU offload device mismatch and LwDetr float16 AMP crash are different code paths." + "reason": "Different failures: CPU offload device mismatch vs float16 AMP CUDA crash." }, { "left": "issue:44857", "right": "issue:45072", "accept": false, - "reason": "LwDetr AMP crash and SwitchTransformers/TimmWrapper dtype mismatch are unrelated." + "reason": "Different models and symptoms; dtype mismatch and AMP crash are not the same bug." }, { "left": "issue:44448", "right": "issue:44977", "accept": false, - "reason": "Different model regressions: Pegasus v4/v5 output drift vs Qwen3.5 flash-attention generation failure." + "reason": "Different models and code paths; both are generation issues but not the same concrete bug." }, { "left": "issue:43701", "right": "issue:45083", "accept": false, - "reason": "Checkpoint key mismatch is unrelated to qwen3_omni_moe feature-length behavior." - }, - { - "left": "issue:43927", - "right": "issue:45698", - "accept": false, - "reason": "DiaConfig token-ID persistence bug and wrong custom module loading after save/load are not the same issue." + "reason": "Checkpoint key mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." }, { "left": "issue:43550", "right": "issue:45083", "accept": false, - "reason": "Bamba torch.compile/SDPA failure and qwen3_omni_moe helper issue are unrelated." + "reason": "torch.compile/SDPA failure in Bamba is unrelated to qwen3_omni_moe helper output lengths." }, { - "left": "issue:44568", - "right": "issue:45491", + "left": "issue:43927", + "right": "issue:45698", "accept": false, - "reason": "Tokenizer BOS/EOS behavior in mdeberta-v3-base and Gemma3 NaN embeddings have different root causes." + "reason": "Both concern save/load semantics, but one loses custom token IDs and the other loads the wrong custom module; not the same defect." }, { "left": "issue:34689", "right": "issue:35141", "accept": false, - "reason": "Llama 3.2 Vision loading breakage and output-embedding reinit after resize are unrelated." + "reason": "Different model-loading and embedding-initialization bugs." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token insertion regression is unrelated to Gemma3 NaN embeddings with mixed-length batching." }, { "left": "issue:29127", "right": "issue:32090", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Trainer `_gpu_broadcast_one` TypeError are unrelated." + "reason": "Error-message clarity for LayoutLMv3 is unrelated to Trainer broadcast TypeError." }, { "left": "issue:40444", "right": "issue:43526", "accept": false, - "reason": "Qwen2.5-VL multi-image iterable dataset failure and BeitImageProcessorFast `reduce_labels` bug are unrelated." + "reason": "Different model/data pipelines: Qwen2.5-VL multi-image iterable dataset failure vs BEiT label reduction bug." }, { "left": "issue:45372", "right": "issue:45588", "accept": false, - "reason": "Gemma 4 processor-loading import error and flash_attention `s_aux=None` crash are different failures." + "reason": "Gemma 4 processor import failure and flash_attention s_aux=None crash are distinct issues." }, { "left": "issue:44977", "right": "issue:45563", "accept": false, - "reason": "Qwen3.5 flash-attention generation bug and stale `num_return_sequences` warning are not the same issue." + "reason": "Generation malfunction and stale warning for num_return_sequences are unrelated." }, { "left": "issue:45198", "right": "issue:45803", "accept": false, - "reason": "Wav2Vec2 save/tokenization failure and Fuyu bare-except error handling are unrelated." + "reason": "Wav2Vec2 save_pretrained/tokenization failure is unrelated to FuyuBatchFeature's bare except bug." }, { "left": "issue:43412", "right": "issue:45588", "accept": false, - "reason": "Gemma3n executorch export failure and flash_attention `s_aux=None` crash are different problems." + "reason": "Executorch export failures and flash_attention sink-less-model crash are different code paths and fixes." } ] }, "evaluator_result": { "accept": false, - "feedback": "The cluster-level summary is a bit too strong for the packet. In particular, `issue:45310` is not open in the packet (it is closed), and the `45310`/`45478` pair is only supported by title/body similarity, not an explicit duplicate relation. So calling it a \"clear duplicate\" or saying it is the same concrete bug as its duplicate overstates the evidence. The other soft-edge rejections look conservative, but this one pair should be phrased more cautiously (e.g. likely same bug / near-duplicate)." + "feedback": "The duplicate-pair conclusion looks right, but the canonicalization rationale is a bit overstated: issue:45310 is older and has one inbound reference versus none for issue:45478, but it does not have more discussion activity (2 vs 4). Please keep the justification more conservative, e.g. \u201colder report with an identical title/near-identical bug description,\u201d rather than implying broader evidence than the packet shows." }, "evaluator_used": true, "retried": true, @@ -8196,7 +8221,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:25251", "issue:29942", @@ -8252,8 +8277,8 @@ "issue:36010|issue:37428", "issue:29942|issue:35141", "issue:42490|issue:43575", - "issue:45372|issue:45459", "issue:43065|issue:45412", + "issue:45372|issue:45459", "issue:44857|issue:45588", "issue:45245|issue:45563", "issue:44448|issue:44466", @@ -8265,214 +8290,202 @@ "issue:25251|issue:32090", "issue:44186|issue:45198", "issue:43066|issue:44462", - "issue:44451|issue:45520", "issue:44206|issue:44479", "issue:42915|issue:42994", + "issue:44451|issue:45520", "issue:44361|issue:45198", "issue:44871|issue:44977", "issue:43065|issue:43994", "issue:44265|issue:45198", "issue:43421|issue:45491", "issue:44734|issue:45406", - "issue:33357|issue:39692", - "issue:29942|issue:30064" + "issue:29942|issue:30064", + "issue:33357|issue:39692" ], - "prepared_review_unit_hash": "2f598be05ec2cfcf3093c505b071df550c5b4aa39f9894244e0f68fed3304d3a", + "prepared_review_unit_hash": "6e4ac5c30a890905b6dd559665bdea1918c4b4f38ffa68677047223b3f90ce9b", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 28, - "serialized_chars": 36222, - "estimated_input_tokens": 9056, - "estimated_eval_tokens": 18368 + "serialized_chars": 36215, + "estimated_input_tokens": 9054, + "estimated_eval_tokens": 18364 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items are a heterogeneous mix of unrelated bugs across tokenization, model loading, attention kernels, training, and documentation. None of the soft pairs look like the same underlying issue/change, so there is no clear canonical duplicate target in this set.", - "confidence": 0.97, - "canonical_issue_reason": null, + "summary": "This is not a true duplicate cluster: the soft pairs span unrelated bugs across tokenizers, model loading, serving, flash-attention, and vision/audio regressions. None of the candidate pairs look like the same underlying fix; they should stay separate.", + "confidence": 0.39, + "canonical_issue_reason": "issue:44462 is the closest broad, user-facing regression here because it concerns core AutoTokenizer loading behavior and has external references, but it is only a loose representative rather than a true duplicate hub.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a strong canonical representative because the set is not one duplicate cluster; the issues span many unrelated subsystems and failure modes.", + "best_issue_reason": "issue:44462 is the most generally applicable and reusable report in an otherwise heterogeneous set; it has clearer cross-cutting impact than the highly model- or subsystem-specific bugs around it.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45459", "right": "issue:45712", "accept": false, - "reason": "Different problems: tokenizer error masking vs leftover dummy classes / repo hygiene." + "reason": "Tokenizer error handling with protobuf missing is unrelated to leftover dummy PT classes and repo checks." }, { "left": "issue:36010", "right": "issue:37428", "accept": false, - "reason": "Both are import errors, but for different symbols and code paths (`GenerationMixin` vs `_flash_supports_window_size`)." + "reason": "GenerationMixin import failure and flash-attention utility import failure affect different code paths and fixes." }, { "left": "issue:29942", "right": "issue:35141", "accept": false, - "reason": "Unrelated: Flash Attention test failures vs embedding reinitialization after resizing tokens." + "reason": "Flash Attention test failures are not the same bug as output embedding reinitialization after resize." }, { "left": "issue:42490", "right": "issue:43575", "accept": false, - "reason": "Local-path import warning is unrelated to tensor-parallel OOM when loading a large model." + "reason": "Trailing-slash local model warning is unrelated to tensor-parallel OOM when loading a specific Qwen model." }, { - "left": "issue:45372", - "right": "issue:45459", + "left": "issue:43065", + "right": "issue:45412", "accept": false, - "reason": "Gemma 4 processor import failure due to missing `ReasoningEffort` is not the same as protobuf hiding tokenizer errors." + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory not being released are distinct issues." }, { - "left": "issue:43065", - "right": "issue:45412", + "left": "issue:45372", + "right": "issue:45459", "accept": false, - "reason": "Dummy Conv2d in a pixel decoder is unrelated to RT-DETR memory not being released on deletion." + "reason": "Gemma 4 processor loading breaks on a missing dependency; the other issue is about hiding tokenizer decode errors when protobuf is absent." }, { "left": "issue:44857", "right": "issue:45588", "accept": false, - "reason": "Different runtime failures: LwDetrImageLoss AMP/CUDA crash vs flash attention sink-less `s_aux=None` AttributeError." + "reason": "AMP/CUDA loss crash for LwDetr is unrelated to flash_attention.py failing on s_aux=None." }, { "left": "issue:45245", "right": "issue:45563", "accept": false, - "reason": "Category-limit RuntimeError is unrelated to stale `num_return_sequences` warning in paged generate()." + "reason": "Category-count runtime error and stale num_return_sequences warning are different behaviors with different fixes." }, { "left": "issue:44448", "right": "issue:44466", "accept": false, - "reason": "Different regression surfaces: generation output change vs serialization of `lm_head.weight`/tied weights." + "reason": "Both involve v4/v5 behavior changes, but one is generation output drift and the other is serialization of lm_head.weight; not the same bug." }, { "left": "issue:43653", "right": "issue:44743", "accept": false, - "reason": "BigBird tokenizer special-token decode bug is unrelated to Qwen3.5 recurrent state resetting with cache." + "reason": "BigBirdTokenizer special-token registration and Qwen3.5 recurrent-state reset are unrelated tokenizer vs model-state problems." }, { "left": "issue:45588", "right": "issue:45823", "accept": false, - "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different code paths and failures." + "reason": "Both touch Gemma-related code, but one is a flash-attention crash and the other is a device-mismatch forward bug." }, { "left": "issue:43976", "right": "issue:45440", "accept": false, - "reason": "Python version support/import issue is unrelated to DeepseekV3MoE behavioral divergence." + "reason": "Python version compatibility and DeepSeekV3 implementation divergence are separate problems." }, { "left": "issue:43278", "right": "issue:43381", "accept": false, - "reason": "Embedding dtype drift in eval is not the same bug as gradient checkpointing being disallowed in eval mode." + "reason": "BF16-to-FP32 dtype drift in eval is unrelated to gradient checkpointing being disallowed in eval mode." }, { "left": "issue:43994", "right": "issue:45412", "accept": false, - "reason": "SigLIP2 output mismatch is unrelated to RT-DETR memory retention." + "reason": "SigLIP2 wrong outputs and RT-DETR memory leaks are different model-specific regressions." }, { "left": "issue:25251", "right": "issue:32090", "accept": false, - "reason": "Pipeline `top_k` nested-list output bug is unrelated to trainer `_gpu_broadcast_one` NoneType crash." + "reason": "Pipeline top_k nesting and Trainer _gpu_broadcast_one NoneType errors are unrelated runtime issues." }, { "left": "issue:44186", "right": "issue:45198", "accept": false, - "reason": "LayoutLMv2 tokenizer crash on NER/padding is unrelated to Wav2Vec2 save/tokenization failure." + "reason": "LayoutLMv2Tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure do not share the same code path." }, { "left": "issue:43066", "right": "issue:44462", "accept": false, - "reason": "Wrong tokenizer decoder type in v5 is not the same as AutoTokenizer ignoring `tokenizer.json`." - }, - { - "left": "issue:44451", - "right": "issue:45520", - "accept": false, - "reason": "Model loading failure for a specific checkpoint is unrelated to Python 3.13 `flash_attn` import-key error." + "reason": "Wrong tokenizer decoder type and ignoring tokenizer.json are both tokenizer-related, but they are different concrete loading/serialization bugs." }, { "left": "issue:44206", "right": "issue:44479", "accept": false, - "reason": "Unsupported `center` arg in LasrFeatureExtractor is unrelated to video input regression in Qwen multimodal models." + "reason": "Unsupported center arg in a feature extractor is unrelated to the Qwen video-input regression." }, { "left": "issue:42915", "right": "issue:42994", "accept": false, - "reason": "FineGrainedFP8Config failure for Qwen3Moe and quantized model saving failure are different issues." + "reason": "FineGrainedFP8Config failure and quantized model saving failure are distinct quantization bugs." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT and flash_attn import KeyError on Python 3.13 are not the same issue." }, { "left": "issue:44361", "right": "issue:45198", "accept": false, - "reason": "MLukeTokenizer AttributeError on tasks is unrelated to Wav2Vec2 save/tokenization failure." + "reason": "MLukeTokenizer attribute errors and Wav2Vec2 save/tokenization failures are separate tokenizer/model bugs." }, { "left": "issue:44871", "right": "issue:44977", "accept": false, - "reason": "Gemma-3 eos_token_id mismatch is not the same as Qwen3.5 flash-attention generation regression." - }, - { - "left": "issue:43065", - "right": "issue:43994", - "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and SigLIP2 nonsensical outputs are unrelated bugs." - }, - { - "left": "issue:44265", - "right": "issue:45198", - "accept": false, - "reason": "torch.export export failure with `torch_compilable_check` is unrelated to Wav2Vec2 save/tokenization failure." + "reason": "Gemma eos_token_id mismatch and Qwen3.5 flash-attention generation failure are unrelated." }, { "left": "issue:43421", "right": "issue:45491", "accept": false, - "reason": "Runtime special-token post-processor update feature request is unrelated to Gemma3 NaN embeddings with mixed-length batches." + "reason": "Runtime special-token post-processing update and Gemma3 NaN embeddings are different tokenizer vs attention/numerics bugs." }, { "left": "issue:44734", "right": "issue:45406", "accept": false, - "reason": "KV cache continuation tensor indexing bug in serve is different from Gemma4Processor missing `_tokenizer`." + "reason": "Serving KV-cache tensor indexing crash and Gemma4Processor missing _tokenizer are separate serve-time failures." }, { - "left": "issue:33357", - "right": "issue:39692", + "left": "issue:29942", + "right": "issue:30064", "accept": false, - "reason": "MacOS bus error with CLIP model and SigLIP2 doc example errors are not the same bug." + "reason": "Flash Attention 2 test failures and void segmentation map processing failure are unrelated subsystems." }, { - "left": "issue:29942", - "right": "issue:30064", + "left": "issue:33357", + "right": "issue:39692", "accept": false, - "reason": "Flash Attention 2 test failures are unrelated to void segmentation map processing in the image processor." + "reason": "MacOS bus error with a community CLIP model and SigLIP2 documentation example errors are different model/documentation problems." } ] }, @@ -8494,7 +8507,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:10000", "issue:15354", @@ -8556,9 +8569,9 @@ "issue:42490|issue:43873", "issue:43278|issue:43575", "issue:43653|issue:44442", + "issue:41720|issue:45229", "issue:45103|issue:45372", "issue:43761|issue:45859", - "issue:41720|issue:45229", "issue:43526|issue:45834", "issue:43381|issue:43701", "issue:45440|issue:45593", @@ -8567,8 +8580,8 @@ "issue:32090|issue:33357", "issue:43334|issue:43531", "issue:43526|issue:44186", - "issue:43824|issue:44279", "issue:44977|issue:45245", + "issue:43824|issue:44279", "issue:43526|issue:44857", "issue:44442|issue:45072", "issue:43262|issue:44206", @@ -8576,208 +8589,208 @@ "issue:44062|issue:45907", "issue:42915|issue:43931" ], - "prepared_review_unit_hash": "b10abc319c587d3573a87c79c9913d7b343a5141dd3993030c33769c79939e42", + "prepared_review_unit_hash": "6842325902c0c9dad78c2148ee37dd66b07bba91753fad7aea7ee48fa3505820", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36376, - "estimated_input_tokens": 9094, - "estimated_eval_tokens": 18444 + "serialized_chars": 36379, + "estimated_input_tokens": 9095, + "estimated_eval_tokens": 18446 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft pair looks like the same underlying bug or change; the set is a grab bag of unrelated model-, tokenizer-, training-, and inference-path issues. I\u2019d keep the open quantization/offloading report as the best representative issue, but there are no convincing duplicate merges here.", - "confidence": 0.88, - "canonical_issue_reason": "issue:43873 is the strongest representative: it is open, has multiple inbound references, and describes a broadly impactful offloading/quantization failure path rather than a narrow model-specific symptom.", + "summary": "This cluster is heterogeneous: the issues span unrelated models, loaders, processors, training utilities, and runtime failures. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.18, + "canonical_issue_reason": "No clear canonical duplicate exists; the cluster is too mixed. If a hub is required, issue 43873 is the broadest and most referenced loading/offload report.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best global issue candidate because it is still open, appears actively relevant, and addresses an infrastructure-level bug that could attract related reports.", + "best_issue_reason": "Issue 43873 is the best cluster hub only because it is broad and relatively well-connected, not because the set is truly duplicate.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:29127", "right": "issue:34567", "accept": false, - "reason": "LayoutLMv3 error-message clarity and Trainer token-count tracking are unrelated bugs in different code paths." + "reason": "Different subsystems: LayoutLMv3 error messaging vs Trainer token-count tracking." }, { "left": "issue:44610", "right": "issue:45412", "accept": false, - "reason": "OmDet-Turbo input-size mismatch and RT-DETR memory release are different model/runtime problems." + "reason": "Processor input-size mismatch and RT-DETR memory leak are unrelated failures." }, { "left": "issue:10000", "right": "issue:15354", "accept": false, - "reason": "German DistilBertModel issue and GeneratorExp torch.jit export failure are unrelated." + "reason": "German DistilBertModel issue and torch.jit GeneratorExp export error are different bugs." }, { "left": "issue:43756", "right": "issue:45440", "accept": false, - "reason": "Smollm3 RoPE-layer behavior and DeepseekV3MoE divergence are separate architecture-specific issues." + "reason": "Different model-specific correctness issues in Smollm3 vs DeepSeekV3MoE." }, { "left": "issue:43873", "right": "issue:45229", "accept": false, - "reason": "Quantization/offloading behavior and Gemma4 multi-GPU OOM are different failure modes, not one concrete bug." + "reason": "Both involve GPU/memory concerns, but one is quantization offload and the other is multi-GPU OOM." }, { "left": "issue:45372", "right": "issue:45406", "accept": false, - "reason": "Gemma4 processor import dependency breakage and Gemma4Processor missing _tokenizer are distinct loader bugs." + "reason": "Gemma 4 processor loading failures, but one is an import dependency issue and the other is a missing attribute." }, { "left": "issue:43723", "right": "issue:44554", "accept": false, - "reason": "Tokenizer loading in v5 and an MPS attention correctness issue do not share the same code defect." + "reason": "Tokenizer import/loading regression vs MPS attention correctness issue; no shared code path." }, { "left": "issue:42490", "right": "issue:43873", "accept": false, - "reason": "Trailing-slash local model import warning is unrelated to quantization/offloading behavior." + "reason": "Trailing-slash import warning is unrelated to quantization/offloading behavior." }, { "left": "issue:43278", "right": "issue:43575", "accept": false, - "reason": "Training/evaluate dtype drift and tensor-parallel OOM on Qwen2-57B are different issues." + "reason": "Embedding dtype mismatch during eval and TP OOM on Qwen2-57B are different problems." }, { "left": "issue:43653", "right": "issue:44442", "accept": false, - "reason": "BigBirdTokenizer special-token decode bug and FastSpeech2ConformerTokenizer load failure are separate tokenizer problems." + "reason": "Both touch tokenizers, but they are different tokenizer bugs with different failure modes." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Different model families and root causes: cudaErrorAssert vs CUDA OOM." }, { "left": "issue:45103", "right": "issue:45372", "accept": false, - "reason": "auto_docstring future-annotations crash and Gemma4 ReasoningEffort import failure affect different subsystems." + "reason": "Auto-docstring annotation crash is unrelated to Gemma 4 processor import failure." }, { "left": "issue:43761", "right": "issue:45859", "accept": false, - "reason": "CLIPVisionModel hidden_states regression and Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility are unrelated." - }, - { - "left": "issue:41720", - "right": "issue:45229", - "accept": false, - "reason": "Qwen3 auto-device-map cudaErrorAssert and Gemma4 OOM are both inference issues but not the same concrete bug." + "reason": "CLIPVisionModel hidden_states regression and Qwen3 MoE CPU-offload incompatibility are unrelated." }, { "left": "issue:43526", "right": "issue:45834", "accept": false, - "reason": "BEiT label reduction and Kosmos2.5 long-OCR indexing are different processor bugs." + "reason": "BeitImageProcessorFast label reduction bug and Kosmos2.5 OCR index error are different processor issues." }, { "left": "issue:43381", "right": "issue:43701", "accept": false, - "reason": "Gradient checkpointing in eval mode and resume_from_checkpoint key mismatch are separate trainer-state issues." + "reason": "Gradient checkpointing in eval mode and resume-from-checkpoint key mismatch are distinct training bugs." }, { "left": "issue:45440", "right": "issue:45593", "accept": false, - "reason": "DeepseekV3MoE divergence and D-FINE auxiliary-loss handling are unrelated model-implementation bugs." + "reason": "DeepSeekV3MoE divergence and D-FINE auxiliary-loss behavior are unrelated model issues." }, { "left": "issue:29942", "right": "issue:36010", "accept": false, - "reason": "Flash Attention 2 test failures and GenerationMixin import failure are not the same underlying defect." + "reason": "Flash Attention test failures and GenerationMixin import errors do not share a code path." }, { "left": "issue:43278", "right": "issue:43329", "accept": false, - "reason": "Embedding dtype drift and multimodal token counting in the video branch are unrelated." + "reason": "Embedding dtype regression and multimodal token counting bug are unrelated." }, { "left": "issue:32090", "right": "issue:33357", "accept": false, - "reason": "Trainer NoneType broadcast error and MacOS CLIP bus error are different runtime failures." + "reason": "Trainer broadcast TypeError and MacOS bus error in CLIP loading are different runtime failures." }, { "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 bugs." + "reason": "Qwen3-VL pad_token_id load failure and Qwen3-MoE sliding_window issue are separate model bugs." }, { "left": "issue:43526", "right": "issue:44186", "accept": false, - "reason": "BEiT reduce_labels behavior and LayoutLMv2 tokenizer crashes are separate tokenizer/processor issues." + "reason": "Different preprocessing stacks and errors: BeitImageProcessorFast vs LayoutLMv2Tokenizer." }, { - "left": "issue:43824", - "right": "issue:44279", + "left": "issue:44977", + "right": "issue:45245", "accept": false, - "reason": "Qwen2.5-VL import error and a generic transformers dependency issue are too broad and not the same bug." + "reason": "Flash-attention generation bug and category-cardinality RuntimeError are unrelated." }, { - "left": "issue:44977", - "right": "issue:45245", + "left": "issue:43824", + "right": "issue:44279", "accept": false, - "reason": "Qwen3.5 flash-attention generation and the 2^24 category-limit error are unrelated." + "reason": "Specific Qwen2.5-VL import failure vs generic dependency issue; not the same bug." }, { "left": "issue:43526", "right": "issue:44857", "accept": false, - "reason": "BEiT label reduction and LwDetrImageLoss AMP crash are separate problems." + "reason": "Image processor label handling and LwDetr float16 AMP crash are unrelated." }, { "left": "issue:44442", "right": "issue:45072", "accept": false, - "reason": "FastSpeech2ConformerTokenizer loading and dtype mismatches in SwitchTransformers/TimmWrapperModel are unrelated." + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are different issues." }, { "left": "issue:43262", "right": "issue:44206", "accept": false, - "reason": "Audio chat-template sample-rate defaulting and LasrFeatureExtractor center-arg crash are different audio-path bugs." + "reason": "Audio chat-template sampling-rate bug and LaserFeatureExtractor center-arg crash are unrelated." }, { "left": "issue:42490", "right": "issue:43381", "accept": false, - "reason": "Trailing-slash import warning and gradient-checkpointing eval-mode behavior do not overlap." + "reason": "Trailing-slash local-model warning has no overlap with gradient checkpointing eval-mode behavior." }, { "left": "issue:44062", "right": "issue:45907", "accept": false, - "reason": "AddedToken special-argument conflict and list_repo_files revision forwarding are unrelated API bugs." + "reason": "AddedToken keyword collision and list_repo_files revision forwarding are unrelated API bugs." }, { "left": "issue:42915", "right": "issue:43931", "accept": false, - "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are different model-loading issues." + "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are different loading problems." } ] }, @@ -8799,7 +8812,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28218", "issue:29127", @@ -8864,210 +8877,210 @@ "issue:43316|issue:43525", "issue:44479|issue:45290", "issue:43761|issue:44079", - "issue:44442|issue:44898", "issue:28218|issue:29127", + "issue:44442|issue:44898", "issue:42907|issue:45698", "issue:33290|issue:34567", "issue:34689|issue:43611", "issue:43931|issue:45216", "issue:43761|issue:44188", + "issue:43316|issue:45759", "issue:43381|issue:43873", "issue:43493|issue:43827", - "issue:43316|issue:45759", "issue:43550|issue:44743", "issue:43720|issue:44442", "issue:41628|issue:45372" ], - "prepared_review_unit_hash": "79d4ba0b40f9e102e8e1df0ba723f34cd83e711255ca7e6b1f6001a362bc5fca", + "prepared_review_unit_hash": "1c9d50eac5881b418575371baa6dcf46aa11c66e2dcb8a1f69f2e0855351ae55", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 27, - "serialized_chars": 35303, - "estimated_input_tokens": 8826, - "estimated_eval_tokens": 17908 + "serialized_chars": 35298, + "estimated_input_tokens": 8825, + "estimated_eval_tokens": 17906 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These items do not form one coherent duplicate cluster; they span many unrelated Transformer regressions and API issues. I reject all soft edges and would treat 43873 as the best broad representative issue only because it is active, high-impact, and discussion-heavy.", - "confidence": 0.95, - "canonical_issue_reason": "No single canonical issue fits this set: the reported bugs cover unrelated models, APIs, and code paths, so there is no true duplicate hub here.", - "canonical_pr_reason": "No pull requests are present in the provided items.", - "best_issue_reason": "Issue 43873 is the best representative if one must be chosen: it is open, broadly scoped, and has the strongest discussion/inbound-reference signal among the listed reports.", - "best_pr_reason": "No pull requests are present, so there is no best PR candidate.", + "summary": "The cluster is highly heterogeneous: most items are distinct bugs, regressions, or docs/import issues rather than duplicates. None of the soft-edge pairs looks like the same underlying change or bug. If a single issue must represent the set, the broad, highly active quantization/offloading report is the best fit.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43873 is the most active open report with repeated community references and a broad runtime/memory regression shape, making it the best representative candidate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 has the strongest triage value here: open, broad symptom, and the most discussion/inbound references among the set.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43441", "right": "issue:45588", "accept": false, - "reason": "Both involve flash-attention, but the titles point to different bugs: a model-specific v5 RC failure vs. an AttributeError in sink-less flash_attention integration." + "reason": "Different failure modes: model-specific FlashAttention regression vs sink-less flash_attention AttributeError." }, { "left": "issue:43575", "right": "issue:43701", "accept": false, - "reason": "Completely different problems: tensor-parallel OOM on Qwen2-57B versus a resume_from_checkpoint key mismatch." + "reason": "OOM during tensor-parallel model loading is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:43646", "right": "issue:44077", "accept": false, - "reason": "Both touch initialization, but one is a broad v5 custom-model init regression and the other is a specific patchtsmixer post_init API constraint." + "reason": "Different regressions in custom model init vs patchtsmixer post_init handling." }, { "left": "issue:43575", "right": "issue:44387", "accept": false, - "reason": "Both mention OOM, but the causes differ: TP loading OOM versus increased reserved memory under int4 quantization." + "reason": "Both mention OOM, but one is TP loading and the other is int4 quantization memory growth; not the same bug." }, { "left": "issue:44743", "right": "issue:44811", "accept": false, - "reason": "Different subsystems and symptoms: recurrent state reset with cache versus Whisper batch_decode skipping special tokens." + "reason": "Cache/state reset in Qwen3.5 is unrelated to Whisper batch_decode skip_special_tokens handling." }, { "left": "issue:44464", "right": "issue:45491", "accept": false, - "reason": "Unrelated bugs: compiled chunked generation inconsistency versus Gemma3 NaN embeddings from sliding-window all-padding cases." + "reason": "Compiled-forward inconsistency and Gemma3 NaN embeddings are different model/pathologies." }, { "left": "issue:29127", "right": "issue:35141", "accept": false, - "reason": "No shared underlying bug; one is a LayoutLMv3 error-message clarity issue, the other is output embedding reinitialization after resize_token_embeddings." + "reason": "LayoutLMv3 error messaging and embedding reinitialization are unrelated issues." }, { "left": "issue:44977", "right": "issue:45584", "accept": false, - "reason": "Different failure modes and models: Qwen3.5 flash-attention generation regression versus Whisper empty-transcription generation failure." + "reason": "Qwen3.5 flash-attention generation bug is unrelated to Whisper empty-transcription/alignment failure." }, { "left": "issue:33357", "right": "issue:38175", "accept": false, - "reason": "Both are vision-model issues, but one is a MacOS bus error and the other is unexpected zero probabilities in SigLIP2." + "reason": "Both are vision-model problems, but bus error on CLIP/MacOS is not the same as SigLIP2 zero-probability outputs." }, { "left": "issue:44964", "right": "issue:45440", "accept": false, - "reason": "Distinct model families and bugs: Phi-4 multimodal loading failure versus DeepseekV3MoE divergence from remote implementation." + "reason": "Different model families and different failure classes: model loading vs implementation divergence." }, { "left": "issue:44442", "right": "issue:45803", "accept": false, - "reason": "One is an AutoTokenizer loading failure; the other is a Fuyu tensor-conversion exception-handling bug. Not the same code path." + "reason": "Tokenizer load failure is unrelated to Fuyu's bare-except error swallowing in tensor conversion." }, { "left": "issue:43316", "right": "issue:43525", "accept": false, - "reason": "Both are config/API problems, but for different models and different attributes; no evidence of one shared defect." + "reason": "Both are config API mismatches, but they involve different models and different missing properties." }, { "left": "issue:44479", "right": "issue:45290", "accept": false, - "reason": "Unrelated regressions: video-input handling for Qwen VLMs versus chat-template crashes on tool-call assistant messages." + "reason": "Video-input regression and chat-template tool-call crash are separate code paths." }, { "left": "issue:43761", - "right": "issue:44079", + "right": "issue:44188", "accept": false, - "reason": "The first is a CLIPVisionModel forward-path bug; the second is a generic ModelOutput key-assignment issue. Too different to merge." + "reason": "CLIPVision hidden_states regression is unrelated to torch.compile attention-kernel branching." }, { - "left": "issue:44442", - "right": "issue:44898", + "left": "issue:28218", + "right": "issue:29127", "accept": false, - "reason": "Different components and symptoms: tokenizer loading versus Perceiver image-classification resolution handling." + "reason": "Tokenizer spacing bug and LayoutLMv3 box-validation error are unrelated." }, { - "left": "issue:28218", - "right": "issue:29127", + "left": "issue:44442", + "right": "issue:44898", "accept": false, - "reason": "No overlap beyond being issues in transformers; tokenizer spacing behavior and LayoutLMv3 error messaging are unrelated." + "reason": "Tokenizer loading and Perceiver non-default-resolution classification failure are different bugs." }, { "left": "issue:42907", "right": "issue:45698", "accept": false, - "reason": "Both concern save/load flows, but one is dequantized model saving and the other is incorrect custom-module resolution after save_pretrained." + "reason": "Saving dequantized models and loading the wrong custom module after save_pretrained are not the same issue." }, { "left": "issue:33290", "right": "issue:34567", "accept": false, - "reason": "OOM under Adafactor/deepspeed is unrelated to TrainerState.num_input_tokens_seen not updating." + "reason": "Adafactor/deepspeed OOM is unrelated to TrainerState token-count updates." }, { "left": "issue:34689", "right": "issue:43611", "accept": false, - "reason": "Both are model-loading regressions, but they refer to different breakages and different root causes." + "reason": "Both are loading regressions, but they affect different mechanisms and model types." }, { "left": "issue:43931", "right": "issue:45216", "accept": false, - "reason": "One is a shape-mismatch load error for Qwen3-VL; the other is an incorrect checkpoint saved by save_pretrained for Qwen3.5." + "reason": "Weight-shape mismatch on load is different from incorrect checkpoint saving in save_pretrained." }, { "left": "issue:43761", "right": "issue:44188", "accept": false, - "reason": "Different layers entirely: CLIPVisionModel hidden_states handling versus attention-kernel branching under torch.compile." + "reason": "Same as above: these are distinct bugs in different execution paths." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model APIs, but one is a text-config discrepancy and the other is from_config unwrapping for multimodal models." }, { "left": "issue:43381", "right": "issue:43873", "accept": false, - "reason": "Gradient checkpointing in eval mode and quantization/offloading behavior are separate bugs with no shared concrete code path." + "reason": "Gradient checkpointing in eval mode is unrelated to quantization offloading behavior." }, { "left": "issue:43493", "right": "issue:43827", "accept": false, - "reason": "A model-parity discrepancy is not the same as stale docs referencing pipeline() after v5 removals." - }, - { - "left": "issue:43316", - "right": "issue:45759", - "accept": false, - "reason": "Both involve configuration, but one is a Gemma3TextConfig API inconsistency and the other is from_config unwrapping for composite Qwen multimodal configs." + "reason": "SigLIP2 implementation drift is unrelated to docs still referencing removed pipeline() APIs." }, { "left": "issue:43550", "right": "issue:44743", "accept": false, - "reason": "Different areas: torch.compile/SDPA failure in Bamba versus cache/recurrent-state reset in Qwen3.5 modular code." + "reason": "torch.compile+SDPA failure is unrelated to cache recurrent-state resets." }, { "left": "issue:43720", "right": "issue:44442", "accept": false, - "reason": "Packed-weight unpacking during accelerate loading and AutoTokenizer loading are unrelated bugs." + "reason": "BitNet packed-weight loading and tokenizer class loading are different code paths and failures." }, { "left": "issue:41628", "right": "issue:45372", "accept": false, - "reason": "Both are import errors, but they concern different symbols, different dependencies, and different processor-loading paths." + "reason": "Both are import errors, but they are for different symbols and different dependency breakages." } ] }, @@ -9089,7 +9102,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:25251", "issue:28282", @@ -9150,8 +9163,8 @@ "issue:44855|issue:45137", "issue:29127|issue:33357", "issue:43316|issue:44877", - "issue:33290|issue:45656", "issue:43540|issue:44514", + "issue:33290|issue:45656", "issue:33290|issue:34689", "issue:42175|issue:43316", "issue:43404|issue:43441", @@ -9170,112 +9183,112 @@ "issue:33290|issue:35141", "issue:33290|issue:36331" ], - "prepared_review_unit_hash": "14ec3e16351ce5adb04475dc823404d6a920238f87ab5298ed2f7d34bc4a2fe4", + "prepared_review_unit_hash": "504199353c6ad43c268b3009ef57e03f33c44e318c79bb8bf2c3aba5bf6d39e2", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 36083, - "estimated_input_tokens": 9021, - "estimated_eval_tokens": 18298 + "serialized_chars": 36095, + "estimated_input_tokens": 9024, + "estimated_eval_tokens": 18304 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The set is heterogeneous and the soft-similarity pairs are mostly false positives. I would not merge any of the candidate pairs; the best single issue to anchor the cluster is the open offloading/quantization report.", - "confidence": 0.82, - "canonical_issue_reason": "issue:43873 is the strongest representative: it is open, has the most inbound references among the open items, and describes a concrete runtime bug with clear user impact.", + "summary": "All soft pairs look like false positives: the issues span unrelated model regressions, config/serialization bugs, training/runtime failures, and environment-specific errors. No PRs are present, and no single canonical duplicate emerges from this set.", + "confidence": 0.99, + "canonical_issue_reason": "No canonical issue: the cluster is heterogeneous, and the candidate pairs do not describe the same underlying bug.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43873 is the best issue to keep as the cluster anchor because it is active, well-discussed, and broad enough to represent a real defect without being overly narrow.", + "best_issue_reason": "No issue is a good global canonical representative because the items cover distinct root causes and code paths.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44568", "right": "issue:45479", "accept": false, - "reason": "Different subsystems and failures: tokenizer special-token behavior vs sequence-classification loss computation." + "reason": "Tokenizer special-token behavior and sequence-classification zero-loss are different bugs." }, { "left": "issue:43643", "right": "issue:44913", "accept": false, - "reason": "Both are config-related, but one is missing fields from trust_remote_code and the other is rotary_pct not persisting on reload; different bugs." + "reason": "Missing fields from trust_remote_code config loading is unrelated to rotary_pct not persisting on reload." }, { "left": "issue:32090", "right": "issue:33290", "accept": false, - "reason": "Trainer NoneType broadcast error is unrelated to Adafactor OOM in DeepSpeed." + "reason": "GPU broadcast NoneType failure is not the same as an AdaFactor/DeepSpeed OOM." }, { "left": "issue:34689", "right": "issue:36010", "accept": false, - "reason": "Model loading regression for Llama 3.2 vision is unrelated to GenerationMixin import failure." + "reason": "Model loading regression and GenerationMixin import error are separate code paths." }, { "left": "issue:43873", "right": "issue:44871", "accept": false, - "reason": "Offloading/quantization behavior is a different bug from Gemma eos_token_id config mismatch." + "reason": "Quantization/offloading behavior and eos_token_id config mismatch are distinct issues." }, { "left": "issue:44190", "right": "issue:44496", "accept": false, - "reason": "Local dataset loading in a training script is unrelated to an unrecognized model/config.json issue." + "reason": "Local dataset script failure is unrelated to an unrecognized model/config error." }, { "left": "issue:44077", "right": "issue:44479", "accept": false, - "reason": "Optional post_init policy for patchtsmixer is unrelated to a video-input regression across Qwen VL models." + "reason": "Optional post_init policy and Qwen video-input regression are different problems." }, { "left": "issue:44855", "right": "issue:45137", "accept": false, - "reason": "Python 3.13 IndentationError in DebertaV2 import is unrelated to a DeepSpeed ZeRO3 deque error." + "reason": "Python 3.13 torch.jit parsing error is unrelated to the DeepSpeed deque underflow." }, { "left": "issue:29127", "right": "issue:33357", "accept": false, - "reason": "LayoutLMv3 error messaging and a MacOS CLIP bus error are different failures." + "reason": "LayoutLMv3 box-handling clarity and MacOS CLIP bus error do not share a root cause." }, { "left": "issue:43316", "right": "issue:44877", "accept": false, - "reason": "API discrepancy in Gemma3TextConfig is not the same as strict config rejection for granite_speech." + "reason": "API discrepancy in Gemma3TextConfig is not the same as strict loading rejecting granite_speech." }, { - "left": "issue:33290", - "right": "issue:45656", + "left": "issue:43540", + "right": "issue:44514", "accept": false, - "reason": "Adafactor OOM in DeepSpeed is not the same as optimizer.step being called twice." + "reason": "Video-input processing failure and batched apply_chat_template padding crash are different processor bugs." }, { - "left": "issue:43540", - "right": "issue:44514", + "left": "issue:33290", + "right": "issue:45656", "accept": false, - "reason": "Qwen3OmniMoe video processing ValueError and Qwen2_5_VL batched chat-template crash are different code paths." + "reason": "OOM in DeepSpeed AdaFactor is not the same as optimizer.step being invoked twice." }, { "left": "issue:33290", "right": "issue:34689", "accept": false, - "reason": "Optimizer memory usage in DeepSpeed is unrelated to a model-loading regression for Llama 3.2 vision." + "reason": "Training OOM and Llama 3.2 Vision model-loading regression are unrelated." }, { "left": "issue:42175", @@ -9287,91 +9300,91 @@ "left": "issue:43404", "right": "issue:43441", "accept": false, - "reason": "Untied lm_head weights in Mistral3ForConditionalGeneration and FlashAttention failure in Ministral-3 are different defects." + "reason": "Weight-tying bug in Mistral3 is not the same as a FlashAttention failure in Ministral-3." }, { "left": "issue:43295", "right": "issue:43825", "accept": false, - "reason": "Processor/tokenizer regression is unrelated to a pipeline error message about translation tasks." + "reason": "Processor.tokenizer regression and pipeline error-message wording are different changes." }, { "left": "issue:44162", "right": "issue:44792", "accept": false, - "reason": "ESM2 model breakage and Janus image-generation test failure are different model-specific issues." + "reason": "ESM2 breakage and janus test failure are separate model-specific issues." }, { "left": "issue:25251", "right": "issue:28282", "accept": false, - "reason": "Pipeline top_k output shape bug is unrelated to missing PyTorch ImportError." + "reason": "Pipeline top_k nesting bug is unrelated to missing PyTorch import error." }, { "left": "issue:41950", "right": "issue:43475", "accept": false, - "reason": "Video-classification pipeline using image processors is unrelated to missing fpn_position_embeddings in SAM3 video." + "reason": "Video-classification processor lookup and Sam3Video attribute error are different failures." }, { "left": "issue:43550", "right": "issue:43701", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to resume_from_checkpoint key mismatch." + "reason": "torch.compile/SDPA failure is unrelated to resume_from_checkpoint key mismatch." }, { "left": "issue:43606", "right": "issue:43701", "accept": false, - "reason": "CPU offload device mismatch is unrelated to resume_from_checkpoint key mismatch." + "reason": "CPU offload device mismatch is a different bug from checkpoint key mismatch." }, { "left": "issue:44871", "right": "issue:45584", "accept": false, - "reason": "Gemma EOS-token configuration mismatch and Whisper empty-transcription generation failure are distinct bugs." + "reason": "Gemma-3 eos_token_id inconsistency does not match Whisper empty-transcription generation failure." }, { "left": "issue:45127", "right": "issue:45200", "accept": false, - "reason": "LoRA merge collapse with tied embeddings is unrelated to mm_token_type_ids defaulting for Gemma 4." + "reason": "LoRA merge with extended vocabulary and mm_token_type_ids defaults are different model issues." }, { "left": "issue:43232", "right": "issue:43388", "accept": false, - "reason": "Generation kwargs update after sync_gpus is unrelated to gather_for_metrics dropping tuple labels." + "reason": "Generation kwarg syncing and metric-gathering label truncation are unrelated." }, { "left": "issue:43295", "right": "issue:44871", "accept": false, - "reason": "Processor/tokenizer access regression is not the same as EOS-token-id inconsistency." + "reason": "Custom processor/tokenizer regression is not the same as Gemma-3 eos_token_id inconsistency." }, { "left": "issue:43761", "right": "issue:44479", "accept": false, - "reason": "CLIPVisionModel hidden_states regression is unrelated to Qwen VL video-input regression." + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are separate paths." }, { "left": "issue:43065", "right": "issue:44617", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder is a model-architecture issue, not the same as Sam3Video CUDA OOM." + "reason": "Dummy Conv2d implementation choice is unrelated to a CUDA OOM." }, { "left": "issue:33290", "right": "issue:35141", "accept": false, - "reason": "Adafactor OOM in DeepSpeed is unrelated to embedding reinitialization in post_init." + "reason": "DeepSpeed optimizer memory issue is unrelated to embedding reinitialization after resize." }, { "left": "issue:33290", "right": "issue:36331", "accept": false, - "reason": "Optimizer memory issue is unrelated to CustomTrainer.compute_loss signature mismatch." + "reason": "OOM in DeepSpeed and CustomTrainer compute_loss kwarg incompatibility are different bugs." } ] }, @@ -9393,7 +9406,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:41720", "issue:42617", @@ -9456,11 +9469,11 @@ "issue:44077|issue:44534", "issue:44479|issue:44734", "issue:43065|issue:44610", - "issue:44617|issue:45584", "issue:43931|issue:44060", + "issue:44617|issue:45584", "issue:44792|issue:44977", - "issue:43827|issue:43994", "issue:43906|issue:45290", + "issue:43827|issue:43994", "issue:44190|issue:44964", "issue:44534|issue:44913", "issue:41720|issue:45245", @@ -9473,20 +9486,20 @@ "issue:43335|issue:44855", "issue:43550|issue:44190" ], - "prepared_review_unit_hash": "e5b2b8eb6806d3f2435f98bafeca7b915518e958cda92ae1e141a398b2d67a18", + "prepared_review_unit_hash": "8caca5ef79378596ce64f6cf6caebb643b203eb7e8df6a986fe74ef063f933e8", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 27, - "serialized_chars": 35908, + "serialized_chars": 35905, "estimated_input_tokens": 8977, "estimated_eval_tokens": 18210 }, @@ -9495,174 +9508,186 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This set is mostly a grab-bag of unrelated Transformers bug reports across model loading, generation, multimodal inputs, and config/serialization. None of the soft-similarity pairs look like the same concrete underlying bug, so they should stay separate.", - "confidence": 0.79, - "canonical_issue_reason": "issue:45698 is the best umbrella candidate: it describes a broad save_pretrained/from_pretrained round-trip failure with clear core-library impact, unlike the narrower model- or environment-specific reports.", + "summary": "This cluster is mostly a grab bag of unrelated Transformers bugs and regressions. None of the soft pairs look like the same underlying issue; they share broad themes at most, not the same code path or fix.", + "confidence": 0.78, + "canonical_issue_reason": "No strong duplicate canon emerges from the evidence. If one issue must anchor the cluster, issue 45698 is the broadest load/save regression and the most reusable representative of the few adjacent serialization reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45698 is the strongest single issue in the set because it targets a fundamental serialization/loading path and has broad reuse value for triage.", + "best_issue_reason": "Issue 45698 is the best global representative because it is the most general and actionable load/save bug in the set, and could plausibly subsume nearby save_pretrained/from_pretrained regressions.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:42617", "right": "issue:43575", "accept": false, - "reason": "Different failures: a script execution problem vs. tensor-parallel OOM on a specific Qwen model." + "reason": "Both involve model execution/loading problems, but one is a script/runtime failure and the other is Qwen2.5 TP OOM; different failure modes and fixes." }, { "left": "issue:43452", "right": "issue:44496", "accept": false, - "reason": "Both are load-time errors, but one is a gguf_file/AutoTokenizer path issue and the other is an unrecognized model/config.model_type issue." + "reason": "Both are loading errors, but gguf tokenizer/model handling is unrelated to a missing model_type in config.json." }, { "left": "issue:43575", "right": "issue:43742", "accept": false, - "reason": "Tensor-parallel OOM on a large model is unrelated to a key error while loading a small MobileLLM model." + "reason": "Different models and different bugs: TP memory exhaustion vs a KeyError while loading MobileLLM." }, { "left": "issue:43504", "right": "issue:45698", "accept": false, - "reason": "Legacy-field preset loading failure is a model-specific config bug, not the same as the custom-module resolution/round-trip issue." + "reason": "Both touch pretrained loading, but Beit legacy-field cleanup is not the same as wrong custom-module resolution after save/load." }, { "left": "issue:44871", "right": "issue:46050", "accept": false, - "reason": "One is an eos_token_id mismatch; the other is a quantized model save/load corruption. Same area, different bug." + "reason": "Both are serialization/config round-trip bugs, but eos_token_id mismatch is a different concrete defect than quantized-model save/load breakage." }, { "left": "issue:43646", "right": "issue:44913", "accept": false, - "reason": "Transformers 5 init breakage is different from GPTNeoX rotary_pct not persisting on reload." + "reason": "Both are config-related regressions, but custom model initialization in v5 is not the same issue as GPTNeoX rotary_pct resetting on reload." }, { "left": "issue:43673", "right": "issue:44743", "accept": false, - "reason": "Both mention cache, but one is a missing GenerationMixin cache in chunked_prefill and the other is recurrent state reset in modular qwen3_5 code." + "reason": "Cache-related, but these are different paths: missing GenerationMixin cache in chunked_prefill vs recurrent state reset in modular_qwen3_5." }, { "left": "issue:43761", "right": "issue:44242", "accept": false, - "reason": "CLIP hidden_states regression is unrelated to the load-balancing loss omission in MoE routing." + "reason": "Different subsystems and symptoms: CLIPVision hidden_states regression vs MoE load-balancing loss omission." }, { "left": "issue:44077", "right": "issue:44534", "accept": false, - "reason": "Optional post_init enforcement and non-persistent buffer junk are different v5 regressions with different code paths." + "reason": "Both are v5 regressions, but patchtsmixer post_init validation and non-persistent buffer corruption are unrelated bugs." }, { "left": "issue:44479", "right": "issue:44734", "accept": false, - "reason": "Video-input regression for several Qwen VL models is separate from a serve/KV-cache tensor indexing crash." + "reason": "One is a multimodal video-input regression, the other a server KV-cache continuation indexing bug; not the same code path." }, { "left": "issue:43065", "right": "issue:44610", "accept": false, - "reason": "Dummy Conv2d in Sam3PixelDecoder and OmDet-Turbo processor size mismatch are unrelated vision preprocessing/model-shape bugs." + "reason": "Different models and failures: dummy Conv2d in Sam3PixelDecoder vs processor/model input-size mismatch in OmDet-Turbo." }, { - "left": "issue:44617", - "right": "issue:45584", + "left": "issue:43931", + "right": "issue:44060", "accept": false, - "reason": "Sam3Video CUDA OOM and Whisper empty-transcription failure are different symptoms in different models." + "reason": "Same family name only; a shape mismatch while loading Qwen3-VL is not the same bug as a bad tied-weights warning in Qwen3-Next." }, { - "left": "issue:43931", - "right": "issue:44060", + "left": "issue:44617", + "right": "issue:45584", "accept": false, - "reason": "Qwen3-VL weight shape mismatch is not the same as a tied-weights warning involving Qwen3-Next dt_bias." + "reason": "CUDA OOM in Sam3Video and Whisper empty-transcription handling are unrelated." }, { "left": "issue:44792", "right": "issue:44977", "accept": false, - "reason": "Failed Janus image-generation test and Qwen3.5 flash-attention generation bug are unrelated model-specific issues." + "reason": "Both affect generation, but Janus image-generation test failure and Qwen3.5 flash-attention generation issue are different code paths." }, { - "left": "issue:43827", - "right": "issue:43994", + "left": "issue:43906", + "right": "issue:45290", "accept": false, - "reason": "Docs still referencing pipeline() is not the same as a SigLIP2 runtime inference quality problem." + "reason": "A reproduction of an old issue and a tool-call chat-template crash are not the same underlying bug." }, { - "left": "issue:43906", - "right": "issue:45290", + "left": "issue:43827", + "right": "issue:43994", "accept": false, - "reason": "An isolated reproduction of another external issue is not the same underlying bug as the chat-template tool-call crash." + "reason": "Docs still referencing pipeline() is separate from a runtime nonsensical-output bug in AutoModel/pipeline for SigLIP2." }, { "left": "issue:44190", "right": "issue:44964", "accept": false, - "reason": "Local dataset loading in a training script and loading a Phi-4 multimodal model are unrelated failures." + "reason": "Local dataset loading in a training script and loading Phi-4 multimodal are unrelated issues." }, { "left": "issue:44534", "right": "issue:44913", "accept": false, - "reason": "Buffer initialization junk and config reload drift are both persistence-related, but they affect different mechanisms and code paths." + "reason": "Non-persistent buffer corruption is a different regression than GPTNeoX rotary_pct not persisting on reload." }, { "left": "issue:41720", "right": "issue:45245", "accept": false, - "reason": "Qwen3 auto device mapping CUDA assert is unrelated to the 2^24 category-count runtime limit." + "reason": "Qwen3 auto device mapping assert and category-count overflow are unrelated." }, { "left": "issue:44855", "right": "issue:45588", "accept": false, - "reason": "Python 3.13 TorchScript parsing error is unrelated to flash_attention crashing on sink-less models." + "reason": "Python 3.13 decorator parsing failure and flash_attention s_aux=None are entirely different defects." }, { "left": "issue:44792", "right": "issue:45600", "accept": false, - "reason": "A Janus test failure is not the same bug as stale auto_mappings entries for removed Sam3LiteText configs." + "reason": "A test failure in Janus and stale auto_mappings entries for removed Sam3LiteText configs are not the same bug." }, { "left": "issue:44737", "right": "issue:45803", "accept": false, - "reason": "XLNet CPU device placement bug is unrelated to Fuyu's bare-except exception swallowing." + "reason": "XLNet CPU-device placement bug and bare except swallowing interrupts are unrelated." }, { "left": "issue:45127", "right": "issue:45357", "accept": false, - "reason": "LoRA/extended-vocab collapse after merge is different from incorrect visual encoder keys saved for Qwen3.5." + "reason": "LoRA merge collapse with extended vocabulary is different from Qwen3.5 saving incorrect visual encoder keys." }, { "left": "issue:44521", "right": "issue:45381", "accept": false, - "reason": "All-zero assistant masks and wrong vision_position_ids are both multimodal-template bugs, but they are different concrete defects." + "reason": "Both are multimodal-chat regressions, but all-zero assistant masks and wrong vision_position_ids are different implementation errors." }, { "left": "issue:44462", "right": "issue:45907", "accept": false, - "reason": "Tokenizer.json being ignored is not the same as list_repo_files failing to forward revision." + "reason": "Tokenizer file selection and list_repo_files revision forwarding are distinct API bugs." }, { "left": "issue:43335", "right": "issue:44855", "accept": false, - "reason": "SwitchTransformers sparse-layer construction and Python 3.13 indentation parsing are unrelated issues." + "reason": "A SwitchTransformers sparse-layer config bug is unrelated to the Python 3.13 IndentationError import failure." }, { "left": "issue:43550", "right": "issue:44190", "accept": false, - "reason": "torch.compile/SDPA failure in Bamba is unrelated to local dataset loading in an image-classification script." + "reason": "Bamba torch.compile/SDPA failure and a local dataset script issue do not share a concrete code path." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Same broad multimodal area, but assistant mask generation and video position-id computation are different bugs; not mergeable into one fix." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Different layers: tokenizer resolution vs Hub file listing revision propagation." } ] }, @@ -9684,7 +9709,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:35141", "issue:36246", @@ -9735,14 +9760,14 @@ "issue:45803" ], "soft_pairs": [ - "issue:44938|issue:45542", "issue:43976|issue:44855", + "issue:44938|issue:45542", "issue:43540|issue:44734", "issue:43644|issue:44913", "issue:44077|issue:44877", "issue:35141|issue:42490", - "issue:44112|issue:45600", "issue:43650|issue:44220", + "issue:44112|issue:45600", "issue:43335|issue:44190", "issue:44496|issue:45803", "issue:43116|issue:44190", @@ -9755,8 +9780,8 @@ "issue:44464|issue:45563", "issue:38175|issue:43065", "issue:44683|issue:45446", - "issue:44466|issue:44913", "issue:43404|issue:45216", + "issue:44466|issue:44913", "issue:44933|issue:45362", "issue:44734|issue:45632", "issue:44246|issue:45003", @@ -9766,20 +9791,20 @@ "issue:43643|issue:44496", "issue:42490|issue:45632" ], - "prepared_review_unit_hash": "23607c342c55e4a6db03f17bc1a6be004d44fc2591de8138dc0d9aa8aee7d074", + "prepared_review_unit_hash": "53a6e976ec4bf55070134cb8e8e751b6499f7d0e276945ef7fa4710205986a29", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36213, + "serialized_chars": 36214, "estimated_input_tokens": 9054, "estimated_eval_tokens": 18364 }, @@ -9788,192 +9813,192 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose semantic grouping of Transformers issues around imports, config loading, serialization, generation, and model-specific bugs. The soft pairs are thematically similar in places, but none look like the same underlying defect or change, so I would not merge any of them as duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "No true duplicate stands out in this heterogeneous cluster; if a representative must be chosen, issue 44466 is the strongest concrete regression to anchor on because it is a reproducible serialization/tied-weights bug with clear behavior differences and good discussion context.", + "summary": "This cluster is mostly a bag of unrelated Transformers issues. None of the soft pairs look like the same underlying bug/change closely enough to merge, so I would not accept any of them as duplicates.", + "confidence": 0.82, + "canonical_issue_reason": "issue:35141 is the clearest root-cause report in the set: it names the resize_token_embeddings / post_init / tie_word_embedding=False interaction explicitly and describes the failure mechanism well.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44466 is the best standalone issue in the set: it is specific, reproducible, and tied to a core model save/load path rather than a vague symptom or a one-off import failure.", + "best_issue_reason": "issue:35141 is the best representative issue overall because it is specific, actionable, and captures the underlying model-weight bug more precisely than the more symptom-level reports.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44938", - "right": "issue:45542", + "left": "issue:43976", + "right": "issue:44855", "accept": false, - "reason": "Both are runtime/loading problems, but one is Python 3.14 startup failure and the other is a tensorboard-without-TF backend issue; different root causes and fixes." + "reason": "Both are Python-version/import failures, but they affect different code paths and have different root causes." }, { - "left": "issue:43976", - "right": "issue:44855", + "left": "issue:44938", + "right": "issue:45542", "accept": false, - "reason": "These are separate Python-version compatibility bugs: one about Transformers 5.1.0 support on 3.9/3.10, the other about a PyTorch script parse error on 3.13." + "reason": "One is a Python 3.14 import/load issue; the other is a TensorFlow backend detection problem. Not the same bug." }, { "left": "issue:43540", "right": "issue:44734", "accept": false, - "reason": "Both involve multimodal/video-serving code paths, but one is a Qwen3OmniMoe video-input validation error and the other is a KV-cache continuation indexing crash in serve responses." + "reason": "Different subsystems and failures: Qwen3OmniMoe video processing vs serve KV-cache continuation indexing." }, { "left": "issue:43644", "right": "issue:44913", "accept": false, - "reason": "Both touch serialization/reload behavior, but one is about non-persistent buffers being junk-filled and the other is a config field reverting on reload; not the same bug." + "reason": "One is about non-persistent buffers being serialized junk in v5; the other is GPTNeoX config reload losing rotary_pct." }, { "left": "issue:44077", "right": "issue:44877", "accept": false, - "reason": "These are both config-related, but one concerns optional post_init handling in patchtsmixer and the other is strict config rejection for granite_speech; different code paths." + "reason": "Both touch config handling, but one is about optional post_init in patchtsmixer and the other about strict granite_speech config loading." }, { "left": "issue:35141", "right": "issue:42490", "accept": false, - "reason": "One is about resizing token embeddings reinitializing the output embedding, the other about local-path slash handling during model loading; unrelated bugs." + "reason": "Resize-token-embedding / weight-tie bug is unrelated to the trailing-slash local-path import warning." }, { - "left": "issue:44112", - "right": "issue:45600", + "left": "issue:43650", + "right": "issue:44220", "accept": false, - "reason": "Both mention CI failures, but they are different breakages in different areas: GraniteSpeech device override vs removed Sam3LiteText auto-mapping entries." + "reason": "No shared bug: generic placeholder issue vs a specific fbank feature extraction failure." }, { - "left": "issue:43650", - "right": "issue:44220", + "left": "issue:44112", + "right": "issue:45600", "accept": false, - "reason": "No concrete overlap: one is a vague request to add data, the other is a specific fbank feature extraction issue." + "reason": "Both are CI-related, but they are different regressions in different Granite/Sam3 code paths." }, { "left": "issue:43335", "right": "issue:44190", "accept": false, - "reason": "A SwitchTransformers config construction bug and a local-dataset loading failure in an example script are unrelated." + "reason": "Completely different topics: SwitchTransformers config construction vs image-classification local dataset loading." }, { "left": "issue:44496", "right": "issue:45803", "accept": false, - "reason": "One is an unrecognized-model/config.json problem, the other is a bare-except bug in Fuyu tensor conversion; different failure modes." + "reason": "One is an unrecognized custom model/config issue; the other is a bare-except bug in Fuyu tensor conversion." }, { "left": "issue:43116", "right": "issue:44190", "accept": false, - "reason": "Both are example-script failures, but one is multi-label classification output logic and the other is dataset loading; not the same underlying issue." + "reason": "Different example scripts and different failures; no concrete shared code-path." }, { "left": "issue:45276", "right": "issue:45584", "accept": false, - "reason": "Gemma4 resize-token-embeddings behavior and Whisper empty-transcription generation after token alignment are unrelated model-specific bugs." + "reason": "Resize-token-embeddings/output-embeddings bug is unrelated to Whisper empty-transcription handling." }, { "left": "issue:45245", "right": "issue:45584", "accept": false, - "reason": "A category-cardinality runtime limit and a Whisper generation edge case have no meaningful bug-level overlap." + "reason": "Category-limit runtime error is unrelated to Whisper generation after align_special_tokens." }, { "left": "issue:43479", "right": "issue:45375", "accept": false, - "reason": "Both are config-field handling issues, but one is default multimodal sub-config initialization and the other is strict dropping of a specific deepstack field." + "reason": "Different config bugs in different models; one is default-init-on-None, the other is strict field dropping." }, { "left": "issue:36246", "right": "issue:41628", "accept": false, - "reason": "Both are import errors, but they concern different missing symbols in different modules; they are not the same API break." + "reason": "Both are ImportErrors, but for different exported symbols and likely different packaging issues." }, { "left": "issue:43295", "right": "issue:45276", "accept": false, - "reason": "A regression in processor/tokenizer custom-model behavior is distinct from Gemma4 embedding resizing/output-embedding behavior." + "reason": "Custom processor/tokenizer regression is not the same as the resize_token_embeddings/output_embeddings bug." }, { "left": "issue:44186", "right": "issue:44734", "accept": false, - "reason": "Different bug classes: tokenizer crashes on NER padding/truncation versus a server-side KV-cache continuation indexing error." + "reason": "Tokenizer padding/NER crash is unrelated to serve KV-cache continuation indexing." }, { "left": "issue:44464", "right": "issue:45563", "accept": false, - "reason": "Chunked generation inconsistencies with compiled forward and a stale num_return_sequences warning are not the same bug." + "reason": "Compiled-forward chunked generation mismatch is different from a stale warning in paged generate." }, { "left": "issue:38175", "right": "issue:43065", "accept": false, - "reason": "These affect different models and subsystems: SigLIP2 zero probabilities versus a dummy Conv2d in Sam3PixelDecoder." + "reason": "Different model-specific bugs with no shared failing mechanism." }, { "left": "issue:44683", "right": "issue:45446", "accept": false, - "reason": "Both are flex_attention-related, but one is a torch>=2.9 compilation failure and the other is an incorrect version check for AuxRequest import; distinct fixes." + "reason": "One is a runtime failure in compiled flex_attention; the other is a version-check/import guard issue. Not the same concrete bug." }, { - "left": "issue:44466", - "right": "issue:44913", + "left": "issue:43404", + "right": "issue:45216", "accept": false, - "reason": "Both involve save/reload semantics, but one is device-dependent lm_head serialization and the other is a config scalar not persisting; different root causes." + "reason": "Both mention weights, but one is a missing tie in Mistral3 and the other is incorrect save_pretrained serialization in Qwen3.5." }, { - "left": "issue:43404", - "right": "issue:45216", + "left": "issue:44466", + "right": "issue:44913", "accept": false, - "reason": "Mistral3 lm_head tying and Qwen3.5 save_pretrained regression are both weight-related, but they are separate model families and failure modes." + "reason": "Inconsistent lm_head serialization is unrelated to GPTNeoX rotary_pct reload behavior." }, { "left": "issue:44933", "right": "issue:45362", "accept": false, - "reason": "A missing image_utils import and a Qwen3.5-35B chat crash are unrelated issues." + "reason": "Missing image_utils import and Qwen3.5 chat crash are different issues." }, { "left": "issue:44734", "right": "issue:45632", "accept": false, - "reason": "One is a KV-cache continuation crash in serve responses; the other is a trust_remote_code cache-path collision. Same broad area, different bug." + "reason": "Serve tensor indexing crash and trust_remote_code cache-path collision are unrelated pathologies." }, { "left": "issue:44246", "right": "issue:45003", "accept": false, - "reason": "Import slowness and unsafe sys.modules access are not the same defect, even if both involve startup/import paths." + "reason": "Import slowness and unsafe sys.modules access are related only loosely; not the same bug." }, { "left": "issue:44561", "right": "issue:45632", "accept": false, - "reason": "One breaks trust_remote_code models because of a removed utility, the other is a cache-path collision for local models; unrelated causes." + "reason": "Removal of is_torch_fx_available affecting trust_remote_code is a different failure from local-model cache-path collisions." }, { "left": "issue:36246", "right": "issue:38617", "accept": false, - "reason": "Both are import failures, but one is a missing Qwen2.5 VL image processor export and the other is a missing configuration utility; different symbols and fixes." + "reason": "Different missing imports in different modules; no evidence of a shared root cause." }, { "left": "issue:45563", "right": "issue:45584", "accept": false, - "reason": "A stale warning in paged generate and a Whisper empty-transcription crash are different generation issues." + "reason": "A stale warning in paged generate is not the same as Whisper failing on empty transcription." }, { "left": "issue:43643", "right": "issue:44496", "accept": false, - "reason": "One is missing fields when trust_remote_code returns AutoConfig, the other is an unrecognized model/config.json error; not the same configuration bug." + "reason": "Missing fields from trust_remote_code AutoConfig and unrecognized model_type are different config-loading bugs." }, { "left": "issue:42490", "right": "issue:45632", "accept": false, - "reason": "Both concern loading local models, but one is a spurious warning for trailing slashes and the other is a cache-path collision between same-named leaf directories." + "reason": "Trailing-slash path handling and leaf-directory cache collisions are distinct path-resolution bugs." } ] }, @@ -9995,7 +10020,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:41950", "issue:42175", @@ -10027,7 +10052,6 @@ "issue:44351", "issue:44368", "issue:44496", - "issue:44683", "issue:44779", "issue:44933", "issue:44964", @@ -10039,17 +10063,17 @@ "issue:45335", "issue:45357", "issue:45405", - "issue:45542", "issue:45584", "issue:45593", "issue:45600", "issue:45759", - "issue:45812" + "issue:45812", + "issue:45823" ], "soft_pairs": [ "issue:41950|issue:44016", - "issue:44964|issue:45600", "issue:44112|issue:44964", + "issue:44964|issue:45600", "issue:42907|issue:43441", "issue:43854|issue:44964", "issue:43673|issue:44336", @@ -10072,220 +10096,220 @@ "issue:41950|issue:45020", "issue:44242|issue:45200", "issue:44351|issue:45278", - "issue:43479|issue:43525", "issue:44016|issue:44062", + "issue:43479|issue:43525", "issue:43824|issue:44933", "issue:44779|issue:45812", - "issue:44683|issue:45542" + "issue:41950|issue:45823" ], - "prepared_review_unit_hash": "9c442d659e36262bdc736328c95c60ec57cb676a8c200608aaff43095e7289a1", + "prepared_review_unit_hash": "08d833fd61695c844ed4b96bd05fcc8211861b63ef1069dcdf1faa1668ea0e69", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 48, - "item_count": 48, + "node_count": 47, + "item_count": 47, "soft_pair_count": 30, - "serialized_chars": 36647, - "estimated_input_tokens": 9162, - "estimated_eval_tokens": 18580 + "serialized_chars": 36080, + "estimated_input_tokens": 9020, + "estimated_eval_tokens": 18296 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a grab bag of recent Transformers regression reports, especially model-loading/import/tokenizer breakages across v5-era releases. The broadest representative issue is the umbrella regression report about recent versions breaking models that rely on remote code.", - "confidence": 0.77, - "canonical_issue_reason": "issue:45020 is the most umbrella-like report: it describes a broad class of regressions in recent Transformers versions, spans multiple affected models/code paths, and best represents the overall cluster of v5-era breakages.", + "summary": "The set is a grab bag of distinct Transformers regressions and docs/test issues; there isn\u2019t a convincing duplicate pair among the soft edges. The clearest cluster anchor is the broad v5 remote-code/model-loading regression report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45020 is the broadest, most central report: it describes a recent-version regression breaking remote_code models, which plausibly covers several narrower load/import failures in this set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45020 is the strongest global representative because it captures the widest regression surface and is more central than the model-specific or single-API issues.", + "best_issue_reason": "issue:45020 is the strongest standalone triage target: broad impact, detailed reproduction, and a clear regression framing that makes it useful as the umbrella issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41950", "right": "issue:44016", "accept": false, - "reason": "Different bugs: pipeline processor lookup vs a notebook syntax error." + "reason": "Video-classification processor selection bug vs a notebook syntax error; unrelated symptoms and code paths." }, { - "left": "issue:44964", - "right": "issue:45600", + "left": "issue:44112", + "right": "issue:44964", "accept": false, - "reason": "Different model families and failures: Phi-4 multimodal load issue vs stale auto_mappings references breaking CI." + "reason": "CI stale device override test in GraniteSpeech vs Phi-4 multimodal model loading; different failures." }, { - "left": "issue:44112", - "right": "issue:44964", + "left": "issue:44964", + "right": "issue:45600", "accept": false, - "reason": "CI test flake in GraniteSpeech device override is unrelated to Phi-4 multimodal loading." + "reason": "Model loading failure for Phi-4 multimodal vs auto-mappings referencing removed Sam3LiteText configs; distinct breakages." }, { "left": "issue:42907", "right": "issue:43441", "accept": false, - "reason": "Both mention Ministral, but one is save/dequantization and the other is FlashAttention loading; not the same underlying bug." + "reason": "Dequantized save failure for Ministral/Devstral vs FlashAttention load failure for Ministral-3; different bug surfaces." }, { "left": "issue:43854", "right": "issue:44964", "accept": false, - "reason": "Different models and code paths: GLM-4.7-Flash unit-test load issue vs Phi-4 multimodal load issue." + "reason": "GLM-4.7-Flash unit-test load issue vs Phi-4 multimodal load issue; not the same model/path." }, { "left": "issue:43673", "right": "issue:44336", "accept": false, - "reason": "Generation cache regression is unrelated to ANSI escape generation in loading_report." + "reason": "Generation cache missing in chunked prefill vs ANSI escape codes in loading_report; unrelated subsystems." }, { "left": "issue:44016", "right": "issue:44220", "accept": false, - "reason": "Notebook syntax error and audio feature extraction bug are unrelated." + "reason": "Notebook syntax error vs audio feature extraction bug; different code paths and symptoms." }, { "left": "issue:43388", "right": "issue:43688", "accept": false, - "reason": "Metric label truncation and auxiliary-loss normalization are different training/evaluation bugs." + "reason": "Metrics label handling vs MoE auxiliary loss normalization; both training-related but not the same defect." }, { "left": "issue:43295", "right": "issue:45335", "accept": false, - "reason": "Processor/tokenizer API regression is unrelated to resize_token_embeddings not updating decoder embeddings." + "reason": "Processor.tokenizer / image-input regression vs t5gemma embedding resize behavior; separate model-family bugs." }, { "left": "issue:43531", "right": "issue:45600", "accept": false, - "reason": "Qwen3-MoE sliding-window behavior and Sam3LiteText auto_mappings cleanup are different issues." + "reason": "Qwen3-MoE sliding_window issue vs removed-config references in auto_mappings; unrelated." }, { "left": "issue:42175", "right": "issue:44279", "accept": false, - "reason": "Package dependency/backend install problem is too broad and not the same as a generic transformers dependency issue." + "reason": "Torch extra omits TensorFlow backend dependency vs generic dependency issue; not the same concrete package problem." }, { "left": "issue:43526", "right": "issue:43901", "accept": false, - "reason": "BeitImageProcessorFast label reduction bug is unrelated to old docs still mentioning return_all_scores." + "reason": "BeitImageProcessorFast reduce_labels bug vs docs mentioning return_all_scores; different layers and outcomes." }, { "left": "issue:44496", "right": "issue:45042", "accept": false, - "reason": "Model config resolution failure and PIL backend torchvision requirement are different regressions." + "reason": "Unrecognized model/config loading error vs PIL image processors requiring torchvision; distinct import/load failures." }, { "left": "issue:43299", "right": "issue:45216", "accept": false, - "reason": "Qwen3VL/MoE model loading failure is not the same as incorrect Qwen3.5 checkpoint saving." + "reason": "Qwen3 VL MoE model loading breakage vs incorrect save_pretrained checkpoint contents; load-time vs save-time bug." }, { "left": "issue:43335", "right": "issue:45593", "accept": false, - "reason": "SwitchTransformers sparse-layer config bug is unrelated to D-FINE auxiliary-loss handling." + "reason": "SwitchTransformersConfig sparse-layer creation bug vs D-FINE auxiliary-loss omission; unrelated model implementations." }, { "left": "issue:44075", "right": "issue:44368", "accept": false, - "reason": "Unused SGD args and a tie_word_embeddings warning are not the same code-path bug." + "reason": "SGD optimizer args ignored vs Qwen3.5 tie_word_embeddings warning; different functionality." }, { "left": "issue:45335", "right": "issue:45584", "accept": false, - "reason": "Embedding resize propagation and Whisper empty-transcription generation are unrelated." + "reason": "Embedding resize propagation bug vs Whisper empty-transcription generation failure; separate behaviors." }, { "left": "issue:43381", "right": "issue:45593", "accept": false, - "reason": "Eval-mode gradient checkpointing and D-FINE denoising-loss behavior are different issues." + "reason": "Gradient checkpointing eval-mode incompatibility vs D-FINE loss handling; not the same issue." }, { "left": "issue:43299", "right": "issue:45357", "accept": false, - "reason": "Both concern Qwen3.5, but one is model loading and the other is save_pretrained key serialization; not mergeable as one fix." + "reason": "Qwen3.5/3.6 loading failure vs incorrect visual encoder keys on save; related model family but different concrete bugs." }, { "left": "issue:43901", "right": "issue:44496", "accept": false, - "reason": "Documentation wording issue is unrelated to model config import failure." + "reason": "Docs/API mismatch for return_all_scores vs unrecognized model config loading; unrelated." }, { "left": "issue:44496", "right": "issue:45759", "accept": false, - "reason": "Unrecognized model/config issue is different from AutoModelForCausalLM not unwrapping text_config." + "reason": "Unrecognized model/config loading error vs from_config not unwrapping text_config; different composite-model path." }, { "left": "issue:43976", "right": "issue:45405", "accept": false, - "reason": "Python-version compatibility and a PEFT minimum-version bump are not the same underlying bug." + "reason": "Python-version compatibility break vs bumped MIN_PEFT_VERSION; one is runtime support, the other a dependency floor." }, { "left": "issue:41950", "right": "issue:45020", "accept": false, - "reason": "Both are broad regressions, but one is a specific video-classification processor lookup while the other is a general remote_code compatibility break." + "reason": "Video pipeline processor lookup bug vs broad remote_code/model-loading regression; not the same underlying defect." }, { "left": "issue:44242", "right": "issue:45200", "accept": false, - "reason": "Router-logit loss computation and Gemma 4 mm_token_type_ids defaults are different model-training bugs." + "reason": "Router-logits load-balancing loss bug vs Gemma 4 mm_token_type_ids defaulting; distinct training/runtime logic." }, { "left": "issue:44351", "right": "issue:45278", "accept": false, - "reason": "A specific HybridCache import error could be one symptom of broader import breakage, but the reports are not clearly the same underlying defect." + "reason": "Missing HybridCache export vs broad import errors after upgrade; the latter is an umbrella symptom, not the same concrete bug." }, { - "left": "issue:43479", - "right": "issue:43525", + "left": "issue:44016", + "right": "issue:44062", "accept": false, - "reason": "Phi4Multimodal default config initialization and Llama4 pad_token_id attribute error are unrelated." + "reason": "Notebook syntax error vs AddedToken keyword-argument TypeError; unrelated parsing/runtime issues." }, { - "left": "issue:44016", - "right": "issue:44062", + "left": "issue:43479", + "right": "issue:43525", "accept": false, - "reason": "Notebook syntax error is unrelated to AddedToken receiving duplicate special kwargs." + "reason": "Phi4Multimodal default config initialization vs Llama4Config missing pad_token_id attribute; different config bugs." }, { "left": "issue:43824", "right": "issue:44933", "accept": false, - "reason": "Missing Qwen2_5_VL export and a nonexistent image_utils import are different import/export problems." + "reason": "Missing Qwen2_5_VLForConditionalGeneration export vs missing image_utils import; both import errors but different symbols and causes." }, { "left": "issue:44779", "right": "issue:45812", "accept": false, - "reason": "Tokenizer regressions for Deepseek and Granite are model-specific and not the same code-path change." + "reason": "Deepseek tokenizer regression vs Granite AutoTokenizer wrong IDs; tokenizer bugs, but model-specific and not the same change." }, { - "left": "issue:44683", - "right": "issue:45542", + "left": "issue:41950", + "right": "issue:45823", "accept": false, - "reason": "Compiled flex_attention on torch>=2.9 is unrelated to an undefined tf backend from tensorboard-only installs." + "reason": "Video pipeline processor lookup vs Gemma4 PLE device mismatch during forward; different model families and failure modes." } ] }, @@ -10307,7 +10331,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:32090", "issue:35141", @@ -10328,7 +10352,6 @@ "issue:43854", "issue:43901", "issue:43976", - "issue:44016", "issue:44162", "issue:44261", "issue:44263", @@ -10351,24 +10374,24 @@ "issue:45325", "issue:45397", "issue:45405", + "issue:45542", "issue:45593", "issue:45600", "issue:45712", - "issue:45823", "issue:45834", "issue:45907" ], "soft_pairs": [ - "issue:41950|issue:45823", + "issue:44683|issue:45542", "issue:43577|issue:45216", "issue:38175|issue:44617", "issue:43299|issue:43854", "issue:39692|issue:43901", - "issue:44279|issue:45405", "issue:32090|issue:35141", + "issue:44279|issue:45405", "issue:41950|issue:43650", - "issue:43295|issue:44779", "issue:44462|issue:45081", + "issue:43295|issue:44779", "issue:43976|issue:44987", "issue:44297|issue:44462", "issue:43976|issue:44279", @@ -10379,218 +10402,211 @@ "issue:43450|issue:44279", "issue:43065|issue:44898", "issue:42994|issue:43317", - "issue:44261|issue:44263", "issue:44623|issue:45397", - "issue:44466|issue:45276", + "issue:44261|issue:44263", "issue:44623|issue:44749", + "issue:44466|issue:45276", "issue:43650|issue:45290", "issue:43441|issue:44683", "issue:43653|issue:45593", - "issue:43723|issue:44162", - "issue:44016|issue:45823" + "issue:43723|issue:44162" ], - "prepared_review_unit_hash": "9f7f2dba7625c4ad5d997712422f106ae4287bf8d0f3c6ec29f4c6975ce087db", + "prepared_review_unit_hash": "6d13fd6ed1247d14279fab11f45e9d9969c50d83ba846cd87e4c56b0570dfb17", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 29, - "serialized_chars": 36413, - "estimated_input_tokens": 9104, - "estimated_eval_tokens": 18464 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35546, + "estimated_input_tokens": 8887, + "estimated_eval_tokens": 18030 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The cluster is heterogeneous: most items are unrelated Transformer regressions across tokenizers, multimodal processors, model loading, serialization, and docs. None of the soft pairs look like true duplicates of the same underlying bug/change.", - "confidence": 0.95, - "canonical_issue_reason": "No true canonical issue stands out because the items are not one duplicate cluster; they are separate bugs spanning different code paths and model families.", + "summary": "This cluster is a loose collection of mostly unrelated transformer regressions and docs issues. The soft pairs are superficially similar in a few tokenizer/model-loading areas, but they do not look like the same underlying bug or change, so none should be merged as duplicates.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 43723 is the broadest, most representative tokenizer-loading regression in the set; it best captures the shared v5 AutoTokenizer breakage theme without being overly narrow to one model or edge case.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44462 is the closest representative of the tokenizer-loading regression subset, but it still does not cover the other issues in the set.", + "best_issue_reason": "Issue 43723 is the best global representative because it is self-contained, user-facing, and closest to the common loading/compatibility failures that recur across the tokenizer-related items.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:41950", - "right": "issue:45823", + "left": "issue:44683", + "right": "issue:45542", "accept": false, - "reason": "Different problems: video-classification processor lookup vs Gemma4 PLE device mismatch during forward." + "reason": "Completely different failures: flex_attention compilation vs missing TensorFlow backend with tensorboard." }, { "left": "issue:43577", "right": "issue:45216", "accept": false, - "reason": "Both involve model state/weights, but one is BLIP2 dtype handling and the other is Qwen3.5 checkpoint serialization; not the same bug." + "reason": "Different models and bugs: BLIP2 dtype propagation vs Qwen3.5 save_pretrained checkpoint serialization." }, { "left": "issue:38175", "right": "issue:44617", "accept": false, - "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to Sam3Video CUDA OOM." + "reason": "Unrelated problems: SIGLIP2 zero probabilities vs Sam3Video CUDA OOM." }, { "left": "issue:43299", "right": "issue:43854", "accept": false, - "reason": "Both are v5 loading regressions, but they affect different models and failure modes." + "reason": "Both are load failures, but for different model families and different root causes; not the same bug." }, { "left": "issue:39692", "right": "issue:43901", "accept": false, - "reason": "SigLIP2 docs/model mismatch and TextClassificationPipeline docs drift are separate documentation issues." + "reason": "Both mention docs, but one is a multimodal SigLIP2 example with runtime errors while the other is a TextClassificationPipeline doc mismatch." }, { - "left": "issue:44279", - "right": "issue:45405", + "left": "issue:32090", + "right": "issue:35141", "accept": false, - "reason": "Generic dependency issue vs a specific PEFT version bump; not the same underlying failure." + "reason": "Trainer GPU broadcast NoneType error is unrelated to resize_token_embeddings reinitializing output embeddings." }, { - "left": "issue:32090", - "right": "issue:35141", + "left": "issue:44279", + "right": "issue:45405", "accept": false, - "reason": "Trainer GPU broadcast TypeError and output embedding reinitialization are unrelated training/model-init bugs." + "reason": "A generic dependency problem is not the same as bumping MIN_PEFT_VERSION to an unreleased version." }, { "left": "issue:41950", "right": "issue:43650", "accept": false, - "reason": "Video pipeline processor lookup is unrelated to an empty placeholder issue." + "reason": "Video pipeline processor lookup and a generic placeholder issue title are unrelated." }, { - "left": "issue:43295", - "right": "issue:44779", + "left": "issue:44462", + "right": "issue:45081", "accept": false, - "reason": "One is processor.tokenizer/custom model regression, the other is DeepSeek tokenizer output corruption." + "reason": "Both involve tokenizers, but one is AutoTokenizer ignoring tokenizer.json while the other is a Mistral regex patch crash; different code paths and failures." }, { - "left": "issue:44462", - "right": "issue:45081", + "left": "issue:43295", + "right": "issue:44779", "accept": false, - "reason": "AutoTokenizer ignoring tokenizer.json and Mistral regex patch crashing are distinct tokenizer-loading bugs." + "reason": "Custom model code accessing processor.tokenizer and Deepseek tokenizer regressions are distinct issues." }, { "left": "issue:43976", "right": "issue:44987", "accept": false, - "reason": "Python version compatibility and loading a specific model are different issues." + "reason": "Python version compatibility and a specific model loading failure are not the same problem." }, { "left": "issue:44297", "right": "issue:44462", "accept": false, - "reason": "Tokenizer_class mismatch on save_pretrained is a save bug, while AutoTokenizer ignoring tokenizer.json is a load bug." + "reason": "Serialization mismatch in tokenizer_config.json is related to, but not the same as, ignoring tokenizer.json from the repo." }, { "left": "issue:43976", "right": "issue:44279", "accept": false, - "reason": "Python compatibility issue does not match a generic dependency problem." + "reason": "Python support regression and dependency/version bump are unrelated." }, { "left": "issue:45081", "right": "issue:45907", "accept": false, - "reason": "Mistral tokenizer regex patch crash is unrelated to list_repo_files not forwarding revision." + "reason": "Tokenizer regex crash and list_repo_files not forwarding revision are unrelated APIs." }, { "left": "issue:44521", "right": "issue:45325", "accept": false, - "reason": "All-zero assistant masks in chat templating and Qwen2.5-VL rope indexing are different multimodal bugs." + "reason": "Both are multimodal, but assistant masks in chat templating and rope index scaling are different bugs." }, { "left": "issue:43441", "right": "issue:45834", "accept": false, - "reason": "FlashAttention failure for Ministral-3 and Kosmos2.5 OCR index error are unrelated model-specific issues." + "reason": "Ministral FlashAttention failure and Kosmos2.5 OCR index error are unrelated." }, { "left": "issue:45600", "right": "issue:45712", "accept": false, - "reason": "auto_mappings.py stale config references and dummy_pt_objects leftovers are separate CI hygiene problems." + "reason": "Removed auto_mappings references and leftover dummy classes are separate CI hygiene problems." }, { "left": "issue:43450", "right": "issue:44279", "accept": false, - "reason": "Video processor batch shape bug is not a dependency issue." + "reason": "Batched video processor shape bug and a dependency issue are unrelated." }, { "left": "issue:43065", "right": "issue:44898", "accept": false, - "reason": "Sam3PixelDecoder dummy Conv2d and Perceiver non-default resolution failure are different model implementations." + "reason": "Dummy Conv2d in Sam3PixelDecoder and Perceiver interpolation failure are different model-specific issues." }, { "left": "issue:42994", "right": "issue:43317", "accept": false, - "reason": "Quantized model saving failure and device_map dequantized offload loading are different quantization paths." + "reason": "Quantized model saving failure and dequantized model offload loading failure are different quantization paths." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing processor save files and gemma-4 zero3 from_pretrained are unrelated." }, { "left": "issue:44261", "right": "issue:44263", "accept": false, - "reason": "Missing rms_norm_eps in MLA q_a_layernorm and torch.split return values in GlmMoeDsaIndexer are separate GLM-MoE bugs." + "reason": "A missing rms_norm_eps precision issue and a torch.split return-value issue are unrelated." }, { "left": "issue:44623", - "right": "issue:45397", + "right": "issue:44749", "accept": false, - "reason": "processor.save_pretrained missing files and Gemma-4 zero3 from_pretrained are not the same failure." + "reason": "Processor save_pretrained file omission and a large slowdown after upgrade are different symptoms and causes." }, { "left": "issue:44466", "right": "issue:45276", "accept": false, - "reason": "lm_head serialization inconsistency and Gemma4 resize_token_embeddings not updating outputs are different weight/resize behaviors." - }, - { - "left": "issue:44623", - "right": "issue:44749", - "accept": false, - "reason": "Missing files on processor save and slower filtering after version upgrade are unrelated." + "reason": "Serialization of lm_head.weight by device and resize_token_embeddings not updating gemma4 embeddings are related only broadly, not the same bug." }, { "left": "issue:43650", "right": "issue:45290", "accept": false, - "reason": "A placeholder issue and chat template crashes with tool-call messages are not duplicates." + "reason": "Generic placeholder issue and chat-template crash on tool-call assistant messages are unrelated." }, { "left": "issue:43441", "right": "issue:44683", "accept": false, - "reason": "FlashAttention failure for a model and compiled flex_attention failing on torch>=2.9 are different attention backends." + "reason": "FlashAttention failure in one model and compiled flex_attention failure on newer torch are different attention bugs." }, { "left": "issue:43653", "right": "issue:45593", "accept": false, - "reason": "BigBirdTokenizer special-token registration bug is unrelated to D-FINE auxiliary-loss logic." + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." }, { "left": "issue:43723", "right": "issue:44162", "accept": false, - "reason": "AutoTokenizer.from_pretrained loading regression and ESM2 model breakage are not the same issue." - }, - { - "left": "issue:44016", - "right": "issue:45823", - "accept": false, - "reason": "Notebook syntax error and Gemma4 device mismatch are unrelated." + "reason": "Tokenizer loading regression and ESM2 breakage are not the same underlying issue." } ] }, @@ -10612,7 +10628,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:16998", "issue:22355", @@ -10632,7 +10648,6 @@ "issue:43673", "issue:43761", "issue:43784", - "issue:43824", "issue:43881", "issue:43901", "issue:43976", @@ -10661,15 +10676,17 @@ "issue:45362", "issue:45397", "issue:45542", - "issue:45593" + "issue:45593", + "issue:45823" ], "soft_pairs": [ + "issue:44016|issue:45823", "issue:44361|issue:45593", "issue:44671|issue:44779", "issue:44987|issue:45542", "issue:43901|issue:43994", - "issue:43784|issue:45542", "issue:43122|issue:43650", + "issue:43784|issue:45542", "issue:44297|issue:45397", "issue:44016|issue:44291", "issue:44188|issue:44336", @@ -10678,212 +10695,223 @@ "issue:43450|issue:44617", "issue:43525|issue:43881", "issue:43525|issue:43643", - "issue:44589|issue:45362", - "issue:41628|issue:43976", "issue:44336|issue:44373", + "issue:41628|issue:43976", + "issue:44589|issue:45362", "issue:43901|issue:44246", - "issue:42491|issue:43299", "issue:44295|issue:45397", + "issue:42491|issue:43299", "issue:44242|issue:45593", "issue:16998|issue:22355", "issue:44246|issue:44496", "issue:41950|issue:44220", "issue:44336|issue:44485", - "issue:43352|issue:45250", "issue:36246|issue:42757", - "issue:36246|issue:44351", - "issue:43824|issue:43976" + "issue:43352|issue:45250", + "issue:36246|issue:44351" ], - "prepared_review_unit_hash": "fd4af739c2c58496ba3e19dff2807095988ab67356f97319d9d05bc5aad4058d", + "prepared_review_unit_hash": "1ab7d779159f3a79aa66d1ef163ae0fdcbd40066a3156ef62ffd11ce82cae804", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 29, - "serialized_chars": 36030, - "estimated_input_tokens": 9008, - "estimated_eval_tokens": 18272 + "serialized_chars": 36013, + "estimated_input_tokens": 9004, + "estimated_eval_tokens": 18264 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This is a loose topical bundle of unrelated Transformers issues (import/export regressions, model-loading failures, pipeline behavior, tokenizer changes, docs). I do not see any soft pair that looks like the same underlying bug/change, so I rejected all soft edges. If a representative issue is needed, the Qwen2.5-VL import/export regression is the best anchor, but it is not a duplicate of the others.", - "confidence": 0.27, - "canonical_issue_reason": "Issue 43824 is the clearest, highest-signal representative of the cluster: a concrete import/export regression with multiple inbound references, and it matches the broad import/loading theme better than the rest.", + "summary": "These items are a heterogeneous mix of unrelated Transformers bugs, regressions, and docs issues; none of the soft pairs look like the same underlying fix target.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue emerges here: the reports span different models, APIs, and failure modes rather than one duplicate bug.", "canonical_pr_reason": null, - "best_issue_reason": "43824 is the best single issue to anchor this set, but only as a representative import-regression example, not as a true duplicate target for the other issues.", + "best_issue_reason": "Issue 44521 is the best standalone anchor if one must be chosen: it is open, detailed, reproducible, and clearly scoped.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 device-mapping mismatch are unrelated problems." + }, { "left": "issue:44361", "right": "issue:45593", "accept": false, - "reason": "Unrelated failures: tokenizer/task AttributeError vs D-FINE auxiliary-loss behavior." + "reason": "Different components and symptoms: tokenizer AttributeError vs D-FINE auxiliary-loss handling." }, { "left": "issue:44671", "right": "issue:44779", "accept": false, - "reason": "Both are v5 regressions, but they affect different models/code paths; not the same bug." + "reason": "Both are model/tokenizer regressions, but they affect different models and code paths." }, { "left": "issue:44987", "right": "issue:45542", "accept": false, - "reason": "Model-loading failure vs missing TensorFlow backend handling; different problems." + "reason": "Loading a physical-intelligence model and TensorFlow backend detection are unrelated." }, { "left": "issue:43901", "right": "issue:43994", "accept": false, - "reason": "Docs mismatch for a pipeline argument vs incorrect model/pipeline outputs; not the same issue." + "reason": "Docs mismatch for return_all_scores is not the same bug as incorrect SigLIP2 outputs." }, { - "left": "issue:43784", - "right": "issue:45542", + "left": "issue:43122", + "right": "issue:43650", "accept": false, - "reason": "Sentence-transformers import NameError vs TensorFlow backend import issue; unrelated." + "reason": "Tokenizer behavior regression and the unrelated placeholder issue title do not match." }, { - "left": "issue:43122", - "right": "issue:43650", + "left": "issue:43784", + "right": "issue:45542", "accept": false, - "reason": "Tokenizer behavior regression vs an unrelated placeholder/data issue." + "reason": "Sentence-transformers import NameError and undefined tf backend are different failures." }, { "left": "issue:44297", "right": "issue:45397", "accept": false, - "reason": "Tokenizer save-pretrained config mismatch vs Gemma-4 zero3 loading failure; different code paths." + "reason": "Tokenizer save_pretrained metadata bug and Gemma4 zero3 loading failure are distinct." }, { "left": "issue:44016", "right": "issue:44291", "accept": false, - "reason": "Notebook syntax error vs init_empty_weights TypeError; unrelated." + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." }, { "left": "issue:44188", "right": "issue:44336", "accept": false, - "reason": "Attention kernel divergence vs ANSI codes in loading report; no shared bug." + "reason": "Attention-kernel branching bug and ANSI output in loading_report are different areas." }, { "left": "issue:43673", "right": "issue:43761", "accept": false, - "reason": "Generation cache regression vs CLIP hidden_states regression; different components." + "reason": "Cache missing in chunked_prefill and CLIP hidden_states regression are different code paths." }, { "left": "issue:43262", "right": "issue:44521", "accept": false, - "reason": "Both touch chat-template/multimodal processing, but the concrete failures and code paths differ." + "reason": "Both mention chat templates, but one is audio sampling-rate defaulting and the other is assistant mask generation." }, { "left": "issue:43450", "right": "issue:44617", "accept": false, - "reason": "Batched video shape bug vs CUDA OOM; not the same underlying issue." + "reason": "Video batch shape bug and Sam3Video CUDA OOM are not the same underlying issue." }, { "left": "issue:43525", "right": "issue:43881", "accept": false, - "reason": "Different model-loading failures with different symptoms and models." + "reason": "Missing pad_token_id and GLM-4V loading failure are separate model/config issues." }, { "left": "issue:43525", "right": "issue:43643", "accept": false, - "reason": "A missing config attribute and a trust_remote_code field-loss issue are related only loosely, not the same bug." + "reason": "Both involve config loading, but the missing-field causes and affected paths differ." }, { - "left": "issue:44589", - "right": "issue:45362", + "left": "issue:44336", + "right": "issue:44373", "accept": false, - "reason": "Float8 storage import/runtime error vs Qwen3.5 chat crash; unrelated." + "reason": "ANSI codes in loading_report and a wrong docstring are unrelated." }, { "left": "issue:41628", "right": "issue:43976", "accept": false, - "reason": "ImportError for a symbol vs Python-version compatibility; not the same issue." + "reason": "Import error for AutoImageProcessor and Python version incompatibility are different issues." }, { - "left": "issue:44336", - "right": "issue:44373", + "left": "issue:44589", + "right": "issue:45362", "accept": false, - "reason": "Loading-report terminal formatting vs a wrong docstring; unrelated." + "reason": "Float8 storage import failure and Qwen3.5 chat crash are unrelated." }, { "left": "issue:43901", "right": "issue:44246", "accept": false, - "reason": "Documentation mismatch vs slow import performance; different problems." + "reason": "A docs note about return_all_scores does not duplicate slow import timing." }, { - "left": "issue:42491", - "right": "issue:43299", + "left": "issue:44295", + "right": "issue:45397", "accept": false, - "reason": "Both involve Qwen3 MoE loading, but one is LoRA compatibility across versions and the other is a different model-loading regression." + "reason": "position_ids buffer access error and Gemma4 zero3 loading failure are unrelated." }, { - "left": "issue:44295", - "right": "issue:45397", + "left": "issue:42491", + "right": "issue:43299", "accept": false, - "reason": "Position_ids buffer access error vs Gemma-4 zero3 loading failure; different code paths." + "reason": "Both mention Qwen3/MoE regressions, but they are different models and failure scenarios." }, { "left": "issue:44242", "right": "issue:45593", "accept": false, - "reason": "Both mention auxiliary losses, but they affect different models and mechanisms; not the same bug." + "reason": "Different loss-calculation bugs in different models and settings." }, { "left": "issue:16998", "right": "issue:22355", "accept": false, - "reason": "Model_max_length question vs missing transformers.onnx import; unrelated." + "reason": "model_max_length question and missing transformers.onnx module are unrelated." }, { "left": "issue:44246", "right": "issue:44496", "accept": false, - "reason": "Import slowness vs unrecognized model config; unrelated." + "reason": "Slow import and unrecognized model config are not the same bug." }, { - "left": "issue:43352", - "right": "issue:45250", + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video classification processor selection and fbank extraction are different preprocessing paths." + }, + { + "left": "issue:44336", + "right": "issue:44485", "accept": false, - "reason": "Generic flash-attention topic vs a specific model not supporting Flash Attention 2.0; not the same concrete bug." + "reason": "Loading report ANSI output and GLM-5 RoPE implementation are unrelated." }, { "left": "issue:36246", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but for different packages/symbols and different root causes." + "reason": "Two separate import errors from different packages and symbols." }, { - "left": "issue:36246", - "right": "issue:44351", + "left": "issue:43352", + "right": "issue:45250", "accept": false, - "reason": "Missing exports/imports in different modules; too broad to treat as the same bug." + "reason": "Generic Flash Attention 2.0 discussion is not enough to match a specific model-support error." }, { - "left": "issue:43824", - "right": "issue:43976", + "left": "issue:36246", + "right": "issue:44351", "accept": false, - "reason": "ImportError for a model symbol vs Python 3.9/3.10 compatibility regression; different issues." + "reason": "Different missing exports: Qwen image processor vs HybridCache." } ] }, @@ -10905,7 +10933,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36246", "issue:43065", @@ -10919,6 +10947,7 @@ "issue:43596", "issue:43653", "issue:43673", + "issue:43824", "issue:43901", "issue:43976", "issue:44162", @@ -10926,8 +10955,6 @@ "issue:44246", "issue:44295", "issue:44336", - "issue:44368", - "issue:44466", "issue:44496", "issue:44561", "issue:44749", @@ -10936,14 +10963,12 @@ "issue:44871", "issue:44877", "issue:44964", - "issue:44977", "issue:44987", "issue:44995", "issue:45003", "issue:45137", "issue:45200", "issue:45292", - "issue:45335", "issue:45362", "issue:45375", "issue:45397", @@ -10954,9 +10979,12 @@ "issue:45588", "issue:45656", "issue:45701", - "issue:45759" + "issue:45759", + "issue:45987", + "issue:46082" ], "soft_pairs": [ + "issue:43824|issue:43976", "issue:43673|issue:44561", "issue:43976|issue:44964", "issue:44242|issue:44857", @@ -10966,8 +10994,9 @@ "issue:44162|issue:45200", "issue:44877|issue:45375", "issue:44779|issue:45292", - "issue:43901|issue:45003", + "issue:45987|issue:46082", "issue:36246|issue:43596", + "issue:43901|issue:45003", "issue:45292|issue:45584", "issue:43232|issue:44336", "issue:45561|issue:45563", @@ -10975,227 +11004,218 @@ "issue:43526|issue:45003", "issue:44987|issue:45459", "issue:44496|issue:45003", - "issue:45375|issue:45759", "issue:43065|issue:43408", - "issue:43257|issue:45137", + "issue:45375|issue:45759", "issue:44995|issue:45200", + "issue:43257|issue:45137", "issue:43262|issue:44246", "issue:43475|issue:43540", "issue:45397|issue:45656", "issue:43653|issue:44162", - "issue:44995|issue:45588", - "issue:44466|issue:45335", - "issue:44368|issue:44977", - "issue:44368|issue:45563" + "issue:44995|issue:45588" ], - "prepared_review_unit_hash": "52f6345af63368d36f9a6f417e7ce0c4517ec58ddb72caf1a0678c3e9cec8090", + "prepared_review_unit_hash": "7ca52e0347631b66d6a4ade66e0b71d4bef910baa6feb66f6f43333faa9d1847", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36862, - "estimated_input_tokens": 9216, - "estimated_eval_tokens": 18688 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35898, + "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 edges are mostly topical false positives: these issues span unrelated models, configs, tokenizer behavior, DeepSpeed/generation bugs, and docs/testing regressions. I don't see a single cohesive duplicate cluster, so no canonical issue/PR stands out.", - "confidence": 0.96, - "canonical_issue_reason": null, + "summary": "This cluster is very heterogeneous, with most pairs only loosely related by model-loading/runtime regressions. I found no soft edge that looks like the same underlying bug/change; all candidate merges should be rejected.", + "confidence": 0.59, + "canonical_issue_reason": "issue:43824 is the clearest, most concrete user-facing regression in the set: a specific ImportError with an explicit missing symbol and obvious repro/impact.", "canonical_pr_reason": null, - "best_issue_reason": null, + "best_issue_reason": "issue:43824 is the best anchor for the cluster because it is a sharply defined API breakage, whereas most other issues here are broader, config-specific, or unrelated failures.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "ImportError for a Qwen2.5 VL symbol is unrelated to a Python-version compatibility bug." + }, { "left": "issue:43673", "right": "issue:44561", "accept": false, - "reason": "Different bugs: cache handling in chunked prefill vs removal of an internal utility breaking trust_remote_code models." + "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available affect different code paths." }, { "left": "issue:43976", "right": "issue:44964", "accept": false, - "reason": "Python version compatibility issue vs a specific multimodal model load failure." + "reason": "Python support/version issue is not the same as loading a specific multimodal model." }, { "left": "issue:44242", "right": "issue:44857", "accept": false, - "reason": "MoE load-balancing loss logic is unrelated to an AMP/CUDA loss crash." + "reason": "MoE load-balancing loss logic is unrelated to mixed-precision image loss crashes." }, { "left": "issue:44246", "right": "issue:44871", "accept": false, - "reason": "Import-time slowness is unrelated to Gemma eos_token_id config mismatch." + "reason": "Import-time slowness and Gemma eos_token_id config mismatch are different problems." }, { "left": "issue:44295", "right": "issue:44749", "accept": false, - "reason": "Buffer access error vs a performance regression after upgrade; not the same code path." + "reason": "position_ids buffer access error is unrelated to tokenizer/filtering slowdown." }, { "left": "issue:45362", "right": "issue:45375", "accept": false, - "reason": "Qwen3.5 chat-generation crash and missing config field are different failures." + "reason": "A chat crash for Qwen3.5-35B and a missing config field in Qwen3_5MoeVisionConfig are not the same bug." }, { "left": "issue:44162", "right": "issue:45200", "accept": false, - "reason": "ESM2 model breakage vs Gemma 4 multimodal token-type defaults." + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaulting are separate model-specific issues." }, { "left": "issue:44877", "right": "issue:45375", "accept": false, - "reason": "Strict config loading for Granite Speech vs Qwen config field dropping." + "reason": "Strict config loading for granite_speech is unrelated to the missing deepstack_visual_indexes field." }, { "left": "issue:44779", "right": "issue:45292", "accept": false, - "reason": "Tokenizer output changes vs token embedding resize not propagating; different subsystems." + "reason": "Tokenizer output regression and resize_token_embeddings/output_embeddings mismatch are different subsystems." }, { - "left": "issue:43901", - "right": "issue:45003", + "left": "issue:45987", + "right": "issue:46082", "accept": false, - "reason": "Pipeline docs mismatch is unrelated to unsafe sys.modules access in modeling utils." + "reason": "Cache-length return type bug and LlamaConfig head_dim validation are unrelated." }, { "left": "issue:36246", "right": "issue:43596", "accept": false, - "reason": "ImportError for a missing image processor class vs a DeepSpeed/BertModel IndexError." + "reason": "Qwen2.5 VL import failure and DeepSpeed/BertModel index error do not share a concrete code path." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Documentation mismatch in a pipeline and unsafe sys.modules access are not the same issue." }, { "left": "issue:45292", "right": "issue:45584", "accept": false, - "reason": "Embedding resize bug is unrelated to Whisper empty-transcription generation failure." + "reason": "Embedding resize behavior and Whisper empty-transcription failure are distinct bugs." }, { "left": "issue:43232", "right": "issue:44336", "accept": false, - "reason": "Generation kwargs update bug vs ANSI output handling in loading_report." + "reason": "Generation kwargs update after sync_gpus is unrelated to ANSI output formatting in loading_report." }, { "left": "issue:45561", "right": "issue:45563", "accept": false, - "reason": "Pytest-xdist file race and a stale generate warning are unrelated." + "reason": "pytest-xdist file-race and stale paging warning in generate() are different behaviors." }, { "left": "issue:45292", "right": "issue:45701", "accept": false, - "reason": "Specific resize_token_embeddings bug vs broad tokenizer-version behavioral change." + "reason": "Embedding resize bug and tokenization changes across versions are not the same defect." }, { "left": "issue:43526", "right": "issue:45003", "accept": false, - "reason": "BEiT label reduction bug is unrelated to sys.modules access in modeling_utils." + "reason": "BeitImageProcessorFast label reduction and sys.modules access are unrelated." }, { "left": "issue:44987", "right": "issue:45459", "accept": false, - "reason": "Model load failure with transformers 5.1.0 is not the same as protobuf error masking." + "reason": "Model-loading failure and protobuf decode-error masking affect different layers." }, { "left": "issue:44496", "right": "issue:45003", "accept": false, - "reason": "Unrecognized-model config issue vs unsafe sys.modules access; different failure modes." - }, - { - "left": "issue:45375", - "right": "issue:45759", - "accept": false, - "reason": "Missing Qwen config field and AutoModelForCausalLM text_config unwrapping are distinct config bugs." + "reason": "Unrecognized model config and unsafe sys.modules lookup are separate failure modes." }, { "left": "issue:43065", "right": "issue:43408", "accept": false, - "reason": "SAM3 pixel decoder dummy layer issue vs model-type warning for sam3_video/sam3_tracker." + "reason": "Dummy Conv2d in Sam3PixelDecoder is not the same as a sam3_video vs sam3_tracker config warning." }, { - "left": "issue:43257", - "right": "issue:45137", + "left": "issue:45375", + "right": "issue:45759", "accept": false, - "reason": "Qwen3 MoE weight conversion problem vs a ZeRO3 deque underflow." + "reason": "Missing config field in Qwen3_5MoeVisionConfig and from_config text_config unwrapping are related only broadly, not the same bug." }, { "left": "issue:44995", "right": "issue:45200", "accept": false, - "reason": "GlmMoeDsa cache bug is unrelated to Gemma 4 token-type defaults." + "reason": "Stale indexer cache crash and Gemma 4 text-only mm_token_type_ids default are different code paths." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed and empty-deque ZeRO3 error are unrelated." }, { "left": "issue:43262", "right": "issue:44246", "accept": false, - "reason": "Audio chat-template sampling-rate default is unrelated to import latency." + "reason": "Audio chat-template sample-rate default and import-time slowness are not the same issue." }, { "left": "issue:43475", "right": "issue:43540", "accept": false, - "reason": "SAM3 vision output attribute missing vs Qwen3Omni video-input processing error." + "reason": "Missing fpn_position_embeddings and Qwen3OmniMoe video input ValueError are separate SAM/video behaviors." }, { "left": "issue:45397", "right": "issue:45656", "accept": false, - "reason": "Gemma-4 ZeRO3 loading bug vs optimizer stepping twice with DeepSpeed." + "reason": "Gemma-4 ZeRO3 loading and double optimizer.step under deepspeed are different training/runtime bugs." }, { "left": "issue:43653", "right": "issue:44162", "accept": false, - "reason": "BigBird tokenizer special-token registration issue is unrelated to ESM2 breakage." + "reason": "Tokenizer special-token registration and ESM2 breakage are unrelated." }, { "left": "issue:44995", "right": "issue:45588", "accept": false, - "reason": "Stale cache crash in GlmMoeDsa is unrelated to flash_attention s_aux=None handling." - }, - { - "left": "issue:44466", - "right": "issue:45335", - "accept": false, - "reason": "Tied-weight serialization inconsistency is not the same as resize_token_embeddings not updating decoder embeddings." - }, - { - "left": "issue:44368", - "right": "issue:44977", - "accept": false, - "reason": "Warning about tie_word_embeddings is unrelated to Qwen3.5 flash-attention generation failure." - }, - { - "left": "issue:44368", - "right": "issue:45563", - "accept": false, - "reason": "A config warning and a stale paged-generate warning are different issues." + "reason": "Stale indexer cache and flash_attention s_aux=None crash do not share a concrete failing code path." } ] }, @@ -11217,13 +11237,12 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28282", "issue:30990", "issue:41628", "issue:42371", - "issue:42673", "issue:42886", "issue:42994", "issue:43232", @@ -11234,7 +11253,6 @@ "issue:43643", "issue:43646", "issue:43673", - "issue:43704", "issue:43827", "issue:43931", "issue:44038", @@ -11244,12 +11262,14 @@ "issue:44297", "issue:44361", "issue:44368", + "issue:44466", "issue:44623", "issue:44661", "issue:44734", "issue:44749", "issue:44869", "issue:44933", + "issue:44977", "issue:45003", "issue:45081", "issue:45092", @@ -11258,17 +11278,20 @@ "issue:45229", "issue:45230", "issue:45310", + "issue:45335", "issue:45356", - "issue:45375", "issue:45381", "issue:45397", "issue:45459", - "issue:45478", "issue:45561", + "issue:45563", "issue:45600", "issue:45656" ], "soft_pairs": [ + "issue:44466|issue:45335", + "issue:44368|issue:44977", + "issue:44368|issue:45563", "issue:42886|issue:45229", "issue:43673|issue:44734", "issue:45003|issue:45561", @@ -11282,9 +11305,9 @@ "issue:43646|issue:44162", "issue:44623|issue:45656", "issue:44749|issue:45656", - "issue:43452|issue:45003", "issue:43673|issue:43827", "issue:44749|issue:45310", + "issue:43452|issue:45003", "issue:45230|issue:45397", "issue:42994|issue:43482", "issue:43232|issue:43673", @@ -11296,189 +11319,204 @@ "issue:41628|issue:44933", "issue:45081|issue:45103", "issue:43475|issue:44661", - "issue:42994|issue:43525", - "issue:45375|issue:45478", - "issue:45310|issue:45375", - "issue:42673|issue:43704" + "issue:42994|issue:43525" ], - "prepared_review_unit_hash": "7e1fd9e453607efdbaac3b7be14539987998baedcc593daed7c32b4d50a29a4b", + "prepared_review_unit_hash": "e7695af7cc30de3cd871c6853d241949318cfba00e9863db25eb5d3078b06dca", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 31, - "serialized_chars": 36916, - "estimated_input_tokens": 9229, - "estimated_eval_tokens": 18714 + "serialized_chars": 36951, + "estimated_input_tokens": 9238, + "estimated_eval_tokens": 18732 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose set of Transformers v5-era loading/init regressions and model-specific failures, not true duplicates. Only one soft pair is a clear duplicate; the rest are thematically similar but different bugs.", - "confidence": 0.72, - "canonical_issue_reason": "issue:43646 is the broadest umbrella report here: Transformers 5.0 breaking custom model initialization. It best represents the shared regression theme across the cluster.", + "summary": "This cluster is heterogeneous: mostly unrelated Transformers v5 regressions, tokenizer/model-loading bugs, and a few docs/test/import issues. None of the soft pairs look like the same concrete bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.81, + "canonical_issue_reason": "issue:43646 is the broadest, most general v5 regression in the set ('custom model initialization') and is the closest thing to a cluster umbrella, even though the overall set is not a true duplicate cluster.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43646 is the most reusable anchor for this cluster because it captures the generic v5 initialization breakage that many of the other reports are adjacent to.", + "best_issue_reason": "issue:43646 is the most representative issue because it describes a broad v5 breakage rather than a narrow model-specific symptom.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both touch tied weights, but one is an inconsistent serialization bug and the other is resize_token_embeddings not updating decoder.embed_tokens; different code paths." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "One is a tied-weights warning during LoRA fine-tuning; the other is a Qwen3.5 flash-attention generation failure. Same model family, different bugs." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Both mention warnings, but one is a tied-weights warning and the other is a stale num_return_sequences warning in paged generate(); not the same issue." + }, { "left": "issue:42886", "right": "issue:45229", "accept": false, - "reason": "Offline tokenizer cache loading and Gemma4 multi-GPU OOM are different failure modes." + "reason": "Offline tokenizer cache loading and multi-GPU CUDA OOM are unrelated failure modes." }, { "left": "issue:43673", "right": "issue:44734", "accept": false, - "reason": "Both mention cache, but chunked_prefill cache missing and serve KV continuation indexing are different code paths." + "reason": "Both involve generation/cache, but one is missing GenerationMixin cache in chunked_prefill and the other is a KV-cache continuation tensor indexing crash in serve; different defects." }, { "left": "issue:45003", "right": "issue:45561", "accept": false, - "reason": "Unsafe sys.modules access and xdist captured_info.txt race are unrelated bugs." + "reason": "sys.modules access safety and a pytest-xdist file race are unrelated." }, { "left": "issue:44060", "right": "issue:44077", "accept": false, - "reason": "Tied-weights warning and patchtsmixer post_init deprecation are not the same issue." + "reason": "One is a tied-weights warning in Qwen3-Next; the other is an optional post_init restriction in patchtsmixer. No shared code bug." }, { "left": "issue:45137", "right": "issue:45600", "accept": false, - "reason": "ZeRO3 deque underflow and removed Sam3LiteText configs are unrelated." + "reason": "A DeepSpeed ZeRO3 deque underflow and stale auto_mappings references are unrelated." }, { "left": "issue:43931", "right": "issue:44368", "accept": false, - "reason": "Qwen3-VL weight-shape mismatch and repeated tie_word_embeddings warnings are distinct model issues." + "reason": "Weight-shape mismatch while loading Qwen3-VL-30B is not the same bug as a tied-weights warning in Qwen3.5 fine-tuning." }, { "left": "issue:44933", "right": "issue:45459", "accept": false, - "reason": "Missing image_utils import and protobuf-related tokenizer error masking are different problems." + "reason": "Both are import/decode related, but one is a nonexistent image_utils import and the other hides tokenizer protobuf decode errors; different root causes." }, { "left": "issue:44297", "right": "issue:44623", "accept": false, - "reason": "tokenizer.save_pretrained metadata mismatch and processor.save_pretrained missing files are related to saving, but not the same bug." + "reason": "Both concern save_pretrained output, but one is tokenizer_class metadata mismatch and the other is missing processor files; not the same concrete bug." }, { "left": "issue:44869", "right": "issue:45356", "accept": false, - "reason": "Whisper timestamp decode crash and Kimi-K2.5 codec/fix_mistral_regex regression are different tokenizer issues." + "reason": "Whisper timestamp decoding crash and Kimi-K2.5 tokenizer regression are unrelated." }, { "left": "issue:44361", "right": "issue:44749", "accept": false, - "reason": "MLukeTokenizer AttributeError and Chinese slowdown after upgrade are not the same defect." + "reason": "MLukeTokenizer task AttributeError and a tokenizer slowdown after upgrade do not share the same failure mechanism." }, { "left": "issue:43646", "right": "issue:44162", "accept": false, - "reason": "Both are v5 regressions, but custom model initialization and ESM2 breakage are separate code-path failures." + "reason": "Both are broad model-loading breakages, but ESM2 is a model-specific failure, not the same custom initialization regression as issue 43646." }, { "left": "issue:44623", "right": "issue:45656", "accept": false, - "reason": "Missing processor files on save and double optimizer.step under deepspeed are unrelated." + "reason": "processor.save_pretrained missing files and optimizer.step being called twice with deepspeed are unrelated." }, { "left": "issue:44749", "right": "issue:45656", "accept": false, - "reason": "Performance slowdown and duplicated optimizer steps are not the same bug." - }, - { - "left": "issue:43452", - "right": "issue:45003", - "accept": false, - "reason": "GGUF loader breakage and unsafe sys.modules access are different loading issues." + "reason": "A performance regression in filtering and a double optimizer-step bug are different code paths." }, { "left": "issue:43673", "right": "issue:43827", "accept": false, - "reason": "Generation cache bug and docs still referencing pipeline() are unrelated runtime vs documentation issues." + "reason": "Generation cache handling and docs still referencing pipeline() are unrelated." }, { "left": "issue:44749", "right": "issue:45310", "accept": false, - "reason": "Language-model slowdown and Qwen3.5 MoE from_pretrained error are distinct failures." + "reason": "Tokenizer slowdown and Qwen3.5 MoE from_pretrained errors are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "gguf_file loading breakage and unsafe sys.modules access are different bugs." }, { "left": "issue:45230", "right": "issue:45397", "accept": false, - "reason": "Generic bug report and Gemma4 ZeRO3 from_pretrained issue are not duplicates." + "reason": "Generic bug report and gemma-4 zero3 from_pretrained failure are not the same issue." }, { "left": "issue:42994", "right": "issue:43482", "accept": false, - "reason": "Quantized model saving failure and Qwen2.5-GGUF loading failure are different directions and different bugs." + "reason": "Quantized model saving and Qwen2.5-GGUF loading under v5 are related only at a very broad quantization level, but the concrete bugs differ." }, { "left": "issue:43232", "right": "issue:43673", "accept": false, - "reason": "Both involve generation internals, but sync_gpus kwargs update and chunked_prefill cache handling are separate defects." + "reason": "sync_gpus generation kwargs handling and missing cache in chunked_prefill are different generation bugs." }, { "left": "issue:44038", "right": "issue:44623", "accept": false, - "reason": "Qwen3-VL-Moe loading problems and processor.save_pretrained missing files are different issues." + "reason": "Qwen3-VL-Moe v5 bug and missing processor.save_pretrained files are unrelated." }, { "left": "issue:42371", "right": "issue:45092", "accept": false, - "reason": "TF32 settings guidance and InternVL2 meta-init incompatibility are unrelated." + "reason": "TF32 settings API guidance and InternVL2 meta-init incompatibility are unrelated." }, { "left": "issue:28282", "right": "issue:30990", "accept": false, - "reason": "Missing PyTorch ImportError and Sentence Transformers loading hang are different environment/runtime problems." + "reason": "Missing PyTorch ImportError and Sentence Transformers loading hang are different symptoms and code paths." }, { "left": "issue:43475", "right": "issue:45381", "accept": false, - "reason": "SAM3 vision encoder missing attribute and qwen2.5-vl video position-id bug are unrelated." + "reason": "SAM3 vision encoder missing attribute and Qwen2.5-VL video position-id bug are unrelated." }, { "left": "issue:43475", "right": "issue:43643", "accept": false, - "reason": "SAM3 attribute error and trust_remote_code missing fields are different model/config issues." + "reason": "SAM3 encoder attribute failure and trust_remote_code missing-fields behavior are unrelated." }, { "left": "issue:41628", "right": "issue:44933", "accept": false, - "reason": "Both are import-related, but AutoImageProcessor import failure and image_utils import failure are not the same symbol or bug." + "reason": "Both are import-related, but one is AutoImageProcessor not being importable and the other is a bad image_utils import reference; not the same concrete break." }, { "left": "issue:45081", @@ -11490,41 +11528,20 @@ "left": "issue:43475", "right": "issue:44661", "accept": false, - "reason": "SAM3 missing attribute and add-new-model-like TOKENIZER_MAPPING_NAMES failure are different code paths." + "reason": "SAM3 output attribute error and add-new-model-like failing for TOKENIZER_MAPPING_NAMES are unrelated." }, { "left": "issue:42994", "right": "issue:43525", "accept": false, - "reason": "Quantized model saving and Llama4Config missing pad_token_id are unrelated." - }, - { - "left": "issue:45375", - "right": "issue:45478", - "accept": false, - "reason": "Missing deepstack_visual_indexes in Qwen3_5MoeVisionConfig and Qwen3.5 MoE from_pretrained failure are related by model family but not the same bug." - }, - { - "left": "issue:45310", - "right": "issue:45375", - "accept": false, - "reason": "A Qwen3.5 MoE load failure and a Qwen3_5MoeVisionConfig field-drop issue are different regressions." - }, - { - "left": "issue:42673", - "right": "issue:43704", - "accept": true, - "reason": "These are the same Qwen3ForCausalLM VRAM leak report with identical title and symptom, just different instances of the same bug." + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are distinct bugs." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The assessment is grounded in the packet and stays conservative. The canonical issue choice of issue:43646 is supported by its broad v5 initialization regression framing, and the soft-pair verdicts align with the issue titles and descriptions. The only accepted duplicate pair, issue:42673/issue:43704, is clearly the same VRAM-leak report with matching titles and symptoms. The summary correctly characterizes the cluster as mostly related-but-distinct regressions rather than duplicates." - }, - "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 }, @@ -11539,7 +11556,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:30333", "issue:30990", @@ -11549,13 +11566,14 @@ "issue:41628", "issue:42175", "issue:42222", + "issue:42673", "issue:42831", "issue:42898", "issue:42994", "issue:43232", "issue:43278", "issue:43377", - "issue:43673", + "issue:43704", "issue:43723", "issue:43784", "issue:43824", @@ -11566,7 +11584,6 @@ "issue:44188", "issue:44222", "issue:44242", - "issue:44295", "issue:44351", "issue:44373", "issue:44496", @@ -11583,14 +11600,17 @@ "issue:45200", "issue:45310", "issue:45356", - "issue:45405", + "issue:45375", + "issue:45478", "issue:45561", "issue:45600", - "issue:45656", "issue:45712", "issue:45812" ], "soft_pairs": [ + "issue:45375|issue:45478", + "issue:45310|issue:45375", + "issue:42673|issue:43704", "issue:41628|issue:44351", "issue:42831|issue:44222", "issue:44222|issue:45310", @@ -11598,11 +11618,11 @@ "issue:36010|issue:41628", "issue:42175|issue:45712", "issue:44038|issue:45310", - "issue:42222|issue:45200", "issue:44496|issue:45561", + "issue:42222|issue:45200", "issue:44964|issue:45137", - "issue:45561|issue:45600", "issue:43377|issue:44242", + "issue:45561|issue:45600", "issue:43901|issue:45561", "issue:43232|issue:44792", "issue:42898|issue:44568", @@ -11614,243 +11634,243 @@ "issue:42898|issue:45812", "issue:43278|issue:45137", "issue:44734|issue:45103", - "issue:30333|issue:33290", "issue:43874|issue:45092", + "issue:30333|issue:33290", "issue:43723|issue:44568", "issue:42898|issue:45356", "issue:44060|issue:45125", - "issue:42898|issue:44779", - "issue:45405|issue:45712", - "issue:44295|issue:45656", - "issue:43673|issue:44188" + "issue:42898|issue:44779" ], - "prepared_review_unit_hash": "23ece413b4acfc710585e878f837c3506dd814955d13598ccfd9fd9594af793b", + "prepared_review_unit_hash": "eaace1783f0ebfb44b30297ca24c7e41d073fc8f500fd25f3789e25d5be02ede", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, "soft_pair_count": 32, - "serialized_chars": 37264, - "estimated_input_tokens": 9316, - "estimated_eval_tokens": 18888 + "serialized_chars": 37305, + "estimated_input_tokens": 9327, + "estimated_eval_tokens": 18910 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is noisy and spans several unrelated bug families: tokenizer/v5 regressions, import/export failures, FP8/MoE issues, generation/runtime bugs, and test/CI problems. The soft pairs mostly share a surface theme only, not the same concrete underlying defect, so none should be merged.", - "confidence": 0.86, - "canonical_issue_reason": "issue:42898 is the broadest tokenizer-v5 regression report in the set and is the best anchor for the small tokenizer-behavior subgroup, even though the cluster as a whole is fragmented.", + "summary": "Only one soft pair is a safe duplicate: the exact-title Qwen3ForCausalLM VRAM leak report (42673/43704). The Qwen3.5 MoE items are related but not the same concrete bug from the packet, so they should stay separate.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 42673 is the best canonical issue: it is open and has an exact-title duplicate in 43704, making it the cleanest representative of the one confirmed issue pair.", "canonical_pr_reason": null, - "best_issue_reason": "issue:42898 is the most general user-facing behavior regression here and the closest thing to a representative issue, but it does not actually duplicate the other items.", + "best_issue_reason": "42673 is the strongest issue anchor because it is the open member of the only clearly duplicated pair and its title matches the duplicate exactly.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same family (Qwen3.5 MoE), but the packet shows different concrete reports: missing deepstack_visual_indexes vs from_pretrained error." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Related model area, but not the same bug: from_pretrained failure vs missing config field silently dropped by @strict." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same title and same VRAM-leak scenario for Qwen3ForCausalLM in multiple dataloader threads." + }, { "left": "issue:41628", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but they are for different missing symbols and likely different export paths." + "reason": "Both are import errors, but they involve different symbols and different failure modes." }, { "left": "issue:42831", "right": "issue:44222", "accept": false, - "reason": "One reports FP8 accuracy drift; the other is about FP8 save_pretrained behavior in MoE, so the defects differ." + "reason": "Accuracy regression with FineGrainedFP8 is a different problem from FP8 save_pretrained failure." }, { "left": "issue:44222", "right": "issue:45310", "accept": false, - "reason": "Both touch FP8/MoE, but one is save/export related while the other is a from_pretrained load error." + "reason": "Both mention Qwen/MoE and FP8/from_pretrained behavior, but the concrete failures are different code paths." }, { "left": "issue:42994", "right": "issue:43824", "accept": false, - "reason": "Quantized model saving failure and a missing model import are unrelated failure modes." + "reason": "Quantized model saving and missing Qwen2_5_VL import are unrelated." }, { "left": "issue:36010", "right": "issue:41628", "accept": false, - "reason": "Both are import-name failures, but they involve different objects and code paths." + "reason": "Different missing-import symbols and different affected modules." }, { "left": "issue:42175", "right": "issue:45712", "accept": false, - "reason": "Backend dependency installation and leftover dummy class cleanup are separate packaging/repo hygiene issues." + "reason": "Dependency/backend packaging issue is unrelated to leftover dummy classes leaking into dir(transformers)." }, { "left": "issue:44038", "right": "issue:45310", "accept": false, - "reason": "Both mention Qwen MoE models, but they are different models and different load-time failures." + "reason": "Both involve Qwen models, but the reported failure modes and model variants differ." }, { - "left": "issue:42222", - "right": "issue:45200", + "left": "issue:44496", + "right": "issue:45561", "accept": false, - "reason": "Vitpose model breakage and Gemma 4 token-type defaults are unrelated." + "reason": "Unrecognized model loading and pytest-xdist file race are unrelated issues." }, { - "left": "issue:44496", - "right": "issue:45561", + "left": "issue:42222", + "right": "issue:45200", "accept": false, - "reason": "A model config load error and a pytest-xdist race in testing utilities are unrelated." + "reason": "VitPose breakage and Gemma 4 token-type defaults are different model-specific bugs." }, { "left": "issue:44964", "right": "issue:45137", "accept": false, - "reason": "Multimodal model loading and DeepSpeed ZeRO3 deque handling are different code paths." + "reason": "Phi-4 multimodal loading and DeepSpeed ZeRO3 deque pop error are unrelated." }, { - "left": "issue:45561", - "right": "issue:45600", + "left": "issue:43377", + "right": "issue:44242", "accept": false, - "reason": "A captured-info race and removed Sam3LiteText config references are separate CI/testing problems." + "reason": "Missing padding-mask support in MIMI encoder is unrelated to MoE load-balancing loss logic." }, { - "left": "issue:43377", - "right": "issue:44242", + "left": "issue:45561", + "right": "issue:45600", "accept": false, - "reason": "Missing padding-mask support in MIMI and missing load-balancing loss are different model behaviors." + "reason": "pytest-xdist capture-file race and auto_mappings CI breakage are separate test/maintenance issues." }, { "left": "issue:43901", "right": "issue:45561", "accept": false, - "reason": "Docs for TextClassificationPipeline and a pytest-xdist race are unrelated." + "reason": "Docs mismatch for TextClassificationPipeline is unrelated to xdist file races." }, { "left": "issue:43232", "right": "issue:44792", "accept": false, - "reason": "Generation kwargs handling and a Janus image-generation test failure are not the same bug." + "reason": "Generation kwargs handling after sync_gpus and a janus image-generation test failure are different bugs." }, { "left": "issue:42898", "right": "issue:44568", "accept": false, - "reason": "Both are tokenizer regressions in v5, but one is cleanup behavior while the other is add_special_tokens/BOS-EOS behavior for a specific tokenizer." + "reason": "Tokenizer cleanup behavior change and missing BOS/EOS insertion are distinct tokenizer regressions." }, { "left": "issue:30990", "right": "issue:35141", "accept": false, - "reason": "Sentence-Transformers loading hang and token-embedding resize reinit are unrelated." + "reason": "Sentence Transformers loading stall and embedding reinitialization after resize are unrelated." }, { "left": "issue:43232", "right": "issue:44188", "accept": false, - "reason": "Generation kwargs after sync_gpus and attention-kernel branching under torch.compile are different runtime issues." + "reason": "Generation-state update logic and torch.compile attention-kernel divergence are different code paths." }, { "left": "issue:44623", "right": "issue:45310", "accept": false, - "reason": "Missing files in processor.save_pretrained and a Qwen3.5 MoE from_pretrained error are different failure modes." + "reason": "Missing processor.save_pretrained files is unrelated to the Qwen3.5 MoE from_pretrained error." }, { "left": "issue:44188", "right": "issue:44373", "accept": false, - "reason": "A torch.compile attention-kernel divergence and a wrong docstring are not duplicates." + "reason": "torch.compile attention branching and a wrong docstring for position_ids are unrelated." }, { "left": "issue:43784", "right": "issue:43824", "accept": false, - "reason": "Different import failures with different missing symbols and package interactions." + "reason": "Different import regressions involving different symbols and packages." }, { "left": "issue:42898", "right": "issue:45812", "accept": false, - "reason": "Both are tokenizer regressions, but one is a cleanup/default-behavior change and the other is wrong token IDs for Granite models." + "reason": "General cleanup-spaces behavior change and Granite token-id regression are different tokenizer bugs." }, { "left": "issue:43278", "right": "issue:45137", "accept": false, - "reason": "Embedding dtype drift during evaluation and a ZeRO3 deque IndexError are unrelated." + "reason": "Embedding dtype drift between train/eval is unrelated to the DeepSpeed deque error." }, { "left": "issue:44734", "right": "issue:45103", "accept": false, - "reason": "Serving KV-cache continuation indexing and auto_docstring future-annotations handling are separate bugs." + "reason": "KV-cache continuation crash in serve and auto_docstring annotation parsing crash are unrelated." }, { - "left": "issue:30333", - "right": "issue:33290", + "left": "issue:43874", + "right": "issue:45092", "accept": false, - "reason": "MLflow reporting on failed training jobs and DeepSpeed Adafactor OOM are unrelated." + "reason": "Missing image-patch count method and InternVL2 meta-init incompatibility are different multimodal issues." }, { - "left": "issue:43874", - "right": "issue:45092", + "left": "issue:30333", + "right": "issue:33290", "accept": false, - "reason": "A missing image-processor method and remote-code checkpoint incompatibility with meta init are different multimodal issues." + "reason": "MLflow reporting after training failure and Adafactor OOM are unrelated." }, { "left": "issue:43723", "right": "issue:44568", "accept": false, - "reason": "Tokenizer loading in v5 and add_special_tokens/BOS-EOS behavior are distinct tokenizer bugs." + "reason": "Tokenizer loading failure in v5 and missing BOS/EOS behavior are different bugs." }, { "left": "issue:42898", "right": "issue:45356", "accept": false, - "reason": "Both are tokenizer regressions, but they affect different models and different failure mechanisms." + "reason": "Tokenizer cleanup behavior change and Kimi-K2.5 codec/regex regression are unrelated." }, { "left": "issue:44060", "right": "issue:45125", "accept": false, - "reason": "Incorrect tied-weights warning and missing _tp_plan are different Qwen3.5 MoE issues." + "reason": "Incorrect tied-weights warning in Qwen3-Next and missing _tp_plan in Qwen3_5Moe are unrelated model bugs." }, { "left": "issue:42898", "right": "issue:44779", "accept": false, - "reason": "Both are tokenizer regressions, but the symptoms and affected models differ." - }, - { - "left": "issue:45405", - "right": "issue:45712", - "accept": false, - "reason": "PEFT version pinning and leftover dummy-class cleanup are unrelated." - }, - { - "left": "issue:44295", - "right": "issue:45656", - "accept": false, - "reason": "A position_ids buffer read error and deepspeed calling optimizer.step twice are different defects." - }, - { - "left": "issue:43673", - "right": "issue:44188", - "accept": false, - "reason": "Missing GenerationMixin cache in chunked_prefill and attention-kernel branching under compile are different generation/runtime bugs." + "reason": "Tokenizer cleanup behavior change and DeepSeek tokenizer regression are different failures." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, - "accepted_nontrivial_soft_edge": false, + "evaluator_result": { + "accept": false, + "feedback": "Rejecting because the summary overstates the evidence for the Qwen3.5 MoE pair. In the packet, issue 45375 is about `Qwen3_5MoeVisionConfig missing deepstack_visual_indexes field`, while 45478 is the `Qwen3.5 Moe from_pretrained error`; they do not have the same title or clearly the same concrete bug from the provided text. The VRAM-leak pair 42673/43704 is grounded by matching titles, but the overall summary and canonical-selection rationale are not fully supported by the packet." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -11865,28 +11885,28 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28282", "issue:30333", - "issue:30990", "issue:34689", "issue:35141", "issue:36331", - "issue:38175", "issue:41628", "issue:42175", "issue:42757", "issue:42831", "issue:42898", - "issue:42907", "issue:43232", "issue:43479", - "issue:43644", + "issue:43673", "issue:43723", + "issue:43761", "issue:43873", "issue:43976", "issue:44079", + "issue:44188", + "issue:44190", "issue:44206", "issue:44222", "issue:44261", @@ -11902,21 +11922,24 @@ "issue:44514", "issue:44623", "issue:44869", - "issue:44871", "issue:44933", "issue:44945", "issue:44977", + "issue:45071", "issue:45092", "issue:45103", "issue:45310", - "issue:45357", + "issue:45405", "issue:45406", "issue:45656", "issue:45712", "issue:45834", - "issue:46050" + "issue:46082" ], "soft_pairs": [ + "issue:45405|issue:45712", + "issue:44295|issue:45656", + "issue:43673|issue:44188", "issue:42898|issue:44448", "issue:44933|issue:45712", "issue:42175|issue:44933", @@ -11924,11 +11947,13 @@ "issue:43479|issue:44079", "issue:44297|issue:45656", "issue:43976|issue:44933", + "issue:44190|issue:46082", "issue:44222|issue:44623", "issue:42831|issue:44623", "issue:43479|issue:44869", "issue:44206|issue:45103", "issue:41628|issue:42757", + "issue:45071|issue:46082", "issue:30333|issue:36331", "issue:44297|issue:45310", "issue:30333|issue:34689", @@ -11938,245 +11963,247 @@ "issue:43723|issue:44977", "issue:28282|issue:30333", "issue:30333|issue:35141", + "issue:43761|issue:46082", "issue:43873|issue:44945", "issue:44373|issue:44485", "issue:44295|issue:44623", "issue:44483|issue:45406", "issue:44263|issue:44360", "issue:44514|issue:45103", - "issue:44261|issue:45092", - "issue:43479|issue:43644", - "issue:45092|issue:45357", - "issue:43723|issue:44871", - "issue:42907|issue:46050", - "issue:30990|issue:38175" + "issue:44261|issue:45092" ], - "prepared_review_unit_hash": "b6cd697cf7bc6f8c0261efc49a800eb097abdda095a0b6133f493280de8b480f", + "prepared_review_unit_hash": "e57cbef2806c02e84e7570cab6477736d765b8b9aa4f1a480537dd5eb5fa2ecd", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 33, - "serialized_chars": 37338, - "estimated_input_tokens": 9335, - "estimated_eval_tokens": 18926 + "soft_pair_count": 34, + "serialized_chars": 37651, + "estimated_input_tokens": 9413, + "estimated_eval_tokens": 19082 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft pair looks like a true duplicate: the matches are mostly broad topical similarity across unrelated bugs (imports, loading, save/load, generation, quantization, docs). I would not merge any of the candidate pairs. The best single issue to represent this set is the narrow, concrete serialization bug in issue 44297.", - "confidence": 0.85, - "canonical_issue_reason": "issue:44297 is the cleanest, most actionable standalone bug report in the set: a specific tokenizer save_pretrained serialization mismatch with a clear failure mode. It is narrower and better scoped than the more generic regressions or subsystem-wide reports.", + "summary": "This cluster is not a true duplicate set: the items span unrelated import errors, trainer issues, generation regressions, tokenizer/config bugs, and model-specific fixes. No soft pair looks like the same underlying bug/change, so all soft edges are rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue exists here; the issues are heterogeneous and do not share one underlying failure mode, so any single item would be a poor representative.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44297 is the strongest representative issue here because it is concrete, reproducible, and centered on one code path. The other items are too heterogeneous to serve as duplicates of it or of each other.", + "best_issue_reason": "No issue is a strong global representative because the cluster is incoherent rather than a single bug family.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "PEFT version pinning and leftover dummy classes are unrelated maintenance concerns." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer access and deepspeed double optimizer-step are different code paths." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked-prefill cache handling and attention-kernel branching on torch.compile are distinct generation issues." + }, { "left": "issue:42898", "right": "issue:44448", "accept": false, - "reason": "Both concern version-related output changes, but one is tokenizer cleanup behavior and the other is model output drift; different bugs and code paths." + "reason": "Tokenization cleanup behavior and Pegasus output differences are unrelated regressions." }, { "left": "issue:44933", "right": "issue:45712", "accept": false, - "reason": "Both are import/symbol visibility complaints, but one is a missing image_utils import and the other is dummy PT objects leaking into namespace/check_repo; not the same underlying defect." + "reason": "Missing image_utils import and dummy PT class cleanup do not describe the same bug." }, { "left": "issue:42175", "right": "issue:44933", "accept": false, - "reason": "Different backends and symptoms: TensorFlow packaging vs a missing image_utils import." + "reason": "Backend packaging omission and a missing image_utils import are different import/package issues." }, { "left": "issue:44222", "right": "issue:44297", "accept": false, - "reason": "Both mention save_pretrained, but one is FP8 MoE saving and the other is tokenizer config metadata; different artifacts and failure modes." + "reason": "FP8 MoE save_pretrained and tokenizer config mismatch affect different serialization paths." }, { "left": "issue:43479", "right": "issue:44079", "accept": false, - "reason": "Config initialization bug vs ModelOutput key assignment bug; unrelated code paths." + "reason": "Default config initialization and ModelOutput key assignment are unrelated object-initialization bugs." }, { "left": "issue:44297", "right": "issue:45656", "accept": false, - "reason": "Tokenizer serialization issue vs DeepSpeed optimizer stepping; unrelated." + "reason": "Tokenizer save metadata and deepspeed optimizer stepping are unrelated." }, { "left": "issue:43976", "right": "issue:44933", "accept": false, - "reason": "Python version compatibility issue vs missing import from image_utils; no shared root cause." + "reason": "Python version support and image_utils import failure are not the same issue." + }, + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Dataset loading script failure and LlamaConfig head_dim validation are unrelated." }, { "left": "issue:44222", "right": "issue:44623", "accept": false, - "reason": "Both involve saving, but they target different classes (FP8 MoE model vs processor) and different missing-file symptoms." + "reason": "FP8 MoE checkpoint saving and processor.save_pretrained missing files are different save-pretrained problems." }, { "left": "issue:42831", "right": "issue:44623", "accept": false, - "reason": "Accuracy regression in FP8 vs processor save_pretrained missing files; different problems." + "reason": "FineGrainedFP8 accuracy and processor file saving are not the same underlying bug." }, { "left": "issue:43479", "right": "issue:44869", "accept": false, - "reason": "Config default handling vs Whisper timestamp decode crash; unrelated." + "reason": "Config default initialization and Whisper timestamp decode crash are unrelated." }, { "left": "issue:44206", "right": "issue:45103", "accept": false, - "reason": "Generation kwargs handling vs autodoc annotation introspection crash; different subsystems." + "reason": "Feature extractor center-arg regression and auto_docstring annotation crash are different subsystems." }, { "left": "issue:41628", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they are for different symbols in different modules and are not the same bug." + "reason": "AutoImageProcessor import failure and is_offline_mode import failure are separate missing-symbol regressions." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "PretrainedConfig type checking and LlamaConfig head_dim validation are different config issues." }, { "left": "issue:30333", "right": "issue:36331", "accept": false, - "reason": "MLflow reporting on failed training vs trainer compute_loss signature change; unrelated." + "reason": "MLflow reporting after failed training and CustomTrainer.compute_loss signature mismatch are unrelated trainer bugs." }, { "left": "issue:44297", "right": "issue:45310", "accept": false, - "reason": "Tokenizer save_pretrained metadata bug vs Qwen3.5 from_pretrained regression; different direction of failure." + "reason": "Tokenizer class metadata mismatch and Qwen3.5 MoE from_pretrained error are different serialization/loading failures." }, { "left": "issue:30333", "right": "issue:34689", "accept": false, - "reason": "Training-job MLflow reporting vs model loading regression; unrelated." + "reason": "Failed-training MLflow reporting and Llama 3.2 model-loading regression are unrelated." }, { "left": "issue:44222", "right": "issue:44484", "accept": false, - "reason": "FP8 save_pretrained bug vs a question about max_shard_size default; not the same issue." + "reason": "FP8 MoE save_pretrained and max_shard_size default behavior are not the same problem." }, { "left": "issue:44263", "right": "issue:45092", "accept": false, - "reason": "DSA indexer split behavior vs remote-code checkpoint/meta-init incompatibility; different bugs." + "reason": "torch.split return handling and remote-code meta-init incompatibility are unrelated model-loading issues." }, { "left": "issue:43232", "right": "issue:45834", "accept": false, - "reason": "Generation state update bug vs long OCR input index error; unrelated." + "reason": "Generation kwargs update after sync_gpus and long OCR index error are different generation/model paths." }, { "left": "issue:43723", "right": "issue:44977", "accept": false, - "reason": "Tokenizer loading issue vs flash-attention generation bug; different code paths." + "reason": "Tokenizer loading regression and flash-attention generation failure are not the same bug." }, { "left": "issue:28282", "right": "issue:30333", "accept": false, - "reason": "PyTorch missing ImportError vs MLflow reporting bug; unrelated." + "reason": "PyTorch-not-found import error and MLflow failed-job reporting are unrelated." }, { "left": "issue:30333", "right": "issue:35141", "accept": false, - "reason": "Training failure reporting vs embedding resize/post_init reinitialization; unrelated." + "reason": "Training-job reporting and token-embedding resizing/post_init reinitialization are different issues." + }, + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and LlamaConfig head_dim validation are unrelated." }, { "left": "issue:43873", "right": "issue:44945", "accept": false, - "reason": "Quantization/offloading behavior vs pipeline-parallel LLM output correctness; different failure modes." + "reason": "Quantization offloading and pipeline-parallelism output correctness are different problems." }, { "left": "issue:44373", "right": "issue:44485", "accept": false, - "reason": "Docstring mismatch vs RoPE implementation discussion; not the same underlying bug." + "reason": "Docstring typo and GLM-5 RoPE implementation are not the same bug." }, { "left": "issue:44295", "right": "issue:44623", "accept": false, - "reason": "Buffer registration/readback bug vs processor save_pretrained file omission; different code paths." + "reason": "Position_ids buffer read and processor save_pretrained file emission are unrelated." }, { "left": "issue:44483", "right": "issue:45406", "accept": false, - "reason": "Server request handling regression vs Gemma4Processor attribute error in serve; related to serving only at a very high level, but not the same bug." + "reason": "chat/completions request handling and Gemma4Processor missing _tokenizer are different serving issues." }, { "left": "issue:44263", "right": "issue:44360", "accept": false, - "reason": "Both touch the DSA indexer, but one is about torch.split returns and the other about a missing ReLU; distinct defects." + "reason": "torch.split return values and DSA indexer missing ReLU are unrelated implementation bugs." }, { "left": "issue:44514", "right": "issue:45103", "accept": false, - "reason": "Processor batched chat-template crash vs autodoc annotation crash; unrelated." + "reason": "Batched chat template crash and auto_docstring annotation crash are different code paths." }, { "left": "issue:44261", "right": "issue:45092", "accept": false, - "reason": "MLA norm epsilon precision issue vs checkpoint/meta-init incompatibility; different models and causes." - }, - { - "left": "issue:43479", - "right": "issue:43644", - "accept": false, - "reason": "Multimodal config defaulting bug vs non-persistent buffer junk-fill regression; unrelated." - }, - { - "left": "issue:45092", - "right": "issue:45357", - "accept": false, - "reason": "Different model families and different save/load regressions; not duplicates." - }, - { - "left": "issue:43723", - "right": "issue:44871", - "accept": false, - "reason": "Tokenizer loading failure vs EOS token config inconsistency; related to loading/configuration but not the same bug." - }, - { - "left": "issue:42907", - "right": "issue:46050", - "accept": false, - "reason": "Both involve quantized model persistence, but one is dequantized saving and the other is sinq save/load corruption; too different to merge." - }, - { - "left": "issue:30990", - "right": "issue:38175", - "accept": false, - "reason": "Sentence Transformers loading hang vs SigLIP2 zero probabilities; unrelated." + "reason": "MLA q_a_layernorm epsilon precision issue and meta-init checkpoint incompatibility are unrelated." } ] }, @@ -12198,12 +12225,13 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:22355", "issue:28282", "issue:30990", "issue:33357", + "issue:38175", "issue:39401", "issue:41628", "issue:42371", @@ -12213,18 +12241,15 @@ "issue:42907", "issue:42994", "issue:43066", - "issue:43122", "issue:43232", - "issue:43408", - "issue:43475", "issue:43479", "issue:43576", + "issue:43644", "issue:43646", "issue:43723", "issue:43756", "issue:43784", "issue:43824", - "issue:43937", "issue:44038", "issue:44060", "issue:44117", @@ -12233,23 +12258,30 @@ "issue:44295", "issue:44297", "issue:44373", - "issue:44442", - "issue:44514", + "issue:44464", "issue:44568", "issue:44704", - "issue:44779", "issue:44829", + "issue:44871", "issue:44913", "issue:44945", + "issue:45092", "issue:45278", "issue:45290", "issue:45310", + "issue:45357", "issue:45593", - "issue:45600", "issue:45753", - "issue:46002" + "issue:46002", + "issue:46050", + "issue:46082" ], "soft_pairs": [ + "issue:45092|issue:45357", + "issue:43479|issue:43644", + "issue:43723|issue:44871", + "issue:42907|issue:46050", + "issue:30990|issue:38175", "issue:44829|issue:46002", "issue:42831|issue:45310", "issue:41628|issue:43824", @@ -12264,231 +12296,219 @@ "issue:43576|issue:43784", "issue:42886|issue:43066", "issue:42371|issue:44263", + "issue:44464|issue:46082", "issue:43232|issue:45593", "issue:44117|issue:44704", "issue:43646|issue:46002", "issue:44295|issue:44297", "issue:30990|issue:33357", - "issue:43756|issue:44060", "issue:44704|issue:45290", - "issue:42907|issue:44945", + "issue:43756|issue:44060", "issue:44261|issue:44373", - "issue:43122|issue:44514", - "issue:41628|issue:45278", - "issue:43784|issue:45600", - "issue:43723|issue:44779", - "issue:42907|issue:43937", - "issue:43723|issue:44442", - "issue:43408|issue:43475" + "issue:42907|issue:44945" ], - "prepared_review_unit_hash": "7b1c22656e88ea3df628f3a7d983d54b30fcd7a1a257cada36100498a6d5ce1c", + "prepared_review_unit_hash": "f97c945d2c9f812f8160ede90c1bf824c38386ef6bd508add6ac800ab6ac45c3", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 30, - "serialized_chars": 36281, - "estimated_input_tokens": 9071, - "estimated_eval_tokens": 18398 + "soft_pair_count": 29, + "serialized_chars": 36079, + "estimated_input_tokens": 9020, + "estimated_eval_tokens": 18296 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a loose similarity set around Transformers v5 import/loading regressions, tokenizer issues, and several unrelated model-specific bugs. I do not see any soft pair that clearly represents the same underlying bug/change, so I reject all soft edges.", - "confidence": 0.63, - "canonical_issue_reason": "Issue 45278 is the broadest umbrella in the set for upgrade-related import breakages, making it the best canonical bucket even though it is broader than many of the specific reports.", + "summary": "This cluster is heterogeneous: most items are unrelated regressions across imports, tokenizers, configs, generation, and quantization. None of the soft pairs look like the same concrete bug/change, so I reject all duplicate links.", + "confidence": 0.96, + "canonical_issue_reason": "No canonical issue is safe here; the items do not share one underlying bug, so any single issue would misrepresent the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "45278 is the most useful triage hub because it captures the general v5 import-regression theme and can absorb related missing-import reports better than the narrower tickets.", + "best_issue_reason": "No global best issue is suitable for duplicate triage because the cluster spans several unrelated failure modes.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Different models and different failures: meta-init incompatibility vs incorrect visual encoder keys on save." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "One is config default initialization; the other is non-persistent buffer corruption, not the same bug." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Both are tokenizer-related, but one is a general v5 load issue and the other is an eos_token_id mismatch for Gemma-3." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantized saving/loading, but they target different quantization flows and failure modes." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different symptoms and models: a hang during loading versus zero probabilities in SigLIP2." + }, { "left": "issue:44829", "right": "issue:46002", "accept": false, - "reason": "Different failure modes: degenerate training with FA3 vs NaNs on checkout/init; not the same code-path bug." + "reason": "Both mention training instability, but one is flash_attention_3 degeneration and the other is NaNs after checkout/init." }, { "left": "issue:42831", "right": "issue:45310", "accept": false, - "reason": "FineGrainedFP8 accuracy issue and Qwen3.5 MoE from_pretrained error are unrelated." + "reason": "Different problems: FP8 accuracy regression versus Qwen3.5 MoE from_pretrained error." }, { "left": "issue:41628", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but they concern different missing symbols and likely different fixes." + "reason": "Both are missing-import errors, but for different exported symbols and likely different root causes." }, { "left": "issue:44263", "right": "issue:44373", "accept": false, - "reason": "One is a torch.split behavior bug, the other is a docstring issue; not duplicates." + "reason": "A torch.split logic question is unrelated to a docstring error about position_ids." }, { "left": "issue:43479", "right": "issue:44913", "accept": false, - "reason": "Different config classes and symptoms; one is multimodal default init, the other is GPTNeoX reload behavior." + "reason": "Config defaulting for multimodal vision/audio is unrelated to GPTNeoX rotary_pct reload behavior." }, { "left": "issue:42831", "right": "issue:44038", "accept": false, - "reason": "Different models and failure classes; no shared concrete bug path." + "reason": "Different Qwen/FP8 issues; no shared concrete code path." }, { "left": "issue:39401", "right": "issue:44568", "accept": false, - "reason": "Separate tokenizer regressions affecting different models and behaviors." + "reason": "Both are tokenizer defects, but they affect different tokenizers and different outputs." }, { "left": "issue:22355", "right": "issue:28282", "accept": false, - "reason": "ONNX module import failure vs missing PyTorch dependency; distinct causes." + "reason": "Different import/dependency problems: missing transformers.onnx module versus missing PyTorch." }, { "left": "issue:42757", "right": "issue:45278", "accept": false, - "reason": "45278 is a broad import-regression umbrella, but 42757 is a specific missing symbol from huggingface_hub; not the same concrete bug." + "reason": "One is a specific huggingface_hub symbol import failure; the other is a broad upgrade-related import breakage." }, { "left": "issue:42886", "right": "issue:42994", "accept": false, - "reason": "Offline cache tokenizer loading and quantized model saving are unrelated." + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated code paths." }, { "left": "issue:44945", "right": "issue:45753", "accept": false, - "reason": "Pipeline-parallelism output corruption vs image-specific infinite loop; different code paths." + "reason": "Pipeline-parallel output corruption is not the same as a model-specific infinite loop on one image." }, { "left": "issue:43576", "right": "issue:43784", "accept": false, - "reason": "CLI env command breakage and sentence-transformers import NameError are separate issues." + "reason": "A broken CLI command and a sentence-transformers import NameError are different failures." }, { "left": "issue:42886", "right": "issue:43066", "accept": false, - "reason": "Offline cache loading and wrong decoder type are different tokenizer problems." + "reason": "Offline cache loading and tokenizer decoder type mismatch are distinct tokenizer issues." }, { "left": "issue:42371", "right": "issue:44263", "accept": false, - "reason": "TF32 settings warning and torch.split return handling are unrelated." + "reason": "TF32 settings behavior is unrelated to the GlmMoeDsaIndexer torch.split issue." + }, + { + "left": "issue:44464", + "right": "issue:46082", + "accept": false, + "reason": "Chunked generation inconsistencies and LlamaConfig head_dim validation are separate problems." }, { "left": "issue:43232", "right": "issue:45593", "accept": false, - "reason": "Generation kwarg update after sync_gpus is unrelated to auxiliary-loss handling in D-FINE." + "reason": "Generation kwargs handling after sync_gpus is unrelated to D-FINE auxiliary loss behavior." }, { "left": "issue:44117", "right": "issue:44704", "accept": false, - "reason": "Tokenizer mapping None handling and AutoProcessor kwargs forwarding are different loader bugs." + "reason": "Tokenizer mapping assumptions and AutoProcessor kwargs forwarding are different API bugs." }, { "left": "issue:43646", "right": "issue:46002", "accept": false, - "reason": "Custom model initialization breakage and NaNs in classification heads do not match." + "reason": "Custom model init breakage is not the same as NaNs in classification heads after checkout/init." }, { "left": "issue:44295", "right": "issue:44297", "accept": false, - "reason": "Reading a bufferized position_ids tensor and tokenizer_class mismatch on save_pretrained are separate defects." + "reason": "A position_ids buffer read issue is unrelated to tokenizer_class serialization mismatch." }, { "left": "issue:30990", "right": "issue:33357", "accept": false, - "reason": "Stuck loading and Mac bus error are not the same underlying bug." - }, - { - "left": "issue:43756", - "right": "issue:44060", - "accept": false, - "reason": "Smollm3 RoPE-layer discrepancy and Qwen3-Next tied-weights warning are unrelated model issues." + "reason": "Loading stalls and Mac bus errors are different model/runtime failures." }, { "left": "issue:44704", "right": "issue:45290", "accept": false, - "reason": "Cached_file kwarg forwarding and chat-template tool-call crashes are different paths." + "reason": "Missing kwargs in cached_file is unrelated to chat template crashes on tool-call assistant messages." }, { - "left": "issue:42907", - "right": "issue:44945", + "left": "issue:43756", + "right": "issue:44060", "accept": false, - "reason": "Dequantized model saving failure is unrelated to pipeline parallelism output errors." + "reason": "RoPE layer dropping and tied-weights warnings are different model bugs." }, { "left": "issue:44261", "right": "issue:44373", "accept": false, - "reason": "Precision/config epsilon bug and docstring mismatch are not duplicates." - }, - { - "left": "issue:43122", - "right": "issue:44514", - "accept": false, - "reason": "Different tokenizer regressions: one changes tokenization output, the other crashes in batched chat templating." - }, - { - "left": "issue:41628", - "right": "issue:45278", - "accept": false, - "reason": "45278 is a broad import-error umbrella, but 41628 is a specific missing export; not enough evidence of one shared code-path bug." - }, - { - "left": "issue:43784", - "right": "issue:45600", - "accept": false, - "reason": "Import-time NameError and stale auto_mappings references are separate issues." - }, - { - "left": "issue:43723", - "right": "issue:44779", - "accept": false, - "reason": "Generic tokenizer loading failure and Deepseek tokenization incorrectness are different problems." + "reason": "Precision drift from missing rms_norm_eps is unrelated to a docstring mistake." }, { "left": "issue:42907", - "right": "issue:43937", - "accept": false, - "reason": "Quantized saving failure and invalid GenerationConfig are unrelated." - }, - { - "left": "issue:43723", - "right": "issue:44442", - "accept": false, - "reason": "Both involve AutoTokenizer loading, but the evidence is too weak to say they are the same concrete bug." - }, - { - "left": "issue:43408", - "right": "issue:43475", + "right": "issue:44945", "accept": false, - "reason": "Wrong model-class warning and missing output attribute are distinct SAM 3 video issues." + "reason": "Quantized save/load failures do not match pipeline-parallel output corruption." } ] }, @@ -12510,7 +12530,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:22355", "issue:28218", @@ -12519,24 +12539,21 @@ "issue:30990", "issue:36296", "issue:39401", - "issue:42222", - "issue:42371", + "issue:41628", "issue:42757", - "issue:42831", "issue:42907", "issue:43066", "issue:43116", "issue:43122", "issue:43232", - "issue:43441", + "issue:43408", "issue:43452", - "issue:43493", + "issue:43475", "issue:43611", + "issue:43723", "issue:43784", "issue:43824", - "issue:43874", "issue:43937", - "issue:43976", "issue:43992", "issue:44038", "issue:44222", @@ -12544,8 +12561,10 @@ "issue:44297", "issue:44351", "issue:44360", + "issue:44442", "issue:44485", "issue:44488", + "issue:44514", "issue:44521", "issue:44625", "issue:44704", @@ -12556,27 +12575,35 @@ "issue:45200", "issue:45216", "issue:45245", + "issue:45278", "issue:45446", "issue:45478", - "issue:45753", + "issue:45600", "issue:46002" ], "soft_pairs": [ + "issue:43122|issue:44514", + "issue:41628|issue:45278", + "issue:43723|issue:44779", + "issue:43723|issue:44442", + "issue:42907|issue:43937", + "issue:43784|issue:45600", "issue:43232|issue:45245", + "issue:43408|issue:43475", "issue:44360|issue:44485", "issue:43122|issue:44521", + "issue:44038|issue:44297", "issue:44625|issue:44829", "issue:43116|issue:45200", - "issue:44038|issue:44297", "issue:42907|issue:44964", - "issue:29127|issue:30990", "issue:44038|issue:44295", + "issue:29127|issue:30990", "issue:43122|issue:44779", "issue:36296|issue:43116", "issue:42907|issue:43452", "issue:44038|issue:44222", - "issue:39401|issue:44488", "issue:43824|issue:44351", + "issue:39401|issue:44488", "issue:45216|issue:45478", "issue:39401|issue:44521", "issue:42757|issue:44351", @@ -12587,221 +12614,234 @@ "issue:22355|issue:29159", "issue:43066|issue:44779", "issue:43937|issue:44485", - "issue:43611|issue:46002", - "issue:42371|issue:43874", - "issue:43976|issue:45446", - "issue:42222|issue:43441", - "issue:43493|issue:45753", - "issue:42831|issue:44297" + "issue:43611|issue:46002" ], - "prepared_review_unit_hash": "481880870dbe59b60cede4256d7b92873aa51cba61feb61c4bbf15d306e5a626", + "prepared_review_unit_hash": "684a256c67ebafc0feb9eac87e68611bcaf51cf6e799bc9ca6033b8a5262ddeb", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 31, - "serialized_chars": 36463, - "estimated_input_tokens": 9116, - "estimated_eval_tokens": 18488 + "soft_pair_count": 33, + "serialized_chars": 37111, + "estimated_input_tokens": 9278, + "estimated_eval_tokens": 18812 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are mostly unrelated single-bug reports. The only loose thematic overlap is tokenizer regressions around v5, but none of the soft pairs look like true duplicates.", - "confidence": 0.83, - "canonical_issue_reason": "issue:43122 is the most broadly phrased and central tokenizer-regression report, so it best serves as the cluster anchor among these mostly unrelated issues.", + "summary": "This set is mostly heterogeneous; the soft-similarity pairs are largely false positives across different bugs (tokenizers, imports, model loading, generation, training, and docs). No pair looks like the same concrete issue/change strongly enough to dedupe.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43122 is the broadest tokenizer-regression report and the closest thing to a cluster anchor, but it still only represents a subgroup rather than a true duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43122 has the clearest cross-cutting scope (tokenization changes across versions) and enough discussion/inbound refs to represent the cluster better than the narrower model-specific reports.", + "best_issue_reason": "43122 is the best representative issue because it captures the widest recurring theme in the candidates: tokenizer behavior regressions around v5.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Both touch tokenization/chat-template behavior, but one is a broad version-regression report and the other is a specific multimodal batching crash; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both mention imports, but one is a single missing symbol and the other is a broad post-upgrade import breakage; too generic to merge." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "One is about tokenizer loading and the other about incorrect tokenization output; related area, but different concrete failures." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both are AutoTokenizer load problems, but they involve different tokenizer classes and likely different root causes." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Unrelated model-specific issues: saving dequantized models versus an invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Different failures in different code paths: a missing import in sentence-transformers integration versus stale auto-mapping references." + }, { "left": "issue:43232", "right": "issue:45245", "accept": false, - "reason": "Generation sync/kwargs handling and a category-cardinality runtime error are unrelated failure modes." + "reason": "Generation-state handling and category-cardinality validation are unrelated bugs." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Same family name, but one is a model-type warning and the other is an attribute-missing crash; not the same issue." }, { "left": "issue:44360", "right": "issue:44485", "accept": false, - "reason": "A DSA indexer bug and a GLM-5 RoPE implementation discussion do not describe the same code-path problem." + "reason": "Completely different topics: DSA indexer activation versus GLM-5 RoPE implementation." }, { "left": "issue:43122", "right": "issue:44521", "accept": false, - "reason": "Both involve tokenization-adjacent behavior, but one is a generic tokenizer regression and the other is multimodal chat-template assistant-mask generation." + "reason": "Both involve tokenization-related APIs, but one is a version-to-version tokenization change and the other is assistant mask generation for multimodal inputs." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe model support and tokenizer_config save metadata are different bugs." }, { "left": "issue:44625", "right": "issue:44829", "accept": false, - "reason": "num_labels propagation in Qwen3.5 is unrelated to flash_attention_3 training degeneration." + "reason": "A config-propagation bug for Qwen3.5 is unrelated to flash-attention training degeneration." }, { "left": "issue:43116", "right": "issue:45200", "accept": false, - "reason": "Empty multi-label classification results in an example script is a different bug from Gemma 4 mm_token_type_ids defaults." - }, - { - "left": "issue:44038", - "right": "issue:44297", - "accept": false, - "reason": "Qwen3-VL-Moe from_pretrained failure and tokenizer_class mismatch on save_pretrained affect different APIs and code paths." + "reason": "Example-script multi-label output and Gemma 4 mm_token_type_ids defaults are unrelated." }, { "left": "issue:42907", "right": "issue:44964", "accept": false, - "reason": "Saving dequantized Ministral/Devstral and loading Phi-4 multimodal are not the same underlying bug." + "reason": "Different model families and different failure modes; no shared underlying bug." }, { - "left": "issue:29127", - "right": "issue:30990", + "left": "issue:44038", + "right": "issue:44295", "accept": false, - "reason": "An error-message clarity issue in LayoutLMv3 is unrelated to Sentence Transformers getting stuck loading." + "reason": "One is a Qwen3-VL-Moe support issue and the other is a position_ids buffer-read bug; unrelated." }, { - "left": "issue:44038", - "right": "issue:44295", + "left": "issue:29127", + "right": "issue:30990", "accept": false, - "reason": "Qwen3-VL-Moe loading and reading a registered position_ids buffer are different concrete failures." + "reason": "Unrelated: LayoutLMv3 error-message clarity versus sentence-transformers loading hang." }, { "left": "issue:43122", "right": "issue:44779", "accept": false, - "reason": "Both mention tokenizer regressions, but the symptoms and affected models differ too much to treat as one bug." + "reason": "Both are tokenizer regressions in v5, but they target different models and concrete symptoms; not enough to treat as one bug." }, { "left": "issue:36296", "right": "issue:43116", "accept": false, - "reason": "Tensor-parallel training instability is unrelated to the classification example script returning empty multi-label results." + "reason": "Tensor-parallel training and multi-label classification output are unrelated." }, { "left": "issue:42907", "right": "issue:43452", "accept": false, - "reason": "Dequantized save failure and gguf_file loading failure are different model-loading/saving bugs." + "reason": "Saving dequantized models and gguf loading failures are different code paths and different problems." }, { "left": "issue:44038", "right": "issue:44222", "accept": false, - "reason": "Both mention MoE/FP8, but one is a Qwen3-VL-Moe load bug and the other is FP8 save_pretrained behavior." + "reason": "Both mention MoE, but one is model loading and the other is FP8 save_pretrained behavior; not the same change." }, { - "left": "issue:39401", - "right": "issue:44488", + "left": "issue:43824", + "right": "issue:44351", "accept": false, - "reason": "Wrong offset mappings for Qwen3 tokenizer and failure to load cjvt/sleng-bert are unrelated symptoms." + "reason": "Both are import errors, but for different symbols/packages and likely different missing exports." }, { - "left": "issue:43824", - "right": "issue:44351", + "left": "issue:39401", + "right": "issue:44488", "accept": false, - "reason": "Missing Qwen2_5_VLForConditionalGeneration and missing HybridCache are different import errors from different symbols." + "reason": "Different tokenizer failures: offset_mapping correctness versus model loading." }, { "left": "issue:45216", "right": "issue:45478", "accept": false, - "reason": "Both are Qwen3.5/Transformers 5.4.0 regressions, but save_pretrained checkpoint corruption and from_pretrained MoE errors are not the same bug." + "reason": "Both concern Qwen3.5 regressions, but one is broken saved checkpoints and the other is from_pretrained loading failure; distinct bugs." }, { "left": "issue:39401", "right": "issue:44521", "accept": false, - "reason": "Tokenizer offset mapping and all-zero assistant masks are separate tokenizer/template issues." + "reason": "Both are tokenizer-adjacent, but one is offset mapping and the other is assistant mask generation." }, { "left": "issue:42757", "right": "issue:44351", "accept": false, - "reason": "One is an import break from huggingface_hub and the other from transformers; different packages, different missing names." + "reason": "Import errors in different libraries and symbols; not a duplicate." }, { "left": "issue:43784", "right": "issue:45446", "accept": false, - "reason": "Sentence-transformers import NameError and a PyTorch version-check bug in flex_attention are unrelated." + "reason": "Sentence-transformers import regression and flex_attention version-check logic are unrelated." }, { "left": "issue:43992", "right": "issue:44704", "accept": false, - "reason": "Missing embed_tokens.weight in from_pretrained and AutoProcessor kwargs not reaching cached_file are different loading-path problems." + "reason": "UMT5 weight-loading and AutoProcessor kwarg forwarding are separate issues." }, { "left": "issue:43122", "right": "issue:44977", "accept": false, - "reason": "Both are tokenizer regressions in v5, but the model families and concrete failures differ; not enough to merge." + "reason": "Both involve tokenizer behavior changes in v5, but one is general tokenization drift and the other is Qwen3.5 flash-attention generation failure." }, { "left": "issue:22355", "right": "issue:28218", "accept": false, - "reason": "Missing transformers.onnx and an extra-space tokenizer bug are unrelated." + "reason": "No module import failure and tokenizer added-space behavior are unrelated." }, { "left": "issue:22355", "right": "issue:29159", "accept": false, - "reason": "Missing transformers.onnx and slow/fast tokenizer inconsistency do not describe the same issue." + "reason": "Import error for transformers.onnx and slow/fast tokenizer inconsistency are different bugs." }, { "left": "issue:43066", "right": "issue:44779", "accept": false, - "reason": "A decoder-type config bug and Deepseek tokenizer wrong outputs are different underlying problems." + "reason": "Both are tokenizer regressions, but one is decoder-type mismatch and the other is incorrect Deepseek tokenization; different code paths." }, { "left": "issue:43937", "right": "issue:44485", "accept": false, - "reason": "Invalid GenerationConfig and GLM-5 RoPE implementation are not the same failure." + "reason": "GLM-5 GenerationConfig validation and GLM-5 RoPE implementation are separate issues." }, { "left": "issue:43611", "right": "issue:46002", "accept": false, - "reason": "base_model_prefix loading regression and NaNs in classification heads are distinct bugs." - }, - { - "left": "issue:42371", - "right": "issue:43874", - "accept": false, - "reason": "TF32 API warning guidance and a missing image-patch helper method are unrelated." - }, - { - "left": "issue:43976", - "right": "issue:45446", - "accept": false, - "reason": "Python version compatibility and an incorrect PyTorch version guard are separate environment-check issues." - }, - { - "left": "issue:42222", - "right": "issue:43441", - "accept": false, - "reason": "VitPose model breakage and Ministral flash-attention failure affect different models and code paths." - }, - { - "left": "issue:43493", - "right": "issue:45753", - "accept": false, - "reason": "SigLIP2 implementation discrepancy and Qwen3_5 infinite-loop generation are unrelated model-specific bugs." + "reason": "Base_model_prefix loading regression and NaNs in classification heads are unrelated." } ] }, @@ -12823,7 +12863,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:22355", "issue:29127", @@ -12831,49 +12871,54 @@ "issue:38617", "issue:39401", "issue:41628", + "issue:42222", + "issue:42371", "issue:42673", + "issue:42831", "issue:43064", "issue:43116", "issue:43381", - "issue:43421", + "issue:43441", "issue:43450", "issue:43493", "issue:43673", "issue:43825", "issue:43827", + "issue:43874", "issue:43937", + "issue:43976", "issue:43986", "issue:44038", "issue:44075", "issue:44117", - "issue:44291", + "issue:44297", "issue:44380", - "issue:44410", "issue:44466", - "issue:44484", "issue:44625", "issue:44779", - "issue:44829", "issue:44936", "issue:44945", "issue:44977", - "issue:45071", "issue:45072", "issue:45081", "issue:45083", - "issue:45216", "issue:45278", - "issue:45310", "issue:45357", "issue:45405", "issue:45446", "issue:45478", "issue:45563", "issue:45588", + "issue:45753", "issue:46002", "issue:46077" ], "soft_pairs": [ + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:42222|issue:43441", + "issue:42831|issue:44297", + "issue:43493|issue:45753", "issue:44075|issue:44936", "issue:45357|issue:45478", "issue:44038|issue:45478", @@ -12897,222 +12942,220 @@ "issue:43450|issue:43986", "issue:44117|issue:45081", "issue:38617|issue:41628", - "issue:42673|issue:45072", - "issue:44410|issue:45310", - "issue:44829|issue:45216", - "issue:44291|issue:45071", - "issue:39401|issue:43421", - "issue:44484|issue:45310" + "issue:42673|issue:45072" ], - "prepared_review_unit_hash": "4dca3bb6db679c21b1f784f58219e4716ee652cd6b286df3be7bbf837c783f9e", + "prepared_review_unit_hash": "d811fcf59c70c5e612857f68e55187bb4822429785c237d9c917881e611fc0c1", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 29, - "serialized_chars": 35767, - "estimated_input_tokens": 8942, - "estimated_eval_tokens": 18140 + "serialized_chars": 35623, + "estimated_input_tokens": 8906, + "estimated_eval_tokens": 18068 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is thematically related to Transformers v5 regressions, but the items split into distinct bugs across imports, tokenizers, Qwen3.5, training, and generation. I don\u2019t see any soft-edge pair that clearly describes the same underlying change or defect, so no merges are justified.", - "confidence": 0.71, - "canonical_issue_reason": "If a single anchor is needed, issue:45278 is the broadest umbrella for the import-regression slice ('many import errors after update to 5.5.0'), but the overall cluster is not a true duplicate set.", + "summary": "This cluster is mostly heterogeneous transformer issues spanning import/export regressions, tokenizer/model bugs, trainer bugs, and attention/backend edge cases. Only the import-error pair (issue:38617 and issue:45278) looks plausibly like the same underlying regression; the rest are too different to merge as duplicates.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it describes the broad import-error regression after upgrading to v5.5, which can reasonably subsume the more specific import-symbol failure in issue:38617.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best representative only in the loose sense that it captures the widest recurring theme (import failures after v5 upgrade); it is not a strict duplicate hub.", + "best_issue_reason": "issue:45278 is the strongest global issue candidate: it is broad, clearly regression-oriented, and closest to a central theme in the cluster. Still, the overall cluster is too mixed for a truly strong canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "Different problems: TF32 behavior settings vs a missing image-processor method causing a multimodal token-count failure." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Both are version-compatibility crashes, but the underlying causes and code paths differ (Python version support vs a bad PyTorch version check in flex_attention)." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Unrelated model-specific breakages: VitPose imports vs Ministral FlashAttention failure." + }, + { + "left": "issue:42831", + "right": "issue:44297", + "accept": false, + "reason": "Accuracy degradation in FP8 is unrelated to tokenizer save/load metadata mismatch." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Different Qwen model bugs with different symptoms and likely different tokenizer/image-processing paths." + }, { "left": "issue:44075", "right": "issue:44936", "accept": false, - "reason": "Unrelated bugs: unused SGD args vs trainer.evaluate() failure after training." + "reason": "Optimizer-argument handling is unrelated to evaluate()-after-train() failure." }, { "left": "issue:45357", "right": "issue:45478", "accept": false, - "reason": "Same model family, but different code paths: save_pretrained key serialization vs from_pretrained loading error." + "reason": "Both mention Qwen3.5, but one is save_pretrained key serialization and the other is from_pretrained loading failure; not clearly the same bug." }, { "left": "issue:44038", "right": "issue:45478", "accept": false, - "reason": "Both mention Qwen3.5/Qwen3-VL-Moe loading issues, but the titles don\u2019t identify the same concrete failure." + "reason": "Different Qwen variants and different failure modes; too weak to call the same underlying bug." }, { "left": "issue:43116", "right": "issue:43825", "accept": false, - "reason": "Different features entirely: multi-label classification example vs pipeline() translation support/error messaging." + "reason": "Example-script multi-label inference failure is unrelated to pipeline() docs/error-message fallout from v5 pipeline removals." }, { "left": "issue:45083", "right": "issue:45446", "accept": false, - "reason": "qwen3_omni_moe feature-length helper behavior is unrelated to flex_attention version-check/import logic." + "reason": "Separate subsystems: qwen3_omni_moe feature-length helper vs flex_attention dependency/version check." }, { "left": "issue:43116", "right": "issue:43493", "accept": false, - "reason": "Different model and symptom: classification example output vs SigLIP2 implementation discrepancy." + "reason": "Multi-label classification example failure is unrelated to SigLIP2 model discrepancy." }, { "left": "issue:43937", "right": "issue:45563", "accept": false, - "reason": "GenerationConfig validation failure and a stale warning for num_return_sequences are different issues." + "reason": "GenerationConfig validation failure and a stale paged-generate warning are different issues." }, { "left": "issue:38617", "right": "issue:45278", - "accept": false, - "reason": "Both are import regressions, but one is a specific missing symbol and the other is a broad upgrade report; not the same underlying bug." + "accept": true, + "reason": "Both are import regressions after the v5 upgrade; issue:45278 is a broad umbrella that plausibly covers the specific missing-symbol import error in issue:38617." }, { "left": "issue:43064", "right": "issue:43673", "accept": false, - "reason": "Optimizer-state corruption in training is unrelated to missing GenerationMixin cache during chunked prefill." + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is unrelated to GenerationMixin cache missing during chunked prefill." }, { "left": "issue:44380", "right": "issue:46077", "accept": false, - "reason": "Both concern attention behavior, but GPT2 scaling under SDPA/FlashAttention and Gemma4 causal masking are distinct code paths." + "reason": "Both involve attention behavior, but they are different model/back-end bugs and not the same concrete code-path failure." }, { "left": "issue:33453", "right": "issue:39401", "accept": false, - "reason": "Tokenizer loading regression vs incorrect offset_mapping are different tokenizer bugs." + "reason": "Both are tokenizer-related, but one is a loading regression and the other is a specific offset_mapping problem for Qwen3; not enough to unify." }, { "left": "issue:44117", "right": "issue:45588", "accept": false, - "reason": "TOKENIZER_MAPPING_NAMES returning None is unrelated to flash_attention.py crashing on s_aux=None." + "reason": "Tokenizer mapping fallback behavior is unrelated to flash_attention.py crashing on s_aux=None." }, { "left": "issue:44625", "right": "issue:46002", "accept": false, - "reason": "Qwen3.5 num_labels propagation and NaNs in classification heads are not the same defect." + "reason": "Config propagation for Qwen3.5 and NaNs in classification-head init are different bugs." }, { "left": "issue:43827", "right": "issue:45446", "accept": false, - "reason": "Docs still referencing pipeline() and a PyTorch version check bug are unrelated." + "reason": "Docs still referencing removed pipeline() APIs is unrelated to a flex_attention import/version check." }, { "left": "issue:39401", "right": "issue:44779", "accept": false, - "reason": "Different tokenizer correctness bugs for different models; not one shared issue." + "reason": "Both are tokenizer correctness bugs, but they affect different models and different failure modes (offset mapping vs incorrect tokenization output)." }, { "left": "issue:22355", "right": "issue:29127", "accept": false, - "reason": "Missing transformers.onnx module and a LayoutLMv3 error-message clarity issue are unrelated." + "reason": "No module named transformers.onnx is unrelated to a layoutlmv3 error-message clarity issue." }, { "left": "issue:43381", "right": "issue:44945", "accept": false, - "reason": "Gradient checkpointing in eval mode and incorrect output under pipeline parallelism are different runtime bugs." + "reason": "Gradient checkpointing in eval mode and pipeline-parallelism output corruption are unrelated training/runtime bugs." }, { "left": "issue:43937", "right": "issue:44977", "accept": false, - "reason": "GenerationConfig invalid and Qwen3.5 flash-attention generation failure are distinct problems." + "reason": "Different generation issues for different models/backends; not the same underlying bug." }, { "left": "issue:44466", "right": "issue:46002", "accept": false, - "reason": "save_pretrained serialization inconsistency is unrelated to NaNs in classification heads." + "reason": "Serialization of tied weights depending on device is unrelated to NaNs in classification head initialization." }, { "left": "issue:45405", "right": "issue:45446", "accept": false, - "reason": "PEFT minimum-version packaging issue and flex_attention import/version check bug are unrelated." + "reason": "PEFT minimum-version packaging problem is unrelated to the flex_attention PyTorch version-check bug." }, { "left": "issue:43450", "right": "issue:43986", "accept": false, - "reason": "Batched video processor shape bug vs AutoProcessor crash without torchvision are different video-processing failures." + "reason": "Batched video shape handling and missing-t torchvision crash are different problems in the video stack." }, { "left": "issue:44117", "right": "issue:45081", "accept": false, - "reason": "Tokenizer mapping None and Mistral regex patch crash are separate tokenizer internals bugs." + "reason": "Tokenizer mapping assumptions and a Mistral regex patch AttributeError are separate code paths." }, { "left": "issue:38617", "right": "issue:41628", "accept": false, - "reason": "Two different import errors with different missing symbols; same broad theme, but not the same bug." + "reason": "Both are import errors, but they involve different missing exports and different causes; too broad to merge." }, { "left": "issue:42673", "right": "issue:45072", "accept": false, - "reason": "VRAM leak in multithreaded Qwen3ForCausalLM usage is unrelated to bfloat16 dtype mismatches." - }, - { - "left": "issue:44410", - "right": "issue:45310", - "accept": false, - "reason": "Missing qwen3next projections and Qwen3.5 from_pretrained loading errors are different model issues." - }, - { - "left": "issue:44829", - "right": "issue:45216", - "accept": false, - "reason": "FlashAttention-3 training degeneration and incorrect checkpoint serialization are unrelated." - }, - { - "left": "issue:44291", - "right": "issue:45071", - "accept": false, - "reason": "Unexpected _is_hf_initialized argument and PretrainedConfig type-checking breakage are separate v5 regressions." - }, - { - "left": "issue:39401", - "right": "issue:43421", - "accept": false, - "reason": "Offset-mapping bug and runtime post-processor update bug are different tokenizer behaviors." - }, - { - "left": "issue:44484", - "right": "issue:45310", - "accept": false, - "reason": "save_pretrained shard-size question is unrelated to Qwen3.5 from_pretrained failure." + "reason": "VRAM leak in multi-threaded Qwen3ForCausalLM use is unrelated to bfloat16 dtype mismatches in CI." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The umbrella issue choice for issue:45278 is supported by the titles, and the soft-edge verdicts generally avoid overclaiming. One minor wording issue: the reason for issue:43493 vs issue:45753 refers to both as Qwen bugs, but 43493 is SigLIP2-related; however, the verdict itself remains conservative." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -13127,9 +13170,10 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:38617", + "issue:39401", "issue:41628", "issue:42175", "issue:42222", @@ -13142,6 +13186,7 @@ "issue:43122", "issue:43335", "issue:43408", + "issue:43421", "issue:43441", "issue:43452", "issue:43577", @@ -13150,14 +13195,12 @@ "issue:43906", "issue:43931", "issue:43937", - "issue:43976", - "issue:43986", "issue:44038", "issue:44075", - "issue:44117", "issue:44220", "issue:44261", "issue:44263", + "issue:44291", "issue:44368", "issue:44410", "issue:44483", @@ -13166,12 +13209,12 @@ "issue:44493", "issue:44496", "issue:44829", - "issue:44945", "issue:44964", "issue:44977", - "issue:44987", "issue:45071", + "issue:45216", "issue:45278", + "issue:45310", "issue:45459", "issue:45464", "issue:45478", @@ -13179,6 +13222,11 @@ "issue:45656" ], "soft_pairs": [ + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071", + "issue:39401|issue:43421", + "issue:44484|issue:45310", "issue:43408|issue:43742", "issue:42222|issue:45542", "issue:43937|issue:44496", @@ -13205,233 +13253,242 @@ "issue:42673|issue:43906", "issue:43931|issue:44038", "issue:43335|issue:45071", - "issue:43097|issue:43452", "issue:43874|issue:44263", - "issue:43408|issue:44368", - "issue:44117|issue:44987", - "issue:43976|issue:44945", - "issue:43986|issue:44484" + "issue:43097|issue:43452", + "issue:43408|issue:44368" ], - "prepared_review_unit_hash": "bcacc9dbb4ec8fe8a783e41f95ca901be9d0e4efc8527bb008870b49a7f10e5c", + "prepared_review_unit_hash": "e888a5026589ed869387aaffcc17bd2c7838a0966d9aed36c21496fc4c3dc754", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 32, - "serialized_chars": 37104, - "estimated_input_tokens": 9276, - "estimated_eval_tokens": 18808 + "soft_pair_count": 34, + "serialized_chars": 37772, + "estimated_input_tokens": 9443, + "estimated_eval_tokens": 19142 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "No soft pair is strong enough to merge as a true duplicate. The cluster is mostly a loose collection of unrelated Transformers regressions and version-5 compatibility reports, with only a few broad thematic overlaps.", - "confidence": 0.85, - "canonical_issue_reason": "issue:45278 is the broadest representative of the cluster\u2019s version-upgrade/import-regression theme, so it is the most plausible umbrella issue among these reports.", + "summary": "This cluster is a loose mix of unrelated Transformers v5 regression reports: tokenizer behavior, model loading, config/API breakages, backend/package issues, and model-specific bugs. I did not find any soft edge that looks like a true duplicate; the best umbrella issue is the broad upgrade-regression report about many import errors after moving to 5.5.0.", + "confidence": 0.68, + "canonical_issue_reason": "issue:45278 is the broadest and most representative umbrella for this cluster\u2019s dominant theme: widespread breakages after upgrading to Transformers 5.x/5.5.0. It best captures the general regression pattern, even though the cluster is not a tight duplicate set.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best global representative because it is broad enough to subsume the import/error-after-upgrade subset, while most other items are narrower, model-specific, or unrelated.", + "best_issue_reason": "issue:45278 is the best global issue candidate because it is the most generic, upgrade-focused report and can serve as the nearest cluster representative for the many v5-related breakage reports.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Same broad Qwen3/Qwen3.5 area, but one is a missing projection issue and the other is a from_pretrained load error; not the same bug." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Different failure modes: one is flash-attention training degeneration, the other is incorrect save_pretrained checkpoint output." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized construction error is unrelated to PretrainedConfig type-checking behavior." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Tokenizer offset_mapping bug and runtime post-processor update bug are distinct tokenizer issues." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "max_shard_size behavior is unrelated to Qwen3.5 Moe from_pretrained loading failure." + }, { "left": "issue:43408", "right": "issue:43742", "accept": false, - "reason": "Different model families and different failure modes: a model-type warning vs a loading key error." + "reason": "A sam3_video vs sam3_tracker warning is not the same as the MobileLLM config key error." }, { "left": "issue:42222", "right": "issue:45542", "accept": false, - "reason": "VitPose model breakage and missing-TF backend packaging are unrelated subsystems." + "reason": "VitPose model breakage and missing TensorFlow backend from a torch-only install are different problems." }, { "left": "issue:43937", "right": "issue:44496", "accept": false, - "reason": "Both are load-time config errors, but one is invalid GenerationConfig and the other is an unrecognized model/config mismatch." + "reason": "Invalid GenerationConfig for GLM-5 and unknown-model loading for Olmo-Hybrid are unrelated." }, { "left": "issue:42175", "right": "issue:42222", "accept": false, - "reason": "Packaging/backend dependency issue versus a specific model breakage; not the same bug." + "reason": "Packaging/backend dependency issue is not the same as the VitPose model failure." }, { "left": "issue:44483", "right": "issue:45464", "accept": false, - "reason": "Same endpoint area, but one is a generic chat-completions rejection and the other is a streaming failure on a specific model." + "reason": "Both mention chat/completions, but one is a general API acceptance problem and the other is a specific streaming inference failure on Qwen3.5-0.8B." }, { "left": "issue:44964", "right": "issue:45278", "accept": false, - "reason": "Phi-4 multimodal loading failure is a model-specific bug, while 45278 is a broad import-regression report." + "reason": "Phi-4 multimodal loading failure is not the same as a broad import-error regression after upgrade." }, { "left": "issue:42371", "right": "issue:44261", "accept": false, - "reason": "TF32 configuration warning and MLA rms_norm_eps precision error are different numerical issues." + "reason": "TF32 control settings and MLA q_a_layernorm epsilon precision are different backend/numerics issues." }, { "left": "issue:44075", "right": "issue:45656", "accept": false, - "reason": "Both involve optimizers, but one says SGD args are ignored while the other says step() is called twice under DeepSpeed." + "reason": "SGD arguments being ignored is not the same as DeepSpeed causing optimizer.step() to run twice." }, { "left": "issue:43066", "right": "issue:43122", "accept": false, - "reason": "Both are tokenizer-related regressions, but one is a decoder-type mismatch and the other is a tokenization behavior change." + "reason": "Both are tokenizer regressions, but one is decoder type selection and the other is changed tokenization output." }, { "left": "issue:43012", "right": "issue:43577", "accept": false, - "reason": "Both mention precision/dtype, but one is a compile warning and the other is a BLIP2 dtype-loading bug." + "reason": "A PyTorch warning during bfloat16 compilation is unrelated to Blip2 dtype remaining float32." }, { "left": "issue:43874", "right": "issue:44261", "accept": false, - "reason": "Different code paths: multimodal token counting in an image processor versus a layernorm config precision issue." + "reason": "Missing get_number_of_image_patches is a different multimodal API bug than the RMS norm epsilon precision issue." }, { "left": "issue:44410", "right": "issue:45478", "accept": false, - "reason": "Different Qwen family bugs: missing projections in a layer versus a from_pretrained error." + "reason": "Different Qwen3.5-related failures: missing projections in qwen3next versus a from_pretrained load error." }, { "left": "issue:44484", "right": "issue:45478", "accept": false, - "reason": "Sharding-size question and Qwen3.5 loading error are unrelated." + "reason": "max_shard_size behavior is unrelated to the Qwen3.5 Moe load regression." }, { "left": "issue:38617", "right": "issue:44220", "accept": false, - "reason": "ImportError for a missing symbol and an audio feature extraction issue are not the same bug." + "reason": "ImportError for layer_type_validation and a _torch_extract_fbank_features issue are unrelated." }, { "left": "issue:44263", "right": "issue:44485", "accept": false, - "reason": "Both are GLM-related, but torch.split return handling and RoPE implementation are different internal defects." + "reason": "torch.split return values in GlmMoeDsaIndexer and GLM-5 RoPE implementation are different code-path bugs." }, { "left": "issue:43097", "right": "issue:44493", "accept": false, - "reason": "Both are v5 regressions, but one is a removed config flag and the other is unexpected position-id keys; not the same underlying change." + "reason": "API removal around tie_embeddings_and_encoder_decoder is not the same as unexpected position-id keys appearing." }, { "left": "issue:41628", "right": "issue:45071", "accept": false, - "reason": "Importing AutoImageProcessor and PretrainedConfig type-checking are distinct failure modes." + "reason": "AutoImageProcessor import failure and PretrainedConfig type checking are distinct regressions." }, { "left": "issue:43012", "right": "issue:43408", "accept": false, - "reason": "Precision warning on compile versus a model-type mismatch warning are unrelated." + "reason": "Compilation warning and model-type mismatch warning are unrelated." }, { "left": "issue:42222", "right": "issue:45459", "accept": false, - "reason": "VitPose model failure and hidden tokenizer errors from protobuf handling are different code paths." + "reason": "VitPose model breakage is not the same as tokenizer errors being masked when protobuf is missing." }, { "left": "issue:45071", "right": "issue:45542", "accept": false, - "reason": "Type-checking breakage in PretrainedConfig and undefined TF backend installation are unrelated." + "reason": "PretrainedConfig type checking regression and missing-TensorFlow backend packaging issue do not share the same underlying bug." }, { "left": "issue:43441", "right": "issue:44829", "accept": false, - "reason": "Both touch FlashAttention, but they describe different concrete bugs and likely different fixes." + "reason": "Both involve flash attention, but they affect different models and concrete failure modes; too broad to merge." }, { "left": "issue:42371", "right": "issue:42831", "accept": false, - "reason": "TF32 behavior control and FineGrainedFP8 accuracy are separate numerical-behavior issues." + "reason": "TF32 API guidance and FineGrainedFP8 accuracy loss are separate numerical issues." }, { "left": "issue:42673", "right": "issue:44977", "accept": false, - "reason": "VRAM leak in dataloader threads and Qwen3.5 flash-attention generation failure are different bugs." + "reason": "A multi-thread VRAM leak and a Qwen3.5 flash-attention generation problem are different bugs." }, { "left": "issue:42673", "right": "issue:43906", "accept": false, - "reason": "The second item is just a reproduction of another issue, not the same VRAM-leak problem." + "reason": "The isolated reproduction issue is not the same concrete bug as the VRAM leak in dataloader threads." }, { "left": "issue:43931", "right": "issue:44038", "accept": false, - "reason": "Both are Qwen3-VL loading issues, but the reported model variants and failures differ." + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-VL-Moe bug reports are related by family only, not the same defect." }, { "left": "issue:43335", "right": "issue:45071", "accept": false, - "reason": "A SwitchTransformers sparse-layer config bug is not the same as a PretrainedConfig typing regression." - }, - { - "left": "issue:43097", - "right": "issue:43452", - "accept": false, - "reason": "Removed config flag warning and gguf/AutoTokenizer loading breakage are distinct regressions." + "reason": "SwitchTransformers sparse-layer construction bug is unrelated to the PretrainedConfig type-checking regression." }, { "left": "issue:43874", "right": "issue:44263", "accept": false, - "reason": "Different GLM components and symptoms; image-patch counting is not the same as torch.split return handling." - }, - { - "left": "issue:43408", - "right": "issue:44368", - "accept": false, - "reason": "Both are warnings, but one is a model-type mismatch and the other is a tie_word_embeddings config warning." + "reason": "Missing image-patch-count method and torch.split return-value handling are different implementation bugs." }, { - "left": "issue:44117", - "right": "issue:44987", - "accept": false, - "reason": "Tokenizer-mapping None handling and loading a specific model package are not clearly the same bug." - }, - { - "left": "issue:43976", - "right": "issue:44945", + "left": "issue:43097", + "right": "issue:43452", "accept": false, - "reason": "Python-version support regression and pipeline-parallelism output corruption are unrelated." + "reason": "Tie-embeddings API removal and gguf_file loading failures are not the same issue." }, { - "left": "issue:43986", - "right": "issue:44484", + "left": "issue:43408", + "right": "issue:44368", "accept": false, - "reason": "Missing torchvision crash in AutoProcessor loading is unrelated to save_pretrained shard sizing." + "reason": "Model-type warning and tie_word_embeddings warning are different configuration warnings with different causes." } ] }, @@ -13453,7 +13510,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:38617", "issue:42617", @@ -13473,6 +13530,7 @@ "issue:43873", "issue:43906", "issue:43931", + "issue:43976", "issue:43986", "issue:43992", "issue:44038", @@ -13483,14 +13541,13 @@ "issue:44351", "issue:44368", "issue:44410", - "issue:44483", "issue:44484", "issue:44485", - "issue:44514", "issue:44655", "issue:44704", + "issue:44945", "issue:44964", - "issue:45071", + "issue:44987", "issue:45103", "issue:45200", "issue:45290", @@ -13504,6 +13561,9 @@ "issue:46050" ], "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43976|issue:44945", + "issue:43986|issue:44484", "issue:38617|issue:42757", "issue:43064|issue:44315", "issue:44410|issue:45375", @@ -13511,7 +13571,6 @@ "issue:44062|issue:44117", "issue:38617|issue:44351", "issue:43097|issue:45588", - "issue:44964|issue:45071", "issue:42673|issue:45200", "issue:44038|issue:44410", "issue:44704|issue:45103", @@ -13533,244 +13592,249 @@ "issue:45341|issue:45588", "issue:43208|issue:43550", "issue:43012|issue:43550", - "issue:43012|issue:44368", "issue:42886|issue:43381", + "issue:43012|issue:44368", "issue:42907|issue:45753", - "issue:42907|issue:44655", - "issue:44483|issue:44514" + "issue:42907|issue:44655" ], - "prepared_review_unit_hash": "fd1ef947585e743250a6b30299db87b1d3c7b2baf304c95e2aea7da2413e4352", + "prepared_review_unit_hash": "b84c391070b1dd4aeeca21800d7028e89c85f924440a35302e92bd3f2ab589b9", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, - "soft_pair_count": 34, - "serialized_chars": 37150, - "estimated_input_tokens": 9288, - "estimated_eval_tokens": 18832 + "soft_pair_count": 35, + "serialized_chars": 37419, + "estimated_input_tokens": 9355, + "estimated_eval_tokens": 18966 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "The soft links are overwhelmingly false positives: these issues span unrelated import errors, model-loading regressions, training/quantization problems, tokenizer/processor bugs, and testing-utils defects. There is no single underlying duplicate thread here.", - "confidence": 0.94, - "canonical_issue_reason": "No clear canonical issue: the candidates cover unrelated code paths and bug classes, so there isn\u2019t one issue that cleanly represents a duplicate cluster.", + "summary": "This cluster is very heterogeneous: it mostly contains unrelated Transformers issues that only share superficial similarity (imports, loading, quantization, model-family bugs). I found no soft-edge pair that looks like the same underlying bug/change.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 43873 is the broadest, most system-level report in the set and has the most discussion/references, but the cluster overall is not a true duplicate group.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45561 is the most triage-ready concrete bug report in the set, with a reproducible race condition and multiple inbound references, so it is the best anchor only in a weak representative sense.", + "best_issue_reason": "43873 is the best single representative only because it is broad and high-signal; the other issues are mostly narrow, model-specific, or unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Both involve tokenizer/loading behavior, but one is a generic mapping None bug and the other is a model load failure for a specific repo; not the same code-path." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility and pipeline-parallel output corruption are unrelated bugs." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor/torchvision crash is unrelated to max shard size behavior in save_pretrained." + }, { "left": "issue:38617", "right": "issue:42757", "accept": false, - "reason": "Different import failures from unrelated symbols/modules." + "reason": "Both are import errors, but they concern different missing symbols in different modules and do not look like one bug." }, { "left": "issue:43064", "right": "issue:44315", "accept": false, - "reason": "Both are training bugs, but one is FSDP/PEFT optimizer-state corruption and the other is Liger Kernel application." + "reason": "FSDP2/PEFT optimizer-state corruption and Liger Kernel not applied with model_init are different training issues." }, { "left": "issue:44410", "right": "issue:45375", "accept": false, - "reason": "Different Qwen model/config defects; no shared underlying code path." + "reason": "Different Qwen3-family model/config bugs; one is missing projections, the other is a config field being dropped." }, { "left": "issue:43097", "right": "issue:46050", "accept": false, - "reason": "One is a config/API removal warning, the other is a quantized save/load breakage." + "reason": "A removed embedding-tie API and quantization save/load breakage are distinct changes." }, { "left": "issue:44062", "right": "issue:44117", "accept": false, - "reason": "Tokenizer constructor error vs mapping lookup assumption; separate failures." + "reason": "AddedToken keyword conflict is unrelated to TOKENIZER_MAPPING_NAMES returning None." }, { "left": "issue:38617", "right": "issue:44351", "accept": false, - "reason": "Both are import errors, but for different missing exports in different modules." + "reason": "Different import failures for different symbols; no evidence of the same underlying breakage." }, { "left": "issue:43097", "right": "issue:45588", "accept": false, - "reason": "Different failure modes: config deprecation warning vs flash-attention crash on sink-less models." - }, - { - "left": "issue:44964", - "right": "issue:45071", - "accept": false, - "reason": "Model-loading failure for Phi-4 vs a PretrainedConfig type-checking regression." + "reason": "Embedding-tie deprecation/removal is unrelated to a flash_attention None-handling crash." }, { "left": "issue:42673", "right": "issue:45200", "accept": false, - "reason": "VRAM leak in multi-threaded dataloader use vs a missing text-only default field." + "reason": "VRAM leakage in multithreaded dataloading is unrelated to mm_token_type_ids defaults." }, { "left": "issue:44038", "right": "issue:44410", "accept": false, - "reason": "Different Qwen variants and different model components are involved." + "reason": "Different model families and different failure modes; too broad to merge." }, { "left": "issue:44704", "right": "issue:45103", "accept": false, - "reason": "AutoProcessor kwargs forwarding bug vs docstring parsing crash." + "reason": "Missing kwargs propagation in AutoProcessor is unrelated to the auto_docstring annotation crash." }, { "left": "issue:43931", "right": "issue:44410", "accept": false, - "reason": "Loading shape mismatch vs missing projections in a different Qwen family model." + "reason": "Weight-shape mismatch on model load is not the same as missing projections in qwen3next." }, { "left": "issue:43502", "right": "issue:43992", "accept": false, - "reason": "Offline/local file access bug vs missing encoder weights on load." + "reason": "Network access despite local_files_only and missing embed_tokens.weight are separate loading bugs." }, { "left": "issue:44261", "right": "issue:44485", "accept": false, - "reason": "RoPE precision/config warning vs a GLM-5 RoPE implementation issue." + "reason": "Precision-warning from missing rms_norm_eps is unrelated to GLM-5 RoPE implementation." }, { "left": "issue:44964", "right": "issue:45341", "accept": false, - "reason": "Phi-4 multimodal loading bug vs an unrelated testing_utils bug." + "reason": "A model-loading regression and a testing_utils bug are unrelated." }, { "left": "issue:45341", "right": "issue:45859", "accept": false, - "reason": "Testing utility bug vs rotary-embedding CPU offload incompatibility." + "reason": "Testing_utils bug and CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding are different code paths." }, { "left": "issue:43986", "right": "issue:44117", "accept": false, - "reason": "AutoProcessor/torchvision crash vs tokenizer mapping None handling." + "reason": "AutoProcessor/torchvision loading crash is unrelated to tokenizer mapping None handling." }, { "left": "issue:43097", "right": "issue:43873", "accept": false, - "reason": "Config deprecation/removal issue vs quantization offloading behavior." + "reason": "Embedding-tie API removal and quantization/offloading problems are not the same bug." }, { "left": "issue:43066", "right": "issue:43906", "accept": false, - "reason": "Wrong tokenizer decoder type vs an isolated reproduction of a different issue." + "reason": "Wrong tokenizer decoder type and an isolated reproduction of another issue do not match as the same defect." }, { "left": "issue:42617", "right": "issue:45341", "accept": false, - "reason": "3d_parallel.py failure and testing_utils bug are unrelated." + "reason": "3d_parallel.py runtime failure and a small testing_utils bug are unrelated." }, { "left": "issue:43986", "right": "issue:45290", "accept": false, - "reason": "Video-model loading crash vs chat-template crash with tool calls." + "reason": "Video-model AutoProcessor crash without torchvision is unrelated to apply_chat_template tool-call handling." }, { "left": "issue:43986", "right": "issue:45372", "accept": false, - "reason": "Video-model loading crash vs Gemma 4 processor import error." + "reason": "Missing torchvision and missing ReasoningEffort are different dependency/import problems." }, { "left": "issue:45341", "right": "issue:45561", "accept": false, - "reason": "Both mention testing utilities, but one is a generic bug and the other is a pytest-xdist race condition." + "reason": "A minor testing_utils issue and an xdist race condition are different bugs." }, { "left": "issue:43825", "right": "issue:44655", "accept": false, - "reason": "Pipeline translation error-message bug vs pipeline save_pretrained failure." + "reason": "Pipeline translation messaging and save_pretrained for Pipeline objects are unrelated." }, { "left": "issue:43986", "right": "issue:45341", "accept": false, - "reason": "Video processor crash vs a testing_utils bug." + "reason": "AutoProcessor loading crash and a testing_utils bug are not the same underlying issue." }, { "left": "issue:43992", "right": "issue:44484", "accept": false, - "reason": "Missing encoder weights vs a question about save_pretrained shard size." + "reason": "Missing embed_tokens.weight during model load is unrelated to the 50GB shard-size question." }, { "left": "issue:45341", "right": "issue:45588", "accept": false, - "reason": "Testing utility bug vs flash-attention AttributeError." + "reason": "Testing_utils bug and flash_attention s_aux=None crash are different subsystems and failures." }, { "left": "issue:43208", "right": "issue:43550", "accept": false, - "reason": "xLSTM training bugs vs Bamba torch.compile/SDPA failure." + "reason": "xLSTM training blockers and Bamba torch.compile/SDPA failure are separate model-specific problems." }, { "left": "issue:43012", "right": "issue:43550", "accept": false, - "reason": "Compile-time warning about bf16 precision vs a concrete compile failure in another model." + "reason": "A bfloat16 precision warning is not the same as a torch.compile SDPA failure." }, { - "left": "issue:43012", - "right": "issue:44368", + "left": "issue:42886", + "right": "issue:43381", "accept": false, - "reason": "Different warnings with different causes: bf16 precision vs tie_word_embeddings." + "reason": "Offline cache loading failure and gradient checkpointing in eval mode are unrelated." }, { - "left": "issue:42886", - "right": "issue:43381", + "left": "issue:43012", + "right": "issue:44368", "accept": false, - "reason": "Offline cache loading bug vs eval-mode gradient checkpointing restriction." + "reason": "The bfloat16 warning and tie_word_embeddings warning are different warnings with different causes." }, { "left": "issue:42907", "right": "issue:45753", "accept": false, - "reason": "Dequantized save failure vs an infinite-loop generation bug on a specific image." + "reason": "Saving dequantized Ministrals/Devstrals and Qwen3_5 infinite-loop on a specific image are unrelated." }, { "left": "issue:42907", "right": "issue:44655", "accept": false, - "reason": "Different save-related bugs in different subsystems." - }, - { - "left": "issue:44483", - "right": "issue:44514", - "accept": false, - "reason": "Chat-completions endpoint rejection vs batched chat-template crash." + "reason": "Saving dequantized models and saving Pipeline objects are different save_pretrained limitations." } ] }, @@ -13792,7 +13856,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:36010", "issue:36683", @@ -13820,7 +13884,6 @@ "issue:43901", "issue:43906", "issue:43937", - "issue:43976", "issue:44038", "issue:44220", "issue:44222", @@ -13830,6 +13893,7 @@ "issue:44380", "issue:44483", "issue:44485", + "issue:44514", "issue:44625", "issue:44655", "issue:44683", @@ -13840,12 +13904,14 @@ "issue:45440", "issue:45478", "issue:45753", - "issue:46077" + "issue:46077", + "issue:46082" ], "soft_pairs": [ + "issue:44483|issue:44514", "issue:44222|issue:45478", - "issue:43208|issue:43526", "issue:42490|issue:43012", + "issue:43208|issue:43526", "issue:43012|issue:44683", "issue:42757|issue:43824", "issue:44038|issue:44230", @@ -13866,236 +13932,248 @@ "issue:44220|issue:44655", "issue:43756|issue:44485", "issue:44625|issue:46077", + "issue:46077|issue:46082", "issue:36683|issue:43525", "issue:43618|issue:45216", "issue:44263|issue:45440", "issue:43906|issue:45753", "issue:36683|issue:44242", - "issue:36683|issue:43881", "issue:43299|issue:45753", - "issue:43901|issue:46077", - "issue:43352|issue:43976" + "issue:36683|issue:43881", + "issue:43901|issue:46077" ], - "prepared_review_unit_hash": "bd5e619bf044e85ecd7ded4fc56768650495ac386e2fa00a8603504d80dfff6d", + "prepared_review_unit_hash": "49d2e48c5262daf1811b506f3e1d66203ee4c339d6cd369052b59afc8af58391", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 47, - "item_count": 47, - "soft_pair_count": 32, - "serialized_chars": 36247, - "estimated_input_tokens": 9062, - "estimated_eval_tokens": 18380 + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37166, + "estimated_input_tokens": 9292, + "estimated_eval_tokens": 18840 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly heterogeneous: the soft-linked issues span unrelated import errors, model-specific config bugs, saving/loading regressions, tokenizer behavior changes, and attention/mask problems. I do not see a duplicate-grade canonical issue or PR, and I would reject all soft edges as distinct bugs/changes.", - "confidence": 0.86, + "summary": "This cluster is a broad mix of unrelated Transformers bugs and regressions (imports, model config attrs, chat templating, quantization/saving, MoE, CLIP, Gemma, Qwen, etc.). None of the proposed soft pairs look like the same underlying bug/change, so they should remain separate.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:44222", - "right": "issue:45478", + "left": "issue:44483", + "right": "issue:44514", "accept": false, - "reason": "Same model family, but one is FP8 save_pretrained failure and the other is from_pretrained loading error; different operations and likely different fixes." + "reason": "Both involve chat-related failures, but one is /v1/chat/completions request handling and the other is batched apply_chat_template with padding=False; different code paths and bugs." }, { - "left": "issue:43208", - "right": "issue:43526", + "left": "issue:44222", + "right": "issue:45478", "accept": false, - "reason": "xLSTM training bugs and a BeitImageProcessorFast label-reduction bug are unrelated subsystems with different symptoms." + "reason": "Both mention MoE/FP8, but one is save_pretrained failure and the other is from_pretrained/load error; not the same concrete defect." }, { "left": "issue:42490", "right": "issue:43012", "accept": false, - "reason": "Local path import-warning behavior and a bfloat16 compile warning are different code paths and different bugs." + "reason": "One is a local path import warning, the other is a PyTorch float32 precision warning during bfloat16 compilation; unrelated." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "Completely different subsystems: xLSTM training bugs versus BeitImageProcessorFast label reduction." }, { "left": "issue:43012", "right": "issue:44683", "accept": false, - "reason": "Both involve compilation, but one is a warning and the other is a hard flex_attention failure on newer torch; not the same bug." + "reason": "Both are compilation-related, but one is a warning about bfloat16 precision and the other is a hard flex_attention failure on torch>=2.9; different issues." }, { "left": "issue:42757", "right": "issue:43824", "accept": false, - "reason": "Both are import errors, but for different symbols from different packages; no shared underlying change is evident." + "reason": "Both are import errors, but for different symbols and different dependency breakages." }, { "left": "issue:44038", "right": "issue:44230", "accept": false, - "reason": "Qwen3-VL-Moe loading bug and fp8 inference support are separate issues, not one concrete defect." + "reason": "Both touch Qwen3-VL/MoE/fp8, but one is a general v5 loading bug and the other is FP8 inference support; not the same bug." }, { "left": "issue:38617", "right": "issue:43502", "accept": false, - "reason": "Missing import from configuration_utils and unexpected network requests with local_files_only=True are unrelated failures." + "reason": "Different failures: missing configuration_utils import versus local_files_only still triggering network calls." }, { "left": "issue:44483", "right": "issue:45290", "accept": false, - "reason": "Chat-completions request rejection and a chat-template crash with tool calls are different layers and different failure modes." + "reason": "Both are chat API/template problems, but one is request acceptance and the other is assistant tool-call serialization; not mergeable as one bug." }, { "left": "issue:43618", "right": "issue:43761", "accept": false, - "reason": "Both are CLIP regressions, but one concerns attentions and the other hidden_states; that is too broad to treat as the same concrete bug." + "reason": "Both are CLIP regressions, but one loses attentions while the other returns hidden_states=None; distinct outputs and code paths." }, { "left": "issue:43064", "right": "issue:44380", "accept": false, - "reason": "FSDP2/PEFT optimizer-state corruption and GPT2 attention-scaling being ignored are unrelated issues." + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is unrelated to GPT2 attention scaling being ignored in SDPA/FlashAttention." }, { "left": "issue:43299", "right": "issue:43867", "accept": false, - "reason": "Both are loading failures, but one is a Qwen3.5/VL model regression and the other is about sorted state_dict loading; different root causes." + "reason": "Qwen3VL-MoE loading failure and a sorted-state_dict load error are different load-time bugs." }, { "left": "issue:44483", "right": "issue:45381", "accept": false, - "reason": "An API request rejection and a Qwen2.5-VL video position-id bug are unrelated." + "reason": "Different model/API layers: chat/completions request rejection versus Qwen2.5-VL video vision_position_ids bug." }, { "left": "issue:43901", "right": "issue:44655", "accept": false, - "reason": "Docs mentioning return_all_scores and inability to save Pipeline objects are different problems." + "reason": "Docs mismatch for return_all_scores is unrelated to saving Pipeline objects with save_pretrained." }, { "left": "issue:36683", "right": "issue:43475", "accept": false, - "reason": "Missing Gemma3Config.vocab_size and missing Sam3VisionEncoderOutput.fpn_position_embeddings are different model-specific attribute bugs." + "reason": "Missing Gemma3Config.vocab_size and missing Sam3VisionEncoderOutput.fpn_position_embeddings are unrelated attribute bugs." }, { "left": "issue:42994", "right": "issue:44655", "accept": false, - "reason": "Quantized model save_pretrained failure and pipeline save_pretrained failure affect different objects and code paths." + "reason": "Both involve saving, but quantized model saving and Pipeline.save_pretrained are different failure modes." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Audio feature extraction bug versus pipeline serialization bug; no shared underlying defect." }, { "left": "issue:45276", "right": "issue:46077", "accept": false, - "reason": "Gemma4 embedding resize behavior and Gemma4 bidirectional-attention masking are distinct model behaviors." + "reason": "Gemma4 resize_token_embeddings propagation bug and Gemma4 bidirectional-attention masking bug affect different code paths." }, { "left": "issue:43352", "right": "issue:43937", "accept": false, - "reason": "Flash Attention support gating and invalid GenerationConfig validation are unrelated." + "reason": "Nemotron FlashAttention2 support error and GLM-5 invalid GenerationConfig are unrelated model-specific issues." }, { "left": "issue:43867", "right": "issue:45216", "accept": false, - "reason": "A state_dict-sorting load error and a Qwen3.5 save_pretrained regression do not point to the same underlying bug." + "reason": "Different load/save regressions: a sorted state_dict load error versus incorrect Qwen3.5 checkpoint saving." }, { "left": "issue:36010", "right": "issue:42757", "accept": false, - "reason": "Both are import errors, but they concern different missing names from different modules." + "reason": "Both are import errors, but for different APIs and different dependency symbols." }, { "left": "issue:42898", "right": "issue:43066", "accept": false, - "reason": "Tokenizer cleanup behavior changes and wrong tokenizer decoder type are both tokenizer regressions, but not the same concrete defect." + "reason": "clean_up_tokenization_spaces behavior change and wrong tokenizer decoder type are separate tokenizer regressions." }, { "left": "issue:44220", "right": "issue:44655", "accept": false, - "reason": "An audio feature-extraction bug and pipeline save_pretrained support are unrelated." + "reason": "Audio feature extraction issue does not match pipeline save_pretrained failure." }, { "left": "issue:43756", "right": "issue:44485", "accept": false, - "reason": "Smollm3 RoPE-layer mismatch and GLM-5 RoPE implementation concerns are different models and different bugs." + "reason": "Both reference RoPE, but one is Smollm3 layer drop and the other is GLM-5 RoPE implementation; not the same bug." }, { "left": "issue:44625", "right": "issue:46077", "accept": false, - "reason": "Qwen3.5 num_labels propagation and Gemma4 attention-mask construction are unrelated model behaviors." + "reason": "num_labels propagation and Gemma4 attention masking are unrelated." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Gemma4 causal-mask bug and LlamaConfig head_dim validation are different config/attention issues." }, { "left": "issue:36683", "right": "issue:43525", "accept": false, - "reason": "Both are missing-config-attribute reports, but for different models and different fields; not the same bug." + "reason": "Both are missing config attributes, but they concern different models and different fields." }, { "left": "issue:43618", "right": "issue:45216", "accept": false, - "reason": "Missing CLIP attentions and Qwen3.5 save_pretrained regression are unrelated." + "reason": "CLIP attentions regression and Qwen3.5 checkpoint save corruption are unrelated." }, { "left": "issue:44263", "right": "issue:45440", "accept": false, - "reason": "A torch.split return-value issue in a GLM MoE indexer and DeepSeekV3 MoE divergence are different code paths." + "reason": "Different MoE implementations and different symptoms: torch.split indexing issue versus DeepseekV3MoE divergence." }, { "left": "issue:43906", "right": "issue:45753", "accept": false, - "reason": "A reproduction of another issue and a Qwen3_5 infinite-loop report are not the same underlying bug." + "reason": "An isolated reproduction of an earlier issue and a Qwen3_5 infinite loop on a specific image are not the same bug." }, { "left": "issue:36683", "right": "issue:44242", "accept": false, - "reason": "A missing Gemma3Config attribute and a load-balancing-loss omission in MoE are unrelated." - }, - { - "left": "issue:36683", - "right": "issue:43881", - "accept": false, - "reason": "Gemma3Config.vocab_size and glm-4v loading failure are different model-specific issues." + "reason": "Missing Gemma3Config.vocab_size is unrelated to load balancing loss not being added when output_router_logits=False." }, { "left": "issue:43299", "right": "issue:45753", "accept": false, - "reason": "Both involve Qwen models, but one is a loading failure and the other is a generation infinite loop; different defects." + "reason": "Qwen3VL-MoE loading failure and Qwen3_5 image infinite loop are different defects." }, { - "left": "issue:43901", - "right": "issue:46077", + "left": "issue:36683", + "right": "issue:43881", "accept": false, - "reason": "Pipeline documentation mismatch and Gemma4 attention-mask behavior are unrelated." + "reason": "Different models and failures: Gemma3Config missing field versus glm-4v-9b loading failure." }, { - "left": "issue:43352", - "right": "issue:43976", + "left": "issue:43901", + "right": "issue:46077", "accept": false, - "reason": "Flash Attention support and Python version compatibility are unrelated problems." + "reason": "Docs mismatch for return_all_scores is unrelated to Gemma4 attention-mask behavior." } ] }, @@ -14117,7 +14195,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:28282", "issue:33453", @@ -14125,6 +14203,7 @@ "issue:36683", "issue:41669", "issue:42490", + "issue:42548", "issue:42890", "issue:43064", "issue:43097", @@ -14143,6 +14222,7 @@ "issue:44117", "issue:44222", "issue:44246", + "issue:44351", "issue:44355", "issue:44360", "issue:44380", @@ -14156,7 +14236,6 @@ "issue:44977", "issue:45125", "issue:45310", - "issue:45335", "issue:45341", "issue:45357", "issue:45375", @@ -14165,16 +14244,15 @@ "issue:45479", "issue:45561", "issue:45588", - "issue:45600", - "issue:46077" + "issue:45600" ], "soft_pairs": [ + "issue:43352|issue:43976", "issue:43992|issue:45310", "issue:43441|issue:44380", - "issue:45335|issue:46077", "issue:43352|issue:44380", - "issue:44355|issue:44855", "issue:44380|issue:45479", + "issue:44355|issue:44855", "issue:43867|issue:45375", "issue:43352|issue:45478", "issue:41669|issue:44246", @@ -14189,253 +14267,248 @@ "issue:43064|issue:44655", "issue:36296|issue:43575", "issue:42490|issue:44075", - "issue:28282|issue:33453", "issue:44360|issue:45440", + "issue:28282|issue:33453", "issue:43867|issue:44484", "issue:43618|issue:44857", "issue:43618|issue:44977", "issue:43618|issue:45588", "issue:44655|issue:44938", - "issue:43901|issue:44938", "issue:42890|issue:44964", + "issue:43901|issue:44938", "issue:42890|issue:44112", "issue:42890|issue:45600", "issue:43502|issue:44062", "issue:42890|issue:45341", - "issue:44222|issue:45125" + "issue:44222|issue:45125", + "issue:42548|issue:44351" ], - "prepared_review_unit_hash": "76bae3fe2591e2b518770d366b56a4ece984269c0e2ecf101c0207699ca5b30a", + "prepared_review_unit_hash": "07ae4759806a643e45420961bf85253691081511d2bc3fee7c4d07f0e6c4c7cd", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 48, "item_count": 48, - "soft_pair_count": 34, - "serialized_chars": 37499, - "estimated_input_tokens": 9375, - "estimated_eval_tokens": 19006 + "soft_pair_count": 35, + "serialized_chars": 37754, + "estimated_input_tokens": 9439, + "estimated_eval_tokens": 19134 }, "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 (loading, flash-attention, tensor parallelism, tests, docs, Python-version regressions). The only obvious near-duplicate signal is the Qwen3.5 MoE from_pretrained error family, but none of the provided soft pairs are true duplicates.", - "confidence": 0.42, - "canonical_issue_reason": "Issue 45310 is the strongest anchor: it is a concrete model-loading regression, has discussion activity, and is echoed by the later same-title issue 45478, which suggests a real duplicate family.", + "summary": "This cluster is very noisy and spans several unrelated themes: import/export regressions, model loading failures, FlashAttention/backend issues, tensor-parallel/training bugs, and flaky tests. I did not find any soft pair that is clearly the same underlying bug/change, so all soft edges should be rejected.", + "confidence": 0.94, + "canonical_issue_reason": "issue:42548 is the clearest representative of the import/export regression thread, which is one of the few repeated themes in the cluster.", "canonical_pr_reason": null, - "best_issue_reason": "45310 is the best representative issue in this set because it is specific, actionable, and clearly tied to a reproducible code-path bug rather than a broad symptom, test flake, or docs-only complaint.", + "best_issue_reason": "issue:42548 is the best global issue anchor here because it is a concrete, user-facing API break and fits the broad import/load subset better than the other candidates.", "best_pr_reason": null, "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Both are runtime/load problems, but one is a FlashAttention 2 support error and the other is a Python-version load failure; different bugs." + }, { "left": "issue:43992", "right": "issue:45310", "accept": false, - "reason": "Different models and failure modes: missing embed_tokens.weight in UMT5Encoder vs Qwen3.5 MoE from_pretrained error." + "reason": "Different models and failures: missing embed_tokens weight vs Qwen3.5 MoE from_pretrained error." }, { "left": "issue:43441", "right": "issue:44380", "accept": false, - "reason": "Both involve FlashAttention/SDPA, but one is a model-specific failure and the other is attention-scaling config being ignored; not the same bug." - }, - { - "left": "issue:45335", - "right": "issue:46077", - "accept": false, - "reason": "resize_token_embeddings not updating decoder.embed_tokens is unrelated to Gemma4 building causal masks for bidirectional attention." + "reason": "Both mention attention backends, but one is a model-specific FlashAttention crash and the other is GPT-2 attention scaling being ignored." }, { "left": "issue:43352", "right": "issue:44380", "accept": false, - "reason": "Unsupported FlashAttention 2.0 on one model is not the same as GPT2 ignoring attention scaling config under SDPA/FlashAttention." + "reason": "Same broad attention area, but the concrete bug is different: unsupported FlashAttention vs ignored scaling config." }, { - "left": "issue:44355", - "right": "issue:44855", + "left": "issue:44380", + "right": "issue:45479", "accept": false, - "reason": "General compiled-Python-file loading errors differ from a specific Python 3.13 torch.jit.script parsing/IndentationError issue." + "reason": "Attention-backend regression vs sequence-classification zero-loss bug; unrelated code paths." }, { - "left": "issue:44380", - "right": "issue:45479", + "left": "issue:44355", + "right": "issue:44855", "accept": false, - "reason": "Attention backend behavior on GPT2 is unrelated to a sequence-classification zero-loss bug." + "reason": "Both fail at import time, but one is about compiled Python files and the other is a torch.jit/script parsing issue on Python 3.13." }, { "left": "issue:43867", "right": "issue:45375", "accept": false, - "reason": "State-dict sorting load failure is unrelated to a missing config field being dropped by @strict." + "reason": "Model load error from sorted state_dict vs a missing Qwen3.5 vision config field; not the same issue." }, { "left": "issue:43352", "right": "issue:45478", "accept": false, - "reason": "FlashAttention unsupported on Nemotron is unrelated to Qwen3.5 MoE from_pretrained failing." + "reason": "FlashAttention support error vs Qwen3.5 MoE from_pretrained regression; different models and symptoms." }, { "left": "issue:41669", "right": "issue:44246", "accept": false, - "reason": "Import-* cleanup/perf work is not the same underlying bug as intermittent import-transformers slowness." + "reason": "Both concern import slowness, but one is a specific import-* cleanup performance issue and the other is only a generic symptom report." }, { "left": "issue:43618", "right": "issue:44380", "accept": false, - "reason": "CLIPOutput attentions assignment regression is unrelated to GPT2 attention scaling under backend changes." + "reason": "CLIPOutput attentions assignment regression vs GPT-2 attention scaling being ignored; not the same defect." }, { "left": "issue:36683", "right": "issue:44117", "accept": false, - "reason": "Missing vocab_size on Gemma3Config is a different problem from TOKENIZER_MAPPING_NAMES returning None." + "reason": "Gemma3Config missing vocab_size and TOKENIZER_MAPPING_NAMES returning None are different loading/metadata bugs." }, { "left": "issue:42890", "right": "issue:45561", "accept": false, - "reason": "Both are test failures, but one is seed-related flakiness and the other is an xdist race on captured_info.txt." + "reason": "Both are test/CI related, but one is missing set_seed in a model integration test and the other is a xdist file race." }, { "left": "issue:43064", "right": "issue:44492", "accept": false, - "reason": "Optimizer-state corruption in FSDP2/PEFT is unrelated to a typo in cache strategy docs/code." + "reason": "FSDP2/PEFT optimizer-state bug vs a cache-strategy typo; unrelated." }, { "left": "issue:43097", "right": "issue:43352", "accept": false, - "reason": "Removed tie_embeddings_and_encoder_decoder API is unrelated to FlashAttention support on a specific model." + "reason": "Removed tie_embeddings_and_encoder_decoder API vs FlashAttention support failure; different changes." }, { "left": "issue:43867", "right": "issue:45357", "accept": false, - "reason": "Sorting-related load error is not the same as saving incorrect visual encoder keys in Qwen3.5." + "reason": "State_dict sorting load error vs incorrect visual encoder keys saved by Qwen3.5; different save/load problems." }, { "left": "issue:43976", "right": "issue:44938", "accept": false, - "reason": "Both mention Python versions, but they describe different version-specific load failures." + "reason": "Both are version-specific load failures, but the Python versions and root causes differ." }, { "left": "issue:43992", "right": "issue:45478", "accept": false, - "reason": "Missing embed_tokens.weight in UMT5Encoder is unrelated to the Qwen3.5 MoE from_pretrained regression." + "reason": "Missing embed_tokens weight vs Qwen3.5 MoE from_pretrained error; not the same bug." }, { "left": "issue:43064", "right": "issue:44655", "accept": false, - "reason": "Training optimizer-state bugs do not match a save_pretrained Pipeline-object serialization issue." + "reason": "Trainer optimizer-state corruption vs Pipeline.save_pretrained support; unrelated." }, { "left": "issue:36296", "right": "issue:43575", "accept": false, - "reason": "Tensor-parallel training bug on one setup is not the same as OOM when loading a specific Qwen2 model with tp." + "reason": "Both involve tensor parallelism, but one is a training bug and the other is an OOM during loading." }, { "left": "issue:42490", "right": "issue:44075", "accept": false, - "reason": "Local-path import warnings are unrelated to SGD arguments being ignored." + "reason": "Local-files-only import warning vs SGD args not being used; unrelated." }, { - "left": "issue:28282", - "right": "issue:33453", + "left": "issue:44360", + "right": "issue:45440", "accept": false, - "reason": "Missing PyTorch environment error is unrelated to tokenizer loading regression." + "reason": "DSA indexer/ReLU discussion vs DeepSeekV3MoE implementation divergence; different subsystems." }, { - "left": "issue:44360", - "right": "issue:45440", + "left": "issue:28282", + "right": "issue:33453", "accept": false, - "reason": "DSA indexer ReLU issue is unrelated to DeepseekV3MoE diverging from remote implementation." + "reason": "AutoModel PyTorch ImportError vs tokenizer-loading regression; both are loading-related but not the same bug." }, { "left": "issue:43867", "right": "issue:44484", "accept": false, - "reason": "State-dict ordering load failures are unrelated to the default 50GB shard size question." + "reason": "Model load failure vs a question about default shard size; not duplicates." }, { "left": "issue:43618", "right": "issue:44857", "accept": false, - "reason": "CLIPOutput attentions regression is unrelated to an AMP/CUDA crash in LwDetrImageLoss." + "reason": "Attentions field regression vs LwDetrImageLoss AMP crash; unrelated." }, { "left": "issue:43618", "right": "issue:44977", "accept": false, - "reason": "CLIPOutput attentions assignment and Qwen3.5 flash-attention generation failure are different code paths." + "reason": "CLIPOutput attentions regression vs Qwen3.5 flash-attention generation bug; different models and failures." }, { "left": "issue:43618", "right": "issue:45588", "accept": false, - "reason": "Missing CLIPOutput attentions is not the same as s_aux=None crashing flash_attention.py." + "reason": "Attentions assignment regression vs flash_attention.py crash on s_aux=None; different code paths." }, { "left": "issue:44655", "right": "issue:44938", "accept": false, - "reason": "Pipeline save_pretrained support is unrelated to Python 3.14 import/load failures." + "reason": "Pipeline save_pretrained issue vs Python 3.14 load failure; unrelated." }, { - "left": "issue:43901", - "right": "issue:44938", + "left": "issue:42890", + "right": "issue:44964", "accept": false, - "reason": "Docs still mentioning return_all_scores is unrelated to a runtime load failure on Python 3.14." + "reason": "Flaky integration test vs Phi-4 multimodal model loading failure; unrelated." }, { - "left": "issue:42890", - "right": "issue:44964", + "left": "issue:42548", + "right": "issue:44351", "accept": false, - "reason": "Test seed flakiness is unrelated to Phi-4 multimodal failing to load on latest transformers." + "reason": "Both are import-name errors, but they concern different missing top-level symbols and do not clearly share one root cause." }, { "left": "issue:42890", "right": "issue:44112", "accept": false, - "reason": "Seed-related test flakiness is not the same as stale device override behavior in CI." + "reason": "Both are test failures, but one is missing seeding and the other is a stale device override assertion; different bugs." }, { - "left": "issue:42890", - "right": "issue:45600", + "left": "issue:44222", + "right": "issue:45125", "accept": false, - "reason": "A flaky model test is unrelated to auto_mappings referencing removed Sam3LiteText configs." + "reason": "FP8 save_pretrained on MoE vs missing _tp_plan for tensor parallelism; related area, but not the same concrete bug." }, { "left": "issue:43502", "right": "issue:44062", "accept": false, - "reason": "Local_files_only still making API requests is unrelated to AddedToken receiving duplicate special arguments." + "reason": "local_files_only network leak vs AddedToken keyword collision; completely different issues." }, { "left": "issue:42890", "right": "issue:45341", "accept": false, - "reason": "A missing set_seed in integration tests is unrelated to a bug in testing_utils.py." - }, - { - "left": "issue:44222", - "right": "issue:45125", - "accept": false, - "reason": "FP8 save_pretrained for MoE is unrelated to a missing _tp_plan for tensor parallelism." + "reason": "Flaky test seeding issue vs a small testing_utils bug; no shared underlying defect." } ] }, @@ -14457,7 +14530,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:30333", "issue:30990", @@ -14485,7 +14558,6 @@ "issue:44230", "issue:44261", "issue:44315", - "issue:44351", "issue:44355", "issue:44360", "issue:44368", @@ -14509,7 +14581,6 @@ "issue:45850" ], "soft_pairs": [ - "issue:42548|issue:44351", "issue:43502|issue:44485", "issue:44355|issue:44749", "issue:45125|issue:45478", @@ -14550,178 +14621,172 @@ "issue:44261|issue:44360", "issue:44623|issue:45230" ], - "prepared_review_unit_hash": "e6223158ab7dfe0c48fce5d97ef1e9d50f909aeeaba8eeea0a18c4bc683e3b80", + "prepared_review_unit_hash": "9f2f25554db55fd6bd7206615a8f801ab2474716e340e49567f73601b4b19bc1", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { - "node_count": 48, - "item_count": 48, - "soft_pair_count": 40, - "serialized_chars": 39106, - "estimated_input_tokens": 9777, - "estimated_eval_tokens": 19810 + "node_count": 47, + "item_count": 47, + "soft_pair_count": 39, + "serialized_chars": 38255, + "estimated_input_tokens": 9564, + "estimated_eval_tokens": 19384 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a loose collection of Transformers v5-era regressions (import/loading, quantization, tensor-parallel, docs), not one tight duplicate set. The best umbrella issue is the broad \"many import errors after update\" report; only the Qwen3.5 MoE loading/tensor-parallel pair looks like the same concrete bug.", - "confidence": 0.49, - "canonical_issue_reason": "issue:45278 is the broadest and most representative umbrella: it explicitly captures multiple import regressions after upgrading to v5.5.0, which aligns with several of the nearby import-failure reports.", + "summary": "This cluster is mostly heterogeneous, with many unrelated Transformers v5 regression reports, import/load failures, docs issues, and a few model-specific bugs. None of the soft-pair candidates look like safe duplicates based on titles alone, so I would keep them split.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 45278 is the best umbrella issue here: it captures the broad v5 upgrade regression pattern with concrete import/load breakage, which matches the dominant theme across the cluster better than the more vague or highly specific reports.", "canonical_pr_reason": null, - "best_issue_reason": "issue:45278 is the best global representative because it is concrete, broad enough to absorb related import/export breakages, and directly describes the version-upgrade regression theme seen in the cluster.", + "best_issue_reason": "Issue 45278 is the most suitable representative because it is broad enough to anchor the cluster while still describing a concrete symptom class (import errors after upgrading), unlike the very generic open-ended complaints.", "best_pr_reason": null, "soft_edge_verdicts": [ - { - "left": "issue:42548", - "right": "issue:44351", - "accept": false, - "reason": "Both are import errors, but they target different symbols and no shared concrete code-path is evident." - }, { "left": "issue:43502", "right": "issue:44485", "accept": false, - "reason": "One is about unwanted API calls with local_files_only; the other is a GLM-5 RoPE implementation issue." + "reason": "One is about unexpected network access with local_files_only; the other is a GLM-5 RoPE implementation bug. Different code paths and symptoms." }, { "left": "issue:44355", "right": "issue:44749", "accept": false, - "reason": "Compiled Python-file errors and post-upgrade slowdown are different failure modes." + "reason": "Running compiled Python files vs slower filtering after upgrading are unrelated problems." }, { "left": "issue:45125", "right": "issue:45478", - "accept": true, - "reason": "Both point to the same Qwen3.5 MoE loading/tensor-parallel regression on newer Transformers versions." + "accept": false, + "reason": "Both touch Qwen3.5 MoE loading, but one is tensor-parallel _tp_plan support and the other is a general from_pretrained error; too different to merge confidently." }, { "left": "issue:30990", "right": "issue:31795", "accept": false, - "reason": "A loading hang and documentation confusion are unrelated." + "reason": "A loading hang in Sentence Transformers and confusing forward docs are not the same underlying bug." }, { "left": "issue:45125", "right": "issue:45375", "accept": false, - "reason": "Missing _tp_plan during loading is a different bug from a config field being silently dropped." + "reason": "Tensor-parallel plan support and a missing config field in Qwen3.5MoeVisionConfig are distinct issues." }, { "left": "issue:30333", "right": "issue:33453", "accept": false, - "reason": "MLFlow reporting after failed training and tokenizer loading regression are unrelated." + "reason": "MLFlow reporting on failed training jobs is unrelated to tokenizer loading regression." }, { "left": "issue:44387", "right": "issue:44556", "accept": false, - "reason": "Int4 memory/OOM behavior and checkpoint reload compatibility are different problems." + "reason": "Int4 memory/OOM behavior and checkpoint reload failures after upgrade are different failure modes." }, { "left": "issue:43010", "right": "issue:45278", "accept": false, - "reason": "Cache update no_grad semantics and broad import errors do not share the same bug." + "reason": "Decorating cache/layer update with no_grad is unrelated to broad import errors after a version upgrade." }, { "left": "issue:43723", "right": "issue:44556", "accept": false, - "reason": "Tokenizer loading and checkpoint reloading touch different code paths." + "reason": "Tokenizer loading in v5 and reloading old checkpoints after upgrade are both load-related but not the same concrete bug." }, { "left": "issue:42831", "right": "issue:43874", "accept": false, - "reason": "FP8 accuracy and a missing image-patch API are not the same issue." + "reason": "FineGrainedFP8 accuracy and a missing image-processor method are separate model/runtime issues." }, { "left": "issue:43502", "right": "issue:44222", "accept": false, - "reason": "Unexpected API requests and FP8 save_pretrained behavior are unrelated." + "reason": "Unexpected hub/API requests and FP8 save_pretrained for MoE are unrelated." }, { "left": "issue:43010", "right": "issue:44368", "accept": false, - "reason": "No-grad decoration on cache updates is not the same as a tied-embeddings warning." + "reason": "Cache update no_grad behavior and a tie_word_embeddings warning are not the same bug." }, { "left": "issue:43502", "right": "issue:44961", "accept": false, - "reason": "A local_files_only networking leak and an unrelated placeholder issue are not duplicates." + "reason": "The title 'racoon' gives no evidence of the same bug; it is unrelated to local_files_only network access." }, { "left": "issue:43010", "right": "issue:45850", "accept": false, - "reason": "A specific cache-update bug is far narrower than a vague \"breaks too many models\" complaint." + "reason": "A generic complaint that v5 breaks many models is too broad and not the same concrete issue as cache/layer update semantics." }, { "left": "issue:44315", "right": "issue:44360", "accept": false, - "reason": "Liger Kernel application and a DSA indexer ReLU issue are unrelated." + "reason": "Applying Liger Kernel via model_init and a missing ReLU in DSA indexer are unrelated." }, { "left": "issue:44355", "right": "issue:45071", "accept": false, - "reason": "Compiled-file runtime errors and PretrainedConfig type-checking are different bugs." + "reason": "Compiled-file runtime errors and PretrainedConfig type checking breakage are distinct regressions." }, { "left": "issue:30333", "right": "issue:36296", "accept": false, - "reason": "MLFlow failure reporting and tensor-parallel training are unrelated." + "reason": "MLFlow failure reporting and tensor-parallel training bugs do not share an underlying code path." }, { "left": "issue:43827", "right": "issue:44961", "accept": false, - "reason": "Docs still referencing pipeline() and a placeholder issue are not the same change." + "reason": "Docs referencing removed pipeline APIs and an unrelated 'racoon' issue are not duplicates." }, { "left": "issue:44355", "right": "issue:44655", "accept": false, - "reason": "Compiled Python-file errors are unrelated to saving Pipeline objects." + "reason": "Compiled Python file errors and inability to save Pipeline objects are separate save/load problems." }, { "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; too different to merge." + "reason": "FP8 save_pretrained for MoE and FP8 inference support for Qwen3-VL/Qwen3.5 MoE are adjacent but not the same fix." }, { "left": "issue:43299", "right": "issue:44556", "accept": false, - "reason": "Qwen3VL MoE loading and v4-to-v5 checkpoint reload issues are different concrete failures." + "reason": "Both are model-loading regressions, but for different model families and likely different root causes." }, { "left": "issue:33453", "right": "issue:34689", "accept": false, - "reason": "Tokenizer-loading regression and a specific Llama 3.2 Vision loading breakage are not the same bug." + "reason": "Tokenizer loading regression and Llama 3.2 Vision model loading failure are not clearly the same bug." }, { "left": "issue:42757", "right": "issue:43576", "accept": false, - "reason": "A missing huggingface_hub symbol and a broken env command are not the same underlying issue." + "reason": "An import error from huggingface_hub and a broken transformers env CLI command are different symptoms." }, { "left": "issue:33453", @@ -14729,81 +14794,108 @@ "accept": false, "reason": "Tokenizer loading and tensor-parallel training are unrelated." }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Decorating update methods with no_grad is unrelated to optimizer step being called twice under deepspeed." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken env CLI and PretrainedConfig type checking are separate regressions." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "CLI env command breakage and a specific model import error do not match." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion in model.forward is unrelated to an ImportError for layer_type_validation." + }, { "left": "issue:44961", "right": "issue:45468", "accept": false, - "reason": "Placeholder racoon issue and Gemma audio positional encoding are unrelated." + "reason": "The generic 'racoon' issue provides no basis for matching Gemma-4 audio positional encoding bugs." }, { "left": "issue:41628", "right": "issue:42548", "accept": false, - "reason": "Both are top-level import errors, but they concern different exported symbols and no single concrete bug is established." + "reason": "Both are import errors, but for different symbols and likely different import paths; too broad to treat as one bug." }, { "left": "issue:43010", "right": "issue:43976", "accept": false, - "reason": "Cache update no-grad behavior and Python version support are unrelated." + "reason": "Cache no_grad behavior and Python version compatibility are unrelated." }, { "left": "issue:38617", "right": "issue:43576", "accept": false, - "reason": "Missing layer_type_validation import and a broken env command are not the same issue." + "reason": "An internal import symbol missing and the env CLI being broken are different issues." }, { "left": "issue:43576", "right": "issue:44938", "accept": false, - "reason": "Broken env command and Python 3.14 loading failure are different regressions." + "reason": "Broken env command and Python 3.14 loading failure are not the same underlying problem." }, { "left": "issue:44908", "right": "issue:44961", "accept": false, - "reason": "Scheduler kwargs being ignored has nothing to do with the placeholder issue." + "reason": "Scheduler kwargs being ignored and the unrelated 'racoon' issue are not duplicates." }, { "left": "issue:36296", "right": "issue:43901", "accept": false, - "reason": "Tensor-parallel training bug and documentation about text classification outputs are unrelated." + "reason": "Tensor-parallel training bug and stale pipeline docs are unrelated." }, { "left": "issue:41628", "right": "issue:44355", "accept": false, - "reason": "Importing AutoImageProcessor and compiled-Python-file errors are different failures." + "reason": "Importing AutoImageProcessor and compiled-file errors are different failure modes." }, { "left": "issue:36296", "right": "issue:43526", "accept": false, - "reason": "Tensor-parallel training and BeitImageProcessorFast label reduction are unrelated." + "reason": "Tensor-parallel training and BeitImageProcessorFast reduce_labels behavior are unrelated." }, { "left": "issue:44261", "right": "issue:44360", "accept": false, - "reason": "MLA layernorm precision and a missing ReLU in the DSA indexer are unrelated." + "reason": "A precision issue in MLA q_a_layernorm and a missing ReLU in DSA indexer are completely different bugs." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files from processor.save_pretrained and a vague bug report title are not enough to identify the same issue." }, { "left": "issue:44623", "right": "issue:45230", "accept": false, - "reason": "Missing processor save_pretrained files is not the same as a generic bug report." + "reason": "Same pair as above; no evidence they refer to the same concrete bug." } ] }, - "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: it correctly treats the cluster as a loose mix of v5-era regressions and uses issue:45278 as a broad umbrella for the import-regression subgroup. The soft-edge decisions are generally conservative, and the one accepted pair (issue:45125 vs issue:45478) is at least plausibly the same Qwen3.5 MoE loading/tensor-parallel regression based on the titles." - }, - "evaluator_used": true, + "evaluator_result": null, + "evaluator_used": false, "retried": false, - "accepted_nontrivial_soft_edge": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -14818,7 +14910,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:31795", "issue:33453", @@ -14875,17 +14967,17 @@ "issue:44038|issue:45125", "issue:43576|issue:44556", "issue:44393|issue:45071", + "issue:44373|issue:44961", "issue:41669|issue:43673", "issue:43525|issue:45850", - "issue:44373|issue:44961", "issue:44556|issue:45092", "issue:45362|issue:45850", "issue:43572|issue:45850", - "issue:44704|issue:44908", "issue:42890|issue:44908", + "issue:44704|issue:44908", "issue:44246|issue:44273", - "issue:43408|issue:44315", "issue:43976|issue:44393", + "issue:43408|issue:44315", "issue:44297|issue:45230", "issue:43352|issue:44393", "issue:44295|issue:45230", @@ -14900,8 +14992,8 @@ "issue:44077|issue:44861", "issue:43827|issue:44908", "issue:41669|issue:44492", - "issue:41669|issue:44908", "issue:31795|issue:33453", + "issue:41669|issue:44908", "issue:44315|issue:44829", "issue:42371|issue:44492", "issue:43576|issue:44273", @@ -14911,290 +15003,287 @@ "issue:44273|issue:44908", "issue:44492|issue:45850" ], - "prepared_review_unit_hash": "204fc5fde89535200f9451aa3b5705c821ab75b321a923cfda5ba1018d475ab9", + "prepared_review_unit_hash": "6c1d03fbe7108b078f541bbcae217c95ae543ffb45b8dd9897b10a14d7ce66e7", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 47, "item_count": 47, "soft_pair_count": 41, - "serialized_chars": 38712, - "estimated_input_tokens": 9678, - "estimated_eval_tokens": 19612 + "serialized_chars": 38714, + "estimated_input_tokens": 9679, + "estimated_eval_tokens": 19614 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of unrelated v5 regressions and model-specific bugs. The only clearly accepted duplicate is the import/lazy-loading pair issue:44246 \u2194 issue:44273; the Qwen3.5-related pairs remain too specific or differ in failure mode to merge as duplicates.", - "confidence": 0.78, - "canonical_issue_reason": "issue:44273 is the broadest open report for the lazy-loading/import regression theme, and it best serves as the umbrella issue for the one confirmed duplicate pair.", + "summary": "This cluster is a loose mix of v5-era import/lazy-loading regressions, model-specific config bugs, and unrelated docs/tests issues. The soft edges look like thematic similarity, not true duplicates, so none should be merged.", + "confidence": 0.66, + "canonical_issue_reason": "issue:44273 is the clearest umbrella for the import/lazy-loading regression theme that appears most often here, even though the cluster overall is heterogeneous.", "canonical_pr_reason": null, - "best_issue_reason": "issue:44273 is the strongest single reference point for the import/lazy-loading cluster because it is open and covers the broad user-visible symptom.", + "best_issue_reason": "issue:44273 is the best representative issue among the set because it is broad enough to cover the shared loading/import theme without collapsing unrelated model/config bugs.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44273", "right": "issue:45542", "accept": false, - "reason": "Both are import-related symptoms, but one is lazy loading/import timing and the other is TensorFlow/tensorboard backend behavior; not the same bug." + "reason": "Both involve loading/runtime behavior, but one is lazy loading and the other is a TF backend/import environment error; different code paths." }, { "left": "issue:44273", "right": "issue:45003", "accept": false, - "reason": "Related to imports, but one is lazy-loading regression and the other is unsafe sys.modules access; different root causes." + "reason": "Related to loading/imports, but one is a generic lazy-loading failure and the other is a specific sys.modules access bug; not the same concrete defect." }, { "left": "issue:44393", "right": "issue:45753", "accept": false, - "reason": "Same model family, but different concrete failures: 2D bbox hallucination/error versus an infinite-loop case." + "reason": "Same model family, but one is 2D bbox output errors and the other is an infinite loop on a specific image; different symptoms and fixes." }, { "left": "issue:44038", "right": "issue:45125", "accept": false, - "reason": "Both mention Qwen/MoE, but one is a broad bug report and the other is a specific missing _tp_plan tensor-parallel issue." + "reason": "Different Qwen3.5/VL model issues: one is a bug report for Qwen3-VL-Moe, the other is missing _tp_plan for tensor parallelism." }, { "left": "issue:43576", "right": "issue:44556", "accept": false, - "reason": "Both are v5-related, but the broken env command and checkpoint reload incompatibility are distinct problems." + "reason": "One is a broken CLI command, the other is checkpoint reload compatibility after upgrade; distinct failures." }, { "left": "issue:44393", "right": "issue:45071", "accept": false, - "reason": "Qwen3-VL output issues and PretrainedConfig type-checking are unrelated code paths." + "reason": "A model output bug and a PretrainedConfig typing regression are unrelated code paths." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "A docstring typo and a placeholder issue title are not the same bug." }, { "left": "issue:41669", "right": "issue:43673", "accept": false, - "reason": "Import-star cleanup/performance and chunked-prefill cache behavior are different defects." + "reason": "Import-star cleanup/performance and missing GenerationMixin cache in chunked_prefill are different changes." }, { "left": "issue:43525", "right": "issue:45850", "accept": false, - "reason": "A specific Llama4Config attribute error is not the same as a broad 'many models break' report." - }, - { - "left": "issue:44373", - "right": "issue:44961", - "accept": false, - "reason": "Docstring wording and a placeholder 'racoon' issue are unrelated." + "reason": "Model-specific pad_token_id error versus a broad complaint that many models break after v5; too vague to be duplicates." }, { "left": "issue:44556", "right": "issue:45092", "accept": false, - "reason": "Both concern upgrade breakage, but the loading/reload failures are on different paths and are not clearly duplicates." + "reason": "Both are upgrade compatibility problems, but they affect different model-loading paths and different checkpoints." }, { "left": "issue:45362", "right": "issue:45850", "accept": false, - "reason": "Specific Qwen3.5 chat crash versus a generic broad regression report; not the same underlying bug." + "reason": "Specific chat crash for Qwen3.5-35B versus a generic 'many models' complaint; not the same issue." }, { "left": "issue:43572", "right": "issue:45850", "accept": false, - "reason": "StableLmConfig missing pad_token_id is a specific config regression, not the same as a generic many-model breakage report." + "reason": "StableLmConfig pad_token_idx regression is a specific model config bug, not the broad v5 breakage claim." }, { - "left": "issue:44704", + "left": "issue:42890", "right": "issue:44908", "accept": false, - "reason": "AutoProcessor cached_file kwargs and scheduler lr_scheduler_kwargs are separate APIs and failures." + "reason": "Missing set_seed in tests and an inverse_sqrt scheduler kwarg bug are unrelated." }, { - "left": "issue:42890", + "left": "issue:44704", "right": "issue:44908", "accept": false, - "reason": "Test flakiness from missing set_seed is unrelated to scheduler keyword handling." + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs handling are separate subsystems." }, { "left": "issue:44246", "right": "issue:44273", - "accept": true, - "reason": "These describe the same import/lazy-loading regression from different angles: slow import behavior and lazy loading not working properly." - }, - { - "left": "issue:43408", - "right": "issue:44315", "accept": false, - "reason": "Model-type mismatch warning and Liger Kernel/model_init behavior are unrelated." + "reason": "Both concern imports, but one is intermittent import slowness and the other is broken lazy loading; not the same concrete defect." }, { "left": "issue:43976", "right": "issue:44393", "accept": false, - "reason": "Python version compatibility and Qwen3-VL output failure are different defects." + "reason": "Python version support regression and a Qwen3-VL output bug do not share a code path." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type warning during instantiation versus Liger Kernel application with model_init are unrelated." }, { "left": "issue:44297", "right": "issue:45230", "accept": false, - "reason": "Tokenizer metadata mismatch and a generic bug placeholder do not indicate the same bug." + "reason": "Tokenizer save_pretrained mismatch and a vague bug report title are not duplicates." }, { "left": "issue:43352", "right": "issue:44393", "accept": false, - "reason": "Different model families and different failures: Nemotron Flash Attention support versus Qwen3-VL output behavior." + "reason": "Flash Attention 2.0 support error for NemotronH and a Qwen3-VL bounding-box bug are different model issues." }, { "left": "issue:44295", "right": "issue:45230", "accept": false, - "reason": "A position_ids buffer-read error is unrelated to a generic placeholder bug report." + "reason": "A position_ids buffer error and a generic bug report are not the same underlying bug." }, { "left": "issue:43576", "right": "issue:44908", "accept": false, - "reason": "The env command regression and inverse_sqrt scheduler kwargs issue are separate problems." + "reason": "CLI env command breakage and scheduler kwarg handling are unrelated." }, { "left": "issue:44908", "right": "issue:45071", "accept": false, - "reason": "Scheduler kwargs handling and PretrainedConfig type checking are distinct code paths." + "reason": "Scheduler kwargs and PretrainedConfig type checking are separate concerns." }, { "left": "issue:41669", "right": "issue:44351", "accept": false, - "reason": "Import-star cleanup/performance and a HybridCache import error are not the same defect." + "reason": "Import-star usage cleanup and inability to import HybridCache are both import-related but not the same bug." }, { "left": "issue:41669", "right": "issue:45341", "accept": false, - "reason": "Import-performance regression and a testing_utils bug are unrelated." + "reason": "Import cleanup/performance and a testing_utils bug are unrelated." }, { "left": "issue:43673", "right": "issue:44492", "accept": false, - "reason": "Generation cache missing during chunked prefill and a cache-strategy typo are not the same bug." + "reason": "Generation cache missing in chunked_prefill and a cache-strategy typo are different issues." }, { "left": "issue:45278", "right": "issue:45850", "accept": false, - "reason": "A broad upgrade/import-error report is not the same as a generic 'many models break' complaint." + "reason": "Specific post-upgrade import errors versus a broad claim that many models break are too nonspecific to be duplicates." }, { "left": "issue:43874", "right": "issue:45850", "accept": false, - "reason": "GLM46V multimodal token handling is unrelated to the broad v5 breakage report." + "reason": "A GLM46V multimodal tokenization bug is not the same as a generic v5 breakage report." }, { "left": "issue:44393", "right": "issue:45478", "accept": false, - "reason": "Both are Qwen3.5/Qwen-related, but the concrete failures differ and are not clearly the same bug." + "reason": "Different Qwen model families and different failure modes." }, { "left": "issue:44077", "right": "issue:44861", "accept": false, - "reason": "Optional post_init validation and _tied_weights_keys list handling are different issues." + "reason": "PatchTSMixer post_init validation and tied-weight key handling are unrelated." }, { "left": "issue:43827", "right": "issue:44908", "accept": false, - "reason": "Docs still mentioning pipeline() and scheduler kwargs handling are unrelated." + "reason": "Docs still referencing pipeline() and scheduler kwargs handling are not the same change." }, { "left": "issue:41669", "right": "issue:44492", "accept": false, - "reason": "Import-star cleanup/performance and a cache-strategy typo are unrelated." + "reason": "Import-star cleanup and cache-strategy typo are unrelated." }, { - "left": "issue:41669", - "right": "issue:44908", + "left": "issue:31795", + "right": "issue:33453", "accept": false, - "reason": "Import-time performance regression and scheduler kwargs handling are different code paths." + "reason": "Documentation confusion about forward arguments and tokenizer loading regression are distinct." }, { - "left": "issue:31795", - "right": "issue:33453", + "left": "issue:41669", + "right": "issue:44908", "accept": false, - "reason": "Docstring confusion and tokenizer-loading regression are unrelated." + "reason": "Import performance cleanup and scheduler kwargs handling are unrelated." }, { "left": "issue:44315", "right": "issue:44829", "accept": false, - "reason": "Liger Kernel with model_init and flash_attention_3 degenerate training are different bugs." + "reason": "Liger Kernel not being applied with model_init and flash_attention_3 causing degenerate training are different training bugs." }, { "left": "issue:42371", "right": "issue:44492", "accept": false, - "reason": "TF32 API guidance and cache-strategy typo are unrelated." + "reason": "TF32 API guidance and a cache-strategy typo are unrelated." }, { "left": "issue:43576", "right": "issue:44273", "accept": false, - "reason": "Both are v5/import related, but the env command regression and lazy-loading failure are not clearly the same root cause." + "reason": "A broken env command and lazy loading failure may both be version-related, but they are different code paths." }, { "left": "issue:44360", "right": "issue:45468", "accept": false, - "reason": "DSA indexer discussion and Gemma-4 audio positional encoding are unrelated." + "reason": "A DSA indexer discussion and a Gemma-4 audio positional encoding bug are unrelated." }, { "left": "issue:44655", "right": "issue:44861", "accept": false, - "reason": "Saving Pipeline objects and tied-weight key handling are different defects." + "reason": "Pipeline save_pretrained failure and _tied_weight_keys attribute handling are different bugs." }, { "left": "issue:45230", "right": "issue:45310", "accept": false, - "reason": "A generic placeholder issue and a concrete Qwen3.5 Moe from_pretrained error are not evidence of duplication." + "reason": "A vague placeholder title and a specific Qwen3.5 Moe from_pretrained error are not duplicates." }, { "left": "issue:44273", "right": "issue:44908", "accept": false, - "reason": "Lazy-loading/import regression and scheduler kwargs handling are separate code paths." + "reason": "Lazy loading/import behavior and scheduler kwargs are unrelated." }, { "left": "issue:44492", "right": "issue:45850", "accept": false, - "reason": "A typo in cache strategies is not the same as a broad model-breakage report." + "reason": "A typo in cache strategies and a broad v5 breakage complaint are not the same underlying issue." } ] }, - "evaluator_result": { - "accept": false, - "feedback": "The overall clustering is mostly conservative, but the summary overstates the evidence by claiming a true duplicate Qwen3.5-MoE from_pretrained pair that is not supported by the packet\u2019s soft-edge verdicts. In the packet, the only clearly accepted soft edge is issue:44246 \u2194 issue:44273; the Qwen3.5-related pairs are all marked false. The lazy-loading/import pair is a plausible umbrella match, but the summary should not elevate unsupported duplicates." - }, - "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": true, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -15209,7 +15298,7 @@ "source": "llm", "cache_hit": false, "model": "gpt-5.4-mini?service_tier=flex", - "cluster_id": "cluster-10000-408", + "cluster_id": "cluster-10000-409", "nodes": [ "issue:30333", "issue:31515", @@ -15265,8 +15354,8 @@ "issue:44908|issue:44998", "issue:44861|issue:45290", "issue:43525|issue:44861", - "issue:43704|issue:44998", "issue:41669|issue:44998", + "issue:43704|issue:44998", "issue:43572|issue:44861", "issue:43066|issue:44998", "issue:31515|issue:38617", @@ -15279,226 +15368,226 @@ "issue:31515|issue:33453", "issue:43298|issue:44230" ], - "prepared_review_unit_hash": "9f78da31f9ffaa2b037e9c581efa3edf64e6d9fa4d3dba02f32cb5b83220136e", + "prepared_review_unit_hash": "0b3e6286efe31bb85ce5dff8aff1d4fb1bf20473c13f06bd7903b5064d3cb0b7", "component_budget": { - "node_count": 408, - "item_count": 408, - "soft_pair_count": 1526, - "serialized_chars": 787332, - "estimated_input_tokens": 196833, - "estimated_eval_tokens": 393922 + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 }, "budget": { "node_count": 33, "item_count": 33, "soft_pair_count": 32, - "serialized_chars": 28207, - "estimated_input_tokens": 7052, - "estimated_eval_tokens": 14360 + "serialized_chars": 28209, + "estimated_input_tokens": 7053, + "estimated_eval_tokens": 14362 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is dominated by soft-similarity false positives across unrelated issues. No pair looks like a true duplicate; the closest thematic area is tokenizer-v5 regression reports, but even those are not the same concrete bug.", - "confidence": 0.41, - "canonical_issue_reason": "Issue 43066 is the most concrete and actionable report among the few tokenizer-v5-adjacent items, but the cluster overall does not have a clear true duplicate anchor.", + "summary": "These soft links are mostly spurious: the issues span unrelated bugs in loading, tokenizers, configs, schedulers, processors, and model internals. I would not merge any of the candidate pairs as duplicates.", + "confidence": 0.86, + "canonical_issue_reason": "No reliable canonical issue emerges here; the similarity links connect unrelated bug classes and subsystems rather than one underlying defect.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 43066 is the best representative of the narrowest recurring theme here (tokenizer behavior regressions in v5), though it is still not a match for most of the cluster.", + "best_issue_reason": "No issue is a safe duplicate hub. Issue 43519 has the most soft links, but those neighbors are not true duplicates of its timestamp-calculation bug.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43519", "right": "issue:44485", "accept": false, - "reason": "Qwen3VL processor timestamp bug vs GLM-5 RoPE implementation; different models and different code paths." + "reason": "Different bugs: Qwen3VL timestamp parsing vs GLM-5 RoPE implementation." }, { "left": "issue:43519", "right": "issue:44908", "accept": false, - "reason": "Processor timestamp calculation vs scheduler kwargs handling; unrelated subsystems." + "reason": "Processor timestamp logic vs lr_scheduler kwargs handling; unrelated code paths." }, { "left": "issue:41669", "right": "issue:43704", "accept": false, - "reason": "Import-* cleanup/perf issue vs VRAM leak in dataloader threads; not the same bug." + "reason": "Import-star cleanup/perf work vs a VRAM leak in Qwen3ForCausalLM; not the same bug." }, { "left": "issue:31795", "right": "issue:34689", "accept": false, - "reason": "Documentation confusion in model.forward vs model-loading regression for Llama 3.2; unrelated." + "reason": "Documentation confusion in model.forward vs a model-loading regression; different problems." }, { "left": "issue:31795", "right": "issue:37428", "accept": false, - "reason": "Forward API docs issue vs flash-attention import error; different problems." + "reason": "Docs issue vs an ImportError from flash-attention utils; unrelated." }, { "left": "issue:44315", "right": "issue:45092", "accept": false, - "reason": "Liger Kernel not applied with model_init vs remote-code meta-init incompatibility; different init bugs." + "reason": "Liger Kernel application bug vs remote-code/meta-init incompatibility; different failure modes." }, { "left": "issue:44485", "right": "issue:45468", "accept": false, - "reason": "GLM-5 RoPE implementation vs Gemma-4 audio positional encoding; different models and fixes." + "reason": "GLM-5 RoPE implementation vs Gemma-4 audio positional encoding; unrelated models/features." }, { "left": "issue:43704", "right": "issue:44485", "accept": false, - "reason": "VRAM leak in Qwen3 multi-threading vs RoPE implementation issue; unrelated." + "reason": "VRAM leak in multi-threaded loading vs RoPE implementation; not the same defect." }, { "left": "issue:43502", "right": "issue:43519", "accept": false, - "reason": "Local-files-only still triggering API requests vs processor timestamp math; unrelated download vs processing behavior." + "reason": "local_files_only network access bug vs Qwen3VL timestamp calculation; different subsystems." }, { "left": "issue:42371", "right": "issue:43704", "accept": false, - "reason": "TF32 settings behavior vs VRAM leak; no shared concrete bug." + "reason": "TF32 behavior/settings issue vs a VRAM leak; unrelated." }, { "left": "issue:43519", "right": "issue:44623", "accept": false, - "reason": "Both involve processors, but one is timestamp calculation and the other is save_pretrained file output; different failures." + "reason": "Timestamp calculation bug vs missing processor save_pretrained files; different code paths." }, { "left": "issue:43519", "right": "issue:43704", "accept": false, - "reason": "Processor timestamp bug vs VRAM leak; unrelated." + "reason": "Qwen3VL timestamp bug vs Qwen3ForCausalLM VRAM leak; not the same issue." }, { "left": "issue:44263", "right": "issue:45468", "accept": false, - "reason": "torch.split return handling in an indexer vs Gemma-4 audio positional encoding; unrelated." + "reason": "torch.split return-value issue in GlmMoeDsaIndexer vs Gemma-4 audio positional encoding." }, { "left": "issue:43606", "right": "issue:45468", "accept": false, - "reason": "CPU offload device mismatch vs Gemma-4 audio encoding; unrelated." + "reason": "CPU offload device mismatch vs Gemma-4 audio positional encoding; unrelated." }, { "left": "issue:44261", "right": "issue:45468", "accept": false, - "reason": "MLA layernorm precision error vs Gemma-4 audio positional encoding; unrelated." + "reason": "MLA layernorm epsilon/config precision bug vs Gemma-4 audio positional encoding." }, { "left": "issue:42913", "right": "issue:43066", "accept": false, - "reason": "Both are tokenizer-v5 related, but one is a broad behavior change report and the other is a specific decoder-type bug; not clearly the same concrete issue." + "reason": "Both involve tokenizer v5 behavior, but one is a broad regression report and the other is a specific decoder-type issue; too vague to treat as the same bug." }, { "left": "issue:44908", "right": "issue:44998", "accept": false, - "reason": "Scheduler kwargs bug vs unrelated 'Unemployment' issue; obviously different." + "reason": "Scheduler kwargs bug vs an unrelated placeholder issue." }, { "left": "issue:44861", "right": "issue:45290", "accept": false, - "reason": "Tied-weights helper crash vs chat template crash with tool calls; different code paths." + "reason": "_get_tied_weight_keys AttributeError vs apply_chat_template crash with tool calls; different code paths." }, { "left": "issue:43525", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_id on Llama4Config vs tied-weights key crash; unrelated model/config bugs." + "reason": "Missing pad_token_id in Llama4Config vs tied-weight-key AttributeError; unrelated." }, { - "left": "issue:43704", + "left": "issue:41669", "right": "issue:44998", "accept": false, - "reason": "VRAM leak vs unrelated issue title; not a duplicate." + "reason": "Import-star cleanup/perf issue vs an unrelated placeholder issue." }, { - "left": "issue:41669", + "left": "issue:43704", "right": "issue:44998", "accept": false, - "reason": "Import-* performance cleanup vs unrelated issue title; not a duplicate." + "reason": "VRAM leak issue vs an unrelated placeholder issue." }, { "left": "issue:43572", "right": "issue:44861", "accept": false, - "reason": "Missing pad_token_idx in StableLmConfig vs tied-weights key crash; different failures." + "reason": "StableLmConfig pad_token_idx bug vs tied-weight-key crash; different surfaces." }, { "left": "issue:43066", "right": "issue:44998", "accept": false, - "reason": "Tokenizer v5 decoder-type bug vs unrelated issue title; not a duplicate." + "reason": "Tokenizer decoder-type regression vs an unrelated placeholder issue." }, { "left": "issue:31515", "right": "issue:38617", "accept": false, - "reason": "Slow checkpoint loading vs ImportError for layer_type_validation; different issues." + "reason": "Slow checkpoint loading vs ImportError for layer_type_validation; unrelated." }, { "left": "issue:44230", "right": "issue:44623", "accept": false, - "reason": "FP8 support request vs processor.save_pretrained missing files; feature request vs bug." + "reason": "FP8 support request vs processor save_pretrained missing files; not the same bug." }, { "left": "issue:44360", "right": "issue:44998", "accept": false, - "reason": "DSA indexer activation issue vs unrelated issue title; not a duplicate." + "reason": "DSA indexer/ReLU discussion vs an unrelated placeholder issue." }, { "left": "issue:30333", "right": "issue:31515", "accept": false, - "reason": "MLflow reporting on failed training jobs vs slow from_pretrained checkpoint loading; unrelated." + "reason": "MLflow reporting failure vs from_pretrained slowness; different problems." }, { "left": "issue:31515", "right": "issue:36296", "accept": false, - "reason": "Slow checkpoint loading vs tensor-parallel training bug; different symptoms and paths." + "reason": "Checkpoint loading performance vs tensor-parallel training bug; unrelated." }, { "left": "issue:44230", "right": "issue:45310", "accept": false, - "reason": "FP8 support request vs Qwen3.5-MoE from_pretrained error; one is feature support, the other is a loading regression." + "reason": "FP8 inference support issue vs Qwen3.5 MoE from_pretrained error; different concrete bugs." }, { "left": "issue:31515", "right": "issue:31795", "accept": false, - "reason": "Checkpoint loading slowdown vs forward-API documentation confusion; unrelated." + "reason": "Loading slowdown vs documentation confusion; not the same issue." }, { "left": "issue:31515", "right": "issue:33453", "accept": false, - "reason": "Both mention loading, but one is slow checkpoint load and the other is a tokenizer loading regression; not the same bug." + "reason": "from_pretrained loading speed vs tokenizer-loading regression; different symptoms and subsystems." }, { "left": "issue:43298", "right": "issue:44230", "accept": false, - "reason": "Continuous batching not supporting audio models vs FP8 infer support for Qwen3-VL/Qwen3.5 MoE; different features." + "reason": "Continuous batching audio-model support vs FP8 support for Qwen3-VL/Qwen3.5; unrelated feature requests." } ] }, @@ -15530,7 +15619,7 @@ "issue:13244|issue:16618", "issue:15980|issue:16618" ], - "prepared_review_unit_hash": "4a6087315dd1fc9e9dd375a78133de7cbbef4dbbd398f8981e9ab2d0eeca5623", + "prepared_review_unit_hash": "b6bbdf41709ef675980f88d18f9830bb442178d8539aea2d827f77f16f5d669e", "component_budget": { "node_count": 3, "item_count": 3, @@ -15552,24 +15641,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three issues are not duplicates: one is about TAPAS tokenization, one is about private-model download/auth messaging, and one is about loading bert-base-uncased. The soft similarities are too broad to merge.", - "confidence": 0.89, - "canonical_issue_reason": "No single canonical duplicate stands out. Issue #16618 is the broadest user-facing model-load failure, but #13244 is a tokenizer mismatch and #15980 is a private-model login/error-message problem, so they are distinct.", + "summary": "These issues are not duplicates of one another: one is about Tapas tokenization behavior, one about an authentication/download error for private models, and one about loading bert-base-uncased. They share only vague model-loading similarity.", + "confidence": 0.93, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "#16618 is the most general and concrete model-loading symptom, so it is the best single issue to anchor triage if one must be chosen, but it should not absorb the others as duplicates.", + "best_issue_reason": "No single issue cleanly represents a duplicate cluster here; if forced, #16618 is the broadest, but it is still not a duplicate of the others.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:13244", "right": "issue:16618", "accept": false, - "reason": "Different problem domains: TAPAS tokenization vs failing to load bert-base-uncased. No evidence of the same code path or fix." + "reason": "Different underlying problem: Tapas tokenization mismatch vs a generic model-load failure for bert-base-uncased; no shared code-path or concrete fix target." }, { "left": "issue:15980", "right": "issue:16618", "accept": false, - "reason": "Both concern model access/loading, but one is specifically a private-model login/download error and the other is a public-model load failure. Too different to treat as the same bug." + "reason": "#15980 is specifically about a bad error message when downloading a private model while logged out, whereas #16618 is a model loading failure for a public model; related area but not the same bug." } ] }, @@ -15599,12 +15688,12 @@ "soft_pairs": [ "issue:26350|issue:33260" ], - "prepared_review_unit_hash": "87edf6d247bfb30ea96758225f4abc89e86732b65c25710776d03d208652be93", + "prepared_review_unit_hash": "f65f1aa5f23acbf02e6934960197294ccf274d493ce81a31bad5c20c96471597", "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 }, @@ -15612,7 +15701,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1589, + "serialized_chars": 1590, "estimated_input_tokens": 398, "estimated_eval_tokens": 1052 }, @@ -15621,18 +15710,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two distinct community contribution feature requests in the same format, not duplicates: one for Flash Attention 2 architecture support and one for GGUF architecture support.", - "confidence": 0.97, - "canonical_issue_reason": "No canonical issue: the titles and likely work items are different feature requests targeting different capabilities.", + "summary": "These are not duplicates: one issue tracks Flash Attention 2 support for more architectures, the other tracks GGUF support for more architectures. They concern different features and likely different code paths.", + "confidence": 0.98, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "Neither issue should be treated as the duplicate representative because they describe separate enhancements rather than the same underlying problem.", + "best_issue_reason": "Neither issue is a strong canonical representative for the cluster because the underlying requests are different. If forced, issue 26350 has slightly more discussion, but it is not the same topic as 33260.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:26350", "right": "issue:33260", "accept": false, - "reason": "Different requested features (Flash Attention 2 vs GGUF support) with no indication they are the same underlying change or bug." + "reason": "Reject: these request different kinds of model support (Flash Attention 2 vs GGUF) and do not describe the same underlying bug or change." } ] }, @@ -15674,12 +15763,12 @@ "issue:43834|issue:44365", "issue:44365|issue:44370" ], - "prepared_review_unit_hash": "86cb838903f2618602e3e5e8bd375367818f9b89ce217007bb7bf542c7c1d204", + "prepared_review_unit_hash": "a69fd6b8d56fefb22a6126202f6726047dba34733285fac21e2b18b15203eadc", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 10, - "serialized_chars": 6441, + "serialized_chars": 6443, "estimated_input_tokens": 1611, "estimated_eval_tokens": 3478 }, @@ -15687,7 +15776,7 @@ "node_count": 5, "item_count": 5, "soft_pair_count": 10, - "serialized_chars": 6441, + "serialized_chars": 6443, "estimated_input_tokens": 1611, "estimated_eval_tokens": 3478 }, @@ -15696,79 +15785,82 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are all docs-translation request issues, but the concrete-language ones are for different locales and the templated ones do not provide enough evidence to treat them as the same underlying request. No soft duplicate edges should be merged.", - "confidence": 0.88, - "canonical_issue_reason": "issue:43834 is the closest thing to a cluster representative because it uses the normalized template title and is nearly identical in form to the other templated translation-request issues, but the set still does not look like true duplicates.", + "summary": "The three generic i18n placeholder issues are likely true duplicates of each other. The Turkish and Spanish issues are separate language-specific translation requests and should not be merged with the generic placeholders or with each other.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43834 is the earliest of the near-identical generic placeholder translation issues and best represents that duplicate subgroup.", "canonical_pr_reason": null, - "best_issue_reason": "issue:43834 is the best global representative only in a loose triage sense: it is the most generic templated translation issue and sits at the center of the near-identical template group, though it should not be considered a true duplicate of the language-specific issues.", + "best_issue_reason": "43834 has the strongest duplicate signal within the cluster: same generic title/body pattern as 44365 and 44370, with the earliest timestamp among them.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:27088", "right": "issue:44370", "accept": false, - "reason": "Both are translation requests, but the available metadata does not show they target the same language or same underlying work; different locale requests should stay separate." + "reason": "Different target languages; Turkish vs generic placeholder. Same broad i18n theme is not enough to treat these as the same request." }, { "left": "issue:27088", "right": "issue:44365", "accept": false, - "reason": "Same rationale: the concrete Turkish request is distinct from the templated translation issue, and there is no evidence they are the same locale or change." + "reason": "Different target languages; this is a Turkish translation request, while the other is a generic placeholder translation issue." }, { "left": "issue:27088", "right": "issue:43834", "accept": false, - "reason": "The Turkish request is a specific locale task, while the other item is only a generic translation template; not enough to say they are the same issue." + "reason": "Turkish-specific translation request vs generic placeholder issue; not the same underlying change." }, { "left": "issue:27088", "right": "issue:28936", "accept": false, - "reason": "Turkish and Spanish docs translations are different locale-specific requests, so they are not the same underlying issue." + "reason": "Turkish and Spanish translation requests are distinct deliverables, so they should not be deduplicated." }, { "left": "issue:28936", "right": "issue:43834", "accept": false, - "reason": "The Spanish request is specific, but the other item is a generic template; no evidence they refer to the same language or exact task." + "reason": "Spanish-specific request does not match the generic placeholder issue closely enough to be the same underlying issue." }, { "left": "issue:28936", "right": "issue:44365", "accept": false, - "reason": "Spanish translation request versus another generic templated translation issue; same broad area, but not the same concrete request." + "reason": "Different language targets; Spanish translation request versus generic placeholder issue." }, { "left": "issue:28936", "right": "issue:44370", "accept": false, - "reason": "Different locale-specific translation request versus a generic template; insufficient evidence for a duplicate." + "reason": "Different language targets; these are separate translation requests, not one bug/change." }, { "left": "issue:43834", "right": "issue:44370", - "accept": false, - "reason": "The titles/body shapes are very similar, but translation requests are typically language-specific and no explicit shared target is shown." + "accept": true, + "reason": "Near-identical generic title/body pattern and no distinguishing details; these look like duplicate copies of the same placeholder issue." }, { "left": "issue:43834", "right": "issue:44365", - "accept": false, - "reason": "Near-identical template text alone is not enough; these could still be separate locale requests and there is no explicit linkage." + "accept": true, + "reason": "Same generic template/title and almost identical body structure; likely duplicate placeholder issues." }, { "left": "issue:44365", "right": "issue:44370", - "accept": false, - "reason": "Both are templated translation issues, but there is no concrete evidence they describe the same language or the same underlying change." + "accept": true, + "reason": "Same generic placeholder translation issue with nearly identical content; safe to deduplicate." } ] }, - "evaluator_result": null, - "evaluator_used": false, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet. The three placeholder issues have nearly identical titles and extremely high similarity scores, and selecting the earliest one as canonical is reasonable. The Turkish and Spanish issues are correctly treated as distinct language-specific requests, and the soft-edge verdicts stay conservative without overstating equivalence." + }, + "evaluator_used": true, "retried": false, - "accepted_nontrivial_soft_edge": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, @@ -15838,12 +15930,12 @@ "issue:37015|issue:45027", "issue:43837|issue:45177" ], - "prepared_review_unit_hash": "5f46c056f1444f060360d5c833cc455193ad2b185d2726b779ac4f9f0cb7a9a0", + "prepared_review_unit_hash": "b0b5982722ea84b61b74050b47a4c5c9e13144ea5e8b708c5ebedcc1027c82f7", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20706, + "serialized_chars": 20708, "estimated_input_tokens": 5177, "estimated_eval_tokens": 10610 }, @@ -15851,7 +15943,7 @@ "node_count": 15, "item_count": 15, "soft_pair_count": 35, - "serialized_chars": 20706, + "serialized_chars": 20708, "estimated_input_tokens": 5177, "estimated_eval_tokens": 10610 }, @@ -15860,252 +15952,222 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not a duplicate set: it groups many distinct model-addition requests spanning different model families and even different modalities (text, OCR, audio, TTS, ASR, detection). No soft edges should be merged.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue for deduplication: the items are separate model requests with different targets and problem statements, not the same underlying bug/change.", + "summary": "This cluster is a set of related-but-distinct model support requests, not true duplicates. The overlap is mostly the generic \u201cadd model/support\u201d framing; the requested model families and tasks differ materially.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 41115 is the broadest and most representative request in the set, with the clearest generic scope and the most cluster activity/references among the open issues.", "canonical_pr_reason": null, - "best_issue_reason": "If one must be named as the broadest representative, issue:42738 ('BERT-like models with RoPE') is the most general, but it is still not a true duplicate canonical for the rest.", + "best_issue_reason": "Issue 41115 is the best cluster anchor because it is a high-activity, broadly phrased model-add request that most cleanly represents the topical group without being overly niche.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:36817", "right": "issue:41211", "accept": false, - "reason": "EuroBert vs DEIMv2 are different models and requests; no shared underlying change." + "reason": "Different model requests: EuroBert vs DEIMv2. Same feature theme, not the same underlying change." }, { "left": "issue:36817", "right": "issue:43671", "accept": false, - "reason": "EuroBert is a text encoder model request; Qwen3-TTS is an audio generation/request for a different modality." + "reason": "EuroBert config support is unrelated to Qwen3-TTS audio support." }, { "left": "issue:36817", "right": "issue:36879", "accept": false, - "reason": "EuroBert and RF-DETR are unrelated architectures (BERT-style encoder vs detection model)." + "reason": "EuroBert vs RF-DETR are distinct model families and use cases." }, { "left": "issue:36879", "right": "issue:41211", "accept": false, - "reason": "RF-DETR and DEIMv2 are distinct detection/vision model additions, not the same model or code path." + "reason": "RF-DETR and DEIMv2 are different detection models; not a duplicate request." }, { "left": "issue:36879", "right": "issue:43909", "accept": false, - "reason": "RF-DETR and LFM2.5 Audio 1.5B are completely different modalities and requests." + "reason": "RF-DETR vision detection and LFM2.5 Audio support are unrelated changes." }, { "left": "issue:36879", "right": "issue:44121", "accept": false, - "reason": "RF-DETR and a weight-sparse transformer request are unrelated model families and implementation paths." + "reason": "RF-DETR and circuit-sparsity transformer support target different architectures and code paths." }, { "left": "issue:36879", "right": "issue:43837", "accept": false, - "reason": "RF-DETR (detection) and Qwen3-ASR (speech recognition) are different tasks and models." + "reason": "RF-DETR vs Qwen3-ASR are different model types and tasks." }, { "left": "issue:36879", "right": "issue:43671", "accept": false, - "reason": "RF-DETR and Qwen3-TTS are unrelated detection vs text-to-speech requests." + "reason": "RF-DETR vision model support is not the same as Qwen3-TTS audio support." }, { "left": "issue:37015", "right": "issue:43837", "accept": false, - "reason": "NeoBERT is a BERT-like text model; Qwen3-ASR is a speech model request." + "reason": "NeoBERT and Qwen3-ASR are unrelated model requests." }, { "left": "issue:37015", "right": "issue:44121", "accept": false, - "reason": "NeoBERT and the sparse-transformer request target different model architectures and changes." + "reason": "NeoBERT vs weight-sparse transformer support are different architectures, not one bug/change." }, { "left": "issue:37015", "right": "issue:43909", "accept": false, - "reason": "NeoBERT and LFM2.5 Audio 1.5B are different modalities and unrelated features." + "reason": "NeoBERT and LFM2.5 Audio request different domains and implementation paths." }, { "left": "issue:36879", "right": "issue:37015", "accept": false, - "reason": "RF-DETR and NeoBERT are unrelated model requests with no shared concrete bug/change." + "reason": "RF-DETR and NeoBERT are unrelated model additions." }, { "left": "issue:37015", "right": "issue:42503", "accept": false, - "reason": "NeoBERT and ModernVBERT are different BERT-like models, but still distinct model additions." + "reason": "NeoBERT and ModernVBERT are different models; shared BERT naming is not enough for duplication." }, { "left": "issue:41115", "right": "issue:43837", "accept": false, - "reason": "MiniCPM3 architecture and Qwen3-ASR address different model families and tasks." + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are distinct model additions." }, { "left": "issue:41115", "right": "issue:44121", "accept": false, - "reason": "MiniCPM3 support and sparse-transformer support are separate architecture requests." + "reason": "MiniCPM3 and circuit-sparsity transformer support are different code paths and requests." }, { "left": "issue:41115", "right": "issue:42503", "accept": false, - "reason": "MiniCPM3 and ModernVBERT are different model-addition requests." + "reason": "MiniCPM3 and ModernVBERT are separate model support requests." }, { "left": "issue:41115", "right": "issue:45027", "accept": false, - "reason": "MiniCPM3 and Voxtral-4B-TTS-2603 are unrelated text vs TTS model requests." + "reason": "MiniCPM3 and Voxtral TTS support are different modalities and implementations." }, { "left": "issue:41211", "right": "issue:43671", "accept": false, - "reason": "DEIMv2 and Qwen3-TTS are different tasks and model families." + "reason": "DEIMv2 and Qwen3-TTS are unrelated model support requests." }, { "left": "issue:42503", "right": "issue:43837", "accept": false, - "reason": "ModernVBERT and Qwen3-ASR are unrelated model additions." + "reason": "ModernVBERT and Qwen3-ASR are different models and tasks." }, { "left": "issue:42503", "right": "issue:43671", "accept": false, - "reason": "ModernVBERT and Qwen3-TTS are different modalities and implementation paths." + "reason": "ModernVBERT vs Qwen3-TTS are unrelated additions." }, { "left": "issue:42503", "right": "issue:42738", "accept": false, - "reason": "ModernVBERT is a specific model request; 'BERT-like models with RoPE' is a broad feature request, not the same change." + "reason": "ModernVBERT and BERT-like models with RoPE are too broad and not the same concrete request." }, { "left": "issue:42738", "right": "issue:45027", "accept": false, - "reason": "RoPE support for BERT-like models and Voxtral TTS support are unrelated changes." + "reason": "BERT-like RoPE support and Voxtral TTS support are unrelated changes." }, { "left": "issue:43671", "right": "issue:43837", "accept": false, - "reason": "Qwen3-TTS and Qwen3-ASR are different sibling models serving different modalities." - }, - { - "left": "issue:43671", - "right": "issue:43909", - "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are different audio model requests." - }, - { - "left": "issue:43671", - "right": "issue:44121", - "accept": false, - "reason": "TTS support and sparse-transformer support are unrelated implementations." + "reason": "Qwen3-TTS and Qwen3-ASR are related by brand, but they are different products and different support paths." }, { "left": "issue:43671", "right": "issue:45027", "accept": false, - "reason": "Qwen3-TTS and Voxtral-4B-TTS-2603 are distinct TTS model requests, not the same concrete change." + "reason": "Qwen3-TTS and Voxtral TTS are distinct model integrations." }, { "left": "issue:43671", "right": "issue:45177", "accept": false, - "reason": "Qwen3-TTS and DeepSeek-OCR2 target different model families and modalities." - }, - { - "left": "issue:43837", - "right": "issue:43909", - "accept": false, - "reason": "Qwen3-ASR and LFM2.5 Audio 1.5B are different audio-related models, not the same request." + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated modalities and requests." }, { - "left": "issue:43837", + "left": "issue:43671", "right": "issue:44121", "accept": false, - "reason": "ASR support and sparse-transformer support are unrelated code-path changes." - }, - { - "left": "issue:43837", - "right": "issue:45027", - "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model requests." + "reason": "Qwen3-TTS support is not the same as the weight-sparse transformer request." }, { "left": "issue:43837", - "right": "issue:45177", + "right": "issue:45322", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are unrelated speech vs OCR model requests." + "reason": "Qwen3-ASR and EUPE are different audio/vision model requests." }, { "left": "issue:43837", - "right": "issue:45322", + "right": "issue:43909", "accept": false, - "reason": "Qwen3-ASR and EUPE are different model proposals with no shared underlying change." + "reason": "Qwen3-ASR and LFM2.5 Audio are both audio-related, but they are different models and implementations." }, { "left": "issue:43909", "right": "issue:44205", "accept": false, - "reason": "LFM2.5 Audio 1.5B and SAM3-LiteText are distinct audio vs multimodal segmentation-related requests." - }, - { - "left": "issue:44121", - "right": "issue:45322", - "accept": false, - "reason": "Sparse transformer support and EUPE are unrelated model/architecture additions." + "reason": "LFM2.5 Audio and SAM3-LiteText are completely different model requests." }, { "left": "issue:43671", "right": "issue:43909", "accept": false, - "reason": "Qwen3-TTS and LFM2.5 Audio 1.5B are different audio model requests." + "reason": "Qwen3-TTS and LFM2.5 Audio are distinct audio model support requests." }, { "left": "issue:44121", "right": "issue:45322", "accept": false, - "reason": "Sparse transformer support and EUPE are unrelated model/architecture additions." + "reason": "Weight-sparse transformer support and EUPE are different architecture proposals." }, { "left": "issue:43837", "right": "issue:44121", "accept": false, - "reason": "ASR support and sparse-transformer support are unrelated code-path changes." + "reason": "Qwen3-ASR and circuit-sparsity transformer support do not describe the same change." }, { "left": "issue:43837", "right": "issue:45027", "accept": false, - "reason": "Qwen3-ASR and Voxtral TTS are different speech-model requests." + "reason": "Qwen3-ASR and Voxtral TTS are different audio model integrations." }, { "left": "issue:37015", "right": "issue:45027", "accept": false, - "reason": "NeoBERT and Voxtral TTS are unrelated text vs speech model requests." + "reason": "NeoBERT and Voxtral TTS are unrelated model support requests." }, { "left": "issue:43837", "right": "issue:45177", "accept": false, - "reason": "Qwen3-ASR and DeepSeek-OCR2 are unrelated speech vs OCR model requests." + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model families and tasks." } ] }, @@ -16148,88 +16210,82 @@ "issue:43668|issue:44031", "issue:43668|issue:43813" ], - "prepared_review_unit_hash": "7a2fab15260baa307cbe533332a0fe225b79d5b0ff640cb95bc9a8e5f1f1824a", + "prepared_review_unit_hash": "4db72b1c7c80e351ff272d4c86fac88e3842d91a776539e76cf791ce2bb90f0a", "component_budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 7189, - "estimated_input_tokens": 1798, - "estimated_eval_tokens": 3852 + "serialized_chars": 7188, + "estimated_input_tokens": 1797, + "estimated_eval_tokens": 3850 }, "budget": { "node_count": 7, "item_count": 7, "soft_pair_count": 9, - "serialized_chars": 7189, - "estimated_input_tokens": 1798, - "estimated_eval_tokens": 3852 + "serialized_chars": 7188, + "estimated_input_tokens": 1797, + "estimated_eval_tokens": 3850 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is not a duplicate set: the issues span unrelated bugs in Llama normalization, Mask2Former loss handling, ModernBERT typing, tokenizer warnings, a typo, and DeepSeek gating. The soft similarities are only superficial keyword overlap.", + "summary": "This is not a true duplicate cluster: the issues span unrelated models, config typing, tokenizer warnings, and an unrelated typo. No soft edge appears to describe the same underlying bug.", "confidence": 0.96, - "canonical_issue_reason": "No canonical issue is justified here; the titles describe different code paths and model families, so the apparent similarity is only generic wording like \"norm\", \"type\", or \"warning\".", + "canonical_issue_reason": "If one issue must be used as a representative, #42936 is the most concrete and discussion-rich report; however, it is not actually a duplicate of the others.", "canonical_pr_reason": null, - "best_issue_reason": "No single issue is a credible global representative. If forced, 43668 is the closest to a generic small bug report, but it is only about a ModernBERTConfig type hint and does not subsume the others.", + "best_issue_reason": "#42936 is the strongest standalone issue in the set, but only as a generic representative\u2014not because it matches the rest of the items.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:37934", "right": "issue:43668", "accept": false, - "reason": "Both mention normalization/configuration, but one asks whether Llama4TextL2Norm should be RMSNorm while the other is only about a ModernBERTConfig type hint. Different models and different bug types." + "reason": "Both mention normalization-related terms, but one questions Llama4TextL2Norm semantics while the other is a ModernBERT config type-hint bug; different models and different problems." }, { "left": "issue:42936", "right": "issue:43240", "accept": false, - "reason": "Mask2Former's unused ignore_value and kwargs not being forwarded to a loss function are distinct bugs in different parts of the training stack." + "reason": "Mask2former ignore_value being unused is a model-specific loss bug, while kwargs not being passed to loss calculation is a separate API/control-flow issue." }, { "left": "issue:42936", "right": "issue:46018", "accept": false, - "reason": "These concern unrelated model behavior: Mask2Former ignore_value handling versus DeepSeek-V4 shared expert gating." + "reason": "These are unrelated DeepSeek-V4 gating and Mask2former ignore_value bugs; same broad ML space, not the same code-path problem." }, { "left": "issue:42936", "right": "issue:44031", "accept": false, - "reason": "A Mask2Former loss parameter issue is unrelated to tokenizer regex warnings after a version bump." + "reason": "A Mask2former loss parameter issue is unrelated to a tokenizer regex warning regression." }, { "left": "issue:42936", "right": "issue:43813", "accept": false, - "reason": "Unused ignore_value in Mask2Former and a typo in a quantization attribute name are unrelated." - }, - { - "left": "issue:42936", - "right": "issue:43668", - "accept": false, - "reason": "Mask2Former ignore_value handling does not match a ModernBERTConfig type-hint correction; different components and fixes." + "reason": "Unused ignore_value in a model loss function does not match a typo in a quantization-operation attribute name." }, { "left": "issue:43240", "right": "issue:43668", "accept": false, - "reason": "Forwarding kwargs to a loss function is a different code-path bug from correcting a config type hint." + "reason": "Loss kwargs propagation and a config type-hint mistake are different kinds of bugs in different components." }, { "left": "issue:43668", - "right": "issue:44031", + "right": "issue:43813", "accept": false, - "reason": "A ModernBERTConfig annotation issue is unrelated to tokenizer regex pattern warnings." + "reason": "ModernBERTConfig norm_eps typing and an orig_conversion.quantization_operation typo are unrelated issues." }, { "left": "issue:43668", - "right": "issue:43813", + "right": "issue:44031", "accept": false, - "reason": "Type-hint cleanup in ModernBERTConfig is unrelated to a typo in a quantization field name." + "reason": "A config type-hint problem is not the same underlying bug as a tokenizer regex warning regression." } ] }, @@ -16259,7 +16315,7 @@ "soft_pairs": [ "issue:41084|issue:43037" ], - "prepared_review_unit_hash": "f28fd63ebba5d749d6e71121cce13a1dba215a596931660fb1740d9b2cf05c4a", + "prepared_review_unit_hash": "4a0a7b6528f68beb2f1518a7e18ec2bf1699d0fd4efb995dbd8fd278467119f9", "component_budget": { "node_count": 2, "item_count": 2, @@ -16281,18 +16337,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two issues are unrelated: one is about block decoding behavior, the other is a model support request for DeepSeek v3.2. There is no evidence they describe the same bug or change.", - "confidence": 0.97, - "canonical_issue_reason": "Issue #41084 is the more specific technical bug report; #43037 is a separate feature/support request for a particular model.", + "summary": "These two issues are not duplicates: one is a specific request about set block decoding, while the other asks for DeepSeek v3.2 support. They describe different features/problems with no shared code-path evidence.", + "confidence": 0.98, + "canonical_issue_reason": null, "canonical_pr_reason": null, - "best_issue_reason": "#41084 is the better canonical issue candidate only because it is more concrete and actionable, but the pair should not be clustered as duplicates.", + "best_issue_reason": "#41084 is the more concrete, narrowly scoped issue; #43037 is a separate model-support feature request.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:41084", "right": "issue:43037", "accept": false, - "reason": "The titles and implied scopes do not match: 'Set Block Decoding' concerns a decoding implementation detail, while 'DeepSeek v3.2 support' is a model compatibility request. They do not appear to be the same underlying issue." + "reason": "Different underlying requests: block decoding vs DeepSeek v3.2 model support. No overlapping targets, filenames, or concrete bug path suggest a duplicate." } ] }, @@ -16322,12 +16378,12 @@ "soft_pairs": [ "issue:43598|issue:43600" ], - "prepared_review_unit_hash": "e8dd61dbce94d203a8e62a6849e5eda688c22bcc9f372fd44f5c748fa73a1b8c", + "prepared_review_unit_hash": "b06bac0bff94ddaeff4c3e5ce9145d8a420a30c3a5a4adb3edd37fd4e6f7917d", "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 }, @@ -16335,7 +16391,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 1584, + "serialized_chars": 1583, "estimated_input_tokens": 396, "estimated_eval_tokens": 1048 }, @@ -16344,18 +16400,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both closed Trainer-related issues, but they address different concerns: one is about `remove_unused_column` customizability, the other about FLOPS estimation for custom trainers. They do not look like duplicates.", - "confidence": 0.91, - "canonical_issue_reason": "Issue #43598 is the more concrete behavior report around a specific Trainer setting; #43600 is a separate accounting/measurement concern.", + "summary": "The two issues are only loosely related by \u201ccustom trainers,\u201d but they describe different trainer behaviors: one is about `remove_unused_column` handling, the other about FLOPS estimation. They are not duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue #43598 is the better cluster representative because it is the broader customizability concern around Trainer behavior; #43600 is a separate FLOPS-accounting problem.", "canonical_pr_reason": null, - "best_issue_reason": "#43598 is the better cluster representative because it is narrower and more actionable, while still sitting in the same Trainer-customization area.", + "best_issue_reason": "#43598 is the more suitable global issue anchor since it describes the core trainer customizability gap more directly and broadly, while #43600 is a narrower, distinct follow-up concern.", "best_pr_reason": null, "soft_edge_verdicts": [ { - "left": "issue:43598", - "right": "issue:43600", + "left": "Revisit `remove_unused_column` in Trainer for better customizability", + "right": "Account for custom trainers when trying to estimate the number of FLOPS", "accept": false, - "reason": "The titles and descriptions point to different underlying problems: unused-column handling vs FLOPS estimation. Shared mention of custom trainers is too broad to treat as the same issue." + "reason": "Both mention custom trainers, but one concerns column-pruning customizability and the other concerns FLOPS estimation. They affect different code paths and are not the same underlying bug." } ] }, @@ -16385,7 +16441,7 @@ "soft_pairs": [ "issue:43684|issue:44405" ], - "prepared_review_unit_hash": "e9a3554b402381f400b71347e74d38f5d831563136076b25ea21db3c466c6eae", + "prepared_review_unit_hash": "e3ff850f5495f1daff034f4625dc9218a3e0306aac88eccc79fa4f5f6aac953f", "component_budget": { "node_count": 2, "item_count": 2, @@ -16407,18 +16463,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are separate feature requests, not duplicates: one asks for Qwen3-Omni registration in AutoModel/AutoModelForConditionalGeneration, the other asks for AutoModelForSequenceClassification support for Qwen3.5. Different model families and different auto classes mean they should stay separate.", - "confidence": 0.96, - "canonical_issue_reason": "No true canonical duplicate exists; if one issue must be kept as the representative request, #43684 is broader and more central to model registration, but it does not subsume #44405.", + "summary": "These issues are related only at a very high level: both concern adding Qwen model support to auto classes, but they target different APIs and different model/config variants. They do not look like the same underlying bug or change.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43684 is the broader request (Qwen3-Omni registration for AutoModel and AutoModelForConditionalGeneration) and is the better representative of the auto-class registration theme, but it is not the same task as 44405.", "canonical_pr_reason": null, - "best_issue_reason": "#43684 is the broader, more foundational registration request and is the better representative issue for this cluster, but it should not be merged with #44405.", + "best_issue_reason": "Issue 43684 is the most general and central of the two; 44405 is a narrower, distinct sequence-classification support request for a different Qwen config.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43684", "right": "issue:44405", "accept": false, - "reason": "Reject: they target different capabilities (Qwen3-Omni auto-registration vs Qwen3.5 sequence-classification support) and different config/model paths, so they are not the same underlying bug or change." + "reason": "Reject: 43684 asks for adding Qwen3-Omni registration to AutoModel/AutoModelForConditionalGeneration, while 44405 asks for AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config). Different model family/config and different auto class behavior, so not the same underlying change." } ] }, @@ -16455,79 +16511,79 @@ "issue:43845|issue:43859", "issue:43846|issue:43859" ], - "prepared_review_unit_hash": "2aeef5e5d4cffa27913ecb1df25995c1a6ec83c96c33fea8d8884aa17b1b1f4a", + "prepared_review_unit_hash": "f21028b2c5e49cdf59db79e8df564356f5bcddf6ded65c5a7390f2d2da6c892f", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4256, - "estimated_input_tokens": 1064, - "estimated_eval_tokens": 2384 + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 }, "budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 4256, - "estimated_input_tokens": 1064, - "estimated_eval_tokens": 2384 + "serialized_chars": 4264, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three issues share the same near-identical title \"huggingface \" and look like duplicates; \"Fett\" does not have enough evidence to join that cluster. Best representative is the oldest of the huggingface issues.", - "confidence": 0.84, - "canonical_issue_reason": "issue #43845 is the best canonical issue candidate: it is the earliest of the three identically titled \"huggingface \" reports, so it is the most natural representative for a duplicate cluster.", + "summary": "Issues 43845, 43846, and 43859 share the exact same generic title \"huggingface \" and form the duplicate cluster; 43835 ('Fett') looks unrelated.", + "confidence": 0.82, + "canonical_issue_reason": "43845 is the earliest issue in the exact-title duplicate set, so it is the best canonical representative.", "canonical_pr_reason": null, - "best_issue_reason": "#43845 is the strongest global issue choice because it matches the duplicate cluster by title and timestamp, while #43835 appears unrelated/noisy.", + "best_issue_reason": "43845 is the best overall issue representative because it matches the other two identical-title reports, while 43835 is unrelated.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:43835", "right": "issue:43845", "accept": false, - "reason": "\"Fett\" and \"huggingface \" do not clearly describe the same underlying issue; the similarity signal alone is too weak." + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." }, { "left": "issue:43835", "right": "issue:43846", "accept": false, - "reason": "No meaningful evidence that these are the same bug; titles are unrelated." + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." }, { "left": "issue:43835", "right": "issue:43859", "accept": false, - "reason": "The titles are unrelated and there is no issue-body detail to tie them together." + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." }, { "left": "issue:43845", "right": "issue:43846", "accept": true, - "reason": "Same title, same topic, and close creation times strongly suggest duplicate reports of the same issue." + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." }, { "left": "issue:43845", "right": "issue:43859", "accept": true, - "reason": "Identical title and clustered timing make these look like duplicate reports of the same issue." + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." }, { "left": "issue:43846", "right": "issue:43859", "accept": true, - "reason": "Identical title with no distinguishing evidence indicates the same underlying issue." + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." } ] }, "evaluator_result": { - "accept": true, - "feedback": "The summary is grounded in the packet: #43845, #43846, and #43859 all have the same title and close creation times, so treating #43845 as the canonical/oldest representative is conservative. The rejection of #43835 is also properly cautious because its title is unrelated and the packet provides no stronger linkage beyond weak soft similarity." + "accept": false, + "feedback": "The cluster summary is mostly grounded, but one soft-edge rationale overstates the evidence: issue 43859 is about 13 hours after 43845/43846, so it is not 'very close' in creation time. If you keep those acceptances, the reasoning should rely only on the identical title and soft similarity, not temporal proximity." }, "evaluator_used": true, - "retried": false, + "retried": true, "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null @@ -16562,88 +16618,88 @@ "issue:44572|issue:44937", "issue:44573|issue:44937" ], - "prepared_review_unit_hash": "db15e395ec2717b2ab8d08e3712313a7f8f756b06cc03bd457226f5b0bb25100", + "prepared_review_unit_hash": "004a283e5934b2987fd297350411e74b9b1e80dfc6edd361a00067162101eb63", "component_budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5794, - "estimated_input_tokens": 1449, - "estimated_eval_tokens": 3154 + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 }, "budget": { "node_count": 5, "item_count": 5, "soft_pair_count": 9, - "serialized_chars": 5794, - "estimated_input_tokens": 1449, - "estimated_eval_tokens": 3154 + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is dominated by low-information spam-like issues. The only comparatively substantive item is the documentation enhancement suggestion, but there is no evidence that any of these are the same underlying issue.", - "confidence": 0.93, - "canonical_issue_reason": "Issue 44418 is the only non-spam, nontrivial title in the set and is the best representative anchor for this noisy cluster.", + "summary": "This cluster looks like unrelated low-information/spam issues with only superficial title similarity. There is no evidence of a shared underlying bug or change, so none should be deduplicated together.", + "confidence": 0.98, + "canonical_issue_reason": "Issue 44371 is the earliest item and is as generic as the rest, but none of the issues provide enough substance to serve as a meaningful canonical report.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 44418 is the most suitable issue to keep as the cluster representative because it is the only item that looks like a real user-facing request rather than spam.", + "best_issue_reason": "44371 is the least bad placeholder only because it is earliest; however, the set is too noisy and content-poor to identify a true canonical issue.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:44371", "right": "issue:44572", "accept": false, - "reason": "Both are titled '' with no body details, but that is not enough to show the same underlying issue or change." + "reason": "Both are generic spam placeholders, but there is no concrete evidence they describe the same report." }, { "left": "issue:44371", "right": "issue:44573", "accept": false, - "reason": "Same spam title and no supporting context; insufficient evidence they are duplicates of the same concrete issue." + "reason": "Identical low-information titles are not enough to prove the same underlying issue." }, { "left": "issue:44371", "right": "issue:44418", "accept": false, - "reason": "One is spam, the other is a documentation enhancement suggestion; they do not appear to describe the same problem." + "reason": "One is spam-like and the other is a documentation suggestion; they do not point to the same problem." }, { "left": "issue:44371", "right": "issue:44937", "accept": false, - "reason": "Spam-like placeholder title versus a specific quoted title; no indication of the same underlying issue." + "reason": "The titles are unrelated; no shared bug, request, or code path is evident." }, { "left": "issue:44418", "right": "issue:44572", "accept": false, - "reason": "Documentation enhancement request and spam placeholder are unrelated and do not share a concrete issue description." + "reason": "A documentation enhancement and a spam placeholder are not the same issue." }, { "left": "issue:44418", "right": "issue:44573", "accept": false, - "reason": "No meaningful overlap beyond both being low-detail issues; not enough to treat as duplicates." + "reason": "Different topics with no concrete overlap beyond being low-information issues." }, { "left": "issue:44572", "right": "issue:44573", "accept": false, - "reason": "Both are spam placeholders, but there is no concrete bug/report content to confirm they refer to the same underlying item." + "reason": "Same generic placeholder title, but no description or target evidence ties them to one underlying report." }, { "left": "issue:44572", "right": "issue:44937", "accept": false, - "reason": "Generic spam title does not match the specific quoted-title issue; no duplicate evidence." + "reason": "Unrelated titles and no explicit shared target or problem statement." }, { "left": "issue:44573", "right": "issue:44937", "accept": false, - "reason": "No shared concrete subject matter; one is spam and the other is a specific named request." + "reason": "No substantive common bug/change is visible; similarity is only superficial." } ] }, @@ -16673,7 +16729,7 @@ "soft_pairs": [ "issue:45145|issue:45151" ], - "prepared_review_unit_hash": "3c4798d7727c87b8e4143b186b794487ba48479339c4d39e280acbbb4364011d", + "prepared_review_unit_hash": "8f5403be315b4b2a7dc7603ea9f431af87f159fb08388fcc07e3455d285814c0", "component_budget": { "node_count": 2, "item_count": 2, @@ -16695,28 +16751,28 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two closed issues appear to be duplicates of the same proposal: identical titles and near-identical bodies about \"N6 Arithmetic\" energy reduction techniques. Issue 45145 is the better canonical due to being created earlier and already having an inbound reference.", - "confidence": 0.99, - "canonical_issue_reason": "Issue 45145 was opened first and has the only inbound reference, so it is the best anchor for this duplicate pair.", + "summary": "The two issues have identical titles and similar content, but the packet only supports a soft duplicate hypothesis rather than an exact duplicate. #45145 is the safest canonical issue because it was created first and already has an inbound reference.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the earlier report and has an inbound reference, so it is the safest canonical representative among two highly similar issues.", "canonical_pr_reason": null, - "best_issue_reason": "Issue 45145 is the strongest representative of the cluster because it is earliest and already referenced; the content is effectively the same as 45151.", + "best_issue_reason": "#45145 is the best issue representative for triage because it is the earliest instance and already referenced elsewhere; the available evidence does not prove a strict duplicate, only strong similarity.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45145", "right": "issue:45151", - "accept": true, - "reason": "Same title and essentially the same body describing the same energy-reduction techniques proposal, so these are the same underlying issue." + "accept": false, + "reason": "The issues share an identical title and look related, but the packet only provides soft similarity (Jaccard 0.63) with no explicit links, targets, or other evidence proving the same underlying report. That is not strong enough to accept as a duplicate." } ] }, "evaluator_result": { - "accept": true, - "feedback": "Grounded in the packet: the issues share an identical title, have very similar body sizes, and the soft-similarity signal supports a duplicate-like relationship. Canonicalizing to 45145 is also justified by earlier creation time and the inbound reference count. The verdict is conservative enough here." + "accept": false, + "feedback": "The canonical choice (#45145) is grounded by earlier creation time and an inbound reference, but the analysis overstates the evidence for duplication. The packet only shows identical titles and soft similarity with Jaccard 0.63; it does not establish an exact duplicate. Also, the claim that #45145 has \u201cslightly more discussion context\u201d is not supported by the packet (it has 0 discussion activity vs. 1 on #45151)." }, "evaluator_used": true, - "retried": false, - "accepted_nontrivial_soft_edge": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null }, @@ -16793,7 +16849,7 @@ "soft_pairs": [ "issue:45672|issue:45674" ], - "prepared_review_unit_hash": "35c023c0c94b71bccda97c11a0cb6d38550dad99138eccf4b0bb018085c97d9a", + "prepared_review_unit_hash": "a4853145fdabf66fe7820c362fb6bd1dd37936cff9b40bc212ff70afd153bdec", "component_budget": { "node_count": 2, "item_count": 2, @@ -16815,18 +16871,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: one is a Gemma4/audio-module NF4 inference failure caused by `torch.finfo()` on `uint8` weights, while the other is a `BitsAndBytesConfig` regression where `llm_int8_skip_modules` removes the default `lm_head` exclusion and triggers an `AssertionError`. Same broad 4-bit inference area, but different bugs and code paths.", - "confidence": 0.96, - "canonical_issue_reason": "No canonical issue: the reports describe different root causes and would not be collapsed into one duplicate.", + "summary": "These are related only at a very broad level (4-bit inference), but they describe different failures in different code paths: one is a Gemma4/audio-module uint8 + `torch.finfo()` TypeError, the other is a BitsAndBytesConfig `llm_int8_skip_modules`/`lm_head` exclusion AssertionError. They should not be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue #45674 is the clearer, more generally described bug report: it names the specific configuration interaction, the affected default exclusion behavior, and the resulting assertion path.", "canonical_pr_reason": null, - "best_issue_reason": "No single best issue for deduplication; neither report subsumes the other, though 45674 is the broader config regression and 45672 is the model-specific inference bug.", + "best_issue_reason": "Issue #45674 is the best representative because it is more precise about the trigger and failure mode, making it easier to triage and fix independently.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45672", "right": "issue:45674", "accept": false, - "reason": "Different failure modes: `torch.finfo()` TypeError in Gemma4 audio NF4 inference vs `llm_int8_skip_modules` clearing the default `lm_head` exclusion and causing an AssertionError. Shared 4-bit context is not enough to treat them as the same bug." + "reason": "Both involve 4-bit inference, but the reported bugs are different: one is a `torch.finfo()` TypeError on uint8 weights in Gemma4 audio modules, the other is an AssertionError caused by `llm_int8_skip_modules` clearing the default `lm_head` exclusion. Different triggers and code paths, so not a duplicate." } ] }, @@ -16856,7 +16912,7 @@ "soft_pairs": [ "issue:45762|issue:45763" ], - "prepared_review_unit_hash": "41ce6ad0e05f344cd3f04a004a2d96190c0dc5b19a0cb1d3acc56ce42a426bd8", + "prepared_review_unit_hash": "82a2f5f5d6cd8bc1d2d0169feb6ba16571c6723e5eec40537266c7004168f3d7", "component_budget": { "node_count": 2, "item_count": 2, @@ -16878,8 +16934,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two closed issues with unrelated title strings (different personal names and dates) and no body, links, or code evidence. They do not look like the same underlying bug or change; this appears more like unrelated/spam entries than a duplicate cluster.", - "confidence": 0.97, + "summary": "The two issues appear unrelated: both titles are just different personal names with different dates, and there is no shared description, filename, target, or discussion evidence suggesting a duplicate bug report.", + "confidence": 0.99, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -16889,7 +16945,7 @@ "left": "issue:45762", "right": "issue:45763", "accept": false, - "reason": "Different named entities and different dates; no shared description, references, or code context, so they do not appear to report the same issue." + "reason": "Different named subjects and different dates; no evidence they describe the same underlying issue or report." } ] }, @@ -16919,7 +16975,7 @@ "soft_pairs": [ "issue:45764|issue:45765" ], - "prepared_review_unit_hash": "941f7083b4e316591282f3a17f97e215a9921db0b9d1cb0263ac98f93708a57f", + "prepared_review_unit_hash": "fefccf9bea33baae59dc78b6f3f6644645b110e77b4be02e51a423ae00a41b91", "component_budget": { "node_count": 2, "item_count": 2, @@ -16941,8 +16997,8 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two closed issues appear unrelated: they are separate personal-name/date titles with no body, links, or shared evidence beyond weak similarity. I would not treat them as duplicates.", - "confidence": 0.97, + "summary": "The two issues are unrelated-looking closed placeholders with different person-name/date titles, no body, no links, and no shared technical context. There is no basis to treat either as a duplicate of the other.", + "confidence": 0.96, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, @@ -16952,7 +17008,7 @@ "left": "issue:45764", "right": "issue:45765", "accept": false, - "reason": "Different names and dates with no issue body, references, or shared targets/files; no evidence they describe the same underlying bug or request." + "reason": "The titles refer to different names and dates, and there is no issue body, discussion, or linking evidence indicating the same underlying bug or request." } ] }, @@ -16992,7 +17048,7 @@ "issue:45871|issue:45873", "issue:45872|issue:45873" ], - "prepared_review_unit_hash": "fa7c607bc0000b1b60214c7dead9dc27a75faf62503a09b2bab7add21c525ef3", + "prepared_review_unit_hash": "4ecad14438dd50d9f9429f93d1cb83f30115331132ae29876c4fbeebe8950426", "component_budget": { "node_count": 5, "item_count": 5, @@ -17014,77 +17070,77 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster looks like two strong near-duplicate issue pairs (45870/45871 and 45872/45873) plus a loosely related financial dataset listing (45869). The evidence supports soft similarity, but not confirmed exact duplicates.", - "confidence": 0.84, - "canonical_issue_reason": "45872 is the best single anchor among the similar subgroup because it is the most concrete request and sits in the strongest soft-similarity pair; however, the cluster is mixed, so no issue cleanly represents all items.", + "summary": "This cluster is not one duplicate set; it splits into two separate exact-duplicate issue pairs: 45870/45871 and 45872/45873. Issue 45869 is only loosely thematically related and should not be merged with either pair.", + "confidence": 0.95, + "canonical_issue_reason": "45870 is the cleanest representative of the first exact-duplicate pair because it matches 45871 verbatim and is the earlier instance. It is not a canonical for the whole cluster, only for its duplicate pair.", "canonical_pr_reason": null, - "best_issue_reason": "45872 is the best overall representative for triage: it is the most substantive of the similar issues and is tightly paired with 45873, while 45869 remains only loosely related and the example issues are narrower.", + "best_issue_reason": "No single issue cleanly represents all five items, but 45870 is the best overall representative to keep as the first exact-duplicate issue. If triaging by subcluster, 45872 would be the corresponding representative for the second exact-duplicate pair.", "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "issue:45869", "right": "issue:45870", "accept": false, - "reason": "Same broad financial-data theme, but a dataset listing and an example request are not enough to treat as the same issue." + "reason": "Same broad financial domain, but 45869 is a dataset/sample offer while 45870 is an example issue about prediction with DataForge; not the same underlying request." }, { "left": "issue:45869", "right": "issue:45871", "accept": false, - "reason": "Loosely related by topic, but the dataset bundle and example topic appear to be different requests." + "reason": "Dataset bundle vs example issue; related topic only, not the same concrete bug/change." }, { "left": "issue:45870", "right": "issue:45871", - "accept": false, - "reason": "Very strong textual match, but the packet only provides soft similarity and not enough certainty to call it a confirmed duplicate." + "accept": true, + "reason": "Identical titles and likely the same issue reported twice." }, { "left": "issue:45870", "right": "issue:45872", "accept": false, - "reason": "Shared DataForge/financial wording, but the example request and scraping-service request are different concrete topics." + "reason": "Both mention financial time series/DataForge, but one is about a prediction example and the other about a scraping service; different concrete requests." }, { "left": "issue:45870", "right": "issue:45873", "accept": false, - "reason": "Broadly related by domain, but not the same underlying request as the scraping-service issue." + "reason": "Different underlying issue: prediction example versus scraping-service request." }, { "left": "issue:45871", "right": "issue:45872", "accept": false, - "reason": "The left is the example topic; the right is a different scraping-service request, so they should not be merged as duplicates." + "reason": "Different concrete topic and likely separate work items, despite shared keywords." }, { "left": "issue:45871", "right": "issue:45873", "accept": false, - "reason": "Same broad domain, but the example issue and the scraping-service issue are distinct enough to stay separate." + "reason": "Prediction example and scraping-service issue are not the same underlying change." }, { "left": "issue:45872", "right": "issue:45873", - "accept": false, - "reason": "Very strong textual match, but the evidence still stops at soft similarity, so this is best treated as a probable near-duplicate rather than a confirmed one." + "accept": true, + "reason": "Identical titles and effectively the same issue duplicated." } ] }, "evaluator_result": { - "accept": false, - "feedback": "The cluster summary is not conservative enough. The packet only supports strong soft similarity (including identical titles/body lengths and jaccard 1.0), but it does not establish exact duplicates with certainty, and the soft-pair entries are all marked deterministic_accept false. The analysis repeatedly upgrades that evidence to 'exact duplicate' and 'clear duplicates,' which overstates the packet. The 45869 relationship also should remain phrased as loosely related rather than definitively unrelated." + "accept": true, + "feedback": "The cluster analysis is grounded in the packet: 45870/45871 and 45872/45873 are the only clearly mergeable duplicate pairs based on identical titles and matching body length, while 45869 is only loosely related. The soft-edge verdicts are conservative and do not overstate evidence." }, "evaluator_used": true, - "retried": true, - "accepted_nontrivial_soft_edge": false, + "retried": false, + "accepted_nontrivial_soft_edge": true, "error_kind": null, "error_message": null }, { "label": "pull_request", "component_index": 1, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17139,202 +17195,202 @@ "pull_request:46065|pull_request:46067", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "6e12f8708167c064a4b060ae1007f348b1ef300b1df366f92c50a9892b038246", + "prepared_review_unit_hash": "c2430217c36b580b17d982a0524f516a2e9172cd23dbe5c4c48d98b7a61a32c4", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 27, - "serialized_chars": 42118, - "estimated_input_tokens": 10530, - "estimated_eval_tokens": 21316 + "serialized_chars": 42112, + "estimated_input_tokens": 10528, + "estimated_eval_tokens": 21312 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 27, - "serialized_chars": 42118, - "estimated_input_tokens": 10530, - "estimated_eval_tokens": 21316 + "serialized_chars": 42112, + "estimated_input_tokens": 10528, + "estimated_eval_tokens": 21312 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is mostly unrelated PRs that share only broad Transformer subsystem similarity. The only true duplicate-looking pair is the two loss-utils fixes (43251 and 43254), which both extend fixed_cross_entropy to pass supported nn.functional.cross_entropy kwargs. All other soft links are different model additions, test-only changes, or unrelated utility fixes and should stay separate.", - "confidence": 0.91, + "summary": "This cluster is mostly noisy and spans unrelated PRs (model additions, docs, tests, kernel/loading fixes). The only clear duplicate/same-change pair is the two `fixed_cross_entropy` patches for the same loss helper.", + "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the best canonical representative for the only real duplicate pair: it directly targets issue 43240 and implements the missing cross_entropy kwargs support in fixed_cross_entropy; 43254 is an alternate formulation of the same fix.", + "canonical_pr_reason": "PR 43251 is the strongest representative because it directly links issue 43240 and makes the same `fixed_cross_entropy` API change as 43254, but in a slightly more complete/structured way.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the strongest global representative because it has the explicit issue link, addresses the same concrete loss-path bug as 43254, and is the clearest merge candidate for the duplicate pair.", + "best_pr_reason": "PR 43251 is the best cluster anchor: it is explicitly issue-linked, targets the core loss helper change, and its duplicate pair (43254) is a near-identical alternative implementation.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated changes: VideoPrism model addition/docs vs Executorch dynamic-shape export test. Different code paths and purposes." + "reason": "Unrelated PRs: VideoPrism model/docs addition vs an Executorch dynamic-shape test. Same general repo area only, not the same bug/change." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Mistral tokenizer methods vs adding MobileLLM model support. No shared bug or mergeable change." + "reason": "Mistral tokenizer helper methods vs adding MobileLLM. Different models and different code paths." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Tokenizer API additions are unrelated to an Executorch export test." + "reason": "Tokenizer API fix vs Executorch export test. No shared underlying bug or change." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-registration/robustness changes are unrelated to MobileLLM model implementation." + "reason": "Processor auto-loading robustness vs adding MobileLLM. Broad processor/model infrastructure only, not the same fix." }, { "left": "pull_request:43251", "right": "pull_request:46067", "accept": false, - "reason": "Loss function kwargs support is unrelated to conversion/base_model_prefix loading fixes." + "reason": "Both touch loading/loss-related code in the repo, but they fix different problems: cross-entropy kwargs vs base_model_prefix conversion handling." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss utility fix vs new MobileLLM model code; different functionality and code paths." + "reason": "Loss helper kwargs fix vs new MobileLLM model addition. Completely different changes." }, { "left": "pull_request:43251", "right": "pull_request:46065", "accept": false, - "reason": "Both are utility fixes, but they address different functions and bugs: cross_entropy kwargs vs device-property detection." + "reason": "Cross-entropy kwargs fix vs testing-utils device detection fix. Unrelated code paths." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Loss helper kwargs support is unrelated to Mistral4 test/model refactoring." + "reason": "Loss helper change vs Mistral4 test/model cleanup. Same broad theme of fixes, but not the same concrete bug." }, { "left": "pull_request:43424", "right": "pull_request:46065", "accept": false, - "reason": "Executorch dynamic-shape test vs test-device-properties fix; different concerns and no shared underlying bug." + "reason": "Executorch dynamic-shape test vs testing-utils device detection. Different functionality." }, { "left": "pull_request:43424", "right": "pull_request:46067", "accept": false, - "reason": "Export tests are unrelated to conversion/loading prefix handling." + "reason": "Executorch export test vs conversion-loading prefix handling. No shared change target." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "Executorch export test and Mistral4 test fixes are different test areas and code paths." + "reason": "Executorch dynamic-shape test vs Mistral4 test fixes. Both test-oriented, but unrelated code paths." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "Executorch test vs MobileLLM model addition; unrelated." + "reason": "Executorch test vs MobileLLM model addition. Not the same bug/change." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "New MobileLLM model support is unrelated to config-resolution ordering in modeling_utils." + "reason": "New MobileLLM model vs config-resolution ordering fix. Different subsystems and issues." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "MobileLLM model addition is unrelated to Falcon output-interface refactoring." + "reason": "MobileLLM addition vs Falcon output-interface refactor. Different model families and changes." }, { "left": "pull_request:43823", "right": "pull_request:46067", "accept": false, - "reason": "New model implementation is unrelated to loading/conversion prefix fixes." + "reason": "MobileLLM addition vs conversion base_model_prefix fix. No common concrete code-path." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon output-collection refactor is unrelated to Mistral4 test fixes." + "reason": "Falcon output-capture refactor vs Mistral4 tests/model fixes. Different models and intent." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon refactor and model-creation skill are entirely different areas." + "reason": "Falcon refactor vs model-creation skill draft. Completely unrelated." }, { "left": "pull_request:44827", "right": "pull_request:46065", "accept": false, - "reason": "Mistral4 test/model work is not the same concrete bug as the testing_utils device-property fix, despite superficial similarity." + "reason": "Do not merge just because both are fixes/tests; Mistral4 test fixes and testing-utils device capability handling are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:46067", "accept": false, - "reason": "Mistral4 test fixes do not match base_model_prefix conversion-loading changes." + "reason": "Mistral4 tests/model work vs base_model_prefix conversion fix. Different underlying problems." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test/model changes are unrelated to the layrnorm->layernorm conversion/model typo fix." + "reason": "Mistral4 test fixes vs layrnorm->layernorm renaming. No shared bug or mergeable single PR." }, { "left": "pull_request:44827", "right": "pull_request:46048", "accept": false, - "reason": "Mistral4 test fixes are unrelated to adding a TDT loss kernel." + "reason": "Mistral4 fixes vs TDT loss kernel integration. Different feature/fix scope." }, { "left": "pull_request:45170", "right": "pull_request:46065", "accept": false, - "reason": "The layernorm typo/conversion fix is unrelated to device-property detection in test utils." + "reason": "LayerNorm rename/conversion mapping fix vs testing-utils device properties fix. Unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Mistral4 test/model changes are unrelated to the model-creation skill PR." + "reason": "Mistral4 fixes vs a new-model skill draft. Not the same change." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "MobileLLM model support is unrelated to the skill-documentation/model-creation workflow." + "reason": "MobileLLM addition vs model-creation skill draft. Different artifact types and purposes." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 changes are unrelated to the config-class resolution-order fix." + "reason": "Mistral4 test fixes vs config-resolution order fix. Different code paths and problems." }, { "left": "pull_request:46065", "right": "pull_request:46067", "accept": false, - "reason": "One fixes testing_utils device detection; the other fixes conversion loading scope/base_model_prefix handling. Different bugs and code paths." + "reason": "Testing-utils device detection fix vs conversion base_model_prefix fix. Both infra changes, but not the same underlying bug." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Same underlying bug in fixed_cross_entropy: both add support for passing supported cross_entropy kwargs, especially weight and label_smoothing, in src/transformers/loss/loss_utils.py; they are mergeable into one PR." + "reason": "Same file and same loss helper (`fixed_cross_entropy`) with the same underlying fix: add supported kwargs/forward them to `nn.functional.cross_entropy` for issue 43240." } ] }, "evaluator_result": { "accept": true, - "feedback": "Grounded overall. The only pair supported by explicit shared issue-target evidence is 43251/43254, and the summary stays conservative about the rest as unrelated soft similarities. No mergeability concerns for the accepted duplicate pair." + "feedback": "The summary is grounded in the packet and stays conservative: it correctly treats the cluster as mostly unrelated noise and only accepts the clear duplicate pair `pull_request:43251`/`pull_request:43254`, which share the same file and issue target `43240`. The rejected soft-edge pairs also look appropriately non-mergeable into a single bugfix PR." }, "evaluator_used": true, "retried": false, @@ -17345,7 +17401,7 @@ { "label": "pull_request", "component_index": 2, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17361,7 +17417,7 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "831e8044140f61ee935914be8d23c3fcb6a8ba4519de869b953cc7e4720012cc", + "prepared_review_unit_hash": "645beec4388498c7c542381a57d9b3f374abbd6ec5a90c46cb0947e51b4b718a", "component_budget": { "node_count": 2, "item_count": 2, @@ -17383,18 +17439,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are about the VibeVoice family, but they are not the same change: #40546 adds the base VibeVoice model, while #42781 adds a realtime variant plus an acoustic tokenizer and related generation/processing updates. They share many filenames because #42781 builds on the same subsystem, but the underlying work differs.", - "confidence": 0.93, + "summary": "Both PRs are about adding VibeVoice support, but PR #42781 is a later, broader realtime follow-up rather than the same concrete change as PR #40546. They overlap heavily on core VibeVoice files, yet the feature scope differs enough that they should not be merged as duplicates.", + "confidence": 0.84, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #40546 is the better canonical PR for the base VibeVoice implementation: it is the broader, more complete initial model integration and appears to be the original landing point for the family.", + "canonical_pr_reason": "PR #42781 is the more comprehensive and newer VibeVoice implementation, covering the realtime path plus the acoustic tokenizer and related generation/model plumbing, so it is the better representative of this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR #40546 is the strongest representative of the cluster because it implements the core VibeVoice model and associated auto/processor/docs plumbing, whereas #42781 is a narrower follow-on for realtime support.", + "best_pr_reason": "PR #42781 is the strongest standalone candidate because it appears to subsume more of the VibeVoice integration surface and likely reflects the most complete implementation direction.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Shared VibeVoice files alone are not enough: #40546 implements the main model, while #42781 adds realtime-specific behavior and an acoustic tokenizer. They are related, but not the same concrete bug/change and would not plausibly merge as one PR." + "reason": "They overlap on VibeVoice infrastructure, but #40546 is the initial implementation while #42781 adds a realtime variant and additional tokenizer/generation pieces. That is related work, not the same concrete fix/change, so I would not merge them as duplicates." } ] }, @@ -17408,7 +17464,7 @@ { "label": "pull_request", "component_index": 3, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17424,12 +17480,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "bb242e6e00ec95b82ea9974c7350aa662c136979ac99b2e173e01f3dce9798d7", + "prepared_review_unit_hash": "42e5168c88d71b4b5f9b570c002b81cbd622ef352af82a0e592d0447bc0ccd49", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4676, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -17437,7 +17493,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4676, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -17446,18 +17502,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The cluster contains two unrelated pull requests: one adds TimesFM covariate forecasting, the other adds DINOv3 image classification support. They do not fix the same bug or implement the same change, so this is not a duplicate cluster.", + "summary": "These two PRs are unrelated feature additions in different model areas: TimesFM covariate forecasting vs DINOv3 image classification support. They do not look like the same underlying change, so the soft duplicate edge should be rejected.", "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "No single PR is a good cluster representative because the items are about different models and different features.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different code paths and model families (TimesFM forecasting vs DINOv3 image classification); no shared underlying change, and they are not mergeable as one PR." + "reason": "Different models and code paths: 40755 adds TimesFM covariate forecasting across timesfm/xreg utilities, while 41224 adds DINOv3 image classification support in auto/modeling docs and DINOv3 code. They are not the same bug or change." } ] }, @@ -17471,7 +17527,7 @@ { "label": "pull_request", "component_index": 4, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17534,7 +17590,7 @@ { "label": "pull_request", "component_index": 5, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17552,12 +17608,12 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "3714f3e0929b23bcfb860cf23a6be8332f436251b936bf5b098c2167a617df68", + "prepared_review_unit_hash": "320fd47de973cbb1571e4e4094f51a56fb88e7ce933c748327f650c62454746e", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10435, + "serialized_chars": 10436, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -17565,7 +17621,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 2, - "serialized_chars": 10435, + "serialized_chars": 10436, "estimated_input_tokens": 2609, "estimated_eval_tokens": 5474 }, @@ -17574,24 +17630,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are unrelated model-addition changes for DeepSeek OCR, Isaac, and Kimi2-6. They share broad Transformers registration/docs scaffolding, but not the same underlying feature or code-path fix.", - "confidence": 0.99, + "summary": "These are three separate new-model addition PRs for different models (DeepSeek OCR, Isaac, Kimi2-6). They share boilerplate registration/docs patterns, but not the same underlying change or code-path fix, so they should not be clustered as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: each patch adds a different model family with distinct configs, processors, model code, and tests.", + "canonical_pr_reason": "No canonical duplicate PR: each change adds a different model integration, with distinct files, configs, processors, and model code.", "best_issue_reason": null, - "best_pr_reason": "No single best duplicate PR: none of these PRs is a mergeable duplicate of the others; they are only loosely similar in being new model integrations.", + "best_pr_reason": "PR 45630 is the strongest representative only in the sense that it has the most review activity and a substantial model integration, but it is still not interchangeable with the others.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model additions (DeepSeek OCR vs Isaac). Shared docs/auto-mapping files are boilerplate for model registration, not the same underlying change." + "reason": "Different model additions (DeepSeek OCR vs Isaac). Shared docs/auto-registration files are boilerplate, not evidence of the same underlying change or a PR that could be merged into one." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model additions (Isaac vs Kimi2-6) with distinct code paths and model families; similarity is limited to generic integration scaffolding." + "reason": "Different model additions (Isaac vs Kimi2-6) with distinct implementation files and model codepaths. The overlap is broad framework registration, not the same concrete fix." } ] }, @@ -17605,7 +17661,7 @@ { "label": "pull_request", "component_index": 6, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17621,7 +17677,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "af10834a4e4e7f7b4f0acc8b62b52cdb576525a3262118910a55469cb4e4233b", + "prepared_review_unit_hash": "4a2184db695189253243cfef43ab3212e29458abfe07ec7f943e2e18b0b47e81", "component_budget": { "node_count": 2, "item_count": 2, @@ -17643,18 +17699,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two workflow-maintenance PRs overlap in files and both upgrade GitHub Actions, but they target different actions and different compatibility goals. They should not be deduplicated.", - "confidence": 0.93, + "summary": "Two open PRs both modernize GitHub Actions workflows, but they update different actions and address different change sets: one focuses on Node 24-compatible workflow action upgrades, the other on bumping docker/build-push-action and a few related workflows. They overlap in filenames but are not the same underlying change.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the broader, more clearly cohesive change: it updates multiple GitHub Actions across workflows specifically for Node 24 compatibility.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the better representative PR because its title and edits align around one concrete maintenance task, whereas PR 42976 is a separate set of action version bumps focused on different actions.", + "best_pr_reason": "PR #42975 is the broader, more coherent workflow-upgrade sweep and is the better representative of the cluster, but it is not a duplicate of #42976.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Both are workflow dependency upgrades, but they change different actions (core GitHub Actions vs docker/build-push-action) and do not fix the same underlying bug or change set. Shared files alone are not enough to merge them into one PR." + "reason": "Reject: both are workflow dependency bumps, but #42975 upgrades core GitHub Actions for Node 24 compatibility while #42976 specifically bumps docker/build-push-action. They touch overlapping files yet fix different action-version migrations and would not plausibly be merged as one PR." } ] }, @@ -17668,7 +17724,7 @@ { "label": "pull_request", "component_index": 7, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17691,12 +17747,12 @@ "pull_request:43448|pull_request:45490", "pull_request:43451|pull_request:45490" ], - "prepared_review_unit_hash": "cc621c54fbf0e313eeb9c196bb35ca3d755d70c7a9d70261a7804b5a0b2305a4", + "prepared_review_unit_hash": "f9099aabcf4cd6ed22c38e7b5ffc03bfc19bc19bb5c2dffcdd4e1f60c08e5290", "component_budget": { "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 14078, + "serialized_chars": 14079, "estimated_input_tokens": 3520, "estimated_eval_tokens": 7296 }, @@ -17704,7 +17760,7 @@ "node_count": 4, "item_count": 4, "soft_pair_count": 6, - "serialized_chars": 14078, + "serialized_chars": 14079, "estimated_input_tokens": 3520, "estimated_eval_tokens": 7296 }, @@ -17713,48 +17769,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are four separate model-addition PRs for different architectures (ViT NEPA, Molmo, Molmo2, CTSM). The overlap is mostly boilerplate around docs and auto-mapping registration, not the same underlying bug or change.", - "confidence": 0.98, + "summary": "Four separate model-addition PRs (ViT NEPA, Molmo, Molmo2, and CTSM) that only look similar because they follow the same Transformers integration template. They touch different model families and code paths, so this is not a duplicate cluster.", + "confidence": 0.99, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR for duplication: each PR introduces a different model family and distinct codepaths, so none should serve as a duplicate anchor.", + "canonical_pr_reason": "No canonical PR: each item introduces a different model integration with distinct files, model classes, and documentation.", "best_issue_reason": null, - "best_pr_reason": "If one PR must be chosen as the most representative of the cluster, #43451 (Molmo2) is the strongest candidate because it is the most expansive and well-developed of the set, but it is still not a duplicate of the others.", + "best_pr_reason": "No best PR for deduplication purposes; the PRs are unrelated changes despite sharing scaffold files like docs and auto-mapping updates.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "ViT NEPA and Molmo are unrelated model additions; shared files are only generic docs/auto-registry scaffolding." + "reason": "ViT NEPA and Molmo are different model additions; shared template files do not indicate the same bug or change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA and Molmo2 are different model families with different implementations and tests; similarity is just boilerplate registration/docs." + "reason": "ViT NEPA and Molmo2 are separate model integrations with different model codepaths and docs." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA and CTSM target different architectures and codepaths; overlap is limited to common model-onboarding files." + "reason": "ViT NEPA is a vision model addition, while CTSM is a time-series model addition; unrelated changes." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related by name but the PRs add distinct models with different modules, processors, and tests, so they are not the same change." + "reason": "Molmo and Molmo2 are distinct model families; overlap is limited to standard integration scaffolding." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM are unrelated model additions; shared files reflect framework integration boilerplate only." + "reason": "Molmo and CTSM touch different model domains and concrete implementations." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM introduce different models and functionality; the common paths are generic registry/docs updates, not one mergeable fix." + "reason": "Molmo2 and CTSM are unrelated model additions with no shared underlying bug or fix." } ] }, @@ -17768,7 +17824,7 @@ { "label": "pull_request", "component_index": 8, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17787,52 +17843,52 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "c0c5690caaa6215c84e791458e6b9983b89f5420498b2ed0cbfc36258ae1efc4", + "prepared_review_unit_hash": "4c0e1f070d69dd463d44b1527021c081c9576db549a1e3fc18b704674c0c9aa6", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 7092, - "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": 7092, - "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 are three unrelated open PRs: a Whisper tokenizer/test fix, a placeholder-looking CLIP/ViT test PR, and a broader FP8 dequant fix. The shared similarity is superficial and not enough to treat any pair as the same underlying change.", - "confidence": 0.96, + "summary": "The three pull requests are not duplicates: one is a Whisper tokenizer/test fix, one is placeholder-like test edits in CLIP/ViT, and one is a substantive FP8 dequant/loading fix. All soft links should be rejected.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:44815 is the strongest standalone PR: it has a coherent dequantization fix across implementation files and tests, with a concrete technical target.", + "canonical_pr_reason": "No canonical PR: the three PRs target unrelated changes, so none should subsume the others.", "best_issue_reason": null, - "best_pr_reason": "pull_request:44815 is the best representative of the cluster because it is the most substantive and clearly scoped change; the other PRs are either narrow test fixes or appear to be placeholder test edits.", + "best_pr_reason": "PR 44815 is the strongest standalone change: it has a coherent, substantive code fix across the loading/FP8 path, unlike the other two which are test-only or Whisper-specific.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Different code paths and purposes: Whisper tokenizer decode logic vs. CLIP/ViT test edits. Shared 'fix' framing is not enough." + "reason": "Whisper tokenizer/timestamp decoding work is unrelated to CLIP/ViT test-assert edits; they do not fix the same bug or change." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper decoding/tokenization changes are unrelated to FP8 dequant/model-loading logic; no shared underlying bug." + "reason": "These touch different code paths and problems: Whisper decoding vs FP8 dequant/loading; no plausible single merged fix." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "The CLIP/ViT test-only edits do not match the FP8 dequant fix, and there is no concrete common failure mode." + "reason": "Test-only placeholder assertions in CLIP/ViT are unrelated to the FP8 dequant fix and should not be merged as one PR." } ] }, @@ -17846,7 +17902,7 @@ { "label": "pull_request", "component_index": 9, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17862,12 +17918,12 @@ "soft_pairs": [ "pull_request:43488|pull_request:43532" ], - "prepared_review_unit_hash": "fc744bc01f992ba805302448934d77014f403170ad9a1a091eb5ee71bcf0bd9d", + "prepared_review_unit_hash": "5f07d366db8167e91ab1dc373367d9f2733f72d69d5d7718d668483dc598ac57", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17875,7 +17931,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4562, + "serialized_chars": 4563, "estimated_input_tokens": 1141, "estimated_eval_tokens": 2538 }, @@ -17884,18 +17940,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two unrelated open PRs that both use the same test file only incidentally. One is a small repo-bot/version/dependency tweak, the other is a broader CI/testing-utils workflow change. They should not be merged or treated as duplicates.", - "confidence": 0.91, + "summary": "Two open PRs, but they are not duplicates: #43488 is a small repo-bot/version-format test PR, while #43532 is a broader CI/workflow and testing-utils change. Shared test-file overlap is incidental.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43532 is the better cluster representative because it has the broader, more substantial change set and touches the main CI/testing code paths, whereas #43488 is a narrower packaging/version check tweak.", + "canonical_pr_reason": "PR #43532 is the better representative of the cluster because it is broader and more substantive; #43488 is a narrow temporary bot-check PR focused on setup/version formatting.", "best_issue_reason": null, - "best_pr_reason": "PR #43532 is the strongest standalone PR in this cluster: it has clearer scope, more files, and a more coherent change set than the small synthetic repo-bot/version PR #43488.", + "best_pr_reason": "#43532 is the closest thing to a cluster anchor, but neither PR is a strong canonical duplicate target because both are marked '[don't merge]' and appear to be validation/infrastructure changes rather than a single fix.", "soft_edge_verdicts": [ { "left": "pull_request:43488", "right": "pull_request:43532", "accept": false, - "reason": "Not the same underlying change. #43488 changes setup/version/dependency metadata and a vit test; #43532 changes CI workflow logic, testing utils, and notification paths. The shared test file is incidental, and the PRs fix different problems." + "reason": "Reject: the PRs touch different change sets and code paths. #43488 is mostly setup/version/dependency and a Vit test tweak; #43532 changes CI workflows, testing utilities, and notifications. They do not look like one mergeable fix." } ] }, @@ -17909,7 +17965,7 @@ { "label": "pull_request", "component_index": 10, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17925,7 +17981,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "42fdb02feefa316ee3ffb61165b1d8b8da1e91c489ea0e6b8d2367a6db702419", + "prepared_review_unit_hash": "aa2386a531936782064adfd47659907515272d3f746895a160efa2ef57072cea", "component_budget": { "node_count": 2, "item_count": 2, @@ -17947,18 +18003,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are two separate pull requests adding different pipeline features: one for Promptable Concept Segmentation and one for Promptable Visual Segmentation. They share some documentation and registration plumbing, but the underlying tasks, model integrations, and codepaths are distinct.", + "summary": "These are two separate feature PRs that both add new promptable segmentation pipelines and share generic scaffolding, but they target different concepts, model families, and code paths. They are similar in shape, not the same underlying change.", "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical duplicate PR: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation; they are distinct features with different implementation targets.", "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the better representative of the cluster because it is the broader, more integrated visual-segmentation addition, touching multiple model backends and the corresponding pipeline/tests/docs. However, it is still not a duplicate of PR 43612.", + "best_pr_reason": "If one representative is needed, 43613 is the broader/more comprehensive feature PR, but it is not a duplicate of 43612.", "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Reject: these add different pipelines for different problems (concept segmentation vs visual segmentation), with different target docs, pipeline modules, and model integrations. Shared registry/docs updates are too broad to treat as the same change." + "reason": "Different pipelines and feature intents; shared docs/registry/test scaffolding is expected and does not indicate the same concrete bug or change." } ] }, @@ -17972,7 +18028,7 @@ { "label": "pull_request", "component_index": 11, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -17988,12 +18044,12 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "d7dc6934cec86171502bdfb749f44775d64d20ccafb769dbe9f3b609b54d135d", + "prepared_review_unit_hash": "619e606e478dff7017bb2c882155b166d1a89d047f3549527ac73382aeec4a17", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, + "serialized_chars": 4290, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -18001,7 +18057,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, + "serialized_chars": 4290, "estimated_input_tokens": 1073, "estimated_eval_tokens": 2402 }, @@ -18010,18 +18066,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two separate trainer extensibility PRs landed in the same file, but they address different code paths: one changes gradient-accumulation loss scaling, the other extracts signature-column filtering for custom trainers/PEFT. They are related in theme, not duplicates.", - "confidence": 0.95, + "summary": "Both items modify `src/transformers/trainer.py`, but they solve different problems: 43651 adds a gradient-accumulation loss-scaling hook, while 43663 extracts signature-column filtering for custom/PEFT trainers. Related area, not duplicate change.", + "confidence": 0.97, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "43651 is the stronger representative: it makes a concrete behavior change in `training_step` for loss scaling, whereas 43663 is a separate column-filtering override hook.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Both touch `trainer.py` and add overridable helpers, but they fix different behaviors: loss scaling during training vs. dataloader column filtering. They are not the same underlying bug/change and would not plausibly be merged as one PR." + "reason": "They share the trainer subsystem but not the same underlying bug or code path: one changes GA loss normalization, the other changes signature-column extraction for data filtering. They would not naturally merge into one PR." } ] }, @@ -18035,7 +18091,7 @@ { "label": "pull_request", "component_index": 12, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18051,7 +18107,7 @@ "soft_pairs": [ "pull_request:43656|pull_request:43842" ], - "prepared_review_unit_hash": "5d0b1899ad32ec7b8237f25c73b26bb3404c0d637a1c941e148db013da9db616", + "prepared_review_unit_hash": "c775f3857e2f95759b6dbf96c81476b6a77323daca53255217d3a56ac888a6c3", "component_budget": { "node_count": 2, "item_count": 2, @@ -18073,18 +18129,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs touch `src/transformers/cli/serve.py` and aim at annotation-related `TypeAdapter` problems, but they fix different concrete issues with different mechanisms. PR #43842 is the narrower fix for `TypeAdapter` not being available at runtime when pydantic is absent; PR #43656 is a broader typing cleanup using `from __future__ import annotations` and other annotation rewrites.", - "confidence": 0.88, + "summary": "These PRs touch the same file but fix different TypeAdapter-related problems: one is a typing/annotation cleanup in `serve.py`, the other specifically handles `pydantic` being absent. They are not duplicates and should not be merged into one PR.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43842 is the better canonical PR: it directly addresses the optional-pydantic `TypeAdapter` NameError with a minimal change and an explicit issue target, whereas #43656 is broader and changes unrelated annotations too.", + "canonical_pr_reason": "No single canonical PR: the two changes address different runtime/typing failure modes in the CLI, so neither subsumes the other.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 is the best overall fit because it is the most targeted fix for the concrete runtime failure described in its title and diff.", + "best_pr_reason": "PR 43842 is the more narrowly targeted fix for the explicit `pydantic`-missing `TypeAdapter` NameError path; PR 43656 is a separate typing-related cleanup/fix.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Related in the same file and both about type-annotation runtime behavior, but they are not the same underlying change: #43656 adds future annotations and rewrites typing, while #43842 specifically makes `TypeAdapter` safe when pydantic is not installed." + "reason": "Different underlying bugs: 43656 is a typing/future-annotations cleanup in `serve.py`, while 43842 fixes the `TypeAdapter` import/forward-reference failure when `pydantic` is not installed." } ] }, @@ -18098,7 +18154,7 @@ { "label": "pull_request", "component_index": 13, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18164,7 +18220,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 2, "status": "reviewed", @@ -18277,7 +18333,7 @@ "pull_request:44044|pull_request:44154", "pull_request:44024|pull_request:44076" ], - "prepared_review_unit_hash": "01820994d5f5c0dee9a06f6fbf6027a45b4d2a61124f27d68c84282e29d493b9", + "prepared_review_unit_hash": "4531250bdf1eee563ec9f94a9846696eedbc3633cd8250707d635a1d0a43d825", "component_budget": { "node_count": 28, "item_count": 28, @@ -18290,7 +18346,7 @@ "node_count": 28, "item_count": 28, "soft_pair_count": 72, - "serialized_chars": 76939, + "serialized_chars": 76938, "estimated_input_tokens": 19235, "estimated_eval_tokens": 38726 }, @@ -18299,360 +18355,372 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is mostly a set of separate model-specific refactors for standardized output tracing, not one single duplicate PR set. The only clear near-duplicates are within the same model family: GPT-Neo (44018/44068) and GPT-J/CodeGen (44066/44085/44722).", - "confidence": 0.83, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the best representative of the cluster\u2019s strongest duplicate family: it is the broadest and most complete GPT-J/CodeGen output-tracing refactor, with the same underlying decorator-based output-capture change and explicit issue linkage.", - "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the most suitable global representative because it most fully implements the standardized output-tracing change in one coherent code path and subsumes the smaller GPT-J variants.", + "summary": "This cluster is mostly a set of independent model-by-model refactors to the new output-tracing/capture_outputs pattern, centered around the shared tracking issue #43979. A few pairs are true near-duplicates within the same model family (notably GPT-Neo and GPT-J/CodeGen), but most cross-model pairs are not the same concrete change.", + "confidence": 0.92, + "canonical_issue_reason": "Issue #43979 is the common umbrella tracker repeatedly referenced by these PRs and appears to be the canonical coordination point for the standardized output-tracing refactor work.", + "canonical_pr_reason": "PR #44722 is the strongest representative: it is a later, more complete GPT-J/CodeGen output-tracing refactor with the same standardized-decorator direction and explicit issue linkage.", + "best_issue_reason": "#43979 is the best global issue anchor because it is explicitly targeted by many of the PRs in this cluster and captures the shared refactor theme.", + "best_pr_reason": "#44722 is the best global PR representative because it clearly implements the standardized output-tracing change in the GPT-J/CodeGen path and appears to be a mature version of that specific refactor.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different model families and different code paths; only share the broad output-tracing theme." + "reason": "Different models and code paths (CVT/FNet vs GPT-J); same broad tracing theme, but not the same concrete change." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different architectures and files; same meta-refactor category, not the same bug/change." + "reason": "Different models (CVT/FNet vs DeBERTa) and unrelated implementation paths." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Both target the same GPT-J output-tracing rewrite in modeling_gptj.py; 44066 is a broader variant of the same concrete change." + "reason": "Both are GPT-J/CodeGen output-tracing refactors with overlapping intent and essentially the same decorator-based change pattern." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/ResNet-family versus EfficientNet; same refactor style, but not the same concrete change." + "reason": "Different families (RegNet/ResNet/RT-DETR vs EfficientNet); same umbrella refactor theme only." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths." + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated code paths." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "GPT-J/CodeGen versus EfficientNet; no shared concrete change." + "reason": "GPT-J/CodeGen vs EfficientNet are different model implementations." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 and DeBERTaV2 are unrelated implementations." + "reason": "MobileNetV2 vs DeBERTa; not the same underlying bug/change." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen versus MGP-STR; only the refactor pattern matches." + "reason": "GPT-J/CodeGen refactor vs MGP-STR refactor; different model code paths." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen versus MPT; different models and code paths." + "reason": "GPT-J/CodeGen vs MPT are different concrete changes." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo file and same output-tracing refactor; 44068 looks like a later revision of the same change." + "reason": "Both target GPT-Neo output tracing in the same files and look like alternate versions of the same refactor." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen versus GPT-Neo; same theme, different code paths." + "reason": "GPT-J/CodeGen and GPT-Neo are separate model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "Different model families; not the same change." + "reason": "GPT-Neo vs GPT-J/CodeGen are different code paths despite similar refactor style." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet versus GPT-J/CodeGen; unrelated concrete changes." + "reason": "ResNet/RT-DETR backbone refactor vs GPT-J/CodeGen refactor are unrelated." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR and GPT-J/CodeGen are unrelated code paths." + "reason": "MGP-STR vs GPT-J/CodeGen are different model families." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet and GPT-J are unrelated models." + "reason": "ResNet-based output tracing and GPT-J output tracing are distinct changes." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo versus ResNet; only the refactor theme overlaps." + "reason": "GPT-Neo and ResNet are different models and code paths." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet and MPT are different model implementations." + "reason": "ResNet vs MPT; same theme, different implementations." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo versus GPT-J/CodeGen; same initiative, different code paths." + "reason": "GPT-Neo vs GPT-J/CodeGen are different model-specific refactors." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo and Flaubert/XLM are unrelated model families." + "reason": "GPT-Neo vs Flaubert are unrelated concrete changes." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT and GPT-J/CodeGen are different code paths." + "reason": "MPT vs GPT-J/CodeGen are different code paths." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo versus Flaubert/XLM; not the same bug/change." + "reason": "GPT-Neo vs Flaubert are different model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo and MGP-STR are unrelated implementations." + "reason": "GPT-Neo vs MGP-STR are not the same change." }, { "left": "pull_request:44018", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo versus GPT-J; same refactor family but different concrete code path." + "reason": "GPT-Neo vs GPT-J/CodeGen are different model-specific refactors." }, { "left": "pull_request:44068", - "right": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are unrelated concrete code-path changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo versus MPT; no shared concrete change." + "reason": "MPT vs MGP-STR are different models and fixes." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT2 and MGP-STR are unrelated models." + "reason": "GPT-2 vs MGP-STR are different concrete changes." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J versus MGP-STR; only the output-tracing pattern overlaps." + "reason": "GPT-J vs MGP-STR are different model families and code paths." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT and Flaubert/XLM are different model families." + "reason": "ViLT vs Flaubert/XLM are different model implementations." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT2 versus GPT-J/CodeGen; different code paths." - }, - { - "left": "pull_request:44068", - "right": "pull_request:44086", - "accept": false, - "reason": "GPT-Neo versus MGP-STR; unrelated implementations." + "reason": "GPT-2 and GPT-J/CodeGen are separate refactors, not one mergeable change." }, { - "left": "pull_request:44071", - "right": "pull_request:44076", + "left": "pull_request:44018", + "right": "pull_request:44071", "accept": false, - "reason": "MPT and ImageGPT are unrelated concrete changes." + "reason": "GPT-Neo vs MPT are different model code paths." }, { - "left": "pull_request:44074", - "right": "pull_request:44101", + "left": "pull_request:44017", + "right": "pull_request:44722", "accept": false, - "reason": "TextNet and Flaubert/XLM are different model code paths." + "reason": "Segformer vs GPT-J/CodeGen are unrelated concrete changes." }, { - "left": "pull_request:44056", + "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "MPNet and LongT5 are unrelated model families." + "reason": "Segformer vs LongT5 are different model-specific refactors." }, { - "left": "pull_request:43997", - "right": "pull_request:44017", + "left": "pull_request:44073", + "right": "pull_request:44101", "accept": false, - "reason": "RegNet and Segformer are different architectures; same refactor style only." + "reason": "VisualBert vs Flaubert/XLM are different concrete changes." }, { - "left": "pull_request:43997", - "right": "pull_request:44056", + "left": "pull_request:44059", + "right": "pull_request:44068", "accept": false, - "reason": "RegNet versus MPNet; no same underlying change." + "reason": "GPT-2 vs GPT-Neo are separate model implementations." }, { - "left": "pull_request:44071", - "right": "pull_request:44129", + "left": "pull_request:44018", + "right": "pull_request:44059", "accept": false, - "reason": "MPT and SpeechT5 are unrelated code paths." + "reason": "GPT-Neo vs GPT-2 are different code paths." }, { - "left": "pull_request:44010", - "right": "pull_request:44071", + "left": "pull_request:44101", + "right": "pull_request:44161", "accept": false, - "reason": "SqueezeBERT and MPT are different model implementations." + "reason": "Flaubert/XLM vs LongT5 are unrelated model refactors." }, { - "left": "pull_request:44010", - "right": "pull_request:44073", + "left": "pull_request:43997", + "right": "pull_request:44017", "accept": false, - "reason": "SqueezeBERT and VisualBert are unrelated concrete changes." + "reason": "RegNet vs Segformer are different model families." }, { - "left": "pull_request:44017", - "right": "pull_request:44722", + "left": "pull_request:43997", + "right": "pull_request:44056", "accept": false, - "reason": "Segformer and GPT-J/CodeGen are different models." + "reason": "RegNet vs MPNet are different concrete changes." }, { - "left": "pull_request:44017", - "right": "pull_request:44161", + "left": "pull_request:43997", + "right": "pull_request:44018", "accept": false, - "reason": "Segformer and LongT5 are unrelated code paths." + "reason": "RegNet vs GPT-Neo are unrelated model-specific refactors." }, { - "left": "pull_request:44017", - "right": "pull_request:44073", + "left": "pull_request:43997", + "right": "pull_request:44074", "accept": false, - "reason": "Segformer and VisualBert are different model families." + "reason": "RegNet vs TextNet are different code paths." }, { "left": "pull_request:43997", "right": "pull_request:44161", "accept": false, - "reason": "RegNet and LongT5 are unrelated concrete changes." + "reason": "RegNet vs LongT5 are unrelated changes." }, { - "left": "pull_request:44074", - "right": "pull_request:44161", + "left": "pull_request:44071", + "right": "pull_request:44129", "accept": false, - "reason": "TextNet and LongT5 are different model implementations." + "reason": "MPT vs SpeechT5 are different model implementations." }, { - "left": "pull_request:43997", - "right": "pull_request:44018", + "left": "pull_request:44010", + "right": "pull_request:44071", "accept": false, - "reason": "RegNet and GPT-Neo are unrelated code paths." + "reason": "SqueezeBert vs MPT are not the same underlying fix." }, { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44010", + "right": "pull_request:44073", "accept": false, - "reason": "RegNet and TextNet are different models." + "reason": "SqueezeBert vs VisualBert are different model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo vs SpeechT5 are different code paths." }, { "left": "pull_request:44010", "right": "pull_request:44018", "accept": false, - "reason": "SqueezeBERT and GPT-Neo are unrelated implementations." + "reason": "SqueezeBert vs GPT-Neo are unrelated model refactors." }, { "left": "pull_request:43996", "right": "pull_request:44161", "accept": false, - "reason": "CVT/FNet and LongT5 are unrelated concrete changes." + "reason": "CVT/FNet vs LongT5 are different model implementations." }, { "left": "pull_request:43996", "right": "pull_request:44017", "accept": false, - "reason": "CVT/FNet versus Segformer; same initiative, different code paths." + "reason": "CVT/FNet vs Segformer are different concrete changes." }, { "left": "pull_request:44010", "right": "pull_request:44044", "accept": false, - "reason": "SqueezeBERT and DeBERTaV2 are unrelated models." + "reason": "SqueezeBert vs DeBERTa are separate model-specific refactors." }, { "left": "pull_request:44044", "right": "pull_request:44074", "accept": false, - "reason": "DeBERTaV2 and TextNet are different code paths." + "reason": "DeBERTa vs TextNet are different model code paths." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are different models; same general output-tracing theme only." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen output-tracing refactor set; 44722 is a broader version of the same concrete change." + "reason": "Both are the same GPT-J/CodeGen standardized output-tracing refactor with heavily overlapping intent and files." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both cover the same GPT-J output-tracing rewrite in modeling_gptj.py; 44722 subsumes the earlier GPT-J-only variant." + "reason": "Both appear to implement the same GPT-J output-tracing change and could plausibly be merged into one PR." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J and SpeechT5 are unrelated code paths." + "reason": "GPT-J vs SpeechT5 are different model families." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "Different model families and different concrete changes." + "reason": "CVT/FNet vs RegNet/ResNet/RT-DETR are different code paths." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet and SpeechT5 are unrelated implementations." + "reason": "CVT/FNet vs SpeechT5 are unrelated model-specific changes." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTaV2 and SpeechT5 are different code paths." + "reason": "DeBERTa vs SpeechT5 are different model implementations." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTaV2 and VITS are unrelated model families." + "reason": "DeBERTa vs VITS are different concrete changes." }, { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "FocalNet and ImageGPT are different concrete changes." + "reason": "FocalNet vs ImageGPT are different models; broad refactor similarity is not enough to treat them as duplicates." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is well grounded in the packet and stays conservative. The representative PR choice (44722) is supported by the shared GPT-J/CodeGen file overlap and broader scope, and the accepted soft-edge pairs look mergeable as same-family, same-refactor variants. I don\u2019t see overstatement beyond the evidence." + "feedback": "The summary is well grounded in the packet: #43979 is clearly a repeated issue target across the cluster, and #44722 is a reasonable representative for the GPT-J/CodeGen subgroup based on its later date, shared files, and explicit issue link. The soft-edge decisions are mostly conservative cross-model negatives, while the accepted pairs are within the same model family and look mergeable as alternate versions of the same bugfix." }, "evaluator_used": true, "retried": false, @@ -18663,7 +18731,7 @@ { "label": "pull_request", "component_index": 14, - "component_count": 26, + "component_count": 27, "review_unit_index": 2, "review_unit_count": 2, "status": "reviewed", @@ -18687,7 +18755,7 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "c9bc2c8f0c9eecdb39e67a6ee63231ce68dd17e66bcf402e9b7bc57278641630", + "prepared_review_unit_hash": "79379a6f038f706cb75b22b230c6def9b84d95b29bd4fa255bdf329eda9eedf2", "component_budget": { "node_count": 28, "item_count": 28, @@ -18700,7 +18768,7 @@ "node_count": 6, "item_count": 6, "soft_pair_count": 5, - "serialized_chars": 13066, + "serialized_chars": 13067, "estimated_input_tokens": 3267, "estimated_eval_tokens": 6790 }, @@ -18709,42 +18777,42 @@ "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are model-specific PRs all migrating to standardized output tracing/capture utilities. They are thematically similar, but they do not describe the same underlying bug or change and should not be deduplicated together.", - "confidence": 0.95, + "summary": "These are thematically similar PRs for model-by-model migration to standardized output tracing, but they are not duplicates of the same fix/change. Each one targets a different architecture and code path.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "44073 is a clean representative of the cluster\u2019s common pattern: a single-model refactor wiring standardized output capture into VisualBert.", + "canonical_pr_reason": "PR 44129 is the best cluster anchor: it has an explicit issue target, a clear refactor scope, and is representative of the standardized output-capture migration pattern.", "best_issue_reason": null, - "best_pr_reason": "44129 is the strongest standalone PR because it is focused, model-specific, and explicitly tied to issue 43979.", + "best_pr_reason": "PR 44129 is the most suitable representative because it is self-contained, explicitly linked to an issue, and clearly scoped to one model's output-tracing refactor.", "soft_edge_verdicts": [ { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both are output-tracing refactors, but they target different models and code paths (VisualBert vs TextNet). Similar pattern, not the same change." + "reason": "Same refactor theme, but different models and different code paths; not the same underlying change." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert are separate model implementations; these are parallel refactors, not one shared bug fix." + "reason": "Both modernize output tracing, but they touch different model implementations and are separate migrations." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "Different models and different forward/capture wiring. The overlap is only the migration style, not the underlying code-path issue." + "reason": "Different model-specific refactors; too broad to treat as one duplicate change." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model-specific changes. They both touch output handling, but not the same defect or mergeable fix." + "reason": "Both are output-tracing cleanups, but for distinct architectures and forward methods, so not duplicates." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 are different subsystems and the diffs reflect distinct refactors, so they should not be merged as duplicates." + "reason": "Shared standardized-output motivation, but they fix separate model implementations and should not be merged as one PR." } ] }, @@ -18758,7 +18826,7 @@ { "label": "pull_request", "component_index": 15, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -18824,7 +18892,7 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "31803759bc2075ed3e405364beb40fa1a3d615db36531a8755bd935b8c895b96", + "prepared_review_unit_hash": "eb6466aa587c221c1979247d16621b7ec521a86b732ed4e300a1e4a5a9abedcf", "component_budget": { "node_count": 13, "item_count": 13, @@ -18846,252 +18914,252 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a loose thematic group of model-specific output-tracing refactors, not a set of duplicate fixes. The PRs touch different architectures and code paths, so none should be merged together as the same change.", - "confidence": 0.98, + "summary": "These PRs share a common theme\u2014model-specific refactors to output tracing / tuple-return handling\u2014but they touch different model code paths and are not duplicate fixes. I would not merge any of the soft-edge pairs as the same underlying change.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the set spans unrelated model implementations and separate refactors, so there is no one underlying change to anchor the cluster.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the best representative seed because it is a substantive output-tracing refactor across two closely related Depth Anything files, but it is still model-specific rather than a duplicate of the others.", + "best_pr_reason": "PR 44025 is the clearest representative of the cluster because it applies the output-tracing refactor in a focused way across two closely related files, but it is still not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and files (timm_backbone vs upernet); same refactor theme only, not the same underlying fix." + "reason": "Different model families and separate forward-path refactors; same broad pattern, not the same change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Different architectures and code paths (timm_backbone vs vision_text_dual_encoder); not mergeable as one PR." + "reason": "Different models and distinct code paths; both refactor output handling but are not mergeable as one fix." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different model implementations (timm_backbone vs univnet); only a shared output-tracing pattern." + "reason": "Unrelated model implementations; only the tracing refactor pattern matches." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Separate code paths across timm_backbone and falcon_mamba/mamba; not the same concrete bug/change." + "reason": "Different architectures and files; this is not the same underlying bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "timm_backbone and rwkv are unrelated model code paths; too broad to treat as duplicate." + "reason": "Same output-tracing theme, but the PRs target different model stacks and code paths." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated implementations; similar refactor style only." + "reason": "Separate models with similar refactoring style, not the same concrete fix." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different models and files; no shared underlying defect." + "reason": "Different model code paths; these are parallel refactors, not duplicates." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "MobileNetV1 vs Depth Anything are separate model-specific changes, not one fix." + "reason": "Different model families and outputs; no shared underlying bug." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "MobileNetV1 and Vision Encoder-Decoder touch unrelated code paths." + "reason": "Both change output-tracing behavior, but for unrelated model wrappers." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "MobileNetV1 and Speech Encoder-Decoder are different model families; not duplicates." + "reason": "Different encoder-decoder model and separate refactor scope." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-Text Dual Encoder and UnivNet do not share a concrete bug or change." + "reason": "Distinct models; same refactoring motif only." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths (vision-text dual encoder vs upernet); only broad refactor similarity." + "reason": "No shared concrete code path despite similar output-tracing cleanup." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Different architectures and files; not the same underlying change." + "reason": "Different model implementations; not one fix split across PRs." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Vision-Text Dual Encoder and Depth Anything are unrelated; cannot be merged as one PR." + "reason": "Related only by refactor style, not by the same bug or code path." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet are separate models with no shared code path." + "reason": "Separate model code paths with similar API cleanup, not a duplicate change." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "UnivNet vs Mamba/Falcon Mamba are unrelated implementations." + "reason": "Different models and files; same broad subsystem but not same change." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Different model families and fixes; same refactor theme is too broad." + "reason": "These are independent model-specific refactors, not one mergeable PR." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are unrelated code paths; not the same concrete bug/change." + "reason": "Different model families; no evidence they fix the same concrete problem." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "UperNet vs Falcon Mamba/Mamba are distinct model-specific refactors." + "reason": "Separate output-tracing refactors in unrelated code paths." }, { "left": "pull_request:44003", "right": "pull_request:44028", "accept": false, - "reason": "Falcon Mamba/Mamba and SuperPoint are different subsystems and not mergeable together." + "reason": "Falcon/Mamba vs SuperPoint: unrelated implementations and changes." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba-related output-tracing refactor vs CodeGen cache/output refactor: different code paths and changes." + "reason": "Different model classes and distinct call sites; not the same underlying fix." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated models; too generic to be a duplicate." + "reason": "Both are refactors around model outputs, but for different models and code paths." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "UnivNet and CodeGen touch different model classes and behaviors." + "reason": "Different models; similar intent but not a shared concrete bug." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "UperNet and CodeGen are separate fixes in different architectures." + "reason": "Distinct model implementations and separate refactor scopes." }, { "left": "pull_request:44000", "right": "pull_request:44004", "accept": false, - "reason": "Vision-Text Dual Encoder and CodeGen are unrelated code paths." + "reason": "Only the general output-tracing theme overlaps; the code paths are unrelated." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Depth Anything vs Vision Encoder-Decoder are unrelated model implementations." + "reason": "Different model families; these are parallel refactors, not duplicate fixes." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Depth Anything and Speech Encoder-Decoder are different code paths; only similar refactor wording." + "reason": "Separate encoder/decoder wrappers and different output logic." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Depth Anything and SuperPoint are unrelated model families." + "reason": "Different models and implementations; no shared concrete bug/change." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Depth Anything and RWKV are separate changes in different subsystems." + "reason": "Same refactor pattern, but not the same model or code path." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Depth Anything and DPR do not share the same concrete fix." + "reason": "Unrelated model code; not mergeable as one PR." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "Vision Encoder-Decoder and RWKV are unrelated model paths." + "reason": "Different model wrappers and separate refactor targets." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Vision Encoder-Decoder and Speech Encoder-Decoder are distinct implementations; not one PR." + "reason": "Same broad refactor theme only; no identical underlying issue." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Vision Encoder-Decoder and SuperPoint are separate model-specific refactors." + "reason": "Different model families and code paths." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Vision Encoder-Decoder and DPR are unrelated code paths." + "reason": "Distinct models; similar output-handling cleanup is not enough to merge." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech Encoder-Decoder and SuperPoint are different model families and fixes." + "reason": "Encoder-decoder wrapper vs keypoint model: unrelated changes." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Speech Encoder-Decoder and RWKV are unrelated changes." + "reason": "Different model systems; same theme, not same fix." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech Encoder-Decoder and DPR do not appear to fix the same underlying issue." + "reason": "No shared code path or bug; only similar refactoring style." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are different subsystems with no shared concrete bug." + "reason": "SuperPoint and RWKV are unrelated; not a duplicate." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "SuperPoint and DPR are unrelated model implementations." + "reason": "Different models and output semantics; not the same change." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR are separate model-specific changes, not a single duplicate fix." + "reason": "RWKV and DPR address different architectures and code paths." } ] }, @@ -19105,7 +19173,7 @@ { "label": "pull_request", "component_index": 16, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19124,12 +19192,12 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "e330250c3f8ee8c5d92e192a946ac6dc6fcca17de29f5fb831b551f03d4510c9", + "prepared_review_unit_hash": "f82019475c3d468ec8a439a580582ebbfa206281bf99de8b15af9aa18eb6585e", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10912, + "serialized_chars": 10910, "estimated_input_tokens": 2728, "estimated_eval_tokens": 5712 }, @@ -19137,7 +19205,7 @@ "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10912, + "serialized_chars": 10910, "estimated_input_tokens": 2728, "estimated_eval_tokens": 5712 }, @@ -19146,30 +19214,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Three independent model-addition PRs for different models (PenguinVL, DeepSeek-OCR-2, and Voxtral TTS). They share framework plumbing and docs patterns, but not the same underlying change, so none should be clustered as duplicates.", + "summary": "These three PRs only look similar at the boilerplate level: they add different models in different modalities (vision-language, OCR, and TTS) with distinct code paths and files. They are not duplicates of one another.", "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 45075 is the strongest standalone representative: it appears the most complete and mature, with model code, conversion tooling, image processing, processing, tests, and config/auto-registration updates for a single concrete model addition.", + "best_pr_reason": "No single PR is a suitable representative because each change introduces a different model family and implementation path; they should remain separate.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model additions for unrelated products (PenguinVL vs Voxtral TTS). Overlapping auto-registration/docs files are generic integration work, not the same bug or change." + "reason": "PenguinVL adds a vision-language model, while Voxtral TTS adds a text-to-speech model; different modalities and concrete implementations, so not the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Different model implementations targeting different architectures and use cases. Shared repo plumbing is incidental; these could not plausibly be merged as one fix." + "reason": "PenguinVL and DeepSeek-OCR-2 are separate model additions with different architectures and targets; shared docs/auto-registration files are boilerplate, not duplicate evidence." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are distinct model families with different code paths and assets. Similar file patterns do not indicate the same underlying change." + "reason": "DeepSeek-OCR-2 is an OCR model, while Voxtral TTS is a speech synthesis model; they do not fix or add the same underlying code path." } ] }, @@ -19183,7 +19251,7 @@ { "label": "pull_request", "component_index": 17, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19199,12 +19267,12 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "89333b7dfe7edd8ee587861bf9dbfd10581a50000e5eb28d65141efbe365704b", + "prepared_review_unit_hash": "46b5def8d7ad9b9a6fa05b7307450383d1c1f2f4afc8847777ab8cd108eb81e9", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4406, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -19212,7 +19280,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4406, + "serialized_chars": 4407, "estimated_input_tokens": 1102, "estimated_eval_tokens": 2460 }, @@ -19221,18 +19289,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Related but distinct fusion efforts: #44979 adds a generic Module Fusion API, while #45363 implements KernelConfig-driven n-to-1 kernel fusion and integration changes. They share the fusion theme but not the same underlying change.", - "confidence": 0.93, + "summary": "These PRs are thematically related to fusion, but they implement different things: #44979 introduces a new generic Module Fusion API, while #45363 adds KernelConfig-based n-to-1 kernel fusion wiring and an example. They are not the same underlying change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "#45363 is the more concrete end-to-end implementation, touching integration points and usage examples; #44979 is a standalone API scaffold.", + "canonical_pr_reason": "#45363 is the more concrete, end-user-facing fusion feature PR: it threads KernelConfig through model loading and adds integration code and an example. #44979 is foundational API work for module fusion, not the same change.", "best_issue_reason": null, - "best_pr_reason": "#45363 is the stronger representative because it delivers the actual kernel-config fusion path and end-user wiring, whereas #44979 is the generic module-fusion API.", + "best_pr_reason": "#45363 best represents the cluster because it has the clearest specific behavior change and broader integration footprint, but it should not be merged as a duplicate of #44979.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Different abstractions and code paths: #44979 defines a generic module-fusion API, while #45363 adds n-to-1 kernel fusion via KernelConfig plus integration plumbing. They are related but not the same fix and would not naturally merge into one PR." + "reason": "Related fusion infrastructure, but not the same code-path problem: #44979 adds a new module-fusion API, while #45363 implements KernelConfig-driven n-to-1 fusion across loading/integration code. They could not plausibly be one PR without changing the scope substantially." } ] }, @@ -19246,7 +19314,7 @@ { "label": "pull_request", "component_index": 18, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19262,7 +19330,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "9886d36d9828ad1bb2dfe7c18cd5cd07fd4112976ac6a56fd3191bfa879b0957", + "prepared_review_unit_hash": "3d1bf6d211963c912c8755860cca402365a7f39513b6425491cf3922575c082c", "component_budget": { "node_count": 2, "item_count": 2, @@ -19284,18 +19352,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests fix the same AttributeError in `_patch_mistral_regex` by switching from `tokenizer.backend_tokenizer.pre_tokenizer` to `tokenizer.pre_tokenizer` in the same code path. PR 45317 is the more complete version because it includes test coverage.", - "confidence": 0.97, + "summary": "Both pull requests target the same Mistral regex patch bug in `tokenization_utils_tokenizers.py` and make the same fix; the later PR adds tests and looks like the stronger canonical choice.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the better canonical PR because it contains the same fix as 45086 plus tests, making it the more complete and reviewable implementation.", + "canonical_pr_reason": "PR #45317 is the better canonical PR because it applies the same code fix as #45086 and also includes test coverage, making it the more complete change set.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the best PR candidate: it addresses the same concrete bug, touches the same lines, and adds regression tests for the fix.", + "best_pr_reason": "PR #45317 is the best overall PR candidate because it addresses the same concrete AttributeError path as #45086 while adding validation in tests, so it is the most merge-ready representative of the fix.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same underlying bug and same code-path change in `_patch_mistral_regex`; the later PR is essentially the same fix with added tests, so they are mergeable as one change." + "reason": "Accept: both PRs fix the same `_patch_mistral_regex` AttributeError in the same file, with the same underlying code-path change; #45317 is essentially a superset with added tests." } ] }, @@ -19309,7 +19377,7 @@ { "label": "pull_request", "component_index": 19, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19325,7 +19393,7 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "58826e1ebdc3524766bf8ec42c3ed98074d2adbf612972611f611e765c810ec1", + "prepared_review_unit_hash": "7edc49898e5d011e5ac2c895c87fc28cc76f7ac79d79cd7e4d51aa5a21e7d65f", "component_budget": { "node_count": 2, "item_count": 2, @@ -19347,18 +19415,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct NemotronH PRs: one refactors/aliases NemotronH around GraniteMoeHybrid conversion logic, the other adds the NemotronHDense/NemotronHSparse model split and supporting docs/tests. They overlap on shared NemotronH files, but they are not the same concrete change.", - "confidence": 0.84, + "summary": "The two PRs overlap on NemotronH internals, but they target different changes: one refactors NemotronH conversion/model inheritance toward GraniteMoeHybrid compatibility, while the other splits NemotronH into separate dense/sparse model families and updates docs/tests. They are related, but not the same underlying fix/change set.", + "confidence": 0.87, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45569 is the more complete and user-facing Nemotron release change: it introduces the dense/sparse model packages, updates auto-mapping/docs, and includes tests. PR #45115 is a narrower refactor/conversion-mapping step.", + "canonical_pr_reason": "PR #45569 is the broader, more complete NemotronH family change: it adds the new dense/sparse model variants, wiring, docs, and tests, rather than only a conversion/inheritance refactor.", "best_issue_reason": null, - "best_pr_reason": "PR #45569 best represents the cluster because it covers the broader end-state change for NemotronH model support, while #45115 is a partial enabling refactor focused on conversion mapping and inheritance wiring.", + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the main architectural reshaping of NemotronH into dedicated variants and includes the associated integration work.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Shared subsystem and files, but different scopes: #45115 is a conversion/inheritance refactor for NemotronH, while #45569 adds separate dense/sparse model implementations, docs, auto mappings, and tests. They are related follow-on work, not the same fix/change." + "reason": "Both touch NemotronH code, but #45115 is a focused GraniteMoeHybrid-style refactor/conversion mapping update, while #45569 creates separate dense/sparse NemotronH models and updates docs/tests. They are not the same concrete bug or change and would not plausibly merge into one PR." } ] }, @@ -19372,7 +19440,7 @@ { "label": "pull_request", "component_index": 20, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19388,7 +19456,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "7765e6fbf84f49d37ddf3e28559a7b735d3f5ae3ef7971532bfa585cecceb87b", + "prepared_review_unit_hash": "bf090aa1584fc20fb417574f8828d68dcc9ded679ebd517a15dea60691572a5b", "component_budget": { "node_count": 2, "item_count": 2, @@ -19410,18 +19478,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related feature PRs, but they are not duplicates: one introduces heterogeneous per-layer config support, while the other adds broader heterogeneous modeling/cache behavior on top of that. The larger PR is the better representative for the overall feature set.", + "summary": "These are related feature PRs for heterogeneous-model support, but they are not duplicates: #45333 introduces heterogeneous config primitives, while #45332 adds broader cache/modeling integration and GPT-OSS support.", "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45332 is the broader, more complete change: it covers heterogeneous model support across config, modeling, cache handling, masking, and tests, so it best represents the combined feature work.", + "canonical_pr_reason": "If a single representative is needed, #45332 is the broader end-to-end heterogeneous model support PR; #45333 is the narrower config-foundation change it builds on.", "best_issue_reason": null, - "best_pr_reason": "PR 45332 is the best overall PR because it contains the concrete runtime/model-path changes in addition to the config plumbing, making it the most comprehensive canonical artifact for this feature area.", + "best_pr_reason": "#45332 is the better global representative for the cluster because it covers the full user-facing heterogeneous-model path, whereas #45333 is only the configuration layer.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Not the same underlying change. 45333 is specifically about per-layer heterogeneous config plumbing, while 45332 adds heterogeneous model/runtime support and additional cache/modeling changes. They are related, but not close enough to merge as duplicates." + "reason": "They share heterogeneity infrastructure, but they are different change sets: #45333 adds per-layer config support, while #45332 adds model/cache behavior and model-specific integration. They are complementary, not the same concrete PR." } ] }, @@ -19435,7 +19503,7 @@ { "label": "pull_request", "component_index": 21, - "component_count": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19451,12 +19519,12 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "947c015a5a5b7f5771602b2ad2097b4ac391a292a0804a545056843ff2615804", + "prepared_review_unit_hash": "b1f01a5a92269bfb47df284710a1454758891e7f5bc3d6c7677ec07f5f85e43d", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5514, + "serialized_chars": 5513, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -19464,7 +19532,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5514, + "serialized_chars": 5513, "estimated_input_tokens": 1379, "estimated_eval_tokens": 3014 }, @@ -19473,18 +19541,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs in the typing/type-checking area, but they address different changes: one is a broad type-checking sweep across many `src/transformers/*.py` files, while the other adds specific typing aliases/protocols and related support for `modeling_utils`/PEFT integration. They are related in theme, not duplicates.", - "confidence": 0.85, + "summary": "Both PRs are typing-related, but they target different changes: 45415 is a broad repo-wide type-checking sweep with config suppressions, while 45425 adds specific typing protocols/helpers for internals. They are not duplicates.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45415 is the broader umbrella change and best represents the cluster\u2019s overall theme of expanding type checking across the codebase.", + "canonical_pr_reason": "No true duplicate canonical PR: 45415 is a broad type-checking enablement sweep; 45425 is a narrower typing-infra update. They do not address the same concrete change.", "best_issue_reason": null, - "best_pr_reason": "PR #45415 is the most central artifact for this cluster because it applies type checking across many modules, whereas #45425 is a narrower typing-support refactor.", + "best_pr_reason": "45425 is the better representative because it makes a focused code-level typing change in shared helper types, whereas 45415 is mostly an expansive sweep/configuration change.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Both are typing-related and share a few files, but they are not the same concrete change: #45415 is a broad type-checking sweep across many modules, while #45425 adds specific typing protocols/aliases and helper support for modeling_utils and PEFT. They would not plausibly be merged as one PR." + "reason": "Shared typing files and similar theme aren't enough: 45415 is a large type-checking pass across many modules, while 45425 adds specific typing protocols and helper aliases for modeling/utilities. They are different underlying changes and wouldn't plausibly be merged as one PR." } ] }, @@ -19498,7 +19566,70 @@ { "label": "pull_request", "component_index": 22, - "component_count": 26, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45513-2", + "nodes": [ + "pull_request:45513", + "pull_request:46084" + ], + "soft_pairs": [ + "pull_request:45513|pull_request:46084" + ], + "prepared_review_unit_hash": "e77e9e03106f298308b3a5c138047666f30e3bfb039fbc2179db0407007ca1ef", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4857, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4857, + "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 both cache-related PRs, but they fix different model families and different code paths. The Mamba2 PR is a focused seq_len>1 use_cache bug fix; the Qwen3.5/Olmo hybrid PR is a broader multi-model linear-attention cached-forward fix. They should not be clustered as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:46084 is the better canonical PR: it is a narrow, explicit fix for Mamba2 use_cache when seq_len > 1, with a direct issue reference (#46032) and a focused diff. The other PR spans multiple models and a different attention path, making it less representative of a single underlying change.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:46084 is the strongest representative of a concrete bug fix because it targets one code path, one model family, and one specific failure mode. pull_request:45513 is broader and less suitable as the global exemplar for this cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Different underlying fixes: 45513 changes cached multi-token forward in Qwen3.5/Olmo hybrid linear attention, while 46084 fixes Mamba2 cuda_kernels_forward for use_cache with seq_len > 1. Similar cache theme, but not the same bug or mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19514,7 +19645,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "6ee5372bc894a41c7f4b74f5a8b4c3ed4cc25e239cd60b99433d3b068b95f831", + "prepared_review_unit_hash": "ff485957f394b1fe05227547bf845b9d5089a5100fe98f6c3751c65e49ec9922", "component_budget": { "node_count": 2, "item_count": 2, @@ -19536,18 +19667,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs are EP-related, but they target different failure modes and code paths: one fixes accelerate/DeepSpeed ZeRO-3 loading and config serialization, the other fixes FSDP2/rank-0 broadcast overwriting expert weights. They should not be merged as duplicates.", - "confidence": 0.96, + "summary": "Two EP-related PRs, but they fix different loading bugs: one targets accelerate/ZeRO-3 serialization and distributed_config handling, the other targets FSDP2/rank-0 broadcast overwriting expert parameters.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45662 is the more concrete, self-contained bug fix: it addresses a specific rank-0 broadcast overwrite path and includes targeted changes in loading and MoE/TP handling. PR #45548 is a separate accelerate/ZeRO-3 loading issue with different mechanics.", + "canonical_pr_reason": "PR 45662 is the stronger representative of the cluster: it fixes a concrete expert-parameter overwrite path in the model-loading code and spans the relevant loading/integration layers.", "best_issue_reason": null, - "best_pr_reason": "PR #45662 is the best representative of the cluster because it describes a precise observable corruption bug with a clear fix path. It is not the same underlying change as #45548, which is about a different loading/deep-speed integration problem.", + "best_pr_reason": "PR 45662 is the best standalone candidate because its bug description is clearer and the fix is more directly tied to a specific incorrect code path; PR 45548 is narrower and addresses a separate accelerate-launch/ZeRO-3 issue.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Different underlying bugs and fix paths: #45548 is about EP + DeepSpeed ZeRO-3 loading via accelerate and config serialization, while #45662 is about FSDP2 experts being overwritten by rank-0 broadcast. Shared EP wording is too broad to treat as one change." + "reason": "Both concern expert parallelism, but they fix different problems: 45548 is about accelerate-launch/DeepSpeed ZeRO-3 loading and config serialization, while 45662 is about FSDP2/rank-0 broadcast silently overwriting experts. The code paths and failure modes are distinct." } ] }, @@ -19560,8 +19691,8 @@ }, { "label": "pull_request", - "component_index": 23, - "component_count": 26, + "component_index": 24, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19577,12 +19708,12 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "235c456a06ff512c3cb64580a3b334dd0211fa6b2b47fa1a21344fcc4ac3877c", + "prepared_review_unit_hash": "abe5f3b567add0957812a6c2d016dcee23afa71a1f526b76f1f58cb7ae1b1b7c", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19590,7 +19721,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4589, + "serialized_chars": 4590, "estimated_input_tokens": 1148, "estimated_eval_tokens": 2552 }, @@ -19599,18 +19730,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same xdist-related captured_info collision in testing_utils. PR 45645 appears to subsume PR 45639 by including the same worker-safe output-file fix plus CI log aggregation changes, so they are likely duplicates or near-duplicates in the same change area.", - "confidence": 0.87, + "summary": "Both PRs target the same xdist collision problem around `captured_info` output from `testing_utils.py`; #45645 is the broader follow-up that includes the core fix plus CI log aggregation, while #45639 is the narrower subset.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the more complete fix: it contains the worker-safe captured_info change in src/transformers/testing_utils.py and also updates CI handling to read multiple captured_info files. It best represents the underlying bug-fix effort.", + "canonical_pr_reason": "PR #45645 is the more complete fix: it includes the xdist-safe per-worker output change in `src/transformers/testing_utils.py` and also updates CI to collect multiple `captured_info*.txt` files, so it subsumes the narrower PR.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the best overall representative because it addresses the core xdist collision and preserves/debug-collects artifacts in CI, whereas PR 45639 is only the narrower code-path fix.", + "best_pr_reason": "PR #45645 is the best representative because it addresses the full end-to-end behavior change for xdist-safe debug logs and preserves CI visibility, not just the library-side write-path fix.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Same underlying bug: xdist collisions for captured_info output in testing_utils. The second PR includes the same fix and extends it for CI artifact consumption, so they plausibly belong in one merged change." + "reason": "Both PRs fix the same underlying `captured_info` xdist collision in `testing_utils.py`; #45645 extends the same fix with the necessary CI workflow adaptation, so they could plausibly be merged into one PR." } ] }, @@ -19623,8 +19754,8 @@ }, { "label": "pull_request", - "component_index": 24, - "component_count": 26, + "component_index": 25, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19686,8 +19817,8 @@ }, { "label": "pull_request", - "component_index": 25, - "component_count": 26, + "component_index": 26, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19752,8 +19883,8 @@ }, { "label": "pull_request", - "component_index": 26, - "component_count": 26, + "component_index": 27, + "component_count": 27, "review_unit_index": 1, "review_unit_count": 1, "status": "reviewed", @@ -19769,7 +19900,7 @@ "soft_pairs": [ "pull_request:46069|pull_request:46073" ], - "prepared_review_unit_hash": "fdbd15c1bfe1a1f6cc0144f6dc5592fb4393941bc199a936d8556d62e91f163a", + "prepared_review_unit_hash": "e3b94c88cfe283bb4ec42d74ec841b5662d6d4e5b614767f6302310ab811870f", "component_budget": { "node_count": 2, "item_count": 2, @@ -19791,18 +19922,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests add attention-dispatch support, but they do so for different models and code paths: ShieldGemma2 image classification versus CTRL. They are related in theme, not duplicates of the same underlying change.", - "confidence": 0.97, + "summary": "These are not duplicates: both PRs add `attn_implementation` dispatch support, but they target different model implementations (`ShieldGemma2` vs `CTRL`) and modify different code paths/files.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the two patches are model-specific and implement attn_implementation dispatch in different architectures.", + "canonical_pr_reason": "No canonical PR: the changes are model-specific and do not appear mergeable into one patch or fix the same concrete code-path problem.", "best_issue_reason": null, - "best_pr_reason": "PR 46069 is the stronger representative of the cluster because it includes a concrete model-side flag change plus tests, but it is still not a duplicate of the CTRL PR.", + "best_pr_reason": "Neither PR is a better duplicate representative because they address separate models; if forced, `#46069` is slightly more self-contained, but it should not subsume `#46073`.", "soft_edge_verdicts": [ { "left": "pull_request:46069", "right": "pull_request:46073", "accept": false, - "reason": "Both are about attn_implementation dispatch, but they target different models (ShieldGemma2 vs CTRL) and different attention implementations, so they are not the same fix." + "reason": "Both are about attention dispatch support, but they touch different model backends and distinct attention implementations. They are related feature work, not the same underlying bug/change." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index 6928860dc862856806a7056f67a4d669e1bce7f7..c9e39fb0377c3121524670f9eedd87d76d980fd7 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260519t180042z", + "analysis_id": "hybrid-model-20260520t000134z", "archived_artifacts": { - "hybrid": "snapshots/20260519T180042Z/analysis-runs/hybrid-model-20260519t180042z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260519T180042Z/analysis-runs/hybrid-model-20260519t180042z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-19T18:16:54Z", + "published_at": "2026-05-20T00:12:12Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260519T180042Z", + "snapshot_id": "20260520T000134Z", "variant": "hybrid" } diff --git a/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..e35068321c6d84015892e4eccd4b136145af972a --- /dev/null +++ b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json @@ -0,0 +1,1997 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260520T000134Z", + "generated_at": "2026-05-20T00:12:11Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.805, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.854, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 713, + 720 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 699, + 705 + ], + [ + 1301, + 1307 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45081-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45081.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45081, + "canonical_pr_number": 45317, + "issue_numbers": [ + 45081 + ], + "pr_numbers": [ + 45086, + 45317 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45086, + "right_pr_number": 45317, + "code_similarity": 0.589, + "size_similarity": 0.34, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.136, + "shared_filenames": [ + "src/transformers/tokenization_utils_tokenizers.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/tokenization_utils_tokenizers.py", + "left_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ], + "right_ranges": [ + [ + 1360, + 1370 + ], + [ + 1374, + 1380 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45561-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45561.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 45561, + "canonical_pr_number": 45645, + "issue_numbers": [ + 45561 + ], + "pr_numbers": [ + 45639, + 45645 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 45639, + "right_pr_number": 45645, + "code_similarity": 0.532, + "size_similarity": 0.619, + "file_overlap": 0.5, + "area_overlap": 0.543, + "patch_similarity": 0.451, + "shared_filenames": [ + "src/transformers/testing_utils.py", + "tests/utils/test_testing_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/testing_utils.py", + "left_ranges": [ + [ + 3529, + 3536 + ], + [ + 3753, + 3787 + ] + ], + "right_ranges": [ + [ + 3525, + 3558 + ], + [ + 3782, + 3788 + ] + ] + }, + { + "filename": "tests/utils/test_testing_utils.py", + "left_ranges": [ + [ + 1, + 86 + ] + ], + "right_ranges": [ + [ + 1, + 114 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43698-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43698.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43698, + "canonical_pr_number": 43779, + "issue_numbers": [ + 43698 + ], + "pr_numbers": [ + 43779, + 43816 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43779, + "right_pr_number": 43816, + "code_similarity": 0.418, + "size_similarity": 0.538, + "file_overlap": 1.0, + "area_overlap": 0.02, + "patch_similarity": 0.02, + "shared_filenames": [ + "src/transformers/integrations/integration_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/integrations/integration_utils.py", + "left_ranges": [ + [ + 2227, + 2241 + ], + [ + 2303, + 2309 + ] + ], + "right_ranges": [ + [ + 2278, + 2291 + ], + [ + 2309, + 2322 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-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 12 discussion comments plus 8 inbound references.", + "score": 162.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..881320483e5692b2affcc16e9b8af6342faa26a7 --- /dev/null +++ b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,19948 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260520T000134Z", + "generated_at": "2026-05-20T00:12:11Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41093", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue:43541", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:45874", + "issue:45901", + "issue:45902", + "issue:45920", + "issue:46015" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:45901|issue:46015", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43596|issue:44805", + "issue:44805|issue:45161", + "issue:44805|issue:44918", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43039|issue:45161", + "issue:43975|issue:44457", + "issue:44292|issue:44457", + "issue:34928|issue:44805", + "issue:24643|issue:30277", + "issue:45859|issue:45902", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43425|issue:44292", + "issue:43828|issue:45161", + "issue:34928|issue:41720", + "issue:44918|issue:45161", + "issue:43716|issue:45685", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:45507|issue:45685", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44560|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:45237|issue:46015", + "issue:34928|issue:36010", + "issue:43039|issue:44805", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:39290|issue:41720", + "issue:45237|issue:45901", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43975|issue:46015", + "issue:45812|issue:45920", + "issue:44863|issue:46015", + "issue:43866|issue:44863", + "issue:44292|issue:46015", + "issue:43854|issue:43866", + "issue:41093|issue:43638" + ], + "prepared_review_unit_hash": "26530e3ae98fc71f92f8d02219f6d991942600bb64c8fd39ed84f60624c9e971", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 66, + "serialized_chars": 47563, + "estimated_input_tokens": 11891, + "estimated_eval_tokens": 24038 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly heterogeneous cluster with a few real duplicate subgroups: one around ZeRO-3 index-out-of-bounds model loading, one around Qwen3.5 MoE rotary-embedding/device materialization, and one around the v5 tokenizer regression.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43596 is the most generic and central report in the ZeRO-3 \"index 0 is out of bounds\" subgroup, and the other accepted reports are model variants of the same loading failure.", + "canonical_pr_reason": null, + "best_issue_reason": "Best single issue for this cluster because it anchors the largest coherent duplicate subgroup; the rest of the items are mostly unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different Qwen3.5 failures with no clear shared code path from the titles alone." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different model and hardware/backend failures; not the same bug." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Mistral dtype mismatch vs GPT-OSS AMD-GPU failure are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different dtype/autocast bug and GPU backend issue." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different GPT-OSS/MoE issues; not the same concrete failure." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different model/runtime failures; no shared underlying bug." + }, + { + "left": "issue:30277", + "right": "issue:35545", + "accept": false, + "reason": "DeepSpeed collective mismatch and ONNX export error are unrelated." + }, + { + "left": "issue:35545", + "right": "issue:42915", + "accept": false, + "reason": "ModernBERT ONNX export and Qwen3Moe FP8 failure are different bugs." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "Different model/export vs device-map runtime failures." + }, + { + "left": "issue:45901", + "right": "issue:46015", + "accept": false, + "reason": "Runtime crash in table QA vs outdated RAG docs; unrelated." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are stale v5 docs, but they point to different removed features and are not clearly the same issue." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export error and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Both are mismatch errors, but different models and different failure mechanisms." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "ZeRO-3 empty-index error vs mask/tensor shape mismatch are different bugs." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Same general error family but different code path and symptom; not clearly the same bug." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Shape-mask failure and GPT-OSS tensor-parallel issue are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Different shape/packing failures; not the same underlying issue." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice_preset and ModernBERT ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Different DeepSpeed failures: collective mismatch vs empty-index loading error." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; only the model context differs." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger cross-entropy routing and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Incorrect detokenization and LoRA merge/save mismatch are different bugs." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime failure vs LoRA merge consistency bug." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "FSDP activation-checkpoint shape recomputation and mask-index mismatch are different failures." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both involve DeepSpeed, but the concrete errors and code paths are different." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": true, + "reason": "Both point to the same Qwen3.5 MoE rotary-embedding state/device-materialization bug." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 index error and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36331", + "accept": false, + "reason": "Activation-checkpoint/FSDP size mismatch vs trainer API signature break are unrelated." + }, + { + "left": "issue:43596", + "right": "issue:45161", + "accept": false, + "reason": "Different model-loading and tensor-parallel issues." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model-family dtype issue and invalid method call." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 config attribute error and Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Same model family, but device-map mismatch and inputs_embeds reverse-lookup are different code paths." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch version compatibility and Qwen-3 NVFP4 runtime failure are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45161", + "accept": false, + "reason": "Autocast dtype mismatch and GPT-OSS tensor-parallel failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "Different training-stack and device-map runtime failures." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Qwen3.5 SFT embedding unpacking and GPT-OSS TP failure are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45685", + "accept": false, + "reason": "Mistral dtype mismatch and MPS histogram int error are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:43716", + "accept": false, + "reason": "Torch dynamo grouped_mm tracing error and image-preprocessor dtype mismatch are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:44292", + "accept": false, + "reason": "Different dtype mismatch and NVFP4 runtime failures." + }, + { + "left": "issue:45507", + "right": "issue:45685", + "accept": false, + "reason": "Different MoE invalid-method and MPS backend errors." + }, + { + "left": "issue:43716", + "right": "issue:44292", + "accept": false, + "reason": "Different model-family dtype and quantization/runtime failures." + }, + { + "left": "issue:44292", + "right": "issue:44918", + "accept": false, + "reason": "Different Qwen model issues with no shared concrete bug." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger kernel cross-entropy issue and SFT embedding unpacking are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": false, + "reason": "Same ZeRO-3 context, but the titles point to different model-specific failures and not clearly one bug." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are stale docs in v5, but they reference different removed artifacts and are not clearly the same change." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Mistral image dtype mismatch and Qwen3-vl video StopIteration are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch and MPS int histogram backend error are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Different vision/video failure and MPS backend error." + }, + { + "left": "issue:43039", + "right": "issue:43828", + "accept": false, + "reason": "Liger kernel issue and autocast dtype mismatch are different bugs." + }, + { + "left": "issue:30277", + "right": "issue:36331", + "accept": false, + "reason": "Different DeepSpeed/trainer issues with no shared underlying code path." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "GPT-OSS AMD GPU failure and table-QA crash are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:36010", + "accept": false, + "reason": "FSDP checkpointing mismatch and GenerationMixin import error are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44805", + "accept": false, + "reason": "Liger kernel cross-entropy issue and mask-shape mismatch are unrelated." + }, + { + "left": "issue:41762", + "right": "issue:43596", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; Gemma3 and BERT are variants of the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Docs mentioning return_all_scores and docs mentioning the removed run command are different issues." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different model/config and device-map runtime failures." + }, + { + "left": "issue:45237", + "right": "issue:45901", + "accept": false, + "reason": "Different model/backend failure and table QA crash." + }, + { + "left": "issue:44841", + "right": "issue:45823", + "accept": false, + "reason": "Processor failure for Voxtral and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:43039", + "right": "issue:44560", + "accept": false, + "reason": "Different Liger-kernel and video-processing failures." + }, + { + "left": "issue:43975", + "right": "issue:46015", + "accept": false, + "reason": "Incorrect detokenization and outdated RAG examples are unrelated." + }, + { + "left": "issue:45812", + "right": "issue:45920", + "accept": true, + "reason": "Same AutoTokenizer wrong-token-IDs v5 regression, with different affected model lists." + }, + { + "left": "issue:44863", + "right": "issue:46015", + "accept": false, + "reason": "Checkpoint loading failure and outdated docs are unrelated." + }, + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Different checkpoint/model-loading problems." + }, + { + "left": "issue:44292", + "right": "issue:46015", + "accept": false, + "reason": "Qwen NVFP4 runtime failure and outdated RAG docs are unrelated." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "Unit-test model loading failure and corrupted checkpoint are different issues." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Mask-index mismatch and ZeRO-3 empty-index error are different failures." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about the soft edges. The three accepted duplicate subgroups (ZeRO-3 index-out-of-bounds loading, Qwen3.5 MoE rotary-embedding/materialization, and the v5 tokenizer regression) are all supported by the titles, while the rejected pairs are not overstated. " + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 2, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36010", + "issue:39290", + "issue:40990", + "issue:41093", + "issue:41762", + "issue:42915", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43645", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44530", + "issue:44589", + "issue:44841", + "issue:44918", + "issue:44960", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45399", + "issue:45464", + "issue:45542", + "issue:45632", + "issue:45685", + "issue:45698", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45901", + "issue:45902" + ], + "soft_pairs": [ + "issue:39290|issue:43531", + "issue:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue: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:44387|issue:45005", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:45020|issue:45800", + "issue:43531|issue:45070", + "issue:43541|issue:44589", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45542|issue:45800", + "issue:45759|issue:45902", + "issue:43716|issue:44918", + "issue:44918|issue:45685", + "issue:45632|issue:45698", + "issue:43404|issue:45005", + "issue:43645|issue:45399", + "issue:40990|issue:44960", + "issue:44530|issue:45005", + "issue:42915|issue:45399" + ], + "prepared_review_unit_hash": "a0eb7335a56c0e5e7a4ca609cc2e440f3d1c98f129590c57108094c2e5c27c76", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 39, + "serialized_chars": 38521, + "estimated_input_tokens": 9631, + "estimated_eval_tokens": 19518 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Heterogeneous cluster with two real duplicate subgroups: SigLIP2 output-regression reports and a separate remote_code/custom-module loading collision pair. The remaining soft edges are mostly false positives across unrelated bugs.", + "confidence": 0.89, + "canonical_issue_reason": "No single canonical issue spans the whole cluster because the accepted duplicates split into at least two distinct subgroups (SigLIP2 regression and remote_code/custom-module path collision), alongside many unrelated issues.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue for the full cluster. If forced within the SigLIP2 subgroup, 43994 is the clearest representative, but it should not absorb the separate remote_code/custom-module pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Different models and config fields; both involve sliding_window, but not the same bug." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper inference failure and table QA crash are unrelated code paths." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch version compatibility and pydantic config breakage are different issues." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "DeepSpeed ZeRO-3 loading error is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Incorrect detokenization and table-question-answering crash do not share a cause." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper runtime failure is not the same as a PretrainedConfig pydantic regression." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a chat crash and the other is a streaming API failure." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "Qwen-3 NVFP4 loading error is unrelated to table QA task crashes." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3 vLLM config error and Gemma4 device mismatch are different model bugs." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Untied lm_head weights and a corrupted checkpoint are unrelated failures." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 streaming API crash and MPS histogram kernel error are different subsystems." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Torch dynamo grouped_mm failure is not the same as the MPS MoE histogram issue." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Both are dtype/runtime problems, but they occur in different models and code paths." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Processor failure for Voxtral is unrelated to a template-node compile error." + }, + { + "left": "issue:36010", + "right": "issue:39290", + "accept": false, + "reason": "ImportError for GenerationMixin is unrelated to Gemma3 sliding_window_pattern." + }, + { + "left": "issue:45800", + "right": "issue:45823", + "accept": false, + "reason": "Torch version incompatibility and Gemma4 device mismatch are different defects." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are IndexErrors, but one is a mask-shape mismatch and the other is ZeRO-3 model loading." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL loading and GGUF gpt-oss support are unrelated model issues." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "Missing pad_token_idx and pydantic PretrainedConfig breakage are different config regressions." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Mixtral tracing failure and GPT-OSS tensor-parallel issue are not the same bug." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 memory growth and tied-weights translation-model regressions are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch on Phi-tiny-MoE is unrelated to Qwen3.5 streaming inference." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "Unexpected _is_hf_initialized arg and pydantic field breakage are different failures." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3.5 streaming API failure do not match." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Remote-code loading breakage is unrelated to torch/transformers incompatibility." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window and PretrainedConfig pydantic issues are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing failure and missing Float8 storage are different runtime problems." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Two IndexErrors, but the tensor shapes and triggering paths are unrelated." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": true, + "reason": "Both report SigLIP2 producing bad embeddings/results; same underlying regression." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TF backend error is unrelated to torch/transformers compatibility." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Composite Qwen config unwrapping and uninitialized rotary embedding are different bugs." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Mistral image preprocessor dtype mismatch and Qwen3.5 SFT embedding unpacking are unrelated." + }, + { + "left": "issue:44918", + "right": "issue:45685", + "accept": false, + "reason": "TRL embedding unpacking failure and MPS MoE histogram error are unrelated." + }, + { + "left": "issue:45632", + "right": "issue:45698", + "accept": true, + "reason": "Both describe remote_code/custom-module loading picking the wrong module due to a path/cache collision." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Untied lm_head in one model and tied-weights issues in translation models are not the same bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "Custom model initialization in notebooks and flash-attn fallback blocking are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "High perplexity on gpt-oss and the GLM5 issue are different model regressions." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache linear_attention failure and tied-weights translation issues are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Qwen3Moe FP8 failure and flash-attn fallback gating are different concerns." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports a heterogeneous cluster, but the summary is too strong in claiming SigLIP2 is the only clear duplicate subgroup. The evidence also shows a separate accepted duplicate pair for remote_code/custom-module loading collisions (`issue:45632` \u2194 `issue:45698`). Because the cluster contains at least these two soft-duplicate subgroups, the canonical/best-issue rationale is not fully grounded as written. The individual soft-edge rejections are mostly conservative, but the high-level cluster summary overstates the evidence." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 3, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39186", + "issue:39692", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43493", + "issue:43643", + "issue:43644", + "issue:43828", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:43950", + "issue:43975", + "issue:44292", + "issue:44360", + "issue:44387", + "issue:44403", + "issue:44451", + "issue:44488", + "issue:44492", + "issue:44512", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:45005", + "issue:45020", + "issue:45507", + "issue:45520", + "issue:45663", + "issue:45685", + "issue:45701", + "issue:45800", + "issue:45823", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:44360|issue:44512", + "issue:39186|issue:44918", + "issue:43873|issue:45005", + "issue:44863|issue:45005", + "issue:44492|issue:44512", + "issue:44918|issue:45507", + "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:41628|issue:45800", + "issue:43866|issue:44403", + "issue:43950|issue:45902", + "issue:43872|issue:44589", + "issue:38175|issue:43054", + "issue:41553|issue:43883", + "issue:43054|issue:45701", + "issue:44910|issue:45859", + "issue:45663|issue:45902", + "issue:41553|issue:43881", + "issue:42947|issue:44387", + "issue:44403|issue:44451", + "issue:43054|issue:43493", + "issue:43643|issue:45020", + "issue:43975|issue:45520", + "issue:44403|issue:44488", + "issue:42947|issue:43856", + "issue:41762|issue:42915", + "issue:45685|issue:45823", + "issue:43881|issue:43883" + ], + "prepared_review_unit_hash": "d58ccd8d21b64e0cd156ba31802f8d74a756fe186a59ed0aadf54bce60bf431d", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 36663, + "estimated_input_tokens": 9166, + "estimated_eval_tokens": 18588 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose collection of Transformers v5/model-loading regressions, but only one pair is a clear duplicate: the non-persistent buffer corruption reports. Most other soft pairs are related only at the subsystem or model-family level and should stay separate.", + "confidence": 0.86, + "canonical_issue_reason": "Issue 43950 is the strongest canonical issue: it states the broad underlying v5 regression around non-persistent buffers being corrupted, and it has a near-identical later duplicate in 44534. It is more general than the model-specific follow-up reports.", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the best overall issue to anchor the cluster because it describes a concrete, reusable bug pattern rather than a single model symptom, and it most clearly matches a duplicate report in the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA indexer/ReLU discussion vs docs mentioning a removed run command; unrelated topics." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-shape RuntimeError vs TRL SFT input-embedding unpacking failure; different code paths." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior vs tied-weights translation-model issue; not the same bug." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "NemotronH checkpoint loading failure vs translation-model tied-weights regression; unrelated." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "Cache-strategies typo vs docs still referencing removed run command; both docs, but different changes." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "Qwen3.5 embedding unpacking issue vs GraniteMoEHybrid invalid-method call; different models and failures." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Detokenization bug vs Qwen-3-8B-NVFP4 runtime error; not the same underlying issue." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 loading/runtime error vs GraniteMoEHybrid invalid-method call; unrelated." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "These are the same underlying regression: non-persistent buffers get corrupted/junked in v5 during model loading/materialization." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "SigLIP2 docs/example errors vs poor text-embedding quality; different problem class." + }, + { + "left": "issue:43643", + "right": "issue:43950", + "accept": false, + "reason": "AutoConfig trust_remote_code missing-fields bug vs non-persistent buffer corruption; unrelated." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Autocast dtype mismatch vs Qwen3.5 gradient explosion/NaN; same model family, but not the same concrete bug." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "CustomTrainer compute_loss signature mismatch vs Gemma3 ZeRO-3 loading error; unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "AutoImageProcessor import failure vs torch/transformers incompatibility; not the same bug." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Corrupted Ovis2 checkpoint vs generic loading noise; unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "Both mention non-persistent buffers, but 45902 is a specific Qwen3_5MoeTextRotaryEmbedding materialization bug and is not clearly the same report as the broader from_pretrained regression." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "bitsandbytes kwarg incompatibility vs missing Float8 storage type; different compatibility issues." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Unexpected zero probabilities vs degraded text embeddings; both SigLIP2-related, but not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "AutoTokenizer loading error for Voxtral vs Molmo tied-weights attribute error; unrelated." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality issue vs tokenization changed across versions; different symptoms and likely different causes." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Both touch Qwen3.5/MoE rotary code, but one is a Flash Attention position_ids crash and the other is CPU-offload compatibility; not the same bug." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states KeyError vs Qwen3_5Moe rotary buffer initialization issue; unrelated." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral tokenizer loading error vs glm-4v-9b loading failure; different models and failure modes." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "Gradient checkpointing ineffectiveness with LoRA vs int4 reserved-memory/OOM regression; different mechanisms." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise vs inability to load ScandiBERT; the titles are too broad and do not indicate the same concrete bug." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Generic loading noise vs inability to load cjvt/sleng-bert; not the same issue." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "SigLIP2 embedding quality vs HF/JAX implementation discrepancy; related model family, but not the same concrete bug." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "AutoConfig missing fields with trust_remote_code vs broader recent remote_code breakage; related area, but too broad to merge as one bug." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "Detokenization bug vs flash_attn import failure on Python 3.13; unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Generic loading noise vs another model loading failure; not the same underlying bug." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "LoRA checkpointing inefficiency vs Qwen3 MoE memory usage; both about memory, but different issues." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Gemma3 ZeRO-3 loading failure vs Qwen3 MoE FineGrainedFP8Config failure; different models and code paths." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "MPS histogram Int error vs Gemma4 PLE device mismatch; unrelated." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "glm-4v-9b loading failure vs Molmo missing all_tied_weights_keys; different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative. The chosen anchor/canonical issue, 43950, is well supported by the title overlap with 44534, and the summary appropriately avoids over-claiming duplicate status for the other soft pairs. I don\u2019t see any soft-edge verdicts that overstate the evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 4, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36331", + "issue:41093", + "issue:41553", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43366", + "issue:43404", + "issue:43638", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43872", + "issue:43940", + "issue:43950", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44560", + "issue:44661", + "issue:44805", + "issue:44863", + "issue:44928", + "issue:44960", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45305", + "issue:45313", + "issue:45356", + "issue:45399", + "issue:45538", + "issue:45588", + "issue:45823", + "issue:45923" + ], + "soft_pairs": [ + "issue:42491|issue:44368", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:44991|issue:45399", + "issue:43828|issue:45823", + "issue:43782|issue:44960", + "issue:45081|issue:45399", + "issue:43827|issue:44509", + "issue:45020|issue:45356", + "issue:43404|issue:43950", + "issue:43742|issue:45399", + "issue:42915|issue:45020", + "issue:43638|issue:45823", + "issue:43792|issue:44220", + "issue:43257|issue:43866", + "issue:43872|issue:44291", + "issue:42915|issue:43872", + "issue:43940|issue:45313", + "issue:43854|issue:44863", + "issue:41553|issue:44991", + "issue:42947|issue:45923", + "issue:36331|issue:41093", + "issue:44928|issue:45588", + "issue:43257|issue:45305", + "issue:43872|issue:45538", + "issue:41093|issue:44805", + "issue:44479|issue:44560", + "issue:44530|issue:44863", + "issue:41553|issue:44488", + "issue:24643|issue:30064", + "issue:43366|issue:43828" + ], + "prepared_review_unit_hash": "529422a86c5f61d4179fec144aec4cbb80e53a7a5c7f34d03497e0e6801dbce6", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 37041, + "estimated_input_tokens": 9261, + "estimated_eval_tokens": 18778 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous cluster of transformer regressions, tokenizer/model-loading issues, and a few docs/video/audio bugs. There is no strong single canonical issue for the whole set; 45020 is only the broadest representative of the loading/regression subgroup. Only a few soft pairs look like true duplicates.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the broadest representative of the recent model-loading/regression subgroup, but it still doesn't cover the unrelated training/docs/audio/video reports in this cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "Related to Qwen3/LoRA, but one is a hf4.x\u2192hf5.x compatibility break and the other is a tie_word_embeddings warning; not the same bug." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Missing Qwen2.5-VL import vs bitsandbytes `_is_hf_initialized` incompatibility are different failure modes." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Generic remote_code breakage vs Gemma4 device_map/PLE forward mismatch; different code paths." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "Tokenizer-mapping edge case is too specific to merge with broad remote_code regressions." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading failure for a specific model vs flash-attn2 fallback gating; unrelated bugs." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch and device placement mismatch are separate model execution issues." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Different models and symptoms; no clear shared code-path bug from the titles alone." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Mistral regex patch crash vs flash-attn fallback checks; distinct tokenizer vs attention-path problems." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both report docs still referencing removed pipeline tasks after v5 removals; same documentation issue." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Remote_code model-loading regressions are not the same as the Kimi-K2.5 tokenizer codec/regression report." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "Untied lm_head in Mistral3 is unrelated to non-persistent buffer corruption during from_pretrained()." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM key error and flash-attn fallback gating are different loading/runtime problems." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "LoRA qwen3_moe hf4/hf5 incompatibility is model/version-specific and not the same as the broad remote_code regressions." + }, + { + "left": "issue:43638", + "right": "issue:45823", + "accept": false, + "reason": "Zero3 index error with a non-pretrained Bert model is unrelated to Gemma4 device placement mismatch." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Whisper can't-run report and `_torch_extract_fbank_features()` are too underspecified to treat as the same bug." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed vs Ovis2 checkpoint corruption are unrelated." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "Both describe the same `_is_hf_initialized` argument regression during model loading/init-empty-weights flows." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "LoRA model compatibility issue vs bitsandbytes constructor-kwarg incompatibility; not the same problem." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both are ZeRO-3 weight-loading failures, but the model families and reported failure modes differ enough to avoid merging." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "GLM-4.7 test-loading problem and NemotronH checkpoint loading failure are different model-specific issues." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Bad Voxtral error message vs est-roberta tokenizer load failure; only loosely related as tokenizer issues." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing ineffective with PEFT LoRA is not the same as a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Trainer compute_loss signature mismatch vs tensor/mask shape mismatch are unrelated." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF NaN/SDPA fallback problem vs flash_attention `s_aux=None` crash are different attention-path failures." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "DeepSpeed weight conversion bug vs gradient averaging-by-GAS bug; different training issues." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "_is_hf_initialized incompatibility has nothing to do with CLIPTokenizer model_max_length." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": true, + "reason": "These are the same mask/index shape-mismatch error pattern, just with different example sizes and wording." + }, + { + "left": "issue:44479", + "right": "issue:44560", + "accept": true, + "reason": "Both point to the same Qwen3/Qwen3.5 video-input regression in v5.3.0 affecting video handling paths." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Voxtral tokenizer error message and sleng-bert loading failure are unrelated tokenizer-specific issues." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "DeepSpeed training weight-dimension error vs void segmentation map processing are clearly unrelated." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF gpt-oss support and autocast dtype mismatch are different model-format vs execution-dtype problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays conservative and matches the packet: the cluster is heterogeneous, 45020 is only a broad representative, and the accepted soft pairs are plausibly duplicates based on the issue titles. No pair is overstated beyond the evidence available here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 5, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41720", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43720", + "issue:43824", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45276", + "issue:45313", + "issue:45325", + "issue:45357", + "issue:45584", + "issue:45663", + "issue:45823", + "issue:45834", + "issue:45902" + ], + "soft_pairs": [ + "issue:45325|issue:45902", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:43550|issue:44910", + "issue:43366|issue:44589", + "issue:43645|issue:43646", + "issue:44560|issue:44918", + "issue:42915|issue:43957", + "issue:43824|issue:43957", + "issue:42617|issue:43366", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:38175|issue:43994", + "issue:43632|issue:45834", + "issue:44560|issue:44805", + "issue:44155|issue:45584", + "issue:43638|issue:44661", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:44877|issue:45030", + "issue:43317|issue:44756", + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:44960|issue:44977", + "issue:45313|issue:45357", + "issue:44451|issue:44488", + "issue:43644|issue:44534", + "issue:41720|issue:42915", + "issue:42491|issue:45276", + "issue:43708|issue:44075" + ], + "prepared_review_unit_hash": "98967f62b2644af3142ee146f00c3785924b2889b39e21ecfbb259a13b7eedf9", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36974, + "estimated_input_tokens": 9244, + "estimated_eval_tokens": 18744 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated model- or feature-specific bugs. Only three soft pairs look like true duplicates: the Transformers v5 custom-init regression, the SigLIP2 bad-output regression, and the non-persistent-buffer junk-fill regression.", + "confidence": 0.82, + "canonical_issue_reason": "Issue 44534 is the clearest general wording of the exact Transformers v5 non-persistent-buffer regression, and it cleanly subsumes the matching 43644 report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44534 is the strongest standalone representative in this set: concise, specific, and an exact duplicate of 43644.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Different models and different failure modes; both are rotary-embedding related at most, but not the same concrete bug." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Same Gemma4 family, but one is an FSDP2 KeyError in shared_kv_states and the other is a device_map forwarding mismatch." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "Unrelated issues: GGUF/gpt-oss support versus a Qwen3-MoE sliding_window bug." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "Different subsystems and symptoms; non-persistent buffer corruption is unrelated to Kosmos2.5 OCR indexing." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different models and different code paths: Bamba torch.compile/SDPA versus Qwen3.5 flash-attention position_ids handling." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "No concrete overlap; GGUF support and Float8 storage loading are separate problems." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "These describe the same Transformers v5 custom-model initialization regression; the notebook mention is just a repro variant." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both involve Qwen-family models, but the failures are different: video StopIteration versus TRL unpacking embeddings." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "Different regressions: FineGrainedFP8Config on Qwen3Moe versus meta-device loading issues across other models." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "ImportError for a missing Qwen2.5-VL class is unrelated to meta-device loading regressions." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "Unrelated: running 3d_parallel.py versus GGUF gpt-oss support." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "Different bugs entirely: GenerationMixin import path versus Qwen3Moe FP8 loading." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping/add-new-model-like behavior is unrelated to Gemma4 PLE device mismatch." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 base model and same bad-output symptom; zero probabilities and nonsensical outputs are likely the same underlying regression." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "Transformers v5 _is_hf_initialized regression is unrelated to Kosmos2.5 long-OCR index errors." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Different failure modes and likely different code paths: video StopIteration versus mask-shape IndexError." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 batched-track leakage is unrelated to Whisper empty-transcription handling." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "Zero3/BertModel initialization and tokenizer-mapping model registration are different bugs." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "Different concrete failures: deepspeed zero3/BertModel indexing versus add-new-model-like tokenizer mapping logic." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "No shared underlying bug; tokenizer-mapping model registration is unrelated to a tensor mask-shape mismatch." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both are config-loading regressions, but they concern different models and different validation failures." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Different problem areas: dequantized model offload loading versus mmap/OOM on Strix Halo." + }, + { + "left": "issue:38175", + "right": "issue:39692", + "accept": false, + "reason": "Same SigLIP2 area, but the bugs are not clearly the same concrete issue: one is bad probabilities, the other is docs/example mismatch and quantization failure." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Qwen3-MoE LoRA compatibility across HF versions is unrelated to BitNet packed-weight loading." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "Different models and failures: GLM5 versus Qwen3.5 flash-attention generation." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Different parts of Qwen3.5 and different operations: ZeRO-3 language_model loading versus save_pretrained visual-encoder key handling." + }, + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading failures, but they target different BERT models and there is not enough evidence they are the same bug." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "Exact same Transformers v5 non-persistent-buffer junk-fill regression; only the version wording differs." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Different Qwen3 issues with different triggers: auto device mapping cudaErrorAssert versus FineGrainedFP8Config." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Unrelated: Qwen3-MoE LoRA compatibility versus Gemma4 resize_token_embeddings behavior." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Trainer resume/max_steps logic is unrelated to SGD optimizer arguments being ignored." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the only positive soft-edge calls are stated conservatively enough. The canonical/best issue choice for the non-persistent-buffer regression is well supported by the titles, and the other pairwise rejections stay within the evidence shown." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 6, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44488", + "issue:44756", + "issue:44910", + "issue:44912", + "issue:44960", + "issue:44991", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:46050" + ], + "soft_pairs": [ + "issue:43854|issue:43931", + "issue:42915|issue:44756", + "issue:45488|issue:45812", + "issue:39692|issue:43994", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42491|issue:43931", + "issue:43644|issue:43645", + "issue:43856|issue:44387", + "issue:44910|issue:45588", + "issue:42491|issue:45292", + "issue:45362|issue:45406", + "issue:44488|issue:44991", + "issue:45276|issue:45335", + "issue:36010|issue:39404", + "issue:44164|issue:44291", + "issue:43404|issue:43454", + "issue:43425|issue:43957", + "issue:44402|issue:44488", + "issue:39692|issue:44960", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:43335|issue:45663", + "issue:45663|issue:45859", + "issue:44155|issue:45823", + "issue:43873|issue:44387", + "issue:44291|issue:44756", + "issue:44960|issue:46050", + "issue:44292|issue:44912", + "issue:43854|issue:45216", + "issue:44387|issue:44756", + "issue:45276|issue:45292", + "issue:45684|issue:45698" + ], + "prepared_review_unit_hash": "b314310e515c24e48a901e5d506201e7460d2b59cde7f81c3807e6e22a3d867f", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37727, + "estimated_input_tokens": 9432, + "estimated_eval_tokens": 19120 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated closed issues about different regressions. The only clear duplicate family is the resize_token_embeddings/output_embeddings reports; the rest are distinct bugs or model-specific failures.", + "confidence": 0.81, + "canonical_issue_reason": "issue:45292 is the broadest, most model-agnostic report of the resize_token_embeddings/output_embeddings regression, so it best serves as the umbrella issue for the related model-specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the best global representative because it states the core API-level symptom without narrowing to one architecture, while the others in that family are narrower manifestations.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different models and different loading failures; no shared concrete bug path." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE FP8 conversion failure vs Strix Halo mmap/OOM workaround; unrelated causes." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but the affected models and failure modes differ too much to be the same bug." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Doc/example errors for SigLIP2 vs nonsensical inference results; not the same underlying issue." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MoE deepspeed/accelerate weight conversion issue is unrelated to GLM-4.7 Flash model loading." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Separate memory-related problems: training memory usage vs quantization/offload behavior." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "LoRA checkpoint compatibility on hf4.x/hf5.x is unrelated to the Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "Different regressions in 5.0.0: buffer initialization vs Jupyter custom model initialization." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Both mention memory, but one is Qwen3 MoE training memory and the other is int4 reserved-memory/OOM behavior." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Flash-attention crash from misread 3D position_ids is a different code path than the s_aux=None AttributeError." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "Qwen3 MoE hf4.x/hf5.x compatibility is unrelated to resize_token_embeddings not updating output_embeddings." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and failures: Qwen3.5 chat crash vs Gemma4Processor missing _tokenizer." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Two tokenizer-loading failures on different models; no evidence of the same root cause." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": true, + "reason": "Both describe the same resize_token_embeddings regression failing to propagate to nested output/decoder embeddings in composite model classes." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "An import error for GenerationMixin is unrelated to Whisper pipeline return_language behavior." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "save/from_pretrained extra_state handling and init_empty_weights argument handling are separate serialization/loading bugs." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Both are untied lm_head reports, but they target different model implementations and no concrete shared code path is evident." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch 2.10 compatibility and meta-device loading regressions are different issues." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size mismatch in one model is not the same as sleng-bert failing to load." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "SigLIP2 example/runtime issues are unrelated to the GLM5 report." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing with PEFT LoRA is a different bug than T5's apex.FusedRMSNorm memory leak." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states bug and Qwen multimodal config unwrapping are distinct code paths." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to the Gemma4 attention KeyError." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "FSDP2 attention-state rebuilding and CPU-offload rotary embedding compatibility are separate issues." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 batched inference leakage is unrelated to Gemma4 PLE device mismatch." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Quantization offloading behavior and increased reserved memory/OOM are not the same bug." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "init_empty_weights argument handling is unrelated to disabling mmap on Strix Halo." + }, + { + "left": "issue:44960", + "right": "issue:46050", + "accept": false, + "reason": "GLM5 is a model-specific report; sinq save/load corruption is a different serialization bug." + }, + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "NVFP4 load failure and MXFP4 fallback are distinct quantization-format problems." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "GLM-4.7 Flash unit-test loading failure is unrelated to the Qwen3.5 save_pretrained regression." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Int4 reserved-memory OOM and Strix Halo mmap OOM have different triggers and fixes." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Both report the same resize_token_embeddings regression; 45292 is the generic output_embeddings case and 45276 is the Gemma4-specific manifestation." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The packet supports 45292 as the broad resize_token_embeddings/output_embeddings umbrella issue, with 45276 and 45335 as model-specific manifestations. The other soft-edge rejections stay conservative by leaning on distinct models/failure modes rather than claiming exact causality." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 7, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36032", + "issue:39404", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43299", + "issue:43381", + "issue:43425", + "issue:43452", + "issue:43596", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43901", + "issue:43906", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44155", + "issue:44164", + "issue:44265", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44918", + "issue:44928", + "issue:45084", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45701", + "issue:45759", + "issue:45823" + ], + "soft_pairs": [ + "issue:43381|issue:44928", + "issue:42947|issue:43381", + "issue:44164|issue:44756", + "issue:44479|issue:44877", + "issue:41720|issue:44155", + "issue:45588|issue:45663", + "issue:43957|issue:44756", + "issue:43646|issue:43708", + "issue:45292|issue:45335", + "issue:43828|issue:43957", + "issue:44402|issue:44451", + "issue:43645|issue:44164", + "issue:43425|issue:43828", + "issue:43257|issue:44863", + "issue:44683|issue:45823", + "issue:44589|issue:44756", + "issue:43425|issue:45823", + "issue:43906|issue:44530", + "issue:43425|issue:43716", + "issue:39404|issue:45701", + "issue:43611|issue:43645", + "issue:44530|issue:45084", + "issue:43901|issue:44509", + "issue:44265|issue:44898", + "issue:39404|issue:44912", + "issue:44479|issue:44805", + "issue:43425|issue:44918", + "issue:44589|issue:45084", + "issue:43299|issue:43931", + "issue:43596|issue:44683", + "issue:43994|issue:44079", + "issue:44164|issue:45759", + "issue:36032|issue:43452" + ], + "prepared_review_unit_hash": "09c00895000605ec566f40ee6fedafd4ac2cb89fc6a32d1055a49568b35e19e3", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37721, + "estimated_input_tokens": 9431, + "estimated_eval_tokens": 19118 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers issues with one clear duplicate pair around `resize_token_embeddings` not propagating to downstream embeddings. No PRs are present.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45292 is the broadest, most general statement of the duplicate bug (`resize_token_embeddings` not updating output embeddings); issue:45335 looks like a model-specific instance of the same propagation problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45292 is the best cluster representative because it describes the underlying bug in generic terms rather than a single model variant.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "Both mention training/gradient behavior, but one is about gradient checkpointing in eval mode and the other about NaNs from Qwen3.5 SDPA fallback; different failure modes." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but one is about ineffective LoRA checkpointing and the other about eval-mode misuse; not the same bug." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "`save/from_pretrained` extra_state handling and Strix Halo mmap OOM are unrelated issues." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Different regressions: video input behavior for Qwen VL models vs strict config loading for granite_speech." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Qwen3 auto device mapping CUDA assert and AudioFlamingo3 batched inference token/embedding leakage are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Both touch attention-related code, but one is a flash_attention sinkless-model crash and the other is a Gemma4 FSDP2 shared_kv_states bug." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading failures and mmap/OOM on Strix Halo are different problems with different triggers." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization and Trainer resume/max_steps calculation are unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same underlying bug: `resize_token_embeddings` does not propagate to the model's output embeddings; 45335 is the t5gemma-specific manifestation." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Both are dtype/device-ish loading issues, but one is autocast on Phi-tiny-MoE and the other is meta-device loading breakage; not the same root cause." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Different tokenizer/model-loading problems for different checkpoints; no clear shared code-path." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Jupyter/custom-model initialization is unrelated to save/from_pretrained extra_state handling." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility and autocast dtype mismatch are different issues." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Both concern model loading, but one is Qwen3 MOE conversion with accelerate+deepspeed and the other is NemotronH checkpoint loading; too different." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup and Strix Halo mmap OOM are different low-level failures." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch 2.10 incompatibility and Gemma4 PLE device-map forward mismatch are not the same bug." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "An isolated reproduction of an older issue and a Qwen3.5 PagedAttentionCache crash are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Generic torch incompatibility versus Mistral-3 image preprocessor/model dtype mismatch; different symptoms and code paths." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline `return_language` regression and generic tokenization changes across versions are not the same issue." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "`base_model_prefix` loading and custom model initialization in notebooks are different model-construction failures." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Qwen3.5 PagedAttentionCache crash and non-template-node compilation error are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but they concern different pipeline API removals/behavior changes." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "`torch.export.export` with `torch_compilable_check` and Perceiver interpolation failure are different model/export issues." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline `return_language` regression and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression for VL models and a mask shape IndexError are different bugs." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "Torch version incompatibility and Qwen3.5 SFT embedding unpacking are unrelated." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Float8 storage lookup failure and template-node compilation error are not the same issue." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both are Qwen3-VL loading problems, but one is a broad 5.0.0.dev0 regression and the other is a specific weight-shape mismatch; not enough evidence of one root cause." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "Deepspeed zero3/BertModel index error and compiled flex_attention failure are unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "Siglip2 nonsensical outputs and ModelOutput key assignment bug are different problem classes." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "`extra_state` save/load handling and `from_config` not unwrapping `text_config` are separate model-serialization issues." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5Tokenizer `add_special_tokens` conflict and gguf_file loading breakage are unrelated tokenizer/loading problems." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: all items are issues, no PRs are present, and the only clearly supported duplicate pair is 45292/45335. The soft-edge verdicts are conservative overall and do not overstate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 8, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43262", + "issue:43317", + "issue:43377", + "issue:43421", + "issue:43452", + "issue:43482", + "issue:43541", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43646", + "issue:43716", + "issue:43856", + "issue:43883", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44464", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44811", + "issue:44849", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45325", + "issue:45507", + "issue:45584", + "issue:45859", + "issue:45987" + ], + "soft_pairs": [ + "issue:39404|issue:44671", + "issue:43856|issue:44756", + "issue:44991|issue:45081", + "issue:44671|issue:44991", + "issue:44737|issue:45859", + "issue:32090|issue:39404", + "issue:44164|issue:44479", + "issue:44661|issue:44683", + "issue:44488|issue:45081", + "issue:43582|issue:43632", + "issue:43611|issue:43644", + "issue:40990|issue:43421", + "issue:43716|issue:45084", + "issue:44206|issue:44220", + "issue:44488|issue:44987", + "issue:43643|issue:44530", + "issue:34567|issue:40444", + "issue:36032|issue:42915", + "issue:44811|issue:45584", + "issue:43883|issue:44488", + "issue:44451|issue:44987", + "issue:43452|issue:43482", + "issue:44464|issue:45987", + "issue:43541|issue:45084", + "issue:42915|issue:44530", + "issue:43644|issue:43646", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:43262|issue:43377" + ], + "prepared_review_unit_hash": "4c9688ded8c9c32783ebbfbf6902f62ed98daedbd1667a764c990fd0812ae46b", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "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 heterogeneous across unrelated model, tokenizer, audio, cache, and training regressions. I only see one likely duplicate pair: the GGUF loading regression in issue:43452 and issue:43482.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43452 is the broader, more generic GGUF/from_pretrained loading regression; issue 43482 looks like a model-specific manifestation of the same failure.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43452 is the best representative issue because it describes the underlying loader breakage in a general way and can subsume the more specific Qwen2.5-GGUF report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Different models and failures: Whisper pipeline return_language vs CamemBERT masked-LM predictions." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both involve performance/memory, but one is Qwen3 MoE training inefficiency and the other is Strix Halo mmap OOM." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer-related regressions, but they hit different code paths and different models." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "Both are v5 tokenizer/model-loading complaints, but the concrete bug and affected model differ." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both mention device/offload behavior, but XLNet CPU arange vs Qwen3.5Moe rotary embedding are separate bugs." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer broadcast NoneType error is unrelated to Whisper pipeline return_language behavior." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "save/from_pretrained extra_state handling is unrelated to the Qwen video-input regression." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Tokenizer mapping/new-model registration is unrelated to compiled flex_attention failing on torch >= 2.9." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Different model-loading failures: BERT tokenizer load vs Mistral regex patch crash." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "AppleSilicon allocator warmup TypeError and _is_hf_initialized regression are different initialization bugs." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "base_model_prefix loading breaks vs non-persistent buffers being junk are distinct v5 regressions." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "High perplexity on gpt-oss is unrelated to runtime post-processor updates in TokenizersBackend." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral-3 dtype mismatch in the image preprocessor is unrelated to template-node compilation errors." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Both are audio-feature issues, but one is an unsupported center argument and the other is a different fbank-extraction problem." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Both are model load failures, but they affect different models and appear to stem from different regressions." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig missing fields with trust_remote_code is unrelated to PagedAttentionCache linear_attention group handling." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token counting and Qwen2.5-VL multi-image IterableDataset failures are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer method conflict is unrelated to Qwen3Moe FineGrainedFP8Config failure." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both are Whisper issues, but batch_decode skip_special_tokens and empty-transcription generation after align_special_tokens are different bugs." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Molmo tied-weights metadata error is unrelated to the sleng-bert loading failure." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Different models and different failure modes: loading physical-intelligence/fast vs tokenizer loading for EMBEDDIA/est-roberta." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": true, + "reason": "Both point to the same GGUF loading regression in transformers v5; 43482 is a specific instance of the broader 43452 bug." + }, + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is not the same as StaticCache.get_seq_length returning the wrong type." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Mixtral grouped_mm tracing errors and non-template-node compilation errors are different compiler failures." + }, + { + "left": "issue:42915", + "right": "issue:44530", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen3.5 PagedAttentionCache linear_attention crash are separate issues." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 custom-model regressions, but non-persistent-buffer corruption is not the same bug as custom model initialization breaking." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "GPU+CPU offload dequantized-model loading and GGUF loading failure are different loader paths." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Qwen3.5 hidden-state output bug is unrelated to Qwen2.5-VL rope index scaling." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer special-token method conflict is unrelated to Jupyter custom-model initialization breakage." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "TypeError compiling non-template nodes is unrelated to GraniteMoEHybrid calling an invalid method." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Default 16 kHz sampling-rate behavior is unrelated to MIMI encoder padding-mask differences between batched and single inputs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft-edge pair, issue:43452 and issue:43482, is plausibly the same GGUF/from_pretrained loading regression at different specificity levels. The other rejections are appropriately cautious given the differing models, code paths, or failure modes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 9, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36032", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43089", + "issue:43296", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43540", + "issue:43611", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43792", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44466", + "issue:44479", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44811", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45020", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45542", + "issue:45987" + ], + "soft_pairs": [ + "issue:43404|issue:44466", + "issue:43089|issue:45987", + "issue:43883|issue:44991", + "issue:44987|issue:44991", + "issue:43994|issue:44610", + "issue:43646|issue:44534", + "issue:43322|issue:43540", + "issue:44403|issue:45081", + "issue:43377|issue:43819", + "issue:42915|issue:45084", + "issue:44265|issue:44610", + "issue:43645|issue:44534", + "issue:44220|issue:44683", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:45216|issue:45357", + "issue:43404|issue:45127", + "issue:42915|issue:44291", + "issue:43632|issue:44756", + "issue:36032|issue:43742", + "issue:44062|issue:44987", + "issue:42915|issue:44589", + "issue:43296|issue:43531", + "issue:43531|issue:44877", + "issue:43425|issue:44403", + "issue:43611|issue:44534", + "issue:44479|issue:45325", + "issue:36032|issue:41720", + "issue:42175|issue:45542", + "issue:43792|issue:44589", + "issue:40990|issue:44811", + "issue:44683|issue:45020" + ], + "prepared_review_unit_hash": "d7489c19b3c0a91abeb8ce834fa41852b906dcb3e969c7cd2ea8eb0a26510f30", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37214, + "estimated_input_tokens": 9304, + "estimated_eval_tokens": 18864 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a family of Transformers v5/v5.x loading and serialization regressions across different models and code paths. Most soft pairs are related thematically but not true duplicates; only the Qwen3.5 save_pretrained regressions look like the same underlying bug.", + "confidence": 0.83, + "canonical_issue_reason": "issue:45020 is the broadest umbrella: it frames the recent-version regressions as a general breakage of model loading/remote_code behavior, which matches the cluster\u2019s dominant theme.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the best tracker candidate because it is general, user-facing, and central to the cluster of v5 loading/serialization regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both involve tied-weights behavior, but one is a missing tie in a specific model class and the other is device-dependent save_pretrained serialization; different bugs." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation performance/sync overhead is unrelated to the StaticCache return-type contract bug." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Different failures: missing all_tied_weights_keys vs tokenizer loading for a specific checkpoint." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are model-loading failures, but they concern different checkpoints and likely different root causes." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Different multimodal regression types: bad results from a model/pipeline path vs processor image-size mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model init breakage and junk-filled buffers are separate v5 regressions." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Segfault while loading Llava Next is not the same as the Qwen3OmniMoe video-processing ValueError." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "Noise/logging during load and a tokenizer patch crash are different code-path problems." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Both are output mismatches, but they affect different models and mechanisms (padding mask vs missing STE)." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "FineGrainedFP8Config failure and template-node compilation errors are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export compatibility is unrelated to OmDet-Turbo processor resolution mismatch." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom-model initialization and non-persistent buffer corruption are different failures." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Audio feature extraction and compiled flex_attention failures are unrelated." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer/model loading failures with no clear shared code-path." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Both are load-time failures, but for different models and different tokenizer/model code paths." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Both report Qwen3.5 save_pretrained regressions producing incorrect checkpoints/keys; same underlying serialization bug." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Tied lm_head weights in a model class is different from LoRA merge collapse with extended vocabulary." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "FP8 config failure and init_empty_weights/_is_hf_initialized constructor breakage are separate regressions." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized initialization issues are unrelated to the Strix Halo mmap/OOM mitigation request." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer add_special_tokens conflict and MobileLLM key error are different load failures." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken argument duplication is unrelated to the physical-intelligence/fast loading issue." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "FP8 config failure and missing Float8 storage are different low-level issues." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL load failure in vLLM and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Sliding-window behavior and strict config loading are distinct model/config regressions." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch version incompatibility is not the same as noisy model loading." + }, + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "base_model_prefix loading breakage and non-persistent buffer junk are different v5 regressions." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "The broad video-input regression and the specific still-image rope-index scaling bug are related only at a high level, not enough to merge." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "T5 tokenizer load conflict and Qwen3 auto device-map cudaErrorAssert are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both touch TF/backend packaging, but one is missing TensorFlow in a torch install and the other is a tensorboard-without-TF backend error." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and missing Float8 storage are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "High perplexity on gpt-oss-20b is unrelated to Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is a specific backend incompatibility, not the broad remote_code loading regression." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative overall. The only accepted soft pair, issue:45216 vs issue:45357, is plausibly the same Qwen3.5 save_pretrained serialization regression and looks mergeable into one fix. The other pairs are appropriately rejected as model-, checkpoint-, or code-path-specific rather than clear duplicates. issue:45020 is a reasonable broad umbrella for the cluster." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 10, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:33666", + "issue:40444", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:42915", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43381", + "issue:43421", + "issue:43454", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43646", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44466", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44829", + "issue:44898", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45663", + "issue:45812", + "issue:45834", + "issue:45923" + ], + "soft_pairs": [ + "issue:43818|issue:45357", + "issue:43421|issue:44568", + "issue:44403|issue:44991", + "issue:43632|issue:44534", + "issue:41553|issue:43582", + "issue:33666|issue:40444", + "issue:44462|issue:45812", + "issue:44079|issue:45663", + "issue:43482|issue:45538", + "issue:43317|issue:43856", + "issue:44829|issue:45479", + "issue:43381|issue:45923", + "issue:40444|issue:45325", + "issue:44291|issue:44589", + "issue:43482|issue:43525", + "issue:43377|issue:45491", + "issue:41720|issue:45081", + "issue:44265|issue:45072", + "issue:42175|issue:43296", + "issue:43531|issue:44291", + "issue:43994|issue:44898", + "issue:43611|issue:43646", + "issue:43632|issue:45072", + "issue:43792|issue:43957", + "issue:44079|issue:44534", + "issue:45325|issue:45834", + "issue:43454|issue:44466", + "issue:42915|issue:43482", + "issue:40444|issue:45381", + "issue:45325|issue:45381" + ], + "prepared_review_unit_hash": "53d8a06899054f3aa2f3426ae3f4d8a61878e1516a02e8c4f778d23d48eb1c08", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36999, + "estimated_input_tokens": 9250, + "estimated_eval_tokens": 18756 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: it mixes unrelated model-loading, tokenizer, vision-language, and training regressions. None of the soft-edge pairs are safe duplicates, so all were rejected.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43611 is the broadest representative of the cluster\u2019s dominant theme (Transformers v5 loading/init regressions), but it is only a loose anchor because the cluster is not a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best global issue anchor among the items, since it captures the common v5 model-loading breakage theme more cleanly than the others; however, it is still not a strong duplicate center for this mixed cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Different models and different bugs: Video-LLaVA temporal-attention/weight-sharing vs Qwen3.5 visual-encoder key serialization." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Both involve tokenizers, but one is about runtime post-processor updates and the other is a tokenizer-specific BOS/EOS failure; different root causes." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "One is about reducing noisy load messages, the other is a concrete tokenizer loading failure for a specific model." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "Unrelated v5 regressions: one is `_is_hf_initialized` handling, the other is non-persistent buffer initialization." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Completely different areas: AutoTokenizer error messaging vs Apple Silicon allocator warmup TypeError." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both Qwen VL training issues, but different versions and different failure modes; not the same concrete bug." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one ignores `tokenizer.json` while the other produces wrong Granite token IDs; too different to merge." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "Different bugs in different code paths: `ModelOutput` key assignment vs Gemma-4 FSDP attention state rebuilding." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "Both touch tokenizer/loading behavior, but GGUF loading failure and `model_max_length` misuse are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "One is device-map/offload loading failure; the other is Qwen3 MoE memory inefficiency during training." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both affect training, but the causes differ: flash-attention-3 degeneration vs classification loss handling for `num_labels=1`." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing appears in both, but one is eval-mode incompatibility and the other is a missing capability flag on a trust-remote-code model." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Same model family, but different bugs: iterable-dataset multi-image finetuning vs wrong still-image position scaling." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Both are loading regressions in v5, but the concrete failures are different: unexpected `_is_hf_initialized` arg vs missing float8 storage type." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Both are loading failures, but one is a GGUF/transformers v5 compatibility issue and the other is a missing config attribute." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "Different architectures and root causes: MIMI padding-mask batching bug vs Gemma3 sliding-window/all-padding NaNs." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "Unrelated failures: Qwen3 auto device mapping CUDA assert vs Mistral regex patch crashing on tokenizer backend access." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "Different systems and symptoms: `torch.export` with `torch_compilable_check` vs dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "Packaging/backend selection issue vs a model loading failure in vLLM; no shared bug path." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "One is a sliding-window issue in Qwen3-MoE, the other is an `init_empty_weights` argument regression; unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision model inference bugs, but different models and different code paths." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": false, + "reason": "Both are broad v5 initialization regressions, but one is about `base_model_prefix` loading and the other about custom model initialization; not the same bug." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Different regressions: `_is_hf_initialized` breakage vs dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Different loading/runtime issues: Whisper model cannot run vs `torch.device('meta')` loading breakage." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "`ModelOutput` key bookkeeping is unrelated to junk-filled non-persistent buffers." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both are multimodal long-input issues, but Qwen2.5-VL position-id scaling and Kosmos2.5 OCR index errors are different bugs." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "AyaVision weight-tying bug and serialization inconsistency in `lm_head.weight` are related only at a very high level, not the same underlying issue." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Qwen3MoE FP8 config failure vs Qwen2.5-GGUF loading failure; different model families and different failure modes." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both Qwen2.5-VL issues, but one is dataset/multi-image finetuning failure and the other is video position-id regression." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Same model family and nearby symptoms, but still-image vs video position-id handling are distinct code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 11, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43644", + "issue:43701", + "issue:43720", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44387", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44568", + "issue:44610", + "issue:44617", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45325", + "issue:45357", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45920", + "issue:45923" + ], + "soft_pairs": [ + "issue:43644|issue:44079", + "issue:43749|issue:44079", + "issue:43296|issue:45800", + "issue:44479|issue:45823", + "issue:35707|issue:40444", + "issue:43606|issue:44265", + "issue:44291|issue:44877", + "issue:44387|issue:44617", + "issue:44568|issue:45920", + "issue:43881|issue:44488", + "issue:43701|issue:45325", + "issue:44186|issue:44265", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:43454|issue:43550", + "issue:43262|issue:43746", + "issue:43377|issue:44610", + "issue:43317|issue:43873", + "issue:39692|issue:40444", + "issue:43572|issue:45759", + "issue:43454|issue:45072", + "issue:43257|issue:45923", + "issue:43377|issue:44898", + "issue:40990|issue:45584", + "issue:40990|issue:42947", + "issue:44466|issue:45357", + "issue:43454|issue:43720", + "issue:43526|issue:43883", + "issue:43296|issue:44877", + "issue:43873|issue:45701" + ], + "prepared_review_unit_hash": "3d268d08262a5d832b5866f425826a3122ea85168143ccdf5ecbafca6a5ebab1", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36927, + "estimated_input_tokens": 9232, + "estimated_eval_tokens": 18720 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These issues are mostly unrelated regressions across loading, quantization/offload, tokenization, multimodal inputs, and model-specific config bugs. I did not find any soft pair that clearly looks like the same concrete underlying bug, so all proposed merges are rejected.", + "confidence": 0.87, + "canonical_issue_reason": "issue:43873 is the least-bad anchor: it is open, has the most activity among the broadly related loading/offloading reports, and is general enough to represent the cluster better than the very model-specific bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best overall issue to anchor on, but only because the cluster is heterogeneous; it has broad offloading/quantization scope and the most discussion/inbound refs among the active candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer initialization vs ModelOutput key assignment; unrelated code paths." + }, + { + "left": "issue:43749", + "right": "issue:44079", + "accept": false, + "reason": "FSDP CPU RAM efficient loading vs ModelOutput key handling; unrelated." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "Specific PaddleOCR-VL/vLLM load failure vs broad torch/transformers incompatibility; not the same bug." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Different multimodal regressions: video-input path vs device mismatch during forward." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values vs VL finetuning on IterableDataset; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch vs torch.export/check-wrapper export failure; different failures." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "Unexpected _is_hf_initialized arg vs strict config loading; different load-time issues." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Int4 reserved-memory/OOM regression vs SAM3Video OOM; not the same cause." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Single tokenizer missing BOS/EOS vs broad wrong-token-IDs regression; related area only, not same bug." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Two separate model-loading failures for different models." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint key mismatch vs rope/position-id scaling bug; unrelated." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/truncation crash vs torch.export failure; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Device mismatch on CPU offload vs DAC.from_latents/STE mismatch; unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Different models and failures: Qwen3 auto device map assert vs Gemma4 PLE mismatch." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "Weight tying/garbage text vs torch.compile+SDPA failure; unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sample-rate default vs PEFT local checkpoint loading; unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "Padding-mask batch inconsistency vs processor/model image-size mismatch; unrelated." + }, + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Both mention offloading/quantization, but one is dequantized loading with device_map=auto and the other is generic offloading behavior; too broad to merge." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "SigLIP2 documentation errors vs Qwen2.5-VL IterableDataset finetuning failure; unrelated." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "Missing pad_token_idx vs from_config not unwrapping text_config; unrelated." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "Weight tying bug vs bfloat16 dtype mismatch in wrappers; unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MoE weight conversion/loading vs missing gradient-checkpointing flag; unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "MIMI padding-mask bug vs Perceiver non-default-resolution failure; unrelated." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "GPT-OSS perplexity regression vs Whisper empty-transcription generation; unrelated." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "Perplexity regression vs LoRA gradient checkpointing ineffective; unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "lm_head serialization inconsistency vs visual-encoder key saving regression; only broadly about saving, not same bug." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Weight tying bug vs packed-weights not unpacked during accelerate loading; unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug vs Molmo tied-weights attribute error; unrelated." + }, + { + "left": "issue:43296", + "right": "issue:44877", + "accept": false, + "reason": "PaddleOCR-VL load failure vs strict config loading for granite_speech; unrelated." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Quantization/offloading issue vs tokenization regression; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 12, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43316", + "issue:43317", + "issue:43322", + "issue:43404", + "issue:43450", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43873", + "issue:43881", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44479", + "issue:44534", + "issue:44610", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44913", + "issue:44918", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45161", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45812", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:43881|issue:44991", + "issue:41720|issue:44977", + "issue:44008|issue:45823", + "issue:43404|issue:45357", + "issue:45632|issue:45684", + "issue:34634|issue:35707", + "issue:43577|issue:43708", + "issue:35707|issue:41720", + "issue:42617|issue:42915", + "issue:44186|issue:45072", + "issue:44423|issue:45406", + "issue:44877|issue:44991", + "issue:43550|issue:43720", + "issue:36331|issue:42915", + "issue:43450|issue:45701", + "issue:43749|issue:44534", + "issue:44610|issue:44898", + "issue:36331|issue:42617", + "issue:43873|issue:44756", + "issue:44186|issue:44610", + "issue:43550|issue:43606", + "issue:43322|issue:46050", + "issue:44479|issue:44918", + "issue:44387|issue:45704", + "issue:42915|issue:43317", + "issue:43316|issue:44913", + "issue:41720|issue:43322", + "issue:43295|issue:45701", + "issue:40990|issue:45701", + "issue:41720|issue:45161", + "issue:45081|issue:45812", + "issue:41720|issue:42617" + ], + "prepared_review_unit_hash": "13df3b4c15783efee13cc6ba42d82a6fb1dc2eef573ec53aee9b0da30f61814a", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36776, + "estimated_input_tokens": 9194, + "estimated_eval_tokens": 18644 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: the soft-similarity links mostly connect unrelated bugs across tokenization, loading, quantization/offload, trainer behavior, and multimodal processing. I do not see any pair that clearly shares the same underlying defect, so all soft edges are rejected.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 45701 is the broadest, most externally referenced item in this set and the best anchor for the mixed regression/tokenization subgroup, though it still does not duplicate the other issues.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the most representative high-signal issue to anchor this cluster, but the cluster is too mixed for a true dedupe canonical to cover the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizer failures, but they affect different models and different failure modes." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Auto device-mapping CUDA assert and flash-attention generation failure are different code paths." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3n forward variable collision and Gemma4 PLE device mismatch are unrelated bugs." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Both touch image-text models, but one is tied weights and the other is save_pretrained key handling." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision and read-only permission propagation are distinct save_pretrained issues." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Bark voice preset loading and progressive generation with inputs_embeds are unrelated." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "A dtype initialization bug and a Trainer resume/max_steps bug are different subsystems." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with embeddings and Qwen3 device-mapping CUDA asserts are not the same defect." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "3d_parallel.py execution failure and Qwen3Moe FP8 loading failure are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer crashes for LayoutLMv2 and dtype mismatches in inference are different problems." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Continuous-batching multimodal crash and missing Gemma4Processor tokenizer attr are separate serve bugs." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config handling for granite_speech and tokenizer loading for est-roberta are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile/SDPA failure and packed-weight unpacking failure are different code paths." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "CustomTrainer compute_loss signature mismatch and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video batch-shape handling and tokenization version regression are different domains." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer corruption are not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Processor image-size mismatch and Perceiver non-default-resolution failure are similar only at a high level, not the same issue." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer loss signature error and 3d_parallel.py failure are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Quantization offload problems and Strix Halo mmap OOM are different memory-management issues." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crashes on batched padding and OmDet processor resolution mismatch are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Bamba torch.compile/SDPA and Bark-small CPU-offload device mismatch are different model/runtime failures." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Llava Next loading segfault and sinq save/load breakage are separate quantization/loading bugs." + }, + { + "left": "issue:44479", + "right": "issue:44918", + "accept": false, + "reason": "Video-input regression and SFT input-embedding unpacking failure affect different paths." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Int4 quantization OOM and T5 apex RMSNorm memory leak are both memory-related but not the same defect." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Qwen3Moe FP8 failure and dequantized model offload loading failure are different quantization/loading bugs." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Gemma3TextConfig API mismatch and GPTNeoXConfig rotary_pct reload regression are unrelated config bugs." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3 device-mapping crash and Llava Next segfault are different failure modes." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor/tokenizer API regression and tokenization-output regression are related only broadly, not the same bug." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "High perplexity on GPT-OSS and tokenization changes are not the same underlying issue." + }, + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "CUDA assert on auto device mapping and GPT-OSS MoE tensor-parallel failure are distinct." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Mistral regex patch crash and Granite token-ID regression are different tokenizer bugs." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 device-mapping crash and 3d_parallel.py 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": 17, + "review_unit_index": 13, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:29159", + "issue:30064", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:36032", + "issue:41720", + "issue:42490", + "issue:42617", + "issue:42915", + "issue:43322", + "issue:43329", + "issue:43388", + "issue:43421", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43746", + "issue:43782", + "issue:43881", + "issue:43927", + "issue:44186", + "issue:44361", + "issue:44368", + "issue:44451", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44545", + "issue:44671", + "issue:44743", + "issue:44898", + "issue:44991", + "issue:45059", + "issue:45072", + "issue:45357", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45759", + "issue:45812" + ], + "soft_pairs": [ + "issue:43531|issue:43572", + "issue:43526|issue:43881", + "issue:43540|issue:43782", + "issue:36010|issue:42617", + "issue:44671|issue:44743", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:45406|issue:45464", + "issue:29159|issue:36032", + "issue:43606|issue:43720", + "issue:30064|issue:34634", + "issue:44492|issue:44509", + "issue:43550|issue:43653", + "issue:43421|issue:45701", + "issue:42915|issue:43322", + "issue:43388|issue:45059", + "issue:43606|issue:43653", + "issue:44514|issue:44545", + "issue:43531|issue:45759", + "issue:34567|issue:35707", + "issue:43421|issue:43927", + "issue:44368|issue:45357", + "issue:44451|issue:44991", + "issue:42490|issue:43329", + "issue:44898|issue:45072", + "issue:41720|issue:43746" + ], + "prepared_review_unit_hash": "192006d3ebc5e5a9fb96acbf0d335f1dd085d8ea7fcf3b6d659e41f1ae036aab", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35063, + "estimated_input_tokens": 8766, + "estimated_eval_tokens": 17788 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated issue reports with only one clear duplicate pair: the two identical Qwen2_5_VLProcessor.apply_chat_template crash reports. The rest are broad tokenizer/model-loading regressions that share themes but not the same concrete bug path.", + "confidence": 0.92, + "canonical_issue_reason": "issue:44545 is the strongest canonical representative because it is an exact duplicate of issue:44514, has the same title/root crash, and has slightly more inbound references indicating it is the more central report.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44545 is the best overall issue in this set because it cleanly represents the only confirmed duplicate pair and is the most reference-central standalone bug report here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Different bugs: one is a Qwen3-MoE sliding_window behavior issue, the other is a StableLmConfig pad_token_idx regression." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "Different subsystems and failures: BeitImageProcessorFast label reduction vs a GLM-4V model loading failure." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Both involve Qwen3 multimodal models, but one is a video-input processing ValueError and the other is a from_pretrained/load-time weight_only error; not the same code path." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "Unrelated: GenerationMixin import error vs a script execution problem for 3d_parallel.py." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "Both are model-specific regressions, but CamemBERT MLM predictions and Qwen3.5 recurrent-state caching are different bugs." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer-related, but one is runtime post-processor updates after special-token edits while the other is wrong Granite token IDs; distinct issues." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Both tokenizer issues, but LayoutLMv2 NER/padding crashes and MLuke task AttributeErrors are different failure modes and code paths." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Different products and failures: Gemma4Processor serve-time missing _tokenizer vs Qwen3.5 streaming inference failure." + }, + { + "left": "issue:29159", + "right": "issue:36032", + "accept": false, + "reason": "Not the same bug: slow/fast tokenizer inconsistency vs a T5Tokenizer add_special_tokens load conflict." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both are loading/offload related, but device mismatch on CPU offload and packed-weight unpacking during accelerate loading are different concrete problems." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Completely different areas: image processor void segmentation handling vs BarkProcessor voice_preset behavior." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A typo fix in cache strategies is unrelated to documentation about removed pipeline tasks." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "Different bugs: Bamba torch.compile/SDPA failure vs BigBirdTokenizer mask-token registration/decoding issue." + }, + { + "left": "issue:43421", + "right": "issue:45701", + "accept": false, + "reason": "Both mention tokenization, but one is a backend post-processor update bug and the other is a broad version-dependent tokenization change report." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Unrelated model/runtime failures: Qwen3Moe FineGrainedFP8Config vs Llava Next loading segfault." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Different issues in different paths: evaluation metric gathering drops tuple labels vs SAM3 text/bbox processing weirdness." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "Both mention CI regressions, but device mismatch on CPU offload and tokenizer mask-token registration are unrelated." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Exact duplicate reports of the same Qwen2_5_VLProcessor.apply_chat_template batched-padding=False crash." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Both touch Qwen3-family model behavior, but sliding_window on Qwen3-MoE and AutoModelForCausalLM config unwrapping are different bugs." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token accounting and progressive generation with inputs_embeds/past_key_values are unrelated." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Related to token IDs, but one is runtime post-processor updates and the other is save/load preserving custom DiaConfig token IDs." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A warning about tie_word_embeddings is unrelated to incorrect visual encoder keys being saved." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer/model-loading complaints, but for different models and different failure mechanisms." + }, + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "A local-path import warning is unrelated to a multimodal video token counting bug." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Different model/runtime problems: Perceiver interpolation failure vs dtype mismatch in bfloat16 inference." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Different loading/runtime failures on different models: Qwen3 auto device mapping cudaErrorAssert vs GraniteSpeech PEFT checkpoint loading." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative on the soft edges. The only accepted pair, issue:44514/issue:44545, is supported by nearly identical titles and the duplicate verdict is reasonable. The canonical choice of issue:44545 is also justified by its slightly higher inbound references. No overstatement stands out." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 14, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:30064", + "issue:33666", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:39692", + "issue:41720", + "issue:42886", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43720", + "issue:43782", + "issue:43819", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44008", + "issue:44062", + "issue:44186", + "issue:44220", + "issue:44451", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44843", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:45042", + "issue:45081", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45907", + "issue:45923" + ], + "soft_pairs": [ + "issue:44987|issue:45042", + "issue:43873|issue:45704", + "issue:43531|issue:44589", + "issue:44062|issue:44451", + "issue:33666|issue:35707", + "issue:45759|issue:45859", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:45588|issue:45759", + "issue:42886|issue:44843", + "issue:45663|issue:45923", + "issue:43421|issue:43653", + "issue:44918|issue:44936", + "issue:43381|issue:43844", + "issue:43421|issue:44186", + "issue:43525|issue:43531", + "issue:43782|issue:45381", + "issue:45704|issue:45859", + "issue:45081|issue:45356", + "issue:34634|issue:41720", + "issue:45356|issue:45907", + "issue:44625|issue:45479", + "issue:39692|issue:43873", + "issue:43994|issue:44671", + "issue:43596|issue:44220", + "issue:44220|issue:44661", + "issue:43720|issue:43819", + "issue:43540|issue:44008", + "issue:30064|issue:36010" + ], + "prepared_review_unit_hash": "3e3d3dafae71da15ff0ba8d34a0195b825cdcb5ec19028ac55489519f9c7bf6a", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 36047, + "estimated_input_tokens": 9012, + "estimated_eval_tokens": 18280 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous cluster of unrelated model/processor/training bugs. The only strong duplicate-style overlap is the HF_HUB_OFFLINE tokenizer regression pair; the rest are broad-theme similarities but not the same concrete bug.", + "confidence": 0.88, + "canonical_issue_reason": "Issue 44843 is the clearest, most specific report: it names the exact failing code path (_patch_mistral_regex/model_info) and the offline regression, making it the best anchor for the only likely duplicate subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44843 is the strongest representative issue in this set because it has an explicit root cause, a reproducible failure mode, and a clear fix target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Different problems: one is a model-loading regression, the other is an image-processor torchvision dependency issue." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Both mention training/runtime behavior, but one is quantization/offloading and the other is a T5 RMSNorm memory leak; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to the Float8 storage import/runtime error." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "Both are tokenizer-loading related, but one is an AddedToken argument collision and the other is a model-specific load failure; too little evidence of the same root cause." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Multi-GPU Qwen2-VL training and progressive generation with embeds/past key values are different code paths." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Both concern Qwen 3.5, but one is config unwrapping and the other is CPU-offload incompatibility in rotary embedding; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Both are model/processor mismatches, but they involve different models and different failure modes." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "T5 RMSNorm leak and a missing supports_gradient_checkpointing flag are unrelated." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sink handling and Qwen multimodal config unwrapping are different issues." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both describe the same offline tokenizer regression; 44843 gives the concrete root cause in _patch_mistral_regex/model_info, while 42886 is the broader symptom." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Gemma-4 FSDP2 shared_kv_states KeyError is unrelated to a missing gradient-checkpointing flag." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both involve special tokens, but one is runtime post-processor refresh and the other is BigBird mask-token registration; not the same concrete bug." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: unpacking input embeddings in SFT versus evaluate() failing after train()." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing eval-mode handling is unrelated to the ZeRO-3 gradient explosion report." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Tokenizer post-processor refresh and LayoutLMv2 NER/padding crashes are different failures." + }, + { + "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:43782", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen VL issues, but one is a weight_only loading error and the other is a video vision_position_ids bug." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "RMSNorm memory leak and CPU-offload rotary embedding incompatibility are distinct code paths." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both touch fix_mistral_regex, but one is a backend_tokenizer crash and the other is a Kimi-K2.5 codec-handling regression; too different to merge as one bug." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice_preset and Qwen3 auto device mapping cudaErrorAssert are unrelated." + }, + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex regression and list_repo_files revision forwarding are completely unrelated." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "A Qwen3.5 config propagation bug and a generic single-label classification zero-loss issue are not the same defect." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 docs/model mismatch is unrelated to quantization offloading behavior." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Both are model-output regressions, but they affect different models and likely different causes." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Zero3/BertModel indexing and _torch_extract_fbank_features are unrelated." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction and add-new-model-like/tokenizer-mapping logic are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "BitNet packed-weight loading and DAC.from_latents STE mismatch are different code paths." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Qwen3OmniMoe video input processing and Gemma 3n variable-name collision are unrelated." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Void segmentation map processing and a GenerationMixin import error are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet and stays conservative. The 42886/44843 pair is well-supported as the only clear duplicate-style overlap, and the other soft-edge rejections do not overclaim same-root-cause evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 15, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:30064", + "issue:36331", + "issue:42915", + "issue:43295", + "issue:43335", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43577", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43873", + "issue:43950", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44448", + "issue:44488", + "issue:44561", + "issue:44625", + "issue:44671", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45381", + "issue:45479", + "issue:45834", + "issue:45987", + "issue:46032", + "issue:46050" + ], + "soft_pairs": [ + "issue:43746|issue:46050", + "issue:43618|issue:43697", + "issue:43653|issue:43720", + "issue:43388|issue:46032", + "issue:45183|issue:45479", + "issue:44077|issue:44625", + "issue:43335|issue:43756", + "issue:43716|issue:44008", + "issue:42915|issue:43746", + "issue:43550|issue:45072", + "issue:43295|issue:45834", + "issue:43550|issue:43819", + "issue:43746|issue:43873", + "issue:43950|issue:45987", + "issue:44186|issue:44898", + "issue:44843|issue:45081", + "issue:44062|issue:44488", + "issue:43653|issue:43819", + "issue:43643|issue:44877", + "issue:43540|issue:45381", + "issue:43531|issue:43643", + "issue:43782|issue:44977", + "issue:43577|issue:43818", + "issue:43421|issue:44811", + "issue:44448|issue:44671", + "issue:30064|issue:36331", + "issue:44561|issue:45020" + ], + "prepared_review_unit_hash": "c7b7d97ffe51005f67351b210bcc20890ac3a2b16c71d290b8de8044697a928d", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36284, + "estimated_input_tokens": 9071, + "estimated_eval_tokens": 18398 + }, + "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. A few items share broad themes like model loading, tokenizers, or remote_code regressions, but none of the soft pairs look like the same concrete bug/change under a strict duplicate standard.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 45020 is the broadest umbrella candidate for the cluster's recurring recent-version / remote_code loading regressions, though the set is heterogeneous and not a clean duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45020 is the best global representative because it is the most umbrella-like report and matches the dominant load/regression theme better than the more narrowly scoped issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "Different failure modes: PEFT adapter local checkpoint loading vs quantized model save/load corruption." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different models and bugs: missing CLIP attentions vs RTDetrV2 output drift in v5." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration bug is unrelated to BitNet packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43388", + "right": "issue:46032", + "accept": false, + "reason": "Different code paths: gather_for_metrics label truncation vs Mamba2 cache correctness with seq_len > 1." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Both concern model input/loss logic, but one is an input validation XOR bug and the other is a degenerate loss from num_labels=1 classification setup." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Unrelated issues: patchtsmixer post_init policy vs Qwen3.5 num_labels propagation." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "Different model internals and symptoms: sparse layer creation bug vs RoPE-layer dropping in Smollm3." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "One is a dtype mismatch in image preprocessing/model loading; the other is a variable name collision in Gemma3n forward." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Different subsystems and models: Qwen3Moe FP8 config failure vs GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Both mention dtype/compile issues, but they affect different models and concrete paths; not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Different regressions: processor.tokenizer access in v4.57.5 vs Kosmos2.5 OCR long-input index error." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Completely different failures: torch.compile + SDPA in Bamba vs DAC.from_latents missing STE consistency." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Adapter loading from local checkpoints is unrelated to quantization offloading behavior." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Non-persistent buffer corruption in from_pretrained is unrelated to StaticCache.get_seq_length return type." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Different tokenizer/image-classification failures with no shared concrete code path." + }, + { + "left": "issue:44843", + "right": "issue:45081", + "accept": false, + "reason": "Both touch Mistral tokenizer patching, but one is offline model_info access and the other is backend_tokenizer attribute handling; too different to merge." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "Token AddedToken construction error is not the same as a model not loading; only broad tokenizer area overlaps." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Mask-token special registration in tokenizers is unrelated to DAC latent decoding consistency." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-loading problems, but one is missing fields with trust_remote_code and the other is strict config rejection of granite_speech." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both involve video inputs in Qwen-family models, but they are different models and different bugs." + }, + { + "left": "issue:43531", + "right": "issue:43643", + "accept": false, + "reason": "Sliding-window behavior in Qwen3-MoE is unrelated to AutoConfig trust_remote_code field loss." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different Qwen models and different inference paths: weight_only load error vs flash-attention generation issue." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Different model families and bugs: BLIP2 dtype handling vs Video-LLaVA temporal-attention/weight-sharing issue." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Both are tokenizer-related, but one is runtime post-processor updates and the other is Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Both are v4-v5 behavioral regressions, but they are distinct models and distinct outputs, not the same underlying bug." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image processor segmentation-map handling and CustomTrainer compute_loss signature are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Close in theme, but 44561 is one specific remote_code breakage cause while 45020 is a broader umbrella report; not enough evidence they are the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 16, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28218", + "issue:29159", + "issue:34634", + "issue:36010", + "issue:39692", + "issue:42175", + "issue:43262", + "issue:43322", + "issue:43404", + "issue:43452", + "issue:43526", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43782", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44060", + "issue:44186", + "issue:44368", + "issue:44442", + "issue:44479", + "issue:44485", + "issue:44509", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44821", + "issue:44857", + "issue:44912", + "issue:44936", + "issue:44991", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45538", + "issue:45584", + "issue:45685", + "issue:45701", + "issue:45834" + ], + "soft_pairs": [ + "issue:43825|issue:43994", + "issue:44821|issue:45084", + "issue:44485|issue:44509", + "issue:39692|issue:45834", + "issue:45584|issue:45834", + "issue:43322|issue:45685", + "issue:44479|issue:45834", + "issue:43606|issue:45072", + "issue:43825|issue:43827", + "issue:44186|issue:44442", + "issue:34634|issue:36010", + "issue:44805|issue:44936", + "issue:43577|issue:43582", + "issue:43452|issue:44991", + "issue:28218|issue:29159", + "issue:44610|issue:45072", + "issue:42175|issue:45081", + "issue:43720|issue:45072", + "issue:43404|issue:43782", + "issue:45081|issue:45406", + "issue:43650|issue:43906", + "issue:43582|issue:44857", + "issue:44671|issue:45701", + "issue:44060|issue:44368", + "issue:43262|issue:43819", + "issue:43526|issue:43697", + "issue:45084|issue:45538", + "issue:43653|issue:44912" + ], + "prepared_review_unit_hash": "fae9706c52964baef1fd5a9fc1e6121c9f1a88cd373135f680fb1329e73c4ab5", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36249, + "estimated_input_tokens": 9063, + "estimated_eval_tokens": 18382 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a grab-bag of unrelated tokenizer, multimodal, loading, and docs issues. Only one soft edge looks like a likely duplicate pair: the added-token spacing regression and the slow/fast tokenizer inconsistency report.", + "confidence": 0.58, + "canonical_issue_reason": "issue:28218 is the most concrete statement of the underlying tokenizer bug (an extra space after an added token), while issue:29159 reads like the broader symptom report of the same inconsistency.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:28218 is the clearest and most actionable representative of the duplicate pair because it names the concrete failure mode directly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "Different problems: a v5 pipeline error-message issue versus a SigLIP2 docs/example failure." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "No shared underlying bug; loading an image processor from URL is unrelated to a template compilation TypeError." + }, + { + "left": "issue:44485", + "right": "issue:44509", + "accept": false, + "reason": "GLM-5 RoPE implementation discussion is unrelated to docs still mentioning removed pipeline tasks." + }, + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Different models and failures: SigLIP2 docs example errors versus Kosmos2.5 OCR index error." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription generation failure is unrelated to the Kosmos2.5 long-input OCR issue." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "A Llava Next loading segfault and an MPS int histogram limitation are distinct bugs." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Video-input regression in Qwen VL models is not the same as Kosmos2.5 OCR indexing." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU offload device mismatch in Bark-small is unrelated to bf16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Both involve v5 pipeline removal, but one is a runtime error message and the other is documentation drift; not the same concrete bug." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer failures on different models; no evidence they share one root cause." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset behavior and a GenerationMixin import error are unrelated." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "Mask-shape IndexError is a different failure from trainer.evaluate() breaking after training." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype loading and AppleSilicon allocator warmup TypeError are separate issues." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizers, but the gguf_file regression and EMBEDDIA tokenizer-loading failure do not appear to be the same bug." + }, + { + "left": "issue:28218", + "right": "issue:29159", + "accept": true, + "reason": "Both describe the same tokenizer regression around added tokens producing inconsistent spacing/behavior between slow and fast tokenizers." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "Processor image-size mismatch and bf16 dtype mismatch are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Dependency/back-end packaging and a Mistral regex patch crash are different problems." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "Packed-weight loading in BitNet is unrelated to bf16 dtype mismatch behavior." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Weight-tying bug in Mistral3 and Qwen3VL weight_only loading error are different model-specific issues." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Mistral tokenizer regex patch crash and Gemma4Processor missing _tokenizer are distinct failures." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "The titles are unrelated; no duplicate relationship is apparent." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "Apple Silicon warmup TypeError and CUDA float16 AMP crash are different environment-specific bugs." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "A CamemBERT masked-LM regression and a generic tokenization-version change report are not the same concrete bug." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but they concern different Qwen models and different symptoms." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC latent/forward mismatch are unrelated audio bugs." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "BEiT label reduction and RT-DETRv2 output differences are different vision issues." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Template compilation TypeError and CLIPTokenizer model_max_length behavior are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and MXFP4 quantization fallback are not the same issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The analysis is grounded in the packet and stays mostly conservative. The one accepted soft edge, issue:28218 vs issue:29159, is plausible from the titles and similarity signal, and the other non-duplicates are reasonably rejected. No mergeability concerns apply here since there are no PR pairs." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 17, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:34567", + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:42490", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43638", + "issue:43643", + "issue:43644", + "issue:43645", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:44291", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44610", + "issue:44811", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:45020", + "issue:45042", + "issue:45356", + "issue:45459", + "issue:45488", + "issue:45600", + "issue:45759", + "issue:45803", + "issue:45859" + ], + "soft_pairs": [ + "issue:43742|issue:45020", + "issue:43329|issue:45600", + "issue:45459|issue:45803", + "issue:43638|issue:44936", + "issue:43644|issue:43749", + "issue:44589|issue:45042", + "issue:43746|issue:44811", + "issue:38175|issue:44610", + "issue:43819|issue:43927", + "issue:39692|issue:44912", + "issue:43854|issue:44977", + "issue:36010|issue:43645", + "issue:43550|issue:44912", + "issue:43526|issue:44554", + "issue:34634|issue:36331", + "issue:43720|issue:44610", + "issue:43454|issue:43577", + "issue:43749|issue:44291", + "issue:43531|issue:45042", + "issue:43257|issue:43329", + "issue:36010|issue:36331", + "issue:43262|issue:44811", + "issue:44568|issue:45356", + "issue:42490|issue:43257", + "issue:43643|issue:45759", + "issue:43329|issue:44479", + "issue:44568|issue:45488", + "issue:43329|issue:43450", + "issue:34567|issue:40990", + "issue:43606|issue:45859" + ], + "prepared_review_unit_hash": "f23a09b0473772fd249c9ffb1dc56d120ba9038eb44bd6f802256d78229b6a88", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37109, + "estimated_input_tokens": 9278, + "estimated_eval_tokens": 18812 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This batch is mostly a collection of unrelated bugs, not a tight duplicate cluster. I rejected all soft-edge duplicate candidates because they point to different code paths, models, or failure modes. If one issue must serve as a representative, #45020 is the broadest regression-style report, but it is not a true duplicate umbrella for the rest.", + "confidence": 0.92, + "canonical_issue_reason": "#45020 is the broadest, most general regression report in the set (remote_code-related loading breakage), so it is the closest thing to a representative issue; however, the batch does not form a real duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "#45020 is the best global representative because it is the least model-specific and most likely to subsume adjacent loading regressions, even though the other issues are still distinct.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Different failures: MobileLLM loading key error vs a broad remote_code regression; not the same code path." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Video token counting bug vs stale auto_mappings references; unrelated problems." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer protobuf error handling vs bare-except swallowing errors in Fuyu tensor conversion; different functions and bugs." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "DeepSpeed ZeRO-3 index error during Bert training vs trainer evaluate-after-train failure; distinct trainer behaviors." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Non-persistent buffer initialization junk vs FSDP CPU RAM efficient loading; different loading issues." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage deserialization error vs PIL backend torchvision dependency regression; unrelated." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT checkpoint loading for GraniteSpeech vs Whisper batch_decode skip_special_tokens; different processor/model paths." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "SigLIP2 zero probabilities vs OmDet-Turbo image size mismatch; different symptoms and code paths." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC latent conversion mismatch vs DiaConfig token ID persistence bug; not the same underlying defect." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "SigLIP2 doc/example errors vs MXFP4 quantization falling back to bf16; different problems." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "GLM-4.7-Flash load issue vs Qwen3.5 flash-attention generation bug; different models and code paths." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import failure vs Jupyter custom-model initialization breakage; related only at a very high level." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile SDPA failure vs quantization fallback to bf16; different concrete bugs." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "BEiT reduce_labels bug vs MPS attention correctness issue; unrelated." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "BarkProcessor voice_preset bug vs CustomTrainer compute_loss signature mismatch; different areas entirely." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "Packed-weight unpacking during accelerate loading vs processor output shape mismatch; not the same change." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision weight tying bug vs BLIP-2 dtype propagation bug; distinct model-init issues." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "FSDP loading regression vs unexpected _is_hf_initialized arg in init_empty_weights; different compatibility failures." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs PIL backend requiring torchvision; unrelated subsystems." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion/loading bug vs undefined video helper usage in multimodal token counting; different bugs." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "Importing GenerationMixin vs CustomTrainer.compute_loss kwargs; unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat-template sampling-rate default bug vs Whisper batch_decode special-token handling; different processor bugs." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "mdeberta special-token regression vs Kimi tokenizer codec/regression warning; different tokenizer paths." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Trailing-slash local-model import warning vs Qwen3 MoE accelerate/deepspeed conversion issue; unrelated." + }, + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Missing fields from AutoConfig with trust_remote_code vs not unwrapping text_config in AutoModelForCausalLM.from_config; different config-loading bugs." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": false, + "reason": "Both involve video VLM behavior, but one is a specific undefined-helper bug and the other is a broader regression; not the same concrete defect." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "add_special_tokens regression vs LlamaTokenizer overriding ByteLevel with Metaspace; related to tokenizers but not the same bug." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Multimodal token counting video branch bug vs batched video processor output shape bug; different stages of processing." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer num_input_tokens_seen not updating vs high perplexity on gpt-oss; unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Bark CPU offload device mismatch vs Qwen3_MoeTextRotaryEmbedding CPU offload incompatibility; different models and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 18, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:24643", + "issue:29159", + "issue:33357", + "issue:34567", + "issue:36331", + "issue:38175", + "issue:41720", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43404", + "issue:43452", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43646", + "issue:43696", + "issue:43697", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43906", + "issue:43927", + "issue:43931", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44560", + "issue:44737", + "issue:44821", + "issue:44849", + "issue:44898", + "issue:44912", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45137", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45538", + "issue:45588", + "issue:45701", + "issue:45823", + "issue:45907", + "issue:45987" + ], + "soft_pairs": [ + "issue:44849|issue:45701", + "issue:43697|issue:45357", + "issue:29159|issue:34567", + "issue:43257|issue:43931", + "issue:44291|issue:45042", + "issue:43452|issue:43582", + "issue:42915|issue:43742", + "issue:41720|issue:43540", + "issue:33357|issue:34567", + "issue:42915|issue:44821", + "issue:43927|issue:44912", + "issue:44479|issue:45381", + "issue:44987|issue:45907", + "issue:44987|issue:45538", + "issue:42915|issue:45538", + "issue:43540|issue:44560", + "issue:43540|issue:44479", + "issue:43317|issue:45538", + "issue:38175|issue:44898", + "issue:43404|issue:45987", + "issue:43577|issue:45072", + "issue:24643|issue:29159", + "issue:45137|issue:45405", + "issue:43257|issue:43756", + "issue:43742|issue:44291", + "issue:44737|issue:45588", + "issue:44062|issue:44991", + "issue:43540|issue:45823", + "issue:43257|issue:43696", + "issue:43906|issue:45381", + "issue:44062|issue:45081", + "issue:34567|issue:36331", + "issue:43646|issue:43749" + ], + "prepared_review_unit_hash": "04a260264fa20c3b763abe26d401ade2afcb2032445de4747b603df9c91f19de", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37601, + "estimated_input_tokens": 9401, + "estimated_eval_tokens": 19058 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous false positives. The only clear duplicate pair is the Qwen2.5-VL video-input regression reports; all other soft pairs describe different bugs, models, or code paths.", + "confidence": 0.84, + "canonical_issue_reason": "issue:44479 is the best canonical issue because it describes the broad v5.3.0 video-input regression across Qwen VL variants; issue:45381 is a narrower reproduction of the same problem.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44479 is the strongest global representative of the only true duplicate area in this set, since it captures the broader regression rather than a single model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Different problems: Qwen3.5 hidden-state behavior vs a general tokenization-version change." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Unrelated failures: RTDetrV2 output differences vs Qwen3.5 visual-encoder key saving." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency is unrelated to TrainerState token counting." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Different loading bugs: Qwen3 MOE weight conversion vs Qwen3-VL weight-shape mismatch." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "Init-empty-weights argument handling is unrelated to PIL image processor torchvision requirements." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "Tokenizer/gguf loading issue and Apple Silicon allocator TypeError are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8 loading and MobileLLM key errors are different model-loading failures." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "CUDA assert with auto device mapping is unrelated to Qwen3OmniMoe video-input ValueError." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "MacOS bus error on CLIP loading is unrelated to TrainerState token counting." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3Moe FP8 failure and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "DiaConfig save/load token IDs and GPT-oss quantization fallback are different bugs." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": true, + "reason": "Both describe the same Qwen VL video-input regression/incorrect vision position ids in transformers 5.3.0." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Model loading on physical-intelligence/fast is unrelated to list_repo_files revision forwarding." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "General model loading failure and CLIPTokenizer max_length bug are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe quantization loading and CLIPTokenizer model_max_length are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Different video bugs in different model families; not the same concrete code path." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Both are video-related, but they affect different Qwen model families and error paths." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "device_map/offload loading failure is unrelated to tokenizer max_length." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to Perceiver non-default-resolution failure." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "Mistral3 lm_head tying bug is unrelated to StaticCache sequence-length return type." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "BLIP2 dtype loading and SwitchTransformers/TimmWrapper bfloat16 mismatches are different issues." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "DeepSpeed weight-dimension runtime error is unrelated to tokenizer inconsistency." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and MIN_PEFT_VERSION bump are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Qwen3 MOE weight conversion and Smollm3 RoPE-layer mismatch are different model bugs." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "MobileLLM load error and init_empty_weights unexpected-arg failure are unrelated." + }, + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "XLNet CPU arange bug is unrelated to flash_attention s_aux=None crash." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "AddedToken special-argument duplication and EMBEDDIA tokenizer loading failure are not the same concrete bug." + }, + { + "left": "issue:43540", + "right": "issue:45823", + "accept": false, + "reason": "Qwen3OmniMoe video input error and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "Qwen3 MOE weight conversion and GPT-oss OOM are unrelated." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Reproduction of issue 38071 is unrelated to the Qwen2.5-VL video-position-id regression." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "AddedToken special duplication and Mistral regex patch AttributeError are different tokenizer bugs." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "TrainerState token counter not updating is unrelated to CustomTrainer compute_loss signature mismatch." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Custom model initialization breakage and FSDP CPU RAM-efficient loading are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet and stays conservative: the single accepted duplicate pair is the only one that clearly matches in the provided titles, and the other soft-edge rejections are supported by the issue descriptions. No obvious overstatement or mergeability issue." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 19, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:34689", + "issue:36010", + "issue:41762", + "issue:42175", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43643", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43994", + "issue:44291", + "issue:44484", + "issue:44488", + "issue:44514", + "issue:44589", + "issue:44625", + "issue:44704", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:44936", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45042", + "issue:45081", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45600", + "issue:45920" + ], + "soft_pairs": [ + "issue:43493|issue:43994", + "issue:43749|issue:44756", + "issue:36010|issue:42175", + "issue:42175|issue:43824", + "issue:45357|issue:45920", + "issue:44291|issue:44821", + "issue:43452|issue:44488", + "issue:43643|issue:45375", + "issue:44792|issue:44964", + "issue:45042|issue:45081", + "issue:28282|issue:34689", + "issue:43526|issue:45479", + "issue:43742|issue:44589", + "issue:43756|issue:45325", + "issue:45405|issue:45600", + "issue:43531|issue:44821", + "issue:43697|issue:45216", + "issue:44514|issue:45381", + "issue:28282|issue:29127", + "issue:43720|issue:44898", + "issue:43582|issue:44977", + "issue:44484|issue:44704", + "issue:41762|issue:44936", + "issue:42175|issue:44938", + "issue:44625|issue:44877", + "issue:43452|issue:43577", + "issue:43452|issue:44843" + ], + "prepared_review_unit_hash": "dec4a574a0b70bb5c8e7e9c8ddc28f895df5325c1db61578f2753255d7c3badb", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 36127, + "estimated_input_tokens": 9032, + "estimated_eval_tokens": 18320 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: many unrelated model-loading, config, and backend issues. I found one plausible duplicate pair around SigLIP2 correctness, but the rest do not look like the same underlying bug/change.", + "confidence": 0.69, + "canonical_issue_reason": "issue:43493 is the best root-cause-style report in the only believable duplicate pair: it describes the SigLIP2 implementation discrepancy directly, while the other report is a downstream symptom (bad outputs).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43493 is the strongest global representative because it is concrete, model-specific, and framed around the likely underlying correctness bug rather than just a user-facing failure mode.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43493", + "right": "issue:43994", + "accept": true, + "reason": "Same model family (SigLIP2) and same underlying symptom class: HF vs reference discrepancy leading to incorrect/nonsensical outputs. These could plausibly be one bug." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "Different failures and environments: FSDP CPU RAM-efficient loading versus mmap/OOM on Strix Halo." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Unrelated: missing GenerationMixin import versus TensorFlow backend packaging omission." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Unrelated install/backend packaging issue versus Qwen2.5-VL import error." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Both are regressions, but they concern different code paths: save_pretrained serialization versus tokenizer ID generation." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "Different areas: init_empty_weights/_is_hf_initialized argument handling versus loading AutoImageProcessor from URL." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "Both involve model loading, but the concrete bugs differ: gguf_file handling versus a specific model load failure." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Related only loosely through missing config fields; the reported causes and affected models are different." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different models and failures: janus image-generation test versus Phi-4 multimodal loading." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "Completely different subsystems: image processor torchvision dependency versus Mistral regex/tokenizer crash." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "Different issues: missing PyTorch dependency import error versus Llama 3.2 Vision loading breakage." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Different bug classes: BEiT image processor label reduction versus sequence-classification loss degeneracy." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "Different concrete failures: MobileLLM key error versus Float8 storage lookup TypeError." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Both mention positional/RoPE logic, but they are different models and different incorrect computations." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "Unrelated: dependency version bump issue versus removed config references breaking CI." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Unrelated: Qwen3-MoE sliding-window behavior versus AutoImageProcessor URL loading." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Different regressions and paths: RTDetrV2 output mismatch versus Qwen3.5 checkpoint saving." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Same model family, but different bugs: batching/padding crash versus wrong video vision_position_ids." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "Unrelated: PyTorch missing import error versus LayoutLMv3 error-message clarity." + }, + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "Different models and code paths: BitNet packed-weight loading versus Perceiver interpolation failure." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Different platforms and bugs: Apple Silicon allocator TypeError versus Qwen3.5 flash-attention generation." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "Different concerns: save_pretrained shard size policy versus passing kwargs to cached_file." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Different failures: DeepSpeed ZeRO-3 load index error versus trainer.evaluate() after train()." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "Unrelated: backend packaging versus Python 3.14 load failure." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Both are config-related, but one is num_labels propagation and the other is strict config blocking a model load." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "Different loading issues: gguf_file/pretrained loading versus Blip2 dtype propagation." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both touch loading, but one is gguf_file support and the other is an offline Mistral regex/network call bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The only accepted soft pair, issue:43493 with issue:43994, is plausible based on shared SigLIP2/model-correctness framing, and the rest of the pairwise rejections are cautious rather than overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 20, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:29159", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:38175", + "issue:41720", + "issue:43295", + "issue:43504", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43643", + "issue:43653", + "issue:43688", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44493", + "issue:44514", + "issue:44561", + "issue:44568", + "issue:44610", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45005", + "issue:45290", + "issue:45356", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45823", + "issue:46002", + "issue:46050" + ], + "soft_pairs": [ + "issue:44514|issue:45290", + "issue:43295|issue:45356", + "issue:44466|issue:45005", + "issue:24643|issue:29127", + "issue:43819|issue:44811", + "issue:44936|issue:45823", + "issue:30064|issue:33666", + "issue:43653|issue:44361", + "issue:38175|issue:43295", + "issue:44361|issue:44442", + "issue:43653|issue:44568", + "issue:43577|issue:43697", + "issue:43643|issue:44561", + "issue:44843|issue:44991", + "issue:44464|issue:44743", + "issue:41720|issue:43906", + "issue:44493|issue:46050", + "issue:29159|issue:33357", + "issue:43653|issue:43927", + "issue:45491|issue:46002", + "issue:43531|issue:43742", + "issue:43550|issue:43927", + "issue:43688|issue:45440", + "issue:44464|issue:44977", + "issue:43550|issue:44361", + "issue:43577|issue:45588", + "issue:43504|issue:43550", + "issue:43504|issue:43720", + "issue:32090|issue:34567", + "issue:43504|issue:44610" + ], + "prepared_review_unit_hash": "2576aedff65917ba2862fe730f97315bee94c275d2ed92a8ffabc8f985e62408", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36847, + "estimated_input_tokens": 9212, + "estimated_eval_tokens": 18680 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No safe duplicate consolidation: the set is a heterogeneous mix of unrelated tokenizer, trainer, vision, generation, and MoE issues. None of the soft pairs look like the same concrete bug/change.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue is a reliable canonical target; the cluster spans many unrelated failure modes and model families.", + "canonical_pr_reason": null, + "best_issue_reason": "No clear global best issue for deduping this cluster, since the items do not describe one underlying problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44514", + "right": "issue:45290", + "accept": false, + "reason": "Both mention apply_chat_template crashes, but the triggers differ (batched padding vs assistant tool-call messages), so this is not the same bug." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer regressions, but one is about processor.tokenizer/image passthrough and the other about codec handling plus a misleading warning; different code paths." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": false, + "reason": "Both touch tied weights, but one is device-dependent lm_head serialization and the other is translation-model v5 weight tying; not enough to be the same defect." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Completely different bugs: DeepSpeed training weight shape error vs LayoutLMv3 box-validation messaging." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "Different subsystems and failures: DAC latent reconstruction mismatch vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer evaluate-after-train failure is unrelated to Gemma4 device-map forward device mismatch." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Image processor segmentation-map handling and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "Both are tokenizer issues, but one is BigBird special-token registration and the other is MLuke task-time AttributeError; different bugs." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "Unrelated: SigLIP2 zero probabilities versus tokenizer/processor regression in v4.57.5." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Both involve tokenizers, but the models and failure modes differ: MLuke AttributeError vs AutoTokenizer failing to load FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Similar theme of special tokens, but BigBird mask-token decode failure and mDeBERTa add_special_tokens BOS/EOS omission are different code paths and symptoms." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Different problems: BLIP2 dtype propagation vs RTDetrV2 output drift in v5." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both mention trust_remote_code, but one is missing fields in AutoConfig and the other is a v5 API removal breaking remote-code models; not the same issue." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Different tokenizer-loading failures: offline model_info call in _patch_mistral_regex vs est-roberta tokenizer loading regression." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both concern generation state, but one is chunked generation with compiled forward and the other is Qwen3.5 modular recurrent-state reset; not clearly the same bug." + }, + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Qwen3 auto device-map cudaErrorAssert is unrelated to an isolated reproduction issue with no matching failure described here." + }, + { + "left": "issue:44493", + "right": "issue:46050", + "accept": false, + "reason": "Unexpected position-id keys on load and sinq quantized save/load breakage are different loading problems." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency is unrelated to the MacOS bus error on CLIP." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "BigBird special-token decoding and DiaConfig losing custom token IDs are different token/config persistence bugs." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Both mention NaNs, but one is sliding-window attention on mixed-length batching and the other is classification-head NaNs after checkout/init; different causes." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and MobileLLM-125M load key error are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "torch.compile+SDPA failure in Bamba is unrelated to DiaConfig save/load token ID loss." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-related, but auxiliary-loss normalization and DeepSeekV3 remote-vs-native divergence are not the same concrete bug." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but compiled-forward chunking and flash-attention on Qwen3.5 are distinct failure modes." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "BEiT legacy-field loading and Bamba torch.compile/SDPA failure are unrelated." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Different loading issues: legacy preset field in BEiT vs packed-weight unpacking in BitNet accelerate loading." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer broadcast NoneType error and TrainerState token counter not updating are separate trainer bugs." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "BEiT model-preset loading and OmDet-Turbo processor output-size mismatch are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 21, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43122", + "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:43906", + "issue:43927", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44479", + "issue:44554", + "issue:44568", + "issue:44625", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45357", + "issue:45405", + "issue:45704", + "issue:45803", + "issue:45812", + "issue:45823", + "issue:45987", + "issue:46050" + ], + "soft_pairs": [ + "issue:43122|issue:43906", + "issue:44466|issue:46050", + "issue:28282|issue:35141", + "issue:43452|issue:44451", + "issue:32090|issue:33666", + "issue:43742|issue:44821", + "issue:45823|issue:46050", + "issue:41720|issue:44464", + "issue:33666|issue:36010", + "issue:43606|issue:43927", + "issue:43493|issue:43825", + "issue:43720|issue:43927", + "issue:44849|issue:45357", + "issue:43525|issue:43572", + "issue:43756|issue:44913", + "issue:44568|issue:45812", + "issue:43262|issue:43295", + "issue:28282|issue:33357", + "issue:43688|issue:43749", + "issue:28282|issue:32090", + "issue:43720|issue:44361", + "issue:33666|issue:36331", + "issue:43577|issue:44554", + "issue:39692|issue:43493", + "issue:43540|issue:44977", + "issue:44964|issue:45405", + "issue:44479|issue:44625", + "issue:45803|issue:45987", + "issue:43688|issue:45704" + ], + "prepared_review_unit_hash": "66c188c5f510a146f9d409984573a6fb2c14b940d53a0a259cb0f4361d99c001", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36560, + "estimated_input_tokens": 9140, + "estimated_eval_tokens": 18536 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous; the items share at most broad subsystems (tokenizers, configs, loading, multimodal models) rather than the same underlying defect. I would not merge any of the soft pairs as duplicates based on the available evidence.", + "confidence": 0.24, + "canonical_issue_reason": "Issue 45812 is the strongest single representative: it describes a concrete, reproducible regression with broad impact across all Granite models and has multiple inbound references.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45812 is the best issue candidate for triage because it is specific, high-impact, and more broadly applicable than the narrower model-specific reports in this set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "43906 is a reproduction of another issue, but the shared root cause is not explicit enough to treat it as the same bug as 43122." + }, + { + "left": "issue:44466", + "right": "issue:46050", + "accept": false, + "reason": "Both concern save/load behavior, but one is tied-weight serialization by device and the other is quantized-model reload failure." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "Unrelated failures: missing PyTorch import vs embedding resize causing post_init reinitialization." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "Both are loading problems, but they point to different mechanisms and no shared concrete code path is shown." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Generic distributed broadcast type error vs Qwen2-VL multi-GPU training issue; too broad to call the same bug." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "Different loading surfaces: MobileLLM key error vs AutoImageProcessor URL loading." + }, + { + "left": "issue:45823", + "right": "issue:46050", + "accept": false, + "reason": "Device-map forward mismatch and quantized save/load breakage are different failure modes." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "Qwen3 auto device-map assert and chunked-generation compiled-forward inconsistency are unrelated." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training behavior vs GenerationMixin import error are not the same defect." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch and DiaConfig save/load token-ID corruption are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs pipeline error-message wording regression do not share a concrete bug." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet accelerate-loading unpacking bug and MLukeTokenizer task AttributeError are distinct." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Both involve Qwen3.5, but one is hidden-states output behavior and the other is save_pretrained key serialization." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are pad-token-related, but they affect different config classes and attributes, so they are not clearly the same bug." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer dropping and GPTNeoX rotary_pct reload reset are different configuration/architecture issues." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but the model families and symptoms differ enough that they do not look like one bug." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate default and processor.tokenizer/image handling regression are different processor-path bugs." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "Missing PyTorch import and Mac bus error in CLIP are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Auxiliary-loss normalization and FSDP CPU RAM-efficient loading are unrelated training issues." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "ImportError on model class vs distributed GPU broadcast type error are unrelated." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "Packed-weight loading bug and tokenizer task AttributeError are different code paths." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Loading dtype propagation for Blip2 is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but doc-example mistakes and HF-vs-JAX implementation discrepancy are not the same underlying problem." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Both are Qwen-family video/vision reports, but the concrete failures differ and do not indicate a shared root cause." + }, + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "Model loading failure vs dependency-version bump are not duplicate symptoms." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression and num_labels propagation bug are separate Qwen3.5 issues." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare-except error swallowing in Fuyu and StaticCache return-type contract violation are unrelated." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Aux-loss normalization bug and T5 apex RMSNorm memory leak are different defects." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 22, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:29942", + "issue:30333", + "issue:33357", + "issue:33666", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "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:43927", + "issue:43994", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44423", + "issue:44466", + "issue:44488", + "issue:44493", + "issue:44521", + "issue:44589", + "issue:44625", + "issue:44734", + "issue:44792", + "issue:44843", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45290", + "issue:45405", + "issue:45520", + "issue:45588", + "issue:45701", + "issue:45759", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:43334|issue:43572", + "issue:43756|issue:45083", + "issue:44488|issue:44843", + "issue:43334|issue:45759", + "issue:45200|issue:45229", + "issue:43493|issue:43844", + "issue:43257|issue:43299", + "issue:43824|issue:44589", + "issue:39692|issue:43295", + "issue:43646|issue:44466", + "issue:43278|issue:43844", + "issue:43504|issue:43606", + "issue:45229|issue:45823", + "issue:43572|issue:44291", + "issue:44589|issue:45520", + "issue:33357|issue:33666", + "issue:43927|issue:44361", + "issue:43688|issue:45701", + "issue:43504|issue:43653", + "issue:44423|issue:44734", + "issue:43606|issue:44112", + "issue:43575|issue:45405", + "issue:44792|issue:45405", + "issue:44625|issue:45759", + "issue:45588|issue:46050", + "issue:43994|issue:44493", + "issue:29942|issue:30333", + "issue:44521|issue:45290" + ], + "prepared_review_unit_hash": "c3b767b2e5d655aa459ad9b584f2c5dc20821cf765821710d1a1aba35c3c7d8a", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35693, + "estimated_input_tokens": 8924, + "estimated_eval_tokens": 18104 + }, + "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. All suggested soft duplicate pairs are false positives; they share broad themes like configs, multimodal models, or serving, but not the same concrete underlying defect.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the items span many different models, APIs, and failure modes, so there is no single underlying bug to anchor the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a strong cluster representative; 44521 is the most active/open item, but it is still unrelated to most others and should not be treated as a canonical duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both are config/token-id regressions, but they affect different models and different missing fields, so they are not the same bug." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Both mention feature-extraction/ROPE behavior, but one is a model-specific RoPE-layer issue and the other is a helper-function bug in qwen3_omni_moe." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "One is a model load failure for cjvt/sleng-bert; the other is an offline-mode tokenizer patch bug. Different code paths." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both involve Qwen multimodal configs, but one is a missing pad token field and the other is AutoModelForCausalLM not unwrapping text_config." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "One is a required token-type default bug; the other is a multi-GPU CUDA OOM. Not the same issue." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 is the only commonality; one is implementation discrepancy, the other is a DeepSpeed/init gradient anomaly." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Both are Qwen3 MoE loading regressions, but they fail in different places and involve different fixes." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "An import error and a float8 storage lookup error are unrelated runtime failures." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "One is a doc-example/model-processor mismatch; the other is a custom-model regression in v4.57.5." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model init breakage and lm_head serialization differences are separate code paths." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype mismatch during eval is unrelated to gradient growth under ZeRO-3." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy-field loading for BEiT is unrelated to a CPU-offload device mismatch in Bark." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4 issues, but one is OOM and the other is a forward-time device mismatch." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx and an unexpected init_empty_weights argument are different compatibility bugs." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "A missing Float8 storage type and a flash_attn import KeyError on Python 3.13 are distinct failures." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizer/config errors with different models and symptoms." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization and tokenization changes are unrelated issues." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "BEiT legacy-field loading and BigBirdTokenizer special-token registration are separate bugs." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both are serve crashes, but they occur in different endpoints and code paths." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "A real device-mismatch bug and a stale CI test are not duplicates." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "TP OOM on a Qwen model and an unreleased dependency version bump are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus test failure and PEFT version pinning are unrelated." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "Both touch Qwen3.5 multimodal configs, but one is num_labels propagation and the other is config unwrapping in model construction." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "A flash_attention sink-less crash and a sinq save/load quantization bug are different problems." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and unexpected position-id keys are not the same defect." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures and MLflow reporting on failed jobs are unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "Both involve chat templates, but one is assistant-mask generation and the other is tool-call tokenization 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": 17, + "review_unit_index": 23, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29159", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:37428", + "issue:38175", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43688", + "issue:43701", + "issue:43824", + "issue:43844", + "issue:43873", + "issue:43957", + "issue:43975", + "issue:44315", + "issue:44464", + "issue:44466", + "issue:44554", + "issue:44610", + "issue:44849", + "issue:44898", + "issue:44964", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45412", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:44464|issue:45584", + "issue:43844|issue:44964", + "issue:44554|issue:45446", + "issue:28218|issue:34567", + "issue:43688|issue:43873", + "issue:43540|issue:45200", + "issue:45084|issue:45520", + "issue:29159|issue:32090", + "issue:15354|issue:38175", + "issue:43232|issue:44849", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:43873|issue:46050", + "issue:43278|issue:43701", + "issue:44315|issue:44849", + "issue:44554|issue:45356", + "issue:28218|issue:33357", + "issue:43295|issue:44610", + "issue:44898|issue:45412", + "issue:43572|issue:44987", + "issue:43572|issue:43957", + "issue:43493|issue:43701", + "issue:44466|issue:45127", + "issue:45200|issue:45325", + "issue:37428|issue:43957", + "issue:43550|issue:43844", + "issue:43295|issue:43450", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:43295|issue:43873", + "issue:38175|issue:45412" + ], + "prepared_review_unit_hash": "164fcb0b857254b1321b6afe9f88c6bcd5973cd8336565222aa06b9d9c4205b1", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36571, + "estimated_input_tokens": 9143, + "estimated_eval_tokens": 18542 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These candidates are mostly false-positive similarity matches across unrelated bugs. I would not merge any of the proposed soft edges.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue emerges here: the proposed pairs span different subsystems and failure modes, so there is no clear duplicate cluster to anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must be chosen as the most representative standalone report, issue:43873 is the strongest candidate because it is active, has inbound references, and describes a concrete reproducible problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Both are generation bugs, but one is about compiled forward output drift and the other about Whisper/align_special_tokens; different code paths." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient growth and a model-loading ImportError are unrelated failures." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "Attention correctness on MPS with mismatched head dims is not the same as a flex_attention import-version check." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer spacing behavior and TrainerState token-count tracking are different issues." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization in MoE models is unrelated to quantization/offloading behavior." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video input processing in Qwen3OmniMoe is not the same as Gemma4 text-only mm_token_type_ids handling." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "A compile-time template-node error and a Python 3.13 flash_attn import error are different root causes." + }, + { + "left": "issue:29159", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency is unrelated to a Trainer distributed broadcast NoneType error." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export failure and SIGLIP2 zero-probability behavior are distinct problems." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs syncing and hidden-states output in Qwen3.5 do not share the same bug." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Both mention Gemma4, but one is missing token-type defaults and the other is a device-map forward mismatch." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "BF16 dtype mismatches during inference are unrelated to Wav2Vec2 save/tokenization failures." + }, + { + "left": "issue:43873", + "right": "issue:46050", + "accept": false, + "reason": "Quantization/offloading misbehavior is not the same as a sinq save/load regression." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "A BF16-to-FP32 evaluation dtype change is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:44315", + "right": "issue:44849", + "accept": false, + "reason": "Liger Kernel not applying with model_init and a Qwen3.5 hidden_states bug are different issues." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness and Kimi-K2.5 tokenizer regression do not describe the same defect." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Added-token spacing and a MacOS bus error in CLIP are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression and OmDet-Turbo image-size mismatch are separate processor bugs." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver resolution handling and RT-DETR memory release are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig and a load failure for physical-intelligence/fast are different model/config issues." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Both involve loading, but one is a config attribute regression and the other is meta-device loading breakage." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 implementation discrepancy is unrelated to checkpoint resume key mismatch." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Tied-weight serialization inconsistency and LoRA merge collapse are different failure modes." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "A flash_attention_utils import error and meta-device model loading are not the same bug." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to DeepSpeed ZeRO-3 gradient growth." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "The former is about processor.tokenizer access with images; the latter is a batched video-shape bug." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both are missing pad_token_id errors, but they affect different config classes and model families." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "A model import error and a tokenizer detokenization regression are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor API regression and quantization/offloading behavior do not share a code path." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SIGLIP2 zero probabilities and RT-DETR memory leaks are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 24, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43335", + "issue:43425", + "issue:43450", + "issue:43493", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43696", + "issue:43819", + "issue:43824", + "issue:43825", + "issue:43827", + "issue:43856", + "issue:43901", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44360", + "issue:44442", + "issue:44448", + "issue:44514", + "issue:44521", + "issue:44561", + "issue:44610", + "issue:44743", + "issue:44792", + "issue:44857", + "issue:45083", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45381", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:42490|issue:43696", + "issue:42915|issue:43824", + "issue:37428|issue:43824", + "issue:44514|issue:44521", + "issue:38175|issue:43493", + "issue:43653|issue:44112", + "issue:44442|issue:45198", + "issue:43278|issue:43856", + "issue:43450|issue:43575", + "issue:43827|issue:43901", + "issue:42490|issue:43493", + "issue:43819|issue:45083", + "issue:43819|issue:44112", + "issue:43262|issue:43450", + "issue:45127|issue:45245", + "issue:44610|issue:44857", + "issue:44206|issue:45584", + "issue:37428|issue:43425", + "issue:44792|issue:45563", + "issue:43335|issue:43550", + "issue:43606|issue:45083", + "issue:45290|issue:45381", + "issue:44857|issue:45593", + "issue:44448|issue:44743", + "issue:45200|issue:45588", + "issue:43278|issue:43825", + "issue:37428|issue:44351", + "issue:44206|issue:45823", + "issue:44360|issue:44561", + "issue:43611|issue:43931", + "issue:43335|issue:43653", + "issue:43550|issue:44112" + ], + "prepared_review_unit_hash": "f35192beef8112b7404cf8e2e765568aedcbdcf3d9bdd43ee6f4afcb7d199036", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37227, + "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 heterogeneous: it mixes import/load regressions, chat-template/processor bugs, model-specific correctness issues, docs/deprecation problems, and CI/test flakes. I don\u2019t see one true canonical issue or PR for the whole set; the soft pairs are mostly near-theme matches rather than duplicates.", + "confidence": 0.44, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster. The items split into multiple unrelated bug families, so a canonical issue would be misleading.", + "canonical_pr_reason": null, + "best_issue_reason": "If forced to choose one issue as the least-bad representative, issue 44521 is the most active and broadly discussion-heavy, but it still only covers one processor/chat-template regression thread and not the full set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Import-warning-on-path-slash and CUDA OOM on GPT-oss-20b are unrelated failures." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Qwen2.5-VL import error are different models and code paths." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Different missing-symbol import errors in different modules; not the same bug." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is a batched padding=False crash and the other is zero assistant masks." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Same model family, but one is zero probabilities and the other is a broader HF-vs-JAX discrepancy." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "Tokenizer special-token registration bug vs GraniteSpeech CI device override failure." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "Different tokenizers/models and different failure modes." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Eval dtype regression and MoE training memory inefficiency are unrelated." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Video batching shape bug and tensor-parallel OOM are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both are docs around pipelines, but they describe different deprecations and behaviors." + }, + { + "left": "issue:42490", + "right": "issue:43493", + "accept": false, + "reason": "Local-path import warning and SigLIP2 output discrepancy are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC latent mismatch and qwen3_omni_moe feature-length behavior are different code paths." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC inference bug and GraniteSpeech CI flake are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate bug and batched video-shape bug are different processors." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA/tied-embedding collapse and category-count runtime limit are unrelated." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Processor image-size mismatch and AMP CUDA loss crash are unrelated." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "Unsupported center arg in feature extractor and Whisper empty-transcription failure are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Flash-attention import error and Torch 2.10 compatibility issue are not the same bug." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure and stale generate() warning are different issues." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "Sparse-layer config bug and Bamba torch.compile SDPA bug are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch and helper-length behavior are different problems." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Tool-call chat-template crash and video vision_position_ids bug are distinct." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "AMP CUDA crash in a loss and missing auxiliary losses are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output difference and recurrent-state reset in qwen3_5 are unrelated." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma4 mm_token_type_ids defaulting and flash_attention s_aux handling are different code paths." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype regression and pipeline error-message/docs issue are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "They are both import errors, but for different missing symbols and modules." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "Feature-extractor center-arg crash and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer discussion and removal of is_torch_fx_available are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "base_model_prefix loading breakage and Qwen3-VL shape mismatch are different failures." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "Sparse-layer creation bug and BigBirdTokenizer special-token bug are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba SDPA compile failure and GraniteSpeech CI flake are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 25, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:40444", + "issue:42490", + "issue:43335", + "issue:43388", + "issue:43412", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43701", + "issue:43720", + "issue:43819", + "issue:43854", + "issue:43927", + "issue:44112", + "issue:44292", + "issue:44448", + "issue:44462", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44779", + "issue:44855", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45310", + "issue:45372", + "issue:45478", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45698", + "issue:45803", + "issue:45859" + ], + "soft_pairs": [ + "issue:39692|issue:43526", + "issue:43388|issue:43526", + "issue:44855|issue:45083", + "issue:45310|issue:45478", + "issue:43335|issue:43504", + "issue:43819|issue:44493", + "issue:43335|issue:45083", + "issue:45588|issue:45859", + "issue:39692|issue:44493", + "issue:29942|issue:32090", + "issue:43335|issue:45072", + "issue:43720|issue:44112", + "issue:43335|issue:44112", + "issue:44448|issue:44779", + "issue:38175|issue:44493", + "issue:44292|issue:45520", + "issue:28218|issue:35141", + "issue:44977|issue:45229", + "issue:42490|issue:43854", + "issue:44561|issue:44779", + "issue:44462|issue:44561", + "issue:43606|issue:44857", + "issue:44857|issue:45072", + "issue:44448|issue:44977", + "issue:43701|issue:45083", + "issue:43550|issue:45083", + "issue:43927|issue:45698", + "issue:34689|issue:35141", + "issue:44568|issue:45491", + "issue:29127|issue:32090", + "issue:40444|issue:43526", + "issue:45372|issue:45588", + "issue:44977|issue:45563", + "issue:45198|issue:45803", + "issue:43412|issue:45588" + ], + "prepared_review_unit_hash": "3d3b6106d1050bcd8f1c670093c0f4e096613f98eef3b654d3d8c91a4eea21ec", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37839, + "estimated_input_tokens": 9460, + "estimated_eval_tokens": 19176 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most pairs are unrelated despite broad surface similarity. The only accepted duplicate is the Qwen3.5 MoE from_pretrained regression: issue:45310 and issue:45478.", + "confidence": 0.96, + "canonical_issue_reason": "issue:45310 is the canonical issue because it is the earlier report and the two issues have the same title and near-identical Qwen3.5 MoE from_pretrained failure description.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best representative of the only accepted duplicate pair, mainly because it is the older report with the clearest matching bug description.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "Different components and failures: SigLIP2 docs/model-processor mismatch vs BeitImageProcessorFast label reduction." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "Different bugs: gather_for_metrics dropping labels in the last batch vs BeitImageProcessorFast returning only one label." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Unrelated failures: DebertaV2 import/JIT parse error vs qwen3_omni_moe helper behavior." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same underlying regression: both describe the transformers>=5.4.0 Qwen3.5 Moe from_pretrained error." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "Different subsystems and symptoms: SwitchTransformers sparse-layer config bug vs BEiT semantic segmentation legacy-field loading bug." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "Different code paths: DAC.from_latents/STE mismatch vs unexpected position-id key warnings across models." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "Only broad model-family overlap; not the same defect." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Different failures in different layers: flash_attention s_aux handling vs Qwen3_5MoeTextRotaryEmbedding CPU-offload incompatibility." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "Docs/example errors are unrelated to the position-id key regression." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Different issues: Flash Attention 2 test failures vs Trainer/_gpu_broadcast_one NoneType TypeError." + }, + { + "left": "issue:43335", + "right": "issue:45072", + "accept": false, + "reason": "Different bugs: SwitchTransformers sparse-layer config vs dtype mismatches in bfloat16 inference." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Different CI/runtime problems: BitNet packed-weight loading vs GraniteSpeech stale device-override test." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "No shared underlying bug; config-layer issue and CI test failure are distinct." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Both are version-related output changes, but they affect different models and likely different code paths." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Different symptom and model: unexpected zero probabilities in SigLIP2 vs position-id key warnings." + }, + { + "left": "issue:44292", + "right": "issue:45520", + "accept": false, + "reason": "Different runtime errors: Qwen-3-8B-NVFP4 run failure vs flash_attn import KeyError on Python 3.13." + }, + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Tokenizer spacing after added token is unrelated to embedding reinitialization during post_init." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Different models and failures: flash-attention generation issue vs multi-GPU CUDA OOM." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Different loading problems: trailing-slash import warning vs GLM-4.7-Flash unit-test load failure." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Different regressions: removal of is_torch_fx_available impacting trust_remote_code vs Deepseek tokenizer output changes." + }, + { + "left": "issue:44462", + "right": "issue:44561", + "accept": false, + "reason": "AutoTokenizer ignoring tokenizer.json and the v5 trust_remote_code breakage are separate issues." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "Different failures: CPU offload device mismatch vs float16 AMP CUDA crash." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Different models and symptoms; dtype mismatch and AMP crash are not the same bug." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and code paths; both are generation issues but not the same concrete bug." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba is unrelated to qwen3_omni_moe helper output lengths." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both concern save/load semantics, but one loses custom token IDs and the other loads the wrong custom module; not the same defect." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Different model-loading and embedding-initialization bugs." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token insertion regression is unrelated to Gemma3 NaN embeddings with mixed-length batching." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "Error-message clarity for LayoutLMv3 is unrelated to Trainer broadcast TypeError." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Different model/data pipelines: Qwen2.5-VL multi-image iterable dataset failure vs BEiT label reduction bug." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma 4 processor import failure and flash_attention s_aux=None crash are distinct issues." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Generation malfunction and stale warning for num_return_sequences are unrelated." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save_pretrained/tokenization failure is unrelated to FuyuBatchFeature's bare except bug." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export failures and flash_attention sink-less-model crash are different code paths and fixes." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The duplicate-pair conclusion looks right, but the canonicalization rationale is a bit overstated: issue:45310 is older and has one inbound reference versus none for issue:45478, but it does not have more discussion activity (2 vs 4). Please keep the justification more conservative, e.g. \u201colder report with an identical title/near-identical bug description,\u201d rather than implying broader evidence than 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": 17, + "review_unit_index": 26, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:25251", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:37428", + "issue:39692", + "issue:42490", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43381", + "issue:43421", + "issue:43575", + "issue:43653", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44451", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44734", + "issue:44743", + "issue:44857", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45491", + "issue:45520", + "issue:45563", + "issue:45588", + "issue:45712", + "issue:45823" + ], + "soft_pairs": [ + "issue:45459|issue:45712", + "issue:36010|issue:37428", + "issue:29942|issue:35141", + "issue:42490|issue:43575", + "issue:43065|issue:45412", + "issue:45372|issue:45459", + "issue:44857|issue:45588", + "issue:45245|issue:45563", + "issue:44448|issue:44466", + "issue:43653|issue:44743", + "issue:45588|issue:45823", + "issue:43976|issue:45440", + "issue:43278|issue:43381", + "issue:43994|issue:45412", + "issue:25251|issue:32090", + "issue:44186|issue:45198", + "issue:43066|issue:44462", + "issue:44206|issue:44479", + "issue:42915|issue:42994", + "issue:44451|issue:45520", + "issue:44361|issue:45198", + "issue:44871|issue:44977", + "issue:43065|issue:43994", + "issue:44265|issue:45198", + "issue:43421|issue:45491", + "issue:44734|issue:45406", + "issue:29942|issue:30064", + "issue:33357|issue:39692" + ], + "prepared_review_unit_hash": "6e4ac5c30a890905b6dd559665bdea1918c4b4f38ffa68677047223b3f90ce9b", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36215, + "estimated_input_tokens": 9054, + "estimated_eval_tokens": 18364 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This is not a true duplicate cluster: the soft pairs span unrelated bugs across tokenizers, model loading, serving, flash-attention, and vision/audio regressions. None of the candidate pairs look like the same underlying fix; they should stay separate.", + "confidence": 0.39, + "canonical_issue_reason": "issue:44462 is the closest broad, user-facing regression here because it concerns core AutoTokenizer loading behavior and has external references, but it is only a loose representative rather than a true duplicate hub.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the most generally applicable and reusable report in an otherwise heterogeneous set; it has clearer cross-cutting impact than the highly model- or subsystem-specific bugs around it.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "Tokenizer error handling with protobuf missing is unrelated to leftover dummy PT classes and repo checks." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "GenerationMixin import failure and flash-attention utility import failure affect different code paths and fixes." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention test failures are not the same bug as output embedding reinitialization after resize." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Trailing-slash local model warning is unrelated to tensor-parallel OOM when loading a specific Qwen model." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and RT-DETR memory not being released are distinct issues." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor loading breaks on a missing dependency; the other issue is about hiding tokenizer decode errors when protobuf is absent." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "AMP/CUDA loss crash for LwDetr is unrelated to flash_attention.py failing on s_aux=None." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count runtime error and stale num_return_sequences warning are different behaviors with different fixes." + }, + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Both involve v4/v5 behavior changes, but one is generation output drift and the other is serialization of lm_head.weight; not the same bug." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and Qwen3.5 recurrent-state reset are unrelated tokenizer vs model-state problems." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Both touch Gemma-related code, but one is a flash-attention crash and the other is a device-mismatch forward bug." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility and DeepSeekV3 implementation divergence are separate problems." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "BF16-to-FP32 dtype drift in eval is unrelated to gradient checkpointing being disallowed in eval mode." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 wrong outputs and RT-DETR memory leaks are different model-specific regressions." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting and Trainer _gpu_broadcast_one NoneType errors are unrelated runtime issues." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2Tokenizer NER/padding crash and Wav2Vec2 save/tokenization failure do not share the same code path." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type and ignoring tokenizer.json are both tokenizer-related, but they are different concrete loading/serialization bugs." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Unsupported center arg in a feature extractor is unrelated to the Qwen video-input regression." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "FineGrainedFP8Config failure and quantized model saving failure are distinct quantization bugs." + }, + { + "left": "issue:44451", + "right": "issue:45520", + "accept": false, + "reason": "Model load failure for ScandiBERT and flash_attn import KeyError on Python 3.13 are not the same issue." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer attribute errors and Wav2Vec2 save/tokenization failures are separate tokenizer/model bugs." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "Gemma eos_token_id mismatch and Qwen3.5 flash-attention generation failure are unrelated." + }, + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Runtime special-token post-processing update and Gemma3 NaN embeddings are different tokenizer vs attention/numerics bugs." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "Serving KV-cache tensor indexing crash and Gemma4Processor missing _tokenizer are separate serve-time failures." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures and void segmentation map processing failure are unrelated subsystems." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error with a community CLIP model and SigLIP2 documentation example errors are different model/documentation problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 27, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43873", + "issue:43931", + "issue:44062", + "issue:44186", + "issue:44206", + "issue:44279", + "issue:44442", + "issue:44554", + "issue:44610", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45593", + "issue:45834", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:29127|issue:34567", + "issue:44610|issue:45412", + "issue:10000|issue:15354", + "issue:43756|issue:45440", + "issue:43873|issue:45229", + "issue:45372|issue:45406", + "issue:43723|issue:44554", + "issue:42490|issue:43873", + "issue:43278|issue:43575", + "issue:43653|issue:44442", + "issue:41720|issue:45229", + "issue:45103|issue:45372", + "issue:43761|issue:45859", + "issue:43526|issue:45834", + "issue:43381|issue:43701", + "issue:45440|issue:45593", + "issue:29942|issue:36010", + "issue:43278|issue:43329", + "issue:32090|issue:33357", + "issue:43334|issue:43531", + "issue:43526|issue:44186", + "issue:44977|issue:45245", + "issue:43824|issue:44279", + "issue:43526|issue:44857", + "issue:44442|issue:45072", + "issue:43262|issue:44206", + "issue:42490|issue:43381", + "issue:44062|issue:45907", + "issue:42915|issue:43931" + ], + "prepared_review_unit_hash": "6842325902c0c9dad78c2148ee37dd66b07bba91753fad7aea7ee48fa3505820", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36379, + "estimated_input_tokens": 9095, + "estimated_eval_tokens": 18446 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the issues span unrelated models, loaders, processors, training utilities, and runtime failures. None of the soft pairs look like the same underlying bug/change, so I would not merge any of them as duplicates.", + "confidence": 0.18, + "canonical_issue_reason": "No clear canonical duplicate exists; the cluster is too mixed. If a hub is required, issue 43873 is the broadest and most referenced loading/offload report.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 is the best cluster hub only because it is broad and relatively well-connected, not because the set is truly duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "Different subsystems: LayoutLMv3 error messaging vs Trainer token-count tracking." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor input-size mismatch and RT-DETR memory leak are unrelated failures." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel issue and torch.jit GeneratorExp export error are different bugs." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Different model-specific correctness issues in Smollm3 vs DeepSeekV3MoE." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Both involve GPU/memory concerns, but one is quantization offload and the other is multi-GPU OOM." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma 4 processor loading failures, but one is an import dependency issue and the other is a missing attribute." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer import/loading regression vs MPS attention correctness issue; no shared code path." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Trailing-slash import warning is unrelated to quantization/offloading behavior." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "Embedding dtype mismatch during eval and TP OOM on Qwen2-57B are different problems." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Both touch tokenizers, but they are different tokenizer bugs with different failure modes." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Different model families and root causes: cudaErrorAssert vs CUDA OOM." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "Auto-docstring annotation crash is unrelated to Gemma 4 processor import failure." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and Qwen3 MoE CPU-offload incompatibility are unrelated." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug and Kosmos2.5 OCR index error are different processor issues." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Gradient checkpointing in eval mode and resume-from-checkpoint key mismatch are distinct training bugs." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeekV3MoE divergence and D-FINE auxiliary-loss behavior are unrelated model issues." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention test failures and GenerationMixin import errors do not share a code path." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Embedding dtype regression and multimodal token counting bug are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast TypeError and MacOS bus error in CLIP loading are different runtime failures." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id load failure and Qwen3-MoE sliding_window issue are separate model bugs." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Different preprocessing stacks and errors: BeitImageProcessorFast vs LayoutLMv2Tokenizer." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation bug and category-cardinality RuntimeError are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure vs generic dependency issue; not the same bug." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Image processor label handling and LwDetr float16 AMP crash are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "Tokenizer loading failure and bfloat16 dtype mismatch are different issues." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio chat-template sampling-rate bug and LaserFeatureExtractor center-arg crash are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Trailing-slash local-model warning has no overlap with gradient checkpointing eval-mode behavior." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "AddedToken keyword collision and list_repo_files revision forwarding are unrelated API bugs." + }, + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Qwen3Moe FineGrainedFP8Config failure and Qwen3-VL weight-shape mismatch are different loading problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 28, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:41628", + "issue:42907", + "issue:43316", + "issue:43381", + "issue:43441", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43575", + "issue:43611", + "issue:43646", + "issue:43701", + "issue:43720", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44077", + "issue:44079", + "issue:44188", + "issue:44387", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44743", + "issue:44811", + "issue:44898", + "issue:44964", + "issue:44977", + "issue:45216", + "issue:45290", + "issue:45372", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45698", + "issue:45759", + "issue:45803" + ], + "soft_pairs": [ + "issue:43441|issue:45588", + "issue:43575|issue:43701", + "issue:43646|issue:44077", + "issue:43575|issue:44387", + "issue:44743|issue:44811", + "issue:44464|issue:45491", + "issue:29127|issue:35141", + "issue:44977|issue:45584", + "issue:33357|issue:38175", + "issue:44964|issue:45440", + "issue:44442|issue:45803", + "issue:43316|issue:43525", + "issue:44479|issue:45290", + "issue:43761|issue:44079", + "issue:28218|issue:29127", + "issue:44442|issue:44898", + "issue:42907|issue:45698", + "issue:33290|issue:34567", + "issue:34689|issue:43611", + "issue:43931|issue:45216", + "issue:43761|issue:44188", + "issue:43316|issue:45759", + "issue:43381|issue:43873", + "issue:43493|issue:43827", + "issue:43550|issue:44743", + "issue:43720|issue:44442", + "issue:41628|issue:45372" + ], + "prepared_review_unit_hash": "1c9d50eac5881b418575371baa6dcf46aa11c66e2dcb8a1f69f2e0855351ae55", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35298, + "estimated_input_tokens": 8825, + "estimated_eval_tokens": 17906 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is highly heterogeneous: most items are distinct bugs, regressions, or docs/import issues rather than duplicates. None of the soft-edge pairs looks like the same underlying change or bug. If a single issue must represent the set, the broad, highly active quantization/offloading report is the best fit.", + "confidence": 0.94, + "canonical_issue_reason": "Issue 43873 is the most active open report with repeated community references and a broad runtime/memory regression shape, making it the best representative candidate.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43873 has the strongest triage value here: open, broad symptom, and the most discussion/inbound references among the set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Different failure modes: model-specific FlashAttention regression vs sink-less flash_attention AttributeError." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "OOM during tensor-parallel model loading is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "Different regressions in custom model init vs patchtsmixer post_init handling." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is TP loading and the other is int4 quantization memory growth; not the same bug." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Cache/state reset in Qwen3.5 is unrelated to Whisper batch_decode skip_special_tokens handling." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward inconsistency and Gemma3 NaN embeddings are different model/pathologies." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error messaging and embedding reinitialization are unrelated issues." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 flash-attention generation bug is unrelated to Whisper empty-transcription/alignment failure." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "Both are vision-model problems, but bus error on CLIP/MacOS is not the same as SigLIP2 zero-probability outputs." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Different model families and different failure classes: model loading vs implementation divergence." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer load failure is unrelated to Fuyu's bare-except error swallowing in tensor conversion." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Both are config API mismatches, but they involve different models and different missing properties." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression and chat-template tool-call crash are separate code paths." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIPVision hidden_states regression is unrelated to torch.compile attention-kernel branching." + }, + { + "left": "issue:28218", + "right": "issue:29127", + "accept": false, + "reason": "Tokenizer spacing bug and LayoutLMv3 box-validation error are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer loading and Perceiver non-default-resolution classification failure are different bugs." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized models and loading the wrong custom module after save_pretrained are not the same issue." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "Adafactor/deepspeed OOM is unrelated to TrainerState token-count updates." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Both are loading regressions, but they affect different mechanisms and model types." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Weight-shape mismatch on load is different from incorrect checkpoint saving in save_pretrained." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "Same as above: these are distinct bugs in different execution paths." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Both involve config/model APIs, but one is a text-config discrepancy and the other is from_config unwrapping for multimodal models." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing in eval mode is unrelated to quantization offloading behavior." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation drift is unrelated to docs still referencing removed pipeline() APIs." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "torch.compile+SDPA failure is unrelated to cache recurrent-state resets." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight loading and tokenizer class loading are different code paths and failures." + }, + { + "left": "issue:41628", + "right": "issue:45372", + "accept": false, + "reason": "Both are import errors, but they are for different symbols and different dependency breakages." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 29, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:29127", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:41950", + "issue:42175", + "issue:43065", + "issue:43232", + "issue:43295", + "issue:43316", + "issue:43388", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43550", + "issue:43606", + "issue:43643", + "issue:43701", + "issue:43761", + "issue:43825", + "issue:43873", + "issue:44077", + "issue:44162", + "issue:44190", + "issue:44479", + "issue:44496", + "issue:44514", + "issue:44568", + "issue:44617", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44877", + "issue:44913", + "issue:45127", + "issue:45137", + "issue:45200", + "issue:45479", + "issue:45584", + "issue:45656" + ], + "soft_pairs": [ + "issue:44568|issue:45479", + "issue:43643|issue:44913", + "issue:32090|issue:33290", + "issue:34689|issue:36010", + "issue:43873|issue:44871", + "issue:44190|issue:44496", + "issue:44077|issue:44479", + "issue:44855|issue:45137", + "issue:29127|issue:33357", + "issue:43316|issue:44877", + "issue:43540|issue:44514", + "issue:33290|issue:45656", + "issue:33290|issue:34689", + "issue:42175|issue:43316", + "issue:43404|issue:43441", + "issue:43295|issue:43825", + "issue:44162|issue:44792", + "issue:25251|issue:28282", + "issue:41950|issue:43475", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:44871|issue:45584", + "issue:45127|issue:45200", + "issue:43232|issue:43388", + "issue:43295|issue:44871", + "issue:43761|issue:44479", + "issue:43065|issue:44617", + "issue:33290|issue:35141", + "issue:33290|issue:36331" + ], + "prepared_review_unit_hash": "504199353c6ad43c268b3009ef57e03f33c44e318c79bb8bf2c3aba5bf6d39e2", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 36095, + "estimated_input_tokens": 9024, + "estimated_eval_tokens": 18304 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All soft pairs look like false positives: the issues span unrelated model regressions, config/serialization bugs, training/runtime failures, and environment-specific errors. No PRs are present, and no single canonical duplicate emerges from this set.", + "confidence": 0.99, + "canonical_issue_reason": "No canonical issue: the cluster is heterogeneous, and the candidate pairs do not describe the same underlying bug.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a good global canonical representative because the items cover distinct root causes and code paths.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token behavior and sequence-classification zero-loss are different bugs." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "Missing fields from trust_remote_code config loading is unrelated to rotary_pct not persisting on reload." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "GPU broadcast NoneType failure is not the same as an AdaFactor/DeepSpeed OOM." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Model loading regression and GenerationMixin import error are separate code paths." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization/offloading behavior and eos_token_id config mismatch are distinct issues." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset script failure is unrelated to an unrecognized model/config error." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "Optional post_init policy and Qwen video-input regression are different problems." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 torch.jit parsing error is unrelated to the DeepSpeed deque underflow." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 box-handling clarity and MacOS CLIP bus error do not share a root cause." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "API discrepancy in Gemma3TextConfig is not the same as strict loading rejecting granite_speech." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Video-input processing failure and batched apply_chat_template padding crash are different processor bugs." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "OOM in DeepSpeed AdaFactor is not the same as optimizer.step being invoked twice." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "Training OOM and Llama 3.2 Vision model-loading regression are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:43316", + "accept": false, + "reason": "Packaging/backend dependency issue is unrelated to a config API discrepancy." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "Weight-tying bug in Mistral3 is not the same as a FlashAttention failure in Ministral-3." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor.tokenizer regression and pipeline error-message wording are different changes." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 breakage and janus test failure are separate model-specific issues." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting bug is unrelated to missing PyTorch import error." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification processor lookup and Sam3Video attribute error are different failures." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure is unrelated to resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch is a different bug from checkpoint key mismatch." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma-3 eos_token_id inconsistency does not match Whisper empty-transcription generation failure." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "LoRA merge with extended vocabulary and mm_token_type_ids defaults are different model issues." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Generation kwarg syncing and metric-gathering label truncation are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Custom processor/tokenizer regression is not the same as Gemma-3 eos_token_id inconsistency." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "CLIPVision hidden_states regression and Qwen video-input regression are separate paths." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d implementation choice is unrelated to a CUDA OOM." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "DeepSpeed optimizer memory issue is unrelated to embedding reinitialization after resize." + }, + { + "left": "issue:33290", + "right": "issue:36331", + "accept": false, + "reason": "OOM in DeepSpeed and CustomTrainer compute_loss kwarg incompatibility are different bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 30, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:41720", + "issue:42617", + "issue:43065", + "issue:43335", + "issue:43452", + "issue:43504", + "issue:43550", + "issue:43575", + "issue:43646", + "issue:43673", + "issue:43742", + "issue:43761", + "issue:43827", + "issue:43906", + "issue:43931", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44462", + "issue:44479", + "issue:44496", + "issue:44521", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44737", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45245", + "issue:45290", + "issue:45357", + "issue:45381", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698", + "issue:45803", + "issue:45907", + "issue:46050" + ], + "soft_pairs": [ + "issue:42617|issue:43575", + "issue:43452|issue:44496", + "issue:43575|issue:43742", + "issue:43504|issue:45698", + "issue:44871|issue:46050", + "issue:43646|issue:44913", + "issue:43673|issue:44743", + "issue:43761|issue:44242", + "issue:44077|issue:44534", + "issue:44479|issue:44734", + "issue:43065|issue:44610", + "issue:43931|issue:44060", + "issue:44617|issue:45584", + "issue:44792|issue:44977", + "issue:43906|issue:45290", + "issue:43827|issue:43994", + "issue:44190|issue:44964", + "issue:44534|issue:44913", + "issue:41720|issue:45245", + "issue:44855|issue:45588", + "issue:44792|issue:45600", + "issue:44737|issue:45803", + "issue:45127|issue:45357", + "issue:44521|issue:45381", + "issue:44462|issue:45907", + "issue:43335|issue:44855", + "issue:43550|issue:44190" + ], + "prepared_review_unit_hash": "8caca5ef79378596ce64f6cf6caebb643b203eb7e8df6a986fe74ef063f933e8", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 27, + "serialized_chars": 35905, + "estimated_input_tokens": 8977, + "estimated_eval_tokens": 18210 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers bugs and regressions. None of the soft pairs look like the same underlying issue; they share broad themes at most, not the same code path or fix.", + "confidence": 0.78, + "canonical_issue_reason": "No strong duplicate canon emerges from the evidence. If one issue must anchor the cluster, issue 45698 is the broadest load/save regression and the most reusable representative of the few adjacent serialization reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45698 is the best global representative because it is the most general and actionable load/save bug in the set, and could plausibly subsume nearby save_pretrained/from_pretrained regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "Both involve model execution/loading problems, but one is a script/runtime failure and the other is Qwen2.5 TP OOM; different failure modes and fixes." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both are loading errors, but gguf tokenizer/model handling is unrelated to a missing model_type in config.json." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "Different models and different bugs: TP memory exhaustion vs a KeyError while loading MobileLLM." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Both touch pretrained loading, but Beit legacy-field cleanup is not the same as wrong custom-module resolution after save/load." + }, + { + "left": "issue:44871", + "right": "issue:46050", + "accept": false, + "reason": "Both are serialization/config round-trip bugs, but eos_token_id mismatch is a different concrete defect than quantized-model save/load breakage." + }, + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Both are config-related regressions, but custom model initialization in v5 is not the same issue as GPTNeoX rotary_pct resetting on reload." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Cache-related, but these are different paths: missing GenerationMixin cache in chunked_prefill vs recurrent state reset in modular_qwen3_5." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Different subsystems and symptoms: CLIPVision hidden_states regression vs MoE load-balancing loss omission." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but patchtsmixer post_init validation and non-persistent buffer corruption are unrelated bugs." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "One is a multimodal video-input regression, the other a server KV-cache continuation indexing bug; not the same code path." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Different models and failures: dummy Conv2d in Sam3PixelDecoder vs processor/model input-size mismatch in OmDet-Turbo." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Same family name only; a shape mismatch while loading Qwen3-VL is not the same bug as a bad tied-weights warning in Qwen3-Next." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "CUDA OOM in Sam3Video and Whisper empty-transcription handling are unrelated." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Both affect generation, but Janus image-generation test failure and Qwen3.5 flash-attention generation issue are different code paths." + }, + { + "left": "issue:43906", + "right": "issue:45290", + "accept": false, + "reason": "A reproduction of an old issue and a tool-call chat-template crash are not the same underlying bug." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs still referencing pipeline() is separate from a runtime nonsensical-output bug in AutoModel/pipeline for SigLIP2." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Local dataset loading in a training script and loading Phi-4 multimodal are unrelated issues." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Non-persistent buffer corruption is a different regression than GPTNeoX rotary_pct not persisting on reload." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "Qwen3 auto device mapping assert and category-count overflow are unrelated." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Python 3.13 decorator parsing failure and flash_attention s_aux=None are entirely different defects." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "A test failure in Janus and stale auto_mappings entries for removed Sam3LiteText configs are not the same bug." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "XLNet CPU-device placement bug and bare except swallowing interrupts are unrelated." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge collapse with extended vocabulary is different from Qwen3.5 saving incorrect visual encoder keys." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal-chat regressions, but all-zero assistant masks and wrong vision_position_ids are different implementation errors." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer file selection and list_repo_files revision forwarding are distinct API bugs." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "A SwitchTransformers sparse-layer config bug is unrelated to the Python 3.13 IndentationError import failure." + }, + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Bamba torch.compile/SDPA failure and a local dataset script issue do not share a concrete code path." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Same broad multimodal area, but assistant mask generation and video position-id computation are different bugs; not mergeable into one fix." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Different layers: tokenizer resolution vs Hub file listing revision propagation." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 31, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:35141", + "issue:36246", + "issue:38175", + "issue:38617", + "issue:41628", + "issue:42490", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43643", + "issue:43644", + "issue:43650", + "issue:43976", + "issue:44077", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44464", + "issue:44466", + "issue:44496", + "issue:44561", + "issue:44683", + "issue:44734", + "issue:44855", + "issue:44877", + "issue:44913", + "issue:44933", + "issue:44938", + "issue:45003", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45362", + "issue:45375", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:45803" + ], + "soft_pairs": [ + "issue:43976|issue:44855", + "issue:44938|issue:45542", + "issue:43540|issue:44734", + "issue:43644|issue:44913", + "issue:44077|issue:44877", + "issue:35141|issue:42490", + "issue:43650|issue:44220", + "issue:44112|issue:45600", + "issue:43335|issue:44190", + "issue:44496|issue:45803", + "issue:43116|issue:44190", + "issue:45276|issue:45584", + "issue:45245|issue:45584", + "issue:43479|issue:45375", + "issue:36246|issue:41628", + "issue:43295|issue:45276", + "issue:44186|issue:44734", + "issue:44464|issue:45563", + "issue:38175|issue:43065", + "issue:44683|issue:45446", + "issue:43404|issue:45216", + "issue:44466|issue:44913", + "issue:44933|issue:45362", + "issue:44734|issue:45632", + "issue:44246|issue:45003", + "issue:44561|issue:45632", + "issue:36246|issue:38617", + "issue:45563|issue:45584", + "issue:43643|issue:44496", + "issue:42490|issue:45632" + ], + "prepared_review_unit_hash": "53a6e976ec4bf55070134cb8e8e751b6499f7d0e276945ef7fa4710205986a29", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36214, + "estimated_input_tokens": 9054, + "estimated_eval_tokens": 18364 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a bag of unrelated Transformers issues. None of the soft pairs look like the same underlying bug/change closely enough to merge, so I would not accept any of them as duplicates.", + "confidence": 0.82, + "canonical_issue_reason": "issue:35141 is the clearest root-cause report in the set: it names the resize_token_embeddings / post_init / tie_word_embedding=False interaction explicitly and describes the failure mechanism well.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:35141 is the best representative issue overall because it is specific, actionable, and captures the underlying model-weight bug more precisely than the more symptom-level reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Both are Python-version/import failures, but they affect different code paths and have different root causes." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "One is a Python 3.14 import/load issue; the other is a TensorFlow backend detection problem. Not the same bug." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Different subsystems and failures: Qwen3OmniMoe video processing vs serve KV-cache continuation indexing." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "One is about non-persistent buffers being serialized junk in v5; the other is GPTNeoX config reload losing rotary_pct." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Both touch config handling, but one is about optional post_init in patchtsmixer and the other about strict granite_speech config loading." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Resize-token-embedding / weight-tie bug is unrelated to the trailing-slash local-path import warning." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "No shared bug: generic placeholder issue vs a specific fbank feature extraction failure." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both are CI-related, but they are different regressions in different Granite/Sam3 code paths." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "Completely different topics: SwitchTransformers config construction vs image-classification local dataset loading." + }, + { + "left": "issue:44496", + "right": "issue:45803", + "accept": false, + "reason": "One is an unrecognized custom model/config issue; the other is a bare-except bug in Fuyu tensor conversion." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Different example scripts and different failures; no concrete shared code-path." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Resize-token-embeddings/output-embeddings bug is unrelated to Whisper empty-transcription handling." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category-limit runtime error is unrelated to Whisper generation after align_special_tokens." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Different config bugs in different models; one is default-init-on-None, the other is strict field dropping." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are ImportErrors, but for different exported symbols and likely different packaging issues." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Custom processor/tokenizer regression is not the same as the resize_token_embeddings/output_embeddings bug." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "Tokenizer padding/NER crash is unrelated to serve KV-cache continuation indexing." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward chunked generation mismatch is different from a stale warning in paged generate." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Different model-specific bugs with no shared failing mechanism." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "One is a runtime failure in compiled flex_attention; the other is a version-check/import guard issue. Not the same concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "Both mention weights, but one is a missing tie in Mistral3 and the other is incorrect save_pretrained serialization in Qwen3.5." + }, + { + "left": "issue:44466", + "right": "issue:44913", + "accept": false, + "reason": "Inconsistent lm_head serialization is unrelated to GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing image_utils import and Qwen3.5 chat crash are different issues." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "Serve tensor indexing crash and trust_remote_code cache-path collision are unrelated pathologies." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Import slowness and unsafe sys.modules access are related only loosely; not the same bug." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Removal of is_torch_fx_available affecting trust_remote_code is a different failure from local-model cache-path collisions." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Different missing imports in different modules; no evidence of a shared root cause." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "A stale warning in paged generate is not the same as Whisper failing on empty transcription." + }, + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Missing fields from trust_remote_code AutoConfig and unrecognized model_type are different config-loading bugs." + }, + { + "left": "issue:42490", + "right": "issue:45632", + "accept": false, + "reason": "Trailing-slash path handling and leaf-directory cache collisions are distinct path-resolution bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 32, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43335", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43673", + "issue:43688", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44220", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44351", + "issue:44368", + "issue:44496", + "issue:44779", + "issue:44933", + "issue:44964", + "issue:45020", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45278", + "issue:45335", + "issue:45357", + "issue:45405", + "issue:45584", + "issue:45593", + "issue:45600", + "issue:45759", + "issue:45812", + "issue:45823" + ], + "soft_pairs": [ + "issue:41950|issue:44016", + "issue:44112|issue:44964", + "issue:44964|issue:45600", + "issue:42907|issue:43441", + "issue:43854|issue:44964", + "issue:43673|issue:44336", + "issue:44016|issue:44220", + "issue:43388|issue:43688", + "issue:43295|issue:45335", + "issue:43531|issue:45600", + "issue:42175|issue:44279", + "issue:43526|issue:43901", + "issue:44496|issue:45042", + "issue:43299|issue:45216", + "issue:43335|issue:45593", + "issue:44075|issue:44368", + "issue:45335|issue:45584", + "issue:43381|issue:45593", + "issue:43299|issue:45357", + "issue:43901|issue:44496", + "issue:44496|issue:45759", + "issue:43976|issue:45405", + "issue:41950|issue:45020", + "issue:44242|issue:45200", + "issue:44351|issue:45278", + "issue:44016|issue:44062", + "issue:43479|issue:43525", + "issue:43824|issue:44933", + "issue:44779|issue:45812", + "issue:41950|issue:45823" + ], + "prepared_review_unit_hash": "08d833fd61695c844ed4b96bd05fcc8211861b63ef1069dcdf1faa1668ea0e69", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 36080, + "estimated_input_tokens": 9020, + "estimated_eval_tokens": 18296 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is a grab bag of distinct Transformers regressions and docs/test issues; there isn\u2019t a convincing duplicate pair among the soft edges. The clearest cluster anchor is the broad v5 remote-code/model-loading regression report.", + "confidence": 0.78, + "canonical_issue_reason": "issue:45020 is the broadest, most central report: it describes a recent-version regression breaking remote_code models, which plausibly covers several narrower load/import failures in this set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45020 is the strongest standalone triage target: broad impact, detailed reproduction, and a clear regression framing that makes it useful as the umbrella issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Video-classification processor selection bug vs a notebook syntax error; unrelated symptoms and code paths." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "CI stale device override test in GraniteSpeech vs Phi-4 multimodal model loading; different failures." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal vs auto-mappings referencing removed Sam3LiteText configs; distinct breakages." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Dequantized save failure for Ministral/Devstral vs FlashAttention load failure for Ministral-3; different bug surfaces." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "GLM-4.7-Flash unit-test load issue vs Phi-4 multimodal load issue; not the same model/path." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Generation cache missing in chunked prefill vs ANSI escape codes in loading_report; unrelated subsystems." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "Notebook syntax error vs audio feature extraction bug; different code paths and symptoms." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Metrics label handling vs MoE auxiliary loss normalization; both training-related but not the same defect." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Processor.tokenizer / image-input regression vs t5gemma embedding resize behavior; separate model-family bugs." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue vs removed-config references in auto_mappings; unrelated." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Torch extra omits TensorFlow backend dependency vs generic dependency issue; not the same concrete package problem." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "BeitImageProcessorFast reduce_labels bug vs docs mentioning return_all_scores; different layers and outcomes." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model/config loading error vs PIL image processors requiring torchvision; distinct import/load failures." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3 VL MoE model loading breakage vs incorrect save_pretrained checkpoint contents; load-time vs save-time bug." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "SwitchTransformersConfig sparse-layer creation bug vs D-FINE auxiliary-loss omission; unrelated model implementations." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "SGD optimizer args ignored vs Qwen3.5 tie_word_embeddings warning; different functionality." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation bug vs Whisper empty-transcription generation failure; separate behaviors." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient checkpointing eval-mode incompatibility vs D-FINE loss handling; not the same issue." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Qwen3.5/3.6 loading failure vs incorrect visual encoder keys on save; related model family but different concrete bugs." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs/API mismatch for return_all_scores vs unrecognized model config loading; unrelated." + }, + { + "left": "issue:44496", + "right": "issue:45759", + "accept": false, + "reason": "Unrecognized model/config loading error vs from_config not unwrapping text_config; different composite-model path." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python-version compatibility break vs bumped MIN_PEFT_VERSION; one is runtime support, the other a dependency floor." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Video pipeline processor lookup bug vs broad remote_code/model-loading regression; not the same underlying defect." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Router-logits load-balancing loss bug vs Gemma 4 mm_token_type_ids defaulting; distinct training/runtime logic." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "Missing HybridCache export vs broad import errors after upgrade; the latter is an umbrella symptom, not the same concrete bug." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error vs AddedToken keyword-argument TypeError; unrelated parsing/runtime issues." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Phi4Multimodal default config initialization vs Llama4Config missing pad_token_id attribute; different config bugs." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Missing Qwen2_5_VLForConditionalGeneration export vs missing image_utils import; both import errors but different symbols and causes." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Deepseek tokenizer regression vs Granite AutoTokenizer wrong IDs; tokenizer bugs, but model-specific and not the same change." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video pipeline processor lookup vs Gemma4 PLE device mismatch during forward; different model families and failure modes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 33, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43065", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43577", + "issue:43650", + "issue:43653", + "issue:43723", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44261", + "issue:44263", + "issue:44279", + "issue:44297", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44898", + "issue:44987", + "issue:45081", + "issue:45216", + "issue:45276", + "issue:45290", + "issue:45325", + "issue:45397", + "issue:45405", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712", + "issue:45834", + "issue:45907" + ], + "soft_pairs": [ + "issue:44683|issue:45542", + "issue:43577|issue:45216", + "issue:38175|issue:44617", + "issue:43299|issue:43854", + "issue:39692|issue:43901", + "issue:32090|issue:35141", + "issue:44279|issue:45405", + "issue:41950|issue:43650", + "issue:44462|issue:45081", + "issue:43295|issue:44779", + "issue:43976|issue:44987", + "issue:44297|issue:44462", + "issue:43976|issue:44279", + "issue:45081|issue:45907", + "issue:44521|issue:45325", + "issue:43441|issue:45834", + "issue:45600|issue:45712", + "issue:43450|issue:44279", + "issue:43065|issue:44898", + "issue:42994|issue:43317", + "issue:44623|issue:45397", + "issue:44261|issue:44263", + "issue:44623|issue:44749", + "issue:44466|issue:45276", + "issue:43650|issue:45290", + "issue:43441|issue:44683", + "issue:43653|issue:45593", + "issue:43723|issue:44162" + ], + "prepared_review_unit_hash": "6d13fd6ed1247d14279fab11f45e9d9969c50d83ba846cd87e4c56b0570dfb17", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35546, + "estimated_input_tokens": 8887, + "estimated_eval_tokens": 18030 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose collection of mostly unrelated transformer regressions and docs issues. The soft pairs are superficially similar in a few tokenizer/model-loading areas, but they do not look like the same underlying bug or change, so none should be merged as duplicates.", + "confidence": 0.41, + "canonical_issue_reason": "Issue 43723 is the broadest, most representative tokenizer-loading regression in the set; it best captures the shared v5 AutoTokenizer breakage theme without being overly narrow to one model or edge case.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43723 is the best global representative because it is self-contained, user-facing, and closest to the common loading/compatibility failures that recur across the tokenizer-related items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "Completely different failures: flex_attention compilation vs missing TensorFlow backend with tensorboard." + }, + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Different models and bugs: BLIP2 dtype propagation vs Qwen3.5 save_pretrained checkpoint serialization." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Unrelated problems: SIGLIP2 zero probabilities vs Sam3Video CUDA OOM." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Both are load failures, but for different model families and different root causes; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Both mention docs, but one is a multimodal SigLIP2 example with runtime errors while the other is a TextClassificationPipeline doc mismatch." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer GPU broadcast NoneType error is unrelated to resize_token_embeddings reinitializing output embeddings." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "A generic dependency problem is not the same as bumping MIN_PEFT_VERSION to an unreleased version." + }, + { + "left": "issue:41950", + "right": "issue:43650", + "accept": false, + "reason": "Video pipeline processor lookup and a generic placeholder issue title are unrelated." + }, + { + "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 failures." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Custom model code accessing processor.tokenizer and Deepseek tokenizer regressions are distinct issues." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Python version compatibility and a specific model loading failure are not the same problem." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Serialization mismatch in tokenizer_config.json is related to, but not the same as, ignoring tokenizer.json from the repo." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "Python support regression and dependency/version bump are unrelated." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex crash and list_repo_files not forwarding revision are unrelated APIs." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal, but assistant masks in chat templating and rope index scaling are different bugs." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "Ministral FlashAttention failure and Kosmos2.5 OCR index error are unrelated." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Removed auto_mappings references and leftover dummy classes are separate CI hygiene problems." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Batched video processor shape bug and a dependency issue are unrelated." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder and Perceiver interpolation failure are different model-specific issues." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized model saving failure and dequantized model offload loading failure are different quantization paths." + }, + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Missing processor save files and gemma-4 zero3 from_pretrained are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "A missing rms_norm_eps precision issue and a torch.split return-value issue are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Processor save_pretrained file omission and a large slowdown after upgrade are different symptoms and causes." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Serialization of lm_head.weight by device and resize_token_embeddings not updating gemma4 embeddings are related only broadly, not the same bug." + }, + { + "left": "issue:43650", + "right": "issue:45290", + "accept": false, + "reason": "Generic placeholder issue and chat-template crash on tool-call assistant messages are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "FlashAttention failure in one model and compiled flex_attention failure on newer torch are different attention bugs." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "BigBirdTokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer loading regression and ESM2 breakage are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 34, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:36246", + "issue:41628", + "issue:41950", + "issue:42491", + "issue:42757", + "issue:43122", + "issue:43262", + "issue:43299", + "issue:43352", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43650", + "issue:43673", + "issue:43761", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44188", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44291", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44351", + "issue:44361", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44521", + "issue:44589", + "issue:44617", + "issue:44671", + "issue:44779", + "issue:44987", + "issue:45250", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44016|issue:45823", + "issue:44361|issue:45593", + "issue:44671|issue:44779", + "issue:44987|issue:45542", + "issue:43901|issue:43994", + "issue:43122|issue:43650", + "issue:43784|issue:45542", + "issue:44297|issue:45397", + "issue:44016|issue:44291", + "issue:44188|issue:44336", + "issue:43673|issue:43761", + "issue:43262|issue:44521", + "issue:43450|issue:44617", + "issue:43525|issue:43881", + "issue:43525|issue:43643", + "issue:44336|issue:44373", + "issue:41628|issue:43976", + "issue:44589|issue:45362", + "issue:43901|issue:44246", + "issue:44295|issue:45397", + "issue:42491|issue:43299", + "issue:44242|issue:45593", + "issue:16998|issue:22355", + "issue:44246|issue:44496", + "issue:41950|issue:44220", + "issue:44336|issue:44485", + "issue:36246|issue:42757", + "issue:43352|issue:45250", + "issue:36246|issue:44351" + ], + "prepared_review_unit_hash": "1ab7d779159f3a79aa66d1ef163ae0fdcbd40066a3156ef62ffd11ce82cae804", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36013, + "estimated_input_tokens": 9004, + "estimated_eval_tokens": 18264 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are a heterogeneous mix of unrelated Transformers bugs, regressions, and docs issues; none of the soft pairs look like the same underlying fix target.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue emerges here: the reports span different models, APIs, and failure modes rather than one duplicate bug.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44521 is the best standalone anchor if one must be chosen: it is open, detailed, reproducible, and clearly scoped.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 device-mapping mismatch are unrelated problems." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "Different components and symptoms: tokenizer AttributeError vs D-FINE auxiliary-loss handling." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are model/tokenizer regressions, but they affect different models and code paths." + }, + { + "left": "issue:44987", + "right": "issue:45542", + "accept": false, + "reason": "Loading a physical-intelligence model and TensorFlow backend detection are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is not the same bug as incorrect SigLIP2 outputs." + }, + { + "left": "issue:43122", + "right": "issue:43650", + "accept": false, + "reason": "Tokenizer behavior regression and the unrelated placeholder issue title do not match." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Sentence-transformers import NameError and undefined tf backend are different failures." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save_pretrained metadata bug and Gemma4 zero3 loading failure are distinct." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights TypeError are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention-kernel branching bug and ANSI output in loading_report are different areas." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Cache missing in chunked_prefill and CLIP hidden_states regression are different code paths." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both mention chat templates, but one is audio sampling-rate defaulting and the other is assistant mask generation." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Video batch shape bug and Sam3Video CUDA OOM are not the same underlying issue." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Missing pad_token_id and GLM-4V loading failure are separate model/config issues." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "Both involve config loading, but the missing-field causes and affected paths differ." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI codes in loading_report and a wrong docstring are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "Import error for AutoImageProcessor and Python version incompatibility are different issues." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Float8 storage import failure and Qwen3.5 chat crash are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "A docs note about return_all_scores does not duplicate slow import timing." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "position_ids buffer access error and Gemma4 zero3 loading failure are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3/MoE regressions, but they are different models and failure scenarios." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Different loss-calculation bugs in different models and settings." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "model_max_length question and missing transformers.onnx module are unrelated." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow import and unrecognized model config are not the same bug." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video classification processor selection and fbank extraction are different preprocessing paths." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "Loading report ANSI output and GLM-5 RoPE implementation are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Two separate import errors from different packages and symbols." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Generic Flash Attention 2.0 discussion is not enough to match a specific model-support error." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Different missing exports: Qwen image processor vs HybridCache." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 35, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36246", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43408", + "issue:43475", + "issue:43526", + "issue:43540", + "issue:43596", + "issue:43653", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44496", + "issue:44561", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44871", + "issue:44877", + "issue:44964", + "issue:44987", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45656", + "issue:45701", + "issue:45759", + "issue:45987", + "issue:46082" + ], + "soft_pairs": [ + "issue:43824|issue:43976", + "issue:43673|issue:44561", + "issue:43976|issue:44964", + "issue:44242|issue:44857", + "issue:44246|issue:44871", + "issue:44295|issue:44749", + "issue:45362|issue:45375", + "issue:44162|issue:45200", + "issue:44877|issue:45375", + "issue:44779|issue:45292", + "issue:45987|issue:46082", + "issue:36246|issue:43596", + "issue:43901|issue:45003", + "issue:45292|issue:45584", + "issue:43232|issue:44336", + "issue:45561|issue:45563", + "issue:45292|issue:45701", + "issue:43526|issue:45003", + "issue:44987|issue:45459", + "issue:44496|issue:45003", + "issue:43065|issue:43408", + "issue:45375|issue:45759", + "issue:44995|issue:45200", + "issue:43257|issue:45137", + "issue:43262|issue:44246", + "issue:43475|issue:43540", + "issue:45397|issue:45656", + "issue:43653|issue:44162", + "issue:44995|issue:45588" + ], + "prepared_review_unit_hash": "7ca52e0347631b66d6a4ade66e0b71d4bef910baa6feb66f6f43333faa9d1847", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35898, + "estimated_input_tokens": 8975, + "estimated_eval_tokens": 18206 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous, with most pairs only loosely related by model-loading/runtime regressions. I found no soft edge that looks like the same underlying bug/change; all candidate merges should be rejected.", + "confidence": 0.59, + "canonical_issue_reason": "issue:43824 is the clearest, most concrete user-facing regression in the set: a specific ImportError with an explicit missing symbol and obvious repro/impact.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43824 is the best anchor for the cluster because it is a sharply defined API breakage, whereas most other issues here are broader, config-specific, or unrelated failures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "ImportError for a Qwen2.5 VL symbol is unrelated to a Python-version compatibility bug." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Chunked-prefill cache handling and removal of is_torch_fx_available affect different code paths." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Python support/version issue is not the same as loading a specific multimodal model." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "MoE load-balancing loss logic is unrelated to mixed-precision image loss crashes." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import-time slowness and Gemma eos_token_id config mismatch are different problems." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "position_ids buffer access error is unrelated to tokenizer/filtering slowdown." + }, + { + "left": "issue:45362", + "right": "issue:45375", + "accept": false, + "reason": "A chat crash for Qwen3.5-35B and a missing config field in Qwen3_5MoeVisionConfig are not the same bug." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 mm_token_type_ids defaulting are separate model-specific issues." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Strict config loading for granite_speech is unrelated to the missing deepstack_visual_indexes field." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer output regression and resize_token_embeddings/output_embeddings mismatch are different subsystems." + }, + { + "left": "issue:45987", + "right": "issue:46082", + "accept": false, + "reason": "Cache-length return type bug and LlamaConfig head_dim validation are unrelated." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2.5 VL import failure and DeepSpeed/BertModel index error do not share a concrete code path." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Documentation mismatch in a pipeline and unsafe sys.modules access are not the same issue." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize behavior and Whisper empty-transcription failure are distinct bugs." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs update after sync_gpus is unrelated to ANSI output formatting in loading_report." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file-race and stale paging warning in generate() are different behaviors." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize bug and tokenization changes across versions are not the same defect." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and sys.modules access are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model-loading failure and protobuf decode-error masking affect different layers." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model config and unsafe sys.modules lookup are separate failure modes." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is not the same as a sam3_video vs sam3_tracker config warning." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing config field in Qwen3_5MoeVisionConfig and from_config text_config unwrapping are related only broadly, not the same bug." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "Stale indexer cache crash and Gemma 4 text-only mm_token_type_ids default are different code paths." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed and empty-deque ZeRO3 error are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sample-rate default and import-time slowness are not the same issue." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Missing fpn_position_embeddings and Qwen3OmniMoe video input ValueError are separate SAM/video behaviors." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "Gemma-4 ZeRO3 loading and double optimizer.step under deepspeed are different training/runtime bugs." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token registration and ESM2 breakage are unrelated." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache and flash_attention s_aux=None crash do not share a concrete failing code path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 36, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:41628", + "issue:42371", + "issue:42886", + "issue:42994", + "issue:43232", + "issue:43452", + "issue:43475", + "issue:43482", + "issue:43525", + "issue:43643", + "issue:43646", + "issue:43673", + "issue:43827", + "issue:43931", + "issue:44038", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44623", + "issue:44661", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44933", + "issue:44977", + "issue:45003", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45229", + "issue:45230", + "issue:45310", + "issue:45335", + "issue:45356", + "issue:45381", + "issue:45397", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45600", + "issue:45656" + ], + "soft_pairs": [ + "issue:44466|issue:45335", + "issue:44368|issue:44977", + "issue:44368|issue:45563", + "issue:42886|issue:45229", + "issue:43673|issue:44734", + "issue:45003|issue:45561", + "issue:44060|issue:44077", + "issue:45137|issue:45600", + "issue:43931|issue:44368", + "issue:44933|issue:45459", + "issue:44297|issue:44623", + "issue:44869|issue:45356", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:44623|issue:45656", + "issue:44749|issue:45656", + "issue:43673|issue:43827", + "issue:44749|issue:45310", + "issue:43452|issue:45003", + "issue:45230|issue:45397", + "issue:42994|issue:43482", + "issue:43232|issue:43673", + "issue:44038|issue:44623", + "issue:42371|issue:45092", + "issue:28282|issue:30990", + "issue:43475|issue:45381", + "issue:43475|issue:43643", + "issue:41628|issue:44933", + "issue:45081|issue:45103", + "issue:43475|issue:44661", + "issue:42994|issue:43525" + ], + "prepared_review_unit_hash": "e7695af7cc30de3cd871c6853d241949318cfba00e9863db25eb5d3078b06dca", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36951, + "estimated_input_tokens": 9238, + "estimated_eval_tokens": 18732 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: mostly unrelated Transformers v5 regressions, tokenizer/model-loading bugs, and a few docs/test/import issues. None of the soft pairs look like the same concrete bug or change, so I would not merge any of them as duplicates.", + "confidence": 0.81, + "canonical_issue_reason": "issue:43646 is the broadest, most general v5 regression in the set ('custom model initialization') and is the closest thing to a cluster umbrella, even though the overall set is not a true duplicate cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the most representative issue because it describes a broad v5 breakage rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both touch tied weights, but one is an inconsistent serialization bug and the other is resize_token_embeddings not updating decoder.embed_tokens; different code paths." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "One is a tied-weights warning during LoRA fine-tuning; the other is a Qwen3.5 flash-attention generation failure. Same model family, different bugs." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Both mention warnings, but one is a tied-weights warning and the other is a stale num_return_sequences warning in paged generate(); not the same issue." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline tokenizer cache loading and multi-GPU CUDA OOM are unrelated failure modes." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Both involve generation/cache, but one is missing GenerationMixin cache in chunked_prefill and the other is a KV-cache continuation tensor indexing crash in serve; different defects." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "sys.modules access safety and a pytest-xdist file race are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "One is a tied-weights warning in Qwen3-Next; the other is an optional post_init restriction in patchtsmixer. No shared code bug." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "A DeepSpeed ZeRO3 deque underflow and stale auto_mappings references are unrelated." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Weight-shape mismatch while loading Qwen3-VL-30B is not the same bug as a tied-weights warning in Qwen3.5 fine-tuning." + }, + { + "left": "issue:44933", + "right": "issue:45459", + "accept": false, + "reason": "Both are import/decode related, but one is a nonexistent image_utils import and the other hides tokenizer protobuf decode errors; different root causes." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "Both concern save_pretrained output, but one is tokenizer_class metadata mismatch and the other is missing processor files; not the same concrete bug." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper timestamp decoding crash and Kimi-K2.5 tokenizer regression are unrelated." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer task AttributeError and a tokenizer slowdown after upgrade do not share the same failure mechanism." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "Both are broad model-loading breakages, but ESM2 is a model-specific failure, not the same custom initialization regression as issue 43646." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "processor.save_pretrained missing files and optimizer.step being called twice with deepspeed are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "A performance regression in filtering and a double optimizer-step bug are different code paths." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache handling and docs still referencing pipeline() are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer slowdown and Qwen3.5 MoE from_pretrained errors are unrelated." + }, + { + "left": "issue:43452", + "right": "issue:45003", + "accept": false, + "reason": "gguf_file loading breakage and unsafe sys.modules access are different bugs." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report and gemma-4 zero3 from_pretrained failure are not the same issue." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving and Qwen2.5-GGUF loading under v5 are related only at a very broad quantization level, but the concrete bugs differ." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "sync_gpus generation kwargs handling and missing cache in chunked_prefill are different generation bugs." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Qwen3-VL-Moe v5 bug and missing processor.save_pretrained files are unrelated." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "TF32 settings API guidance and InternVL2 meta-init incompatibility are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "Missing PyTorch ImportError and Sentence Transformers loading hang are different symptoms and code paths." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "SAM3 vision encoder missing attribute and Qwen2.5-VL video position-id bug are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "SAM3 encoder attribute failure and trust_remote_code missing-fields behavior are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but one is AutoImageProcessor not being importable and the other is a bad image_utils import reference; not the same concrete break." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Mistral regex patch crash and auto_docstring future-annotations crash are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "SAM3 output attribute error and add-new-model-like failing for TOKENIZER_MAPPING_NAMES are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Quantized model saving failure and Llama4Config missing pad_token_id are distinct bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 37, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:33290", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43704", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43901", + "issue:44038", + "issue:44060", + "issue:44188", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44373", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44792", + "issue:44964", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45137", + "issue:45200", + "issue:45310", + "issue:45356", + "issue:45375", + "issue:45478", + "issue:45561", + "issue:45600", + "issue:45712", + "issue:45812" + ], + "soft_pairs": [ + "issue:45375|issue:45478", + "issue:45310|issue:45375", + "issue:42673|issue:43704", + "issue:41628|issue:44351", + "issue:42831|issue:44222", + "issue:44222|issue:45310", + "issue:42994|issue:43824", + "issue:36010|issue:41628", + "issue:42175|issue:45712", + "issue:44038|issue:45310", + "issue:44496|issue:45561", + "issue:42222|issue:45200", + "issue:44964|issue:45137", + "issue:43377|issue:44242", + "issue:45561|issue:45600", + "issue:43901|issue:45561", + "issue:43232|issue:44792", + "issue:42898|issue:44568", + "issue:30990|issue:35141", + "issue:43232|issue:44188", + "issue:44623|issue:45310", + "issue:44188|issue:44373", + "issue:43784|issue:43824", + "issue:42898|issue:45812", + "issue:43278|issue:45137", + "issue:44734|issue:45103", + "issue:43874|issue:45092", + "issue:30333|issue:33290", + "issue:43723|issue:44568", + "issue:42898|issue:45356", + "issue:44060|issue:45125", + "issue:42898|issue:44779" + ], + "prepared_review_unit_hash": "eaace1783f0ebfb44b30297ca24c7e41d073fc8f500fd25f3789e25d5be02ede", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37305, + "estimated_input_tokens": 9327, + "estimated_eval_tokens": 18910 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Only one soft pair is a safe duplicate: the exact-title Qwen3ForCausalLM VRAM leak report (42673/43704). The Qwen3.5 MoE items are related but not the same concrete bug from the packet, so they should stay separate.", + "confidence": 0.92, + "canonical_issue_reason": "Issue 42673 is the best canonical issue: it is open and has an exact-title duplicate in 43704, making it the cleanest representative of the one confirmed issue pair.", + "canonical_pr_reason": null, + "best_issue_reason": "42673 is the strongest issue anchor because it is the open member of the only clearly duplicated pair and its title matches the duplicate exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same family (Qwen3.5 MoE), but the packet shows different concrete reports: missing deepstack_visual_indexes vs from_pretrained error." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Related model area, but not the same bug: from_pretrained failure vs missing config field silently dropped by @strict." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact same title and same VRAM-leak scenario for Qwen3ForCausalLM in multiple dataloader threads." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they involve different symbols and different failure modes." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Accuracy regression with FineGrainedFP8 is a different problem from FP8 save_pretrained failure." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen/MoE and FP8/from_pretrained behavior, but the concrete failures are different code paths." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Quantized model saving and missing Qwen2_5_VL import are unrelated." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Different missing-import symbols and different affected modules." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Dependency/backend packaging issue is unrelated to leftover dummy classes leaking into dir(transformers)." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Both involve Qwen models, but the reported failure modes and model variants differ." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrecognized model loading and pytest-xdist file race are unrelated issues." + }, + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "VitPose breakage and Gemma 4 token-type defaults are different model-specific bugs." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Phi-4 multimodal loading and DeepSpeed ZeRO3 deque pop error are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Missing padding-mask support in MIMI encoder is unrelated to MoE load-balancing loss logic." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "pytest-xdist capture-file race and auto_mappings CI breakage are separate test/maintenance issues." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Docs mismatch for TextClassificationPipeline is unrelated to xdist file races." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus and a janus image-generation test failure are different bugs." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer cleanup behavior change and missing BOS/EOS insertion are distinct tokenizer regressions." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Sentence Transformers loading stall and embedding reinitialization after resize are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation-state update logic and torch.compile attention-kernel divergence are different code paths." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Missing processor.save_pretrained files is unrelated to the Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "torch.compile attention branching and a wrong docstring for position_ids are unrelated." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Different import regressions involving different symbols and packages." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "General cleanup-spaces behavior change and Granite token-id regression are different tokenizer bugs." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Embedding dtype drift between train/eval is unrelated to the DeepSpeed deque error." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation crash in serve and auto_docstring annotation parsing crash are unrelated." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image-patch count method and InternVL2 meta-init incompatibility are different multimodal issues." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow reporting after training failure and Adafactor OOM are unrelated." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "Tokenizer loading failure in v5 and missing BOS/EOS behavior are different bugs." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Tokenizer cleanup behavior change and Kimi-K2.5 codec/regex regression are unrelated." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Incorrect tied-weights warning in Qwen3-Next and missing _tp_plan in Qwen3_5Moe are unrelated model bugs." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer cleanup behavior change and DeepSeek tokenizer regression are different failures." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Rejecting because the summary overstates the evidence for the Qwen3.5 MoE pair. In the packet, issue 45375 is about `Qwen3_5MoeVisionConfig missing deepstack_visual_indexes field`, while 45478 is the `Qwen3.5 Moe from_pretrained error`; they do not have the same title or clearly the same concrete bug from the provided text. The VRAM-leak pair 42673/43704 is grounded by matching titles, but the overall summary and canonical-selection rationale are not fully supported by the packet." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 38, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:41628", + "issue:42175", + "issue:42757", + "issue:42831", + "issue:42898", + "issue:43232", + "issue:43479", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43873", + "issue:43976", + "issue:44079", + "issue:44188", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44448", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44869", + "issue:44933", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45092", + "issue:45103", + "issue:45310", + "issue:45405", + "issue:45406", + "issue:45656", + "issue:45712", + "issue:45834", + "issue:46082" + ], + "soft_pairs": [ + "issue:45405|issue:45712", + "issue:44295|issue:45656", + "issue:43673|issue:44188", + "issue:42898|issue:44448", + "issue:44933|issue:45712", + "issue:42175|issue:44933", + "issue:44222|issue:44297", + "issue:43479|issue:44079", + "issue:44297|issue:45656", + "issue:43976|issue:44933", + "issue:44190|issue:46082", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:43479|issue:44869", + "issue:44206|issue:45103", + "issue:41628|issue:42757", + "issue:45071|issue:46082", + "issue:30333|issue:36331", + "issue:44297|issue:45310", + "issue:30333|issue:34689", + "issue:44222|issue:44484", + "issue:44263|issue:45092", + "issue:43232|issue:45834", + "issue:43723|issue:44977", + "issue:28282|issue:30333", + "issue:30333|issue:35141", + "issue:43761|issue:46082", + "issue:43873|issue:44945", + "issue:44373|issue:44485", + "issue:44295|issue:44623", + "issue:44483|issue:45406", + "issue:44263|issue:44360", + "issue:44514|issue:45103", + "issue:44261|issue:45092" + ], + "prepared_review_unit_hash": "e57cbef2806c02e84e7570cab6477736d765b8b9aa4f1a480537dd5eb5fa2ecd", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37651, + "estimated_input_tokens": 9413, + "estimated_eval_tokens": 19082 + }, + "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 import errors, trainer issues, generation regressions, tokenizer/config bugs, and model-specific fixes. No soft pair looks like the same underlying bug/change, so all soft edges are rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue exists here; the issues are heterogeneous and do not share one underlying failure mode, so any single item would be a poor representative.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a strong global representative because the cluster is incoherent rather than a single bug family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "PEFT version pinning and leftover dummy classes are unrelated maintenance concerns." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer access and deepspeed double optimizer-step are different code paths." + }, + { + "left": "issue:43673", + "right": "issue:44188", + "accept": false, + "reason": "Chunked-prefill cache handling and attention-kernel branching on torch.compile are distinct generation issues." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Tokenization cleanup behavior and Pegasus output differences are unrelated regressions." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "Missing image_utils import and dummy PT class cleanup do not describe the same bug." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "Backend packaging omission and a missing image_utils import are different import/package issues." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 MoE save_pretrained and tokenizer config mismatch affect different serialization paths." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Default config initialization and ModelOutput key assignment are unrelated object-initialization bugs." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer save metadata and deepspeed optimizer stepping are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version support and image_utils import failure are not the same issue." + }, + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Dataset loading script failure and LlamaConfig head_dim validation are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "FP8 MoE checkpoint saving and processor.save_pretrained missing files are different save-pretrained problems." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy and processor file saving are not the same underlying bug." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Config default initialization and Whisper timestamp decode crash are unrelated." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature extractor center-arg regression and auto_docstring annotation crash are different subsystems." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "AutoImageProcessor import failure and is_offline_mode import failure are separate missing-symbol regressions." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "PretrainedConfig type checking and LlamaConfig head_dim validation are different config issues." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow reporting after failed training and CustomTrainer.compute_loss signature mismatch are unrelated trainer bugs." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer class metadata mismatch and Qwen3.5 MoE from_pretrained error are different serialization/loading failures." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "Failed-training MLflow reporting and Llama 3.2 model-loading regression are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 MoE save_pretrained and max_shard_size default behavior are not the same problem." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split return handling and remote-code meta-init incompatibility are unrelated model-loading issues." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and long OCR index error are different generation/model paths." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "Tokenizer loading regression and flash-attention generation failure are not the same bug." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "PyTorch-not-found import error and MLflow failed-job reporting are unrelated." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "Training-job reporting and token-embedding resizing/post_init reinitialization are different issues." + }, + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "CLIPVisionModel hidden_states regression and LlamaConfig head_dim validation are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantization offloading and pipeline-parallelism output correctness are different problems." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring typo and GLM-5 RoPE implementation are not the same bug." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "Position_ids buffer read and processor save_pretrained file emission are unrelated." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "chat/completions request handling and Gemma4Processor missing _tokenizer are different serving issues." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "torch.split return values and DSA indexer missing ReLU are unrelated implementation bugs." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched chat template crash and auto_docstring annotation crash are different code paths." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA q_a_layernorm epsilon precision issue and meta-init checkpoint incompatibility are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 39, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:33357", + "issue:38175", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43232", + "issue:43479", + "issue:43576", + "issue:43644", + "issue:43646", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43824", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44464", + "issue:44568", + "issue:44704", + "issue:44829", + "issue:44871", + "issue:44913", + "issue:44945", + "issue:45092", + "issue:45278", + "issue:45290", + "issue:45310", + "issue:45357", + "issue:45593", + "issue:45753", + "issue:46002", + "issue:46050", + "issue:46082" + ], + "soft_pairs": [ + "issue:45092|issue:45357", + "issue:43479|issue:43644", + "issue:43723|issue:44871", + "issue:42907|issue:46050", + "issue:30990|issue:38175", + "issue:44829|issue:46002", + "issue:42831|issue:45310", + "issue:41628|issue:43824", + "issue:44263|issue:44373", + "issue:43479|issue:44913", + "issue:42831|issue:44038", + "issue:39401|issue:44568", + "issue:22355|issue:28282", + "issue:42757|issue:45278", + "issue:42886|issue:42994", + "issue:44945|issue:45753", + "issue:43576|issue:43784", + "issue:42886|issue:43066", + "issue:42371|issue:44263", + "issue:44464|issue:46082", + "issue:43232|issue:45593", + "issue:44117|issue:44704", + "issue:43646|issue:46002", + "issue:44295|issue:44297", + "issue:30990|issue:33357", + "issue:44704|issue:45290", + "issue:43756|issue:44060", + "issue:44261|issue:44373", + "issue:42907|issue:44945" + ], + "prepared_review_unit_hash": "f97c945d2c9f812f8160ede90c1bf824c38386ef6bd508add6ac800ab6ac45c3", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36079, + "estimated_input_tokens": 9020, + "estimated_eval_tokens": 18296 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: most items are unrelated regressions across imports, tokenizers, configs, generation, and quantization. None of the soft pairs look like the same concrete bug/change, so I reject all duplicate links.", + "confidence": 0.96, + "canonical_issue_reason": "No canonical issue is safe here; the items do not share one underlying bug, so any single issue would misrepresent the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "No global best issue is suitable for duplicate triage because the cluster spans several unrelated failure modes.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Different models and different failures: meta-init incompatibility vs incorrect visual encoder keys on save." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "One is config default initialization; the other is non-persistent buffer corruption, not the same bug." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Both are tokenizer-related, but one is a general v5 load issue and the other is an eos_token_id mismatch for Gemma-3." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Both involve quantized saving/loading, but they target different quantization flows and failure modes." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Different symptoms and models: a hang during loading versus zero probabilities in SigLIP2." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "Both mention training instability, but one is flash_attention_3 degeneration and the other is NaNs after checkout/init." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "Different problems: FP8 accuracy regression versus Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Both are missing-import errors, but for different exported symbols and likely different root causes." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "A torch.split logic question is unrelated to a docstring error about position_ids." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Config defaulting for multimodal vision/audio is unrelated to GPTNeoX rotary_pct reload behavior." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Different Qwen/FP8 issues; no shared concrete code path." + }, + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer defects, but they affect different tokenizers and different outputs." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "Different import/dependency problems: missing transformers.onnx module versus missing PyTorch." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "One is a specific huggingface_hub symbol import failure; the other is a broad upgrade-related import breakage." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Offline tokenizer cache loading and quantized model saving are unrelated code paths." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallel output corruption is not the same as a model-specific infinite loop on one image." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "A broken CLI command and a sentence-transformers import NameError are different failures." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading and tokenizer decoder type mismatch are distinct tokenizer issues." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings behavior is unrelated to the GlmMoeDsaIndexer torch.split issue." + }, + { + "left": "issue:44464", + "right": "issue:46082", + "accept": false, + "reason": "Chunked generation inconsistencies and LlamaConfig head_dim validation are separate problems." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs handling after sync_gpus is unrelated to D-FINE auxiliary loss behavior." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "Tokenizer mapping assumptions and AutoProcessor kwargs forwarding are different API bugs." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model init breakage is not the same as NaNs in classification heads after checkout/init." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "A position_ids buffer read issue is unrelated to tokenizer_class serialization mismatch." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Loading stalls and Mac bus errors are different model/runtime failures." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "Missing kwargs in cached_file is unrelated to chat template crashes on tool-call assistant messages." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "RoPE layer dropping and tied-weights warnings are different model bugs." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "Precision drift from missing rms_norm_eps is unrelated to a docstring mistake." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Quantized save/load failures do not match pipeline-parallel output corruption." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 40, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29127", + "issue:29159", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:41628", + "issue:42757", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43452", + "issue:43475", + "issue:43611", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43937", + "issue:43992", + "issue:44038", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44360", + "issue:44442", + "issue:44485", + "issue:44488", + "issue:44514", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44964", + "issue:44977", + "issue:45200", + "issue:45216", + "issue:45245", + "issue:45278", + "issue:45446", + "issue:45478", + "issue:45600", + "issue:46002" + ], + "soft_pairs": [ + "issue:43122|issue:44514", + "issue:41628|issue:45278", + "issue:43723|issue:44779", + "issue:43723|issue:44442", + "issue:42907|issue:43937", + "issue:43784|issue:45600", + "issue:43232|issue:45245", + "issue:43408|issue:43475", + "issue:44360|issue:44485", + "issue:43122|issue:44521", + "issue:44038|issue:44297", + "issue:44625|issue:44829", + "issue:43116|issue:45200", + "issue:42907|issue:44964", + "issue:44038|issue:44295", + "issue:29127|issue:30990", + "issue:43122|issue:44779", + "issue:36296|issue:43116", + "issue:42907|issue:43452", + "issue:44038|issue:44222", + "issue:43824|issue:44351", + "issue:39401|issue:44488", + "issue:45216|issue:45478", + "issue:39401|issue:44521", + "issue:42757|issue:44351", + "issue:43784|issue:45446", + "issue:43992|issue:44704", + "issue:43122|issue:44977", + "issue:22355|issue:28218", + "issue:22355|issue:29159", + "issue:43066|issue:44779", + "issue:43937|issue:44485", + "issue:43611|issue:46002" + ], + "prepared_review_unit_hash": "684a256c67ebafc0feb9eac87e68611bcaf51cf6e799bc9ca6033b8a5262ddeb", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37111, + "estimated_input_tokens": 9278, + "estimated_eval_tokens": 18812 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is mostly heterogeneous; the soft-similarity pairs are largely false positives across different bugs (tokenizers, imports, model loading, generation, training, and docs). No pair looks like the same concrete issue/change strongly enough to dedupe.", + "confidence": 0.84, + "canonical_issue_reason": "Issue 43122 is the broadest tokenizer-regression report and the closest thing to a cluster anchor, but it still only represents a subgroup rather than a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "43122 is the best representative issue because it captures the widest recurring theme in the candidates: tokenizer behavior regressions around v5.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Both touch tokenization/chat-template behavior, but one is a broad version-regression report and the other is a specific multimodal batching crash; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Both mention imports, but one is a single missing symbol and the other is a broad post-upgrade import breakage; too generic to merge." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "One is about tokenizer loading and the other about incorrect tokenization output; related area, but different concrete failures." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": false, + "reason": "Both are AutoTokenizer load problems, but they involve different tokenizer classes and likely different root causes." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Unrelated model-specific issues: saving dequantized models versus an invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Different failures in different code paths: a missing import in sentence-transformers integration versus stale auto-mapping references." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation-state handling and category-cardinality validation are unrelated bugs." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Same family name, but one is a model-type warning and the other is an attribute-missing crash; not the same issue." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "Completely different topics: DSA indexer activation versus GLM-5 RoPE implementation." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Both involve tokenization-related APIs, but one is a version-to-version tokenization change and the other is assistant mask generation for multimodal inputs." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe model support and tokenizer_config save metadata are different bugs." + }, + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "A config-propagation bug for Qwen3.5 is unrelated to flash-attention training degeneration." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Example-script multi-label output and Gemma 4 mm_token_type_ids defaults are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44964", + "accept": false, + "reason": "Different model families and different failure modes; no shared underlying bug." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "One is a Qwen3-VL-Moe support issue and the other is a position_ids buffer-read bug; unrelated." + }, + { + "left": "issue:29127", + "right": "issue:30990", + "accept": false, + "reason": "Unrelated: LayoutLMv3 error-message clarity versus sentence-transformers loading hang." + }, + { + "left": "issue:43122", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they target different models and concrete symptoms; not enough to treat as one bug." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training and multi-label classification output are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Saving dequantized models and gguf loading failures are different code paths and different problems." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Both mention MoE, but one is model loading and the other is FP8 save_pretrained behavior; not the same change." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols/packages and likely different missing exports." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Different tokenizer failures: offset_mapping correctness versus model loading." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both concern Qwen3.5 regressions, but one is broken saved checkpoints and the other is from_pretrained loading failure; distinct bugs." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Both are tokenizer-adjacent, but one is offset mapping and the other is assistant mask generation." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Import errors in different libraries and symbols; not a duplicate." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import regression and flex_attention version-check logic are unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight-loading and AutoProcessor kwarg forwarding are separate issues." + }, + { + "left": "issue:43122", + "right": "issue:44977", + "accept": false, + "reason": "Both involve tokenizer behavior changes in v5, but one is general tokenization drift and the other is Qwen3.5 flash-attention generation failure." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "No module import failure and tokenizer added-space behavior are unrelated." + }, + { + "left": "issue:22355", + "right": "issue:29159", + "accept": false, + "reason": "Import error for transformers.onnx and slow/fast tokenizer inconsistency are different bugs." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions, but one is decoder-type mismatch and the other is incorrect Deepseek tokenization; different code paths." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GLM-5 GenerationConfig validation and GLM-5 RoPE implementation are separate issues." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "Base_model_prefix loading regression and NaNs in classification heads are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 41, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:43064", + "issue:43116", + "issue:43381", + "issue:43441", + "issue:43450", + "issue:43493", + "issue:43673", + "issue:43825", + "issue:43827", + "issue:43874", + "issue:43937", + "issue:43976", + "issue:43986", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44297", + "issue:44380", + "issue:44466", + "issue:44625", + "issue:44779", + "issue:44936", + "issue:44945", + "issue:44977", + "issue:45072", + "issue:45081", + "issue:45083", + "issue:45278", + "issue:45357", + "issue:45405", + "issue:45446", + "issue:45478", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002", + "issue:46077" + ], + "soft_pairs": [ + "issue:42371|issue:43874", + "issue:43976|issue:45446", + "issue:42222|issue:43441", + "issue:42831|issue:44297", + "issue:43493|issue:45753", + "issue:44075|issue:44936", + "issue:45357|issue:45478", + "issue:44038|issue:45478", + "issue:43116|issue:43825", + "issue:45083|issue:45446", + "issue:43116|issue:43493", + "issue:43937|issue:45563", + "issue:38617|issue:45278", + "issue:43064|issue:43673", + "issue:44380|issue:46077", + "issue:33453|issue:39401", + "issue:44117|issue:45588", + "issue:44625|issue:46002", + "issue:43827|issue:45446", + "issue:39401|issue:44779", + "issue:22355|issue:29127", + "issue:43381|issue:44945", + "issue:43937|issue:44977", + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:43450|issue:43986", + "issue:44117|issue:45081", + "issue:38617|issue:41628", + "issue:42673|issue:45072" + ], + "prepared_review_unit_hash": "d811fcf59c70c5e612857f68e55187bb4822429785c237d9c917881e611fc0c1", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 29, + "serialized_chars": 35623, + "estimated_input_tokens": 8906, + "estimated_eval_tokens": 18068 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous transformer issues spanning import/export regressions, tokenizer/model bugs, trainer bugs, and attention/backend edge cases. Only the import-error pair (issue:38617 and issue:45278) looks plausibly like the same underlying regression; the rest are too different to merge as duplicates.", + "confidence": 0.67, + "canonical_issue_reason": "issue:45278 is the best umbrella representative because it describes the broad import-error regression after upgrading to v5.5, which can reasonably subsume the more specific import-symbol failure in issue:38617.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the strongest global issue candidate: it is broad, clearly regression-oriented, and closest to a central theme in the cluster. Still, the overall cluster is too mixed for a truly strong canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "Different problems: TF32 behavior settings vs a missing image-processor method causing a multimodal token-count failure." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Both are version-compatibility crashes, but the underlying causes and code paths differ (Python version support vs a bad PyTorch version check in flex_attention)." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "Unrelated model-specific breakages: VitPose imports vs Ministral FlashAttention failure." + }, + { + "left": "issue:42831", + "right": "issue:44297", + "accept": false, + "reason": "Accuracy degradation in FP8 is unrelated to tokenizer save/load metadata mismatch." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Different Qwen model bugs with different symptoms and likely different tokenizer/image-processing paths." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer-argument handling is unrelated to evaluate()-after-train() failure." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5, but one is save_pretrained key serialization and the other is from_pretrained loading failure; not clearly the same bug." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen variants and different failure modes; too weak to call the same underlying bug." + }, + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Example-script multi-label inference failure is unrelated to pipeline() docs/error-message fallout from v5 pipeline removals." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Separate subsystems: qwen3_omni_moe feature-length helper vs flex_attention dependency/version check." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Multi-label classification example failure is unrelated to SigLIP2 model discrepancy." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig validation failure and a stale paged-generate warning are different issues." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": true, + "reason": "Both are import regressions after the v5 upgrade; issue:45278 is a broad umbrella that plausibly covers the specific missing-symbol import error in issue:38617." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is unrelated to GenerationMixin cache missing during chunked prefill." + }, + { + "left": "issue:44380", + "right": "issue:46077", + "accept": false, + "reason": "Both involve attention behavior, but they are different model/back-end bugs and not the same concrete code-path failure." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Both are tokenizer-related, but one is a loading regression and the other is a specific offset_mapping problem for Qwen3; not enough to unify." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "Tokenizer mapping fallback behavior is unrelated to flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Config propagation for Qwen3.5 and NaNs in classification-head init are different bugs." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Docs still referencing removed pipeline() APIs is unrelated to a flex_attention import/version check." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer correctness bugs, but they affect different models and different failure modes (offset mapping vs incorrect tokenization output)." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "No module named transformers.onnx is unrelated to a layoutlmv3 error-message clarity issue." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient checkpointing in eval mode and pipeline-parallelism output corruption are unrelated training/runtime bugs." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "Different generation issues for different models/backends; not the same underlying bug." + }, + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "Serialization of tied weights depending on device is unrelated to NaNs in classification head initialization." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "PEFT minimum-version packaging problem is unrelated to the flex_attention PyTorch version-check bug." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Batched video shape handling and missing-t torchvision crash are different problems in the video stack." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping assumptions and a Mistral regex patch AttributeError are separate code paths." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they involve different missing exports and different causes; too broad to merge." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in multi-threaded Qwen3ForCausalLM use is unrelated to bfloat16 dtype mismatches in CI." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays appropriately conservative. The umbrella issue choice for issue:45278 is supported by the titles, and the soft-edge verdicts generally avoid overclaiming. One minor wording issue: the reason for issue:43493 vs issue:45753 refers to both as Qwen bugs, but 43493 is SigLIP2-related; however, the verdict itself remains conservative." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 42, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:43012", + "issue:43066", + "issue:43097", + "issue:43122", + "issue:43335", + "issue:43408", + "issue:43421", + "issue:43441", + "issue:43452", + "issue:43577", + "issue:43742", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43937", + "issue:44038", + "issue:44075", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44291", + "issue:44368", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45459", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45656" + ], + "soft_pairs": [ + "issue:44410|issue:45310", + "issue:44829|issue:45216", + "issue:44291|issue:45071", + "issue:39401|issue:43421", + "issue:44484|issue:45310", + "issue:43408|issue:43742", + "issue:42222|issue:45542", + "issue:43937|issue:44496", + "issue:42175|issue:42222", + "issue:44483|issue:45464", + "issue:44964|issue:45278", + "issue:42371|issue:44261", + "issue:44075|issue:45656", + "issue:43066|issue:43122", + "issue:43012|issue:43577", + "issue:43874|issue:44261", + "issue:44410|issue:45478", + "issue:44484|issue:45478", + "issue:38617|issue:44220", + "issue:44263|issue:44485", + "issue:43097|issue:44493", + "issue:41628|issue:45071", + "issue:43012|issue:43408", + "issue:42222|issue:45459", + "issue:45071|issue:45542", + "issue:43441|issue:44829", + "issue:42371|issue:42831", + "issue:42673|issue:44977", + "issue:42673|issue:43906", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43874|issue:44263", + "issue:43097|issue:43452", + "issue:43408|issue:44368" + ], + "prepared_review_unit_hash": "e888a5026589ed869387aaffcc17bd2c7838a0966d9aed36c21496fc4c3dc754", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 34, + "serialized_chars": 37772, + "estimated_input_tokens": 9443, + "estimated_eval_tokens": 19142 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of unrelated Transformers v5 regression reports: tokenizer behavior, model loading, config/API breakages, backend/package issues, and model-specific bugs. I did not find any soft edge that looks like a true duplicate; the best umbrella issue is the broad upgrade-regression report about many import errors after moving to 5.5.0.", + "confidence": 0.68, + "canonical_issue_reason": "issue:45278 is the broadest and most representative umbrella for this cluster\u2019s dominant theme: widespread breakages after upgrading to Transformers 5.x/5.5.0. It best captures the general regression pattern, even though the cluster is not a tight duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the best global issue candidate because it is the most generic, upgrade-focused report and can serve as the nearest cluster representative for the many v5-related breakage reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Same broad Qwen3/Qwen3.5 area, but one is a missing projection issue and the other is a from_pretrained load error; not the same bug." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "Different failure modes: one is flash-attention training degeneration, the other is incorrect save_pretrained checkpoint output." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights/_is_hf_initialized construction error is unrelated to PretrainedConfig type-checking behavior." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Tokenizer offset_mapping bug and runtime post-processor update bug are distinct tokenizer issues." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "max_shard_size behavior is unrelated to Qwen3.5 Moe from_pretrained loading failure." + }, + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "A sam3_video vs sam3_tracker warning is not the same as the MobileLLM config key error." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage and missing TensorFlow backend from a torch-only install are different problems." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Invalid GenerationConfig for GLM-5 and unknown-model loading for Olmo-Hybrid are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "Packaging/backend dependency issue is not the same as the VitPose model failure." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Both mention chat/completions, but one is a general API acceptance problem and the other is a specific streaming inference failure on Qwen3.5-0.8B." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Phi-4 multimodal loading failure is not the same as a broad import-error regression after upgrade." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 control settings and MLA q_a_layernorm epsilon precision are different backend/numerics issues." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "SGD arguments being ignored is not the same as DeepSpeed causing optimizer.step() to run twice." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both are tokenizer regressions, but one is decoder type selection and the other is changed tokenization output." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "A PyTorch warning during bfloat16 compilation is unrelated to Blip2 dtype remaining float32." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing get_number_of_image_patches is a different multimodal API bug than the RMS norm epsilon precision issue." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3.5-related failures: missing projections in qwen3next versus a from_pretrained load error." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "max_shard_size behavior is unrelated to the Qwen3.5 Moe load regression." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for layer_type_validation and a _torch_extract_fbank_features issue are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "torch.split return values in GlmMoeDsaIndexer and GLM-5 RoPE implementation are different code-path bugs." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "API removal around tie_embeddings_and_encoder_decoder is not the same as unexpected position-id keys appearing." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import failure and PretrainedConfig type checking are distinct regressions." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "Compilation warning and model-type mismatch warning are unrelated." + }, + { + "left": "issue:42222", + "right": "issue:45459", + "accept": false, + "reason": "VitPose model breakage is not the same as tokenizer errors being masked when protobuf is missing." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "PretrainedConfig type checking regression and missing-TensorFlow backend packaging issue do not share the same underlying bug." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both involve flash attention, but they affect different models and concrete failure modes; too broad to merge." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 API guidance and FineGrainedFP8 accuracy loss are separate numerical issues." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "A multi-thread VRAM leak and a Qwen3.5 flash-attention generation problem are different bugs." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "The isolated reproduction issue is not the same concrete bug as the VRAM leak in dataloader threads." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch and Qwen3-VL-Moe bug reports are related by family only, not the same defect." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug is unrelated to the PretrainedConfig type-checking regression." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Missing image-patch-count method and torch.split return-value handling are different implementation bugs." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Tie-embeddings API removal and gguf_file loading failures are not the same issue." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "Model-type warning and tie_word_embeddings warning are different configuration warnings with different causes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 43, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:38617", + "issue:42617", + "issue:42673", + "issue:42757", + "issue:42886", + "issue:42907", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43381", + "issue:43502", + "issue:43550", + "issue:43825", + "issue:43873", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44655", + "issue:44704", + "issue:44945", + "issue:44964", + "issue:44987", + "issue:45103", + "issue:45200", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45561", + "issue:45588", + "issue:45753", + "issue:45859", + "issue:46050" + ], + "soft_pairs": [ + "issue:44117|issue:44987", + "issue:43976|issue:44945", + "issue:43986|issue:44484", + "issue:38617|issue:42757", + "issue:43064|issue:44315", + "issue:44410|issue:45375", + "issue:43097|issue:46050", + "issue:44062|issue:44117", + "issue:38617|issue:44351", + "issue:43097|issue:45588", + "issue:42673|issue:45200", + "issue:44038|issue:44410", + "issue:44704|issue:45103", + "issue:43931|issue:44410", + "issue:43502|issue:43992", + "issue:44261|issue:44485", + "issue:44964|issue:45341", + "issue:45341|issue:45859", + "issue:43986|issue:44117", + "issue:43097|issue:43873", + "issue:43066|issue:43906", + "issue:42617|issue:45341", + "issue:43986|issue:45290", + "issue:43986|issue:45372", + "issue:45341|issue:45561", + "issue:43825|issue:44655", + "issue:43986|issue:45341", + "issue:43992|issue:44484", + "issue:45341|issue:45588", + "issue:43208|issue:43550", + "issue:43012|issue:43550", + "issue:42886|issue:43381", + "issue:43012|issue:44368", + "issue:42907|issue:45753", + "issue:42907|issue:44655" + ], + "prepared_review_unit_hash": "b84c391070b1dd4aeeca21800d7028e89c85f924440a35302e92bd3f2ab589b9", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 35, + "serialized_chars": 37419, + "estimated_input_tokens": 9355, + "estimated_eval_tokens": 18966 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very heterogeneous: it mostly contains unrelated Transformers issues that only share superficial similarity (imports, loading, quantization, model-family bugs). I found no soft-edge pair that looks like the same underlying bug/change.", + "confidence": 0.91, + "canonical_issue_reason": "Issue 43873 is the broadest, most system-level report in the set and has the most discussion/references, but the cluster overall is not a true duplicate group.", + "canonical_pr_reason": null, + "best_issue_reason": "43873 is the best single representative only because it is broad and high-signal; the other issues are mostly narrow, model-specific, or unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Both involve tokenizer/loading behavior, but one is a generic mapping None bug and the other is a model load failure for a specific repo; not the same code-path." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python-version compatibility and pipeline-parallel output corruption are unrelated bugs." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "AutoProcessor/torchvision crash is unrelated to max shard size behavior in save_pretrained." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols in different modules and do not look like one bug." + }, + { + "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." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Different Qwen3-family model/config bugs; one is missing projections, the other is a config field being dropped." + }, + { + "left": "issue:43097", + "right": "issue:46050", + "accept": false, + "reason": "A removed embedding-tie API and quantization save/load breakage are distinct changes." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken keyword conflict is unrelated to TOKENIZER_MAPPING_NAMES returning None." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Different import failures for different symbols; no evidence of the same underlying breakage." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Embedding-tie deprecation/removal is unrelated to a flash_attention None-handling crash." + }, + { + "left": "issue:42673", + "right": "issue:45200", + "accept": false, + "reason": "VRAM leakage in multithreaded dataloading is unrelated to mm_token_type_ids defaults." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Different model families and different failure modes; too broad to merge." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "Missing kwargs propagation in AutoProcessor is unrelated to the auto_docstring annotation crash." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Weight-shape mismatch on model load is not the same as missing projections in qwen3next." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "Network access despite local_files_only and missing embed_tokens.weight are separate loading bugs." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "Precision-warning from missing rms_norm_eps is unrelated to GLM-5 RoPE implementation." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "A model-loading regression and a testing_utils bug are unrelated." + }, + { + "left": "issue:45341", + "right": "issue:45859", + "accept": false, + "reason": "Testing_utils bug and CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding are different code paths." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "AutoProcessor/torchvision loading crash is unrelated to tokenizer mapping None handling." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Embedding-tie API removal and quantization/offloading problems are not the same bug." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type and an isolated reproduction of another issue do not match as the same defect." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel.py runtime failure and a small testing_utils bug are unrelated." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Video-model AutoProcessor crash without torchvision is unrelated to apply_chat_template tool-call handling." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Missing torchvision and missing ReasoningEffort are different dependency/import problems." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "A minor testing_utils issue and an xdist race condition are different bugs." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline translation messaging and save_pretrained for Pipeline objects are unrelated." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "AutoProcessor loading crash and a testing_utils bug are not the same underlying issue." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing embed_tokens.weight during model load is unrelated to the 50GB shard-size question." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing_utils bug and flash_attention s_aux=None crash are different subsystems and failures." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers and Bamba torch.compile/SDPA failure are separate model-specific problems." + }, + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "A bfloat16 precision warning is not the same as a torch.compile SDPA failure." + }, + { + "left": "issue:42886", + "right": "issue:43381", + "accept": false, + "reason": "Offline cache loading failure and gradient checkpointing in eval mode are unrelated." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "The bfloat16 warning and tie_word_embeddings warning are different warnings with different causes." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and Qwen3_5 infinite-loop on a specific image are unrelated." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Saving dequantized models and saving Pipeline objects are different save_pretrained limitations." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 44, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:36010", + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42898", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43208", + "issue:43299", + "issue:43352", + "issue:43475", + "issue:43502", + "issue:43525", + "issue:43526", + "issue:43618", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43867", + "issue:43881", + "issue:43901", + "issue:43906", + "issue:43937", + "issue:44038", + "issue:44220", + "issue:44222", + "issue:44230", + "issue:44242", + "issue:44263", + "issue:44380", + "issue:44483", + "issue:44485", + "issue:44514", + "issue:44625", + "issue:44655", + "issue:44683", + "issue:45216", + "issue:45276", + "issue:45290", + "issue:45381", + "issue:45440", + "issue:45478", + "issue:45753", + "issue:46077", + "issue:46082" + ], + "soft_pairs": [ + "issue:44483|issue:44514", + "issue:44222|issue:45478", + "issue:42490|issue:43012", + "issue:43208|issue:43526", + "issue:43012|issue:44683", + "issue:42757|issue:43824", + "issue:44038|issue:44230", + "issue:38617|issue:43502", + "issue:44483|issue:45290", + "issue:43618|issue:43761", + "issue:43064|issue:44380", + "issue:43299|issue:43867", + "issue:44483|issue:45381", + "issue:43901|issue:44655", + "issue:36683|issue:43475", + "issue:42994|issue:44655", + "issue:45276|issue:46077", + "issue:43352|issue:43937", + "issue:43867|issue:45216", + "issue:36010|issue:42757", + "issue:42898|issue:43066", + "issue:44220|issue:44655", + "issue:43756|issue:44485", + "issue:44625|issue:46077", + "issue:46077|issue:46082", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:44263|issue:45440", + "issue:43906|issue:45753", + "issue:36683|issue:44242", + "issue:43299|issue:45753", + "issue:36683|issue:43881", + "issue:43901|issue:46077" + ], + "prepared_review_unit_hash": "49d2e48c5262daf1811b506f3e1d66203ee4c339d6cd369052b59afc8af58391", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37166, + "estimated_input_tokens": 9292, + "estimated_eval_tokens": 18840 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a broad mix of unrelated Transformers bugs and regressions (imports, model config attrs, chat templating, quantization/saving, MoE, CLIP, Gemma, Qwen, etc.). None of the proposed soft pairs look like the same underlying bug/change, so they should remain separate.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Both involve chat-related failures, but one is /v1/chat/completions request handling and the other is batched apply_chat_template with padding=False; different code paths and bugs." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "Both mention MoE/FP8, but one is save_pretrained failure and the other is from_pretrained/load error; not the same concrete defect." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "One is a local path import warning, the other is a PyTorch float32 precision warning during bfloat16 compilation; unrelated." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "Completely different subsystems: xLSTM training bugs versus BeitImageProcessorFast label reduction." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "Both are compilation-related, but one is a warning about bfloat16 precision and the other is a hard flex_attention failure on torch>=2.9; different issues." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "Both are import errors, but for different symbols and different dependency breakages." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Both touch Qwen3-VL/MoE/fp8, but one is a general v5 loading bug and the other is FP8 inference support; not the same bug." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Different failures: missing configuration_utils import versus local_files_only still triggering network calls." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Both are chat API/template problems, but one is request acceptance and the other is assistant tool-call serialization; not mergeable as one bug." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Both are CLIP regressions, but one loses attentions while the other returns hidden_states=None; distinct outputs and code paths." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "Trainer/FSDP/PEFT optimizer-state corruption is unrelated to GPT2 attention scaling being ignored in SDPA/FlashAttention." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-MoE loading failure and a sorted-state_dict load error are different load-time bugs." + }, + { + "left": "issue:44483", + "right": "issue:45381", + "accept": false, + "reason": "Different model/API layers: chat/completions request rejection versus Qwen2.5-VL video vision_position_ids bug." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to saving Pipeline objects with save_pretrained." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Missing Gemma3Config.vocab_size and missing Sam3VisionEncoderOutput.fpn_position_embeddings are unrelated attribute bugs." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Both involve saving, but quantized model saving and Pipeline.save_pretrained are different failure modes." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Audio feature extraction bug versus pipeline serialization bug; no shared underlying defect." + }, + { + "left": "issue:45276", + "right": "issue:46077", + "accept": false, + "reason": "Gemma4 resize_token_embeddings propagation bug and Gemma4 bidirectional-attention masking bug affect different code paths." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Nemotron FlashAttention2 support error and GLM-5 invalid GenerationConfig are unrelated model-specific issues." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Different load/save regressions: a sorted state_dict load error versus incorrect Qwen3.5 checkpoint saving." + }, + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different APIs and different dependency symbols." + }, + { + "left": "issue:42898", + "right": "issue:43066", + "accept": false, + "reason": "clean_up_tokenization_spaces behavior change and wrong tokenizer decoder type are separate tokenizer regressions." + }, + { + "left": "issue:44220", + "right": "issue:44655", + "accept": false, + "reason": "Audio feature extraction issue does not match pipeline save_pretrained failure." + }, + { + "left": "issue:43756", + "right": "issue:44485", + "accept": false, + "reason": "Both reference RoPE, but one is Smollm3 layer drop and the other is GLM-5 RoPE implementation; not the same bug." + }, + { + "left": "issue:44625", + "right": "issue:46077", + "accept": false, + "reason": "num_labels propagation and Gemma4 attention masking are unrelated." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Gemma4 causal-mask bug and LlamaConfig head_dim validation are different config/attention issues." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Both are missing config attributes, but they concern different models and different fields." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP attentions regression and Qwen3.5 checkpoint save corruption are unrelated." + }, + { + "left": "issue:44263", + "right": "issue:45440", + "accept": false, + "reason": "Different MoE implementations and different symptoms: torch.split indexing issue versus DeepseekV3MoE divergence." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "An isolated reproduction of an earlier issue and a Qwen3_5 infinite loop on a specific image are not the same bug." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Missing Gemma3Config.vocab_size is unrelated to load balancing loss not being added when output_router_logits=False." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL-MoE loading failure and Qwen3_5 image infinite loop are different defects." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Different models and failures: Gemma3Config missing field versus glm-4v-9b loading failure." + }, + { + "left": "issue:43901", + "right": "issue:46077", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to Gemma4 attention-mask behavior." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 45, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42490", + "issue:42548", + "issue:42890", + "issue:43064", + "issue:43097", + "issue:43352", + "issue:43441", + "issue:43502", + "issue:43575", + "issue:43618", + "issue:43867", + "issue:43901", + "issue:43976", + "issue:43992", + "issue:44062", + "issue:44075", + "issue:44112", + "issue:44117", + "issue:44222", + "issue:44246", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44380", + "issue:44484", + "issue:44492", + "issue:44655", + "issue:44855", + "issue:44857", + "issue:44938", + "issue:44964", + "issue:44977", + "issue:45125", + "issue:45310", + "issue:45341", + "issue:45357", + "issue:45375", + "issue:45440", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45588", + "issue:45600" + ], + "soft_pairs": [ + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:43441|issue:44380", + "issue:43352|issue:44380", + "issue:44380|issue:45479", + "issue:44355|issue:44855", + "issue:43867|issue:45375", + "issue:43352|issue:45478", + "issue:41669|issue:44246", + "issue:43618|issue:44380", + "issue:36683|issue:44117", + "issue:42890|issue:45561", + "issue:43064|issue:44492", + "issue:43097|issue:43352", + "issue:43867|issue:45357", + "issue:43976|issue:44938", + "issue:43992|issue:45478", + "issue:43064|issue:44655", + "issue:36296|issue:43575", + "issue:42490|issue:44075", + "issue:44360|issue:45440", + "issue:28282|issue:33453", + "issue:43867|issue:44484", + "issue:43618|issue:44857", + "issue:43618|issue:44977", + "issue:43618|issue:45588", + "issue:44655|issue:44938", + "issue:42890|issue:44964", + "issue:43901|issue:44938", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:43502|issue:44062", + "issue:42890|issue:45341", + "issue:44222|issue:45125", + "issue:42548|issue:44351" + ], + "prepared_review_unit_hash": "07ae4759806a643e45420961bf85253691081511d2bc3fee7c4d07f0e6c4c7cd", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 37754, + "estimated_input_tokens": 9439, + "estimated_eval_tokens": 19134 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is very noisy and spans several unrelated themes: import/export regressions, model loading failures, FlashAttention/backend issues, tensor-parallel/training bugs, and flaky tests. I did not find any soft pair that is clearly the same underlying bug/change, so all soft edges should be rejected.", + "confidence": 0.94, + "canonical_issue_reason": "issue:42548 is the clearest representative of the import/export regression thread, which is one of the few repeated themes in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42548 is the best global issue anchor here because it is a concrete, user-facing API break and fits the broad import/load subset better than the other candidates.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "Both are runtime/load problems, but one is a FlashAttention 2 support error and the other is a Python-version load failure; different bugs." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different models and failures: missing embed_tokens weight vs Qwen3.5 MoE from_pretrained error." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both mention attention backends, but one is a model-specific FlashAttention crash and the other is GPT-2 attention scaling being ignored." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Same broad attention area, but the concrete bug is different: unsupported FlashAttention vs ignored scaling config." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention-backend regression vs sequence-classification zero-loss bug; unrelated code paths." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Both fail at import time, but one is about compiled Python files and the other is a torch.jit/script parsing issue on Python 3.13." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Model load error from sorted state_dict vs a missing Qwen3.5 vision config field; not the same issue." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "FlashAttention support error vs Qwen3.5 MoE from_pretrained regression; different models and symptoms." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": false, + "reason": "Both concern import slowness, but one is a specific import-* cleanup performance issue and the other is only a generic symptom report." + }, + { + "left": "issue:43618", + "right": "issue:44380", + "accept": false, + "reason": "CLIPOutput attentions assignment regression vs GPT-2 attention scaling being ignored; not the same defect." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Gemma3Config missing vocab_size and TOKENIZER_MAPPING_NAMES returning None are different loading/metadata bugs." + }, + { + "left": "issue:42890", + "right": "issue:45561", + "accept": false, + "reason": "Both are test/CI related, but one is missing set_seed in a model integration test and the other is a xdist file race." + }, + { + "left": "issue:43064", + "right": "issue:44492", + "accept": false, + "reason": "FSDP2/PEFT optimizer-state bug vs a cache-strategy typo; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43352", + "accept": false, + "reason": "Removed tie_embeddings_and_encoder_decoder API vs FlashAttention support failure; different changes." + }, + { + "left": "issue:43867", + "right": "issue:45357", + "accept": false, + "reason": "State_dict sorting load error vs incorrect visual encoder keys saved by Qwen3.5; different save/load problems." + }, + { + "left": "issue:43976", + "right": "issue:44938", + "accept": false, + "reason": "Both are version-specific load failures, but the Python versions and root causes differ." + }, + { + "left": "issue:43992", + "right": "issue:45478", + "accept": false, + "reason": "Missing embed_tokens weight vs Qwen3.5 MoE from_pretrained error; not the same bug." + }, + { + "left": "issue:43064", + "right": "issue:44655", + "accept": false, + "reason": "Trainer optimizer-state corruption vs Pipeline.save_pretrained support; unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43575", + "accept": false, + "reason": "Both involve tensor parallelism, but one is a training bug and the other is an OOM during loading." + }, + { + "left": "issue:42490", + "right": "issue:44075", + "accept": false, + "reason": "Local-files-only import warning vs SGD args not being used; unrelated." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer/ReLU discussion vs DeepSeekV3MoE implementation divergence; different subsystems." + }, + { + "left": "issue:28282", + "right": "issue:33453", + "accept": false, + "reason": "AutoModel PyTorch ImportError vs tokenizer-loading regression; both are loading-related but not the same bug." + }, + { + "left": "issue:43867", + "right": "issue:44484", + "accept": false, + "reason": "Model load failure vs a question about default shard size; not duplicates." + }, + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Attentions field regression vs LwDetrImageLoss AMP crash; unrelated." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "CLIPOutput attentions regression vs Qwen3.5 flash-attention generation bug; different models and failures." + }, + { + "left": "issue:43618", + "right": "issue:45588", + "accept": false, + "reason": "Attentions assignment regression vs flash_attention.py crash on s_aux=None; different code paths." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "Pipeline save_pretrained issue vs Python 3.14 load failure; unrelated." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "Flaky integration test vs Phi-4 multimodal model loading failure; unrelated." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import-name errors, but they concern different missing top-level symbols and do not clearly share one root cause." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Both are test failures, but one is missing seeding and the other is a stale device override assertion; different bugs." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained on MoE vs missing _tp_plan for tensor parallelism; related area, but not the same concrete bug." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "local_files_only network leak vs AddedToken keyword collision; completely different issues." + }, + { + "left": "issue:42890", + "right": "issue:45341", + "accept": false, + "reason": "Flaky test seeding issue vs a small testing_utils bug; 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": 17, + "review_unit_index": 46, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "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:44261", + "issue:44315", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44485", + "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" + ], + "soft_pairs": [ + "issue:43502|issue:44485", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30990|issue:31795", + "issue:45125|issue:45375", + "issue:30333|issue:33453", + "issue:44387|issue:44556", + "issue:43010|issue:45278", + "issue:43723|issue:44556", + "issue:42831|issue:43874", + "issue:43502|issue:44222", + "issue:43010|issue:44368", + "issue:43502|issue:44961", + "issue:43010|issue:45850", + "issue:44315|issue:44360", + "issue:44355|issue:45071", + "issue:30333|issue:36296", + "issue:43827|issue:44961", + "issue:44355|issue:44655", + "issue:44222|issue:44230", + "issue:43299|issue:44556", + "issue:33453|issue:34689", + "issue:42757|issue:43576", + "issue:33453|issue:36296", + "issue:43010|issue:45656", + "issue:43576|issue:45071", + "issue:43576|issue:43824", + "issue:31795|issue:38617", + "issue:44961|issue:45468", + "issue:41628|issue:42548", + "issue:43010|issue:43976", + "issue:38617|issue:43576", + "issue:43576|issue:44938", + "issue:44908|issue:44961", + "issue:36296|issue:43901", + "issue:41628|issue:44355", + "issue:36296|issue:43526", + "issue:44261|issue:44360", + "issue:44623|issue:45230" + ], + "prepared_review_unit_hash": "9f2f25554db55fd6bd7206615a8f801ab2474716e340e49567f73601b4b19bc1", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 39, + "serialized_chars": 38255, + "estimated_input_tokens": 9564, + "estimated_eval_tokens": 19384 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous, with many unrelated Transformers v5 regression reports, import/load failures, docs issues, and a few model-specific bugs. None of the soft-pair candidates look like safe duplicates based on titles alone, so I would keep them split.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 45278 is the best umbrella issue here: it captures the broad v5 upgrade regression pattern with concrete import/load breakage, which matches the dominant theme across the cluster better than the more vague or highly specific reports.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the most suitable representative because it is broad enough to anchor the cluster while still describing a concrete symptom class (import errors after upgrading), unlike the very generic open-ended complaints.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "One is about unexpected network access with local_files_only; the other is a GLM-5 RoPE implementation bug. Different code paths and symptoms." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Running compiled Python files vs slower filtering after upgrading are unrelated problems." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both touch Qwen3.5 MoE loading, but one is tensor-parallel _tp_plan support and the other is a general from_pretrained error; too different to merge confidently." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "A loading hang in Sentence Transformers and confusing forward docs are not the same underlying bug." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Tensor-parallel plan support and a missing config field in Qwen3.5MoeVisionConfig are distinct issues." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLFlow reporting on failed training jobs is unrelated to tokenizer loading regression." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "Int4 memory/OOM behavior and checkpoint reload failures after upgrade are different failure modes." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Decorating cache/layer update with no_grad is unrelated to broad import errors after a version upgrade." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer loading in v5 and reloading old checkpoints after upgrade are both load-related but not the same concrete bug." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and a missing image-processor method are separate model/runtime issues." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Unexpected hub/API requests and FP8 save_pretrained for MoE are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "Cache update no_grad behavior and a tie_word_embeddings warning are not the same bug." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "The title 'racoon' gives no evidence of the same bug; it is unrelated to local_files_only network access." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "A generic complaint that v5 breaks many models is too broad and not the same concrete issue as cache/layer update semantics." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Applying Liger Kernel via model_init and a missing ReLU in DSA indexer are unrelated." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file runtime errors and PretrainedConfig type checking breakage are distinct regressions." + }, + { + "left": "issue:30333", + "right": "issue:36296", + "accept": false, + "reason": "MLFlow failure reporting and tensor-parallel training bugs do not share an underlying code path." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs referencing removed pipeline APIs and an unrelated 'racoon' issue are not duplicates." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled Python file errors and inability to save Pipeline objects are separate save/load problems." + }, + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "FP8 save_pretrained for MoE and FP8 inference support for Qwen3-VL/Qwen3.5 MoE are adjacent but not the same fix." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Both are model-loading regressions, but for different model families and likely different root causes." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 Vision model loading failure are not clearly the same bug." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "An import error from huggingface_hub and a broken transformers env CLI command are different symptoms." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading and tensor-parallel training are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:45656", + "accept": false, + "reason": "Decorating update methods with no_grad is unrelated to optimizer step being called twice under deepspeed." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "Broken env CLI and PretrainedConfig type checking are separate regressions." + }, + { + "left": "issue:43576", + "right": "issue:43824", + "accept": false, + "reason": "CLI env command breakage and a specific model import error do not match." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion in model.forward is unrelated to an ImportError for layer_type_validation." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "The generic 'racoon' issue provides no basis for matching Gemma-4 audio positional encoding bugs." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different import paths; too broad to treat as one bug." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache no_grad behavior and Python version compatibility are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:43576", + "accept": false, + "reason": "An internal import symbol missing and the env CLI being broken are different issues." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Broken env command and Python 3.14 loading failure are not the same underlying problem." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs being ignored and the unrelated 'racoon' issue are not duplicates." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor-parallel training bug and stale pipeline docs are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:44355", + "accept": false, + "reason": "Importing AutoImageProcessor and compiled-file errors are different failure modes." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor-parallel training and BeitImageProcessorFast reduce_labels behavior are unrelated." + }, + { + "left": "issue:44261", + "right": "issue:44360", + "accept": false, + "reason": "A precision issue in MLA q_a_layernorm and a missing ReLU in DSA indexer are completely different bugs." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Missing files from processor.save_pretrained and a vague bug report title are not enough to identify the same issue." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "Same pair as above; no evidence they refer to the same concrete bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 47, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "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:44246", + "issue:44273", + "issue:44295", + "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" + ], + "soft_pairs": [ + "issue:44273|issue:45542", + "issue:44273|issue:45003", + "issue:44393|issue:45753", + "issue:44038|issue:45125", + "issue:43576|issue:44556", + "issue:44393|issue:45071", + "issue:44373|issue:44961", + "issue:41669|issue:43673", + "issue:43525|issue:45850", + "issue:44556|issue:45092", + "issue:45362|issue:45850", + "issue:43572|issue:45850", + "issue:42890|issue:44908", + "issue:44704|issue:44908", + "issue:44246|issue:44273", + "issue:43976|issue:44393", + "issue:43408|issue:44315", + "issue:44297|issue:45230", + "issue:43352|issue:44393", + "issue:44295|issue:45230", + "issue:43576|issue:44908", + "issue:44908|issue:45071", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:43673|issue:44492", + "issue:45278|issue:45850", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:41669|issue:44492", + "issue:31795|issue:33453", + "issue:41669|issue:44908", + "issue:44315|issue:44829", + "issue:42371|issue:44492", + "issue:43576|issue:44273", + "issue:44360|issue:45468", + "issue:44655|issue:44861", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:44492|issue:45850" + ], + "prepared_review_unit_hash": "6c1d03fbe7108b078f541bbcae217c95ae543ffb45b8dd9897b10a14d7ce66e7", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 41, + "serialized_chars": 38714, + "estimated_input_tokens": 9679, + "estimated_eval_tokens": 19614 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is a loose mix of v5-era import/lazy-loading regressions, model-specific config bugs, and unrelated docs/tests issues. The soft edges look like thematic similarity, not true duplicates, so none should be merged.", + "confidence": 0.66, + "canonical_issue_reason": "issue:44273 is the clearest umbrella for the import/lazy-loading regression theme that appears most often here, even though the cluster overall is heterogeneous.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44273 is the best representative issue among the set because it is broad enough to cover the shared loading/import theme without collapsing unrelated model/config bugs.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Both involve loading/runtime behavior, but one is lazy loading and the other is a TF backend/import environment error; different code paths." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Related to loading/imports, but one is a generic lazy-loading failure and the other is a specific sys.modules access bug; not the same concrete defect." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "Same model family, but one is 2D bbox output errors and the other is an infinite loop on a specific image; different symptoms and fixes." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Different Qwen3.5/VL model issues: one is a bug report for Qwen3-VL-Moe, the other is missing _tp_plan for tensor parallelism." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "One is a broken CLI command, the other is checkpoint reload compatibility after upgrade; distinct failures." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "A model output bug and a PretrainedConfig typing regression are unrelated code paths." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "A docstring typo and a placeholder issue title are not the same bug." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star cleanup/performance and missing GenerationMixin cache in chunked_prefill are different changes." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Model-specific pad_token_id error versus a broad complaint that many models break after v5; too vague to be duplicates." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both are upgrade compatibility problems, but they affect different model-loading paths and different checkpoints." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Specific chat crash for Qwen3.5-35B versus a generic 'many models' complaint; not the same issue." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression is a specific model config bug, not the broad v5 breakage claim." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Missing set_seed in tests and an inverse_sqrt scheduler kwarg bug are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs handling are separate subsystems." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Both concern imports, but one is intermittent import slowness and the other is broken lazy loading; not the same concrete defect." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version support regression and a Qwen3-VL output bug do not share a code path." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type warning during instantiation versus Liger Kernel application with model_init are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained mismatch and a vague bug report title are not duplicates." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2.0 support error for NemotronH and a Qwen3-VL bounding-box bug are different model issues." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "A position_ids buffer error and a generic bug report are not the same underlying bug." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "CLI env command breakage and scheduler kwarg handling are unrelated." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs and PretrainedConfig type checking are separate concerns." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star usage cleanup and inability to import HybridCache are both import-related but not the same bug." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import cleanup/performance and a testing_utils bug are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Generation cache missing in chunked_prefill and a cache-strategy typo are different issues." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Specific post-upgrade import errors versus a broad claim that many models break are too nonspecific to be duplicates." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "A GLM46V multimodal tokenization bug is not the same as a generic v5 breakage report." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model families and different failure modes." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "PatchTSMixer post_init validation and tied-weight key handling are unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs still referencing pipeline() and scheduler kwargs handling are not the same change." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star cleanup and cache-strategy typo are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Documentation confusion about forward arguments and tokenizer loading regression are distinct." + }, + { + "left": "issue:41669", + "right": "issue:44908", + "accept": false, + "reason": "Import performance cleanup and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger Kernel not being applied with model_init and flash_attention_3 causing degenerate training are different training bugs." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API guidance and a cache-strategy typo are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "A broken env command and lazy loading failure may both be version-related, but they are different code paths." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "A DSA indexer discussion and a Gemma-4 audio positional encoding bug are unrelated." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Pipeline save_pretrained failure and _tied_weight_keys attribute handling are different bugs." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "A vague placeholder title and a specific Qwen3.5 Moe from_pretrained error are not duplicates." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading/import behavior and scheduler kwargs are unrelated." + }, + { + "left": "issue:44492", + "right": "issue:45850", + "accept": false, + "reason": "A typo in cache strategies and a broad v5 breakage complaint are not the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 17, + "review_unit_index": 48, + "review_unit_count": 48, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-409", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:37428", + "issue:38617", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43606", + "issue:43704", + "issue:44230", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44360", + "issue:44485", + "issue:44623", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45092", + "issue:45290", + "issue:45310", + "issue:45468" + ], + "soft_pairs": [ + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31795|issue:37428", + "issue:44315|issue:45092", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:43502|issue:43519", + "issue:42371|issue:43704", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:44263|issue:45468", + "issue:43606|issue:45468", + "issue:44261|issue:45468", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43525|issue:44861", + "issue:41669|issue:44998", + "issue:43704|issue:44998", + "issue:43572|issue:44861", + "issue:43066|issue:44998", + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:44360|issue:44998", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:44230|issue:45310", + "issue:31515|issue:31795", + "issue:31515|issue:33453", + "issue:43298|issue:44230" + ], + "prepared_review_unit_hash": "0b3e6286efe31bb85ce5dff8aff1d4fb1bf20473c13f06bd7903b5064d3cb0b7", + "component_budget": { + "node_count": 409, + "item_count": 409, + "soft_pair_count": 1530, + "serialized_chars": 789356, + "estimated_input_tokens": 197339, + "estimated_eval_tokens": 394934 + }, + "budget": { + "node_count": 33, + "item_count": 33, + "soft_pair_count": 32, + "serialized_chars": 28209, + "estimated_input_tokens": 7053, + "estimated_eval_tokens": 14362 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These soft links are mostly spurious: the issues span unrelated bugs in loading, tokenizers, configs, schedulers, processors, and model internals. I would not merge any of the candidate pairs as duplicates.", + "confidence": 0.86, + "canonical_issue_reason": "No reliable canonical issue emerges here; the similarity links connect unrelated bug classes and subsystems rather than one underlying defect.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue is a safe duplicate hub. Issue 43519 has the most soft links, but those neighbors are not true duplicates of its timestamp-calculation bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Different bugs: Qwen3VL timestamp parsing vs GLM-5 RoPE implementation." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp logic vs lr_scheduler kwargs handling; unrelated code paths." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star cleanup/perf work vs a VRAM leak in Qwen3ForCausalLM; not the same bug." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Documentation confusion in model.forward vs a model-loading regression; different problems." + }, + { + "left": "issue:31795", + "right": "issue:37428", + "accept": false, + "reason": "Docs issue vs an ImportError from flash-attention utils; unrelated." + }, + { + "left": "issue:44315", + "right": "issue:45092", + "accept": false, + "reason": "Liger Kernel application bug vs remote-code/meta-init incompatibility; different failure modes." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "GLM-5 RoPE implementation vs Gemma-4 audio positional encoding; unrelated models/features." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in multi-threaded loading vs RoPE implementation; not the same defect." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only network access bug vs Qwen3VL timestamp calculation; different subsystems." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 behavior/settings issue vs a VRAM leak; unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Timestamp calculation bug vs missing processor save_pretrained files; different code paths." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Qwen3VL timestamp bug vs Qwen3ForCausalLM VRAM leak; not the same issue." + }, + { + "left": "issue:44263", + "right": "issue:45468", + "accept": false, + "reason": "torch.split return-value issue in GlmMoeDsaIndexer vs Gemma-4 audio positional encoding." + }, + { + "left": "issue:43606", + "right": "issue:45468", + "accept": false, + "reason": "CPU offload device mismatch vs Gemma-4 audio positional encoding; unrelated." + }, + { + "left": "issue:44261", + "right": "issue:45468", + "accept": false, + "reason": "MLA layernorm epsilon/config precision bug vs Gemma-4 audio positional encoding." + }, + { + "left": "issue:42913", + "right": "issue:43066", + "accept": false, + "reason": "Both involve tokenizer v5 behavior, but one is a broad regression report and the other is a specific decoder-type issue; too vague to treat as the same bug." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug vs an unrelated placeholder issue." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "_get_tied_weight_keys AttributeError vs apply_chat_template crash with tool calls; different code paths." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in Llama4Config vs tied-weight-key AttributeError; unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-star cleanup/perf issue vs an unrelated placeholder issue." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak issue vs an unrelated placeholder issue." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "StableLmConfig pad_token_idx bug vs tied-weight-key crash; different surfaces." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Tokenizer decoder-type regression vs an unrelated placeholder issue." + }, + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Slow checkpoint loading vs ImportError for layer_type_validation; unrelated." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 support request vs processor save_pretrained missing files; not the same bug." + }, + { + "left": "issue:44360", + "right": "issue:44998", + "accept": false, + "reason": "DSA indexer/ReLU discussion vs an unrelated placeholder issue." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLflow reporting failure vs from_pretrained slowness; different problems." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint loading performance vs tensor-parallel training bug; unrelated." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "FP8 inference support issue vs Qwen3.5 MoE from_pretrained error; different concrete bugs." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Loading slowdown vs documentation confusion; not the same issue." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "from_pretrained loading speed vs tokenizer-loading regression; different symptoms and subsystems." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching audio-model support vs FP8 support for Qwen3-VL/Qwen3.5; unrelated feature requests." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "b6bbdf41709ef675980f88d18f9830bb442178d8539aea2d827f77f16f5d669e", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 2478, + "estimated_input_tokens": 620, + "estimated_eval_tokens": 1496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are not duplicates of one another: one is about Tapas tokenization behavior, one about an authentication/download error for private models, and one about loading bert-base-uncased. They share only vague model-loading similarity.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "No single issue cleanly represents a duplicate cluster here; if forced, #16618 is the broadest, but it is still not a duplicate of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different underlying problem: Tapas tokenization mismatch vs a generic model-load failure for bert-base-uncased; no shared code-path or concrete fix target." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "#15980 is specifically about a bad error message when downloading a private model while logged out, whereas #16618 is a model loading failure for a public model; related area but not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "f65f1aa5f23acbf02e6934960197294ccf274d493ce81a31bad5c20c96471597", + "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 not duplicates: one issue tracks Flash Attention 2 support for more architectures, the other tracks GGUF support for more architectures. They concern different features and likely different code paths.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a strong canonical representative for the cluster because the underlying requests are different. If forced, issue 26350 has slightly more discussion, but it is not the same topic as 33260.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Reject: these request different kinds of model support (Flash Attention 2 vs GGUF) and do not describe the same underlying bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 4, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-5", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:43834", + "issue:44365", + "issue:44370" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:44370", + "issue:43834|issue:44370", + "issue:43834|issue:44365", + "issue:44365|issue:44370" + ], + "prepared_review_unit_hash": "a69fd6b8d56fefb22a6126202f6726047dba34733285fac21e2b18b15203eadc", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6443, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 10, + "serialized_chars": 6443, + "estimated_input_tokens": 1611, + "estimated_eval_tokens": 3478 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The three generic i18n placeholder issues are likely true duplicates of each other. The Turkish and Spanish issues are separate language-specific translation requests and should not be merged with the generic placeholders or with each other.", + "confidence": 0.79, + "canonical_issue_reason": "Issue 43834 is the earliest of the near-identical generic placeholder translation issues and best represents that duplicate subgroup.", + "canonical_pr_reason": null, + "best_issue_reason": "43834 has the strongest duplicate signal within the cluster: same generic title/body pattern as 44365 and 44370, with the earliest timestamp among them.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different target languages; Turkish vs generic placeholder. Same broad i18n theme is not enough to treat these as the same request." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Different target languages; this is a Turkish translation request, while the other is a generic placeholder translation issue." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Turkish-specific translation request vs generic placeholder issue; not the same underlying change." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Turkish and Spanish translation requests are distinct deliverables, so they should not be deduplicated." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish-specific request does not match the generic placeholder issue closely enough to be the same underlying issue." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Different language targets; Spanish translation request versus generic placeholder issue." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Different language targets; these are separate translation requests, not one bug/change." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": true, + "reason": "Near-identical generic title/body pattern and no distinguishing details; these look like duplicate copies of the same placeholder issue." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": true, + "reason": "Same generic template/title and almost identical body structure; likely duplicate placeholder issues." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": true, + "reason": "Same generic placeholder translation issue with nearly identical content; safe to deduplicate." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet. The three placeholder issues have nearly identical titles and extremely high similarity scores, and selecting the earliest one as canonical is reasonable. The Turkish and Spanish issues are correctly treated as distinct language-specific requests, and the soft-edge verdicts stay conservative without overstating equivalence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 5, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-15", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:45322", + "issue:43837|issue:43909", + "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" + ], + "prepared_review_unit_hash": "b0b5982722ea84b61b74050b47a4c5c9e13144ea5e8b708c5ebedcc1027c82f7", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 35, + "serialized_chars": 20708, + "estimated_input_tokens": 5177, + "estimated_eval_tokens": 10610 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is a set of related-but-distinct model support requests, not true duplicates. The overlap is mostly the generic \u201cadd model/support\u201d framing; the requested model families and tasks differ materially.", + "confidence": 0.97, + "canonical_issue_reason": "Issue 41115 is the broadest and most representative request in the set, with the clearest generic scope and the most cluster activity/references among the open issues.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 41115 is the best cluster anchor because it is a high-activity, broadly phrased model-add request that most cleanly represents the topical group without being overly niche.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different model requests: EuroBert vs DEIMv2. Same feature theme, not the same underlying change." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "EuroBert config support is unrelated to Qwen3-TTS audio support." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert vs RF-DETR are distinct model families and use cases." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "RF-DETR and DEIMv2 are different detection models; not a duplicate request." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "RF-DETR vision detection and LFM2.5 Audio support are unrelated changes." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR and circuit-sparsity transformer support target different architectures and code paths." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "RF-DETR vs Qwen3-ASR are different model types and tasks." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "RF-DETR vision model support is not the same as Qwen3-TTS audio support." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT and Qwen3-ASR are unrelated model requests." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT vs weight-sparse transformer support are different architectures, not one bug/change." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT and LFM2.5 Audio request different domains and implementation paths." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR and NeoBERT are unrelated model additions." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT and ModernVBERT are different models; shared BERT naming is not enough for duplication." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture support and Qwen3-ASR support are distinct model additions." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 and circuit-sparsity transformer support are different code paths and requests." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 and ModernVBERT are separate model support requests." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 and Voxtral TTS support are different modalities and implementations." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 and Qwen3-TTS are unrelated model support requests." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT and Qwen3-ASR are different models and tasks." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT vs Qwen3-TTS are unrelated additions." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT and BERT-like models with RoPE are too broad and not the same concrete request." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE support and Voxtral TTS support are unrelated changes." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3-TTS and Qwen3-ASR are related by brand, but they are different products and different support paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-TTS and Voxtral TTS are distinct model integrations." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-TTS and DeepSeek-OCR2 are unrelated modalities and requests." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-TTS support is not the same as the weight-sparse transformer request." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "Qwen3-ASR and EUPE are different audio/vision model requests." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-ASR and LFM2.5 Audio are both audio-related, but they are different models and implementations." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "LFM2.5 Audio and SAM3-LiteText are completely different model requests." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "Qwen3-TTS and LFM2.5 Audio are distinct audio model support requests." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Weight-sparse transformer support and EUPE are different architecture proposals." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3-ASR and circuit-sparsity transformer support do not describe the same change." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "Qwen3-ASR and Voxtral TTS are different audio model integrations." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT and Voxtral TTS are unrelated model support requests." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "Qwen3-ASR and DeepSeek-OCR2 are different model families and tasks." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 6, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-37934-7", + "nodes": [ + "issue:37934", + "issue:42936", + "issue:43240", + "issue:43668", + "issue:43813", + "issue:44031", + "issue:46018" + ], + "soft_pairs": [ + "issue:37934|issue:43668", + "issue:42936|issue:43240", + "issue:42936|issue:46018", + "issue:42936|issue:44031", + "issue:42936|issue:43813", + "issue:42936|issue:43668", + "issue:43240|issue:43668", + "issue:43668|issue:44031", + "issue:43668|issue:43813" + ], + "prepared_review_unit_hash": "4db72b1c7c80e351ff272d4c86fac88e3842d91a776539e76cf791ce2bb90f0a", + "component_budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 7188, + "estimated_input_tokens": 1797, + "estimated_eval_tokens": 3850 + }, + "budget": { + "node_count": 7, + "item_count": 7, + "soft_pair_count": 9, + "serialized_chars": 7188, + "estimated_input_tokens": 1797, + "estimated_eval_tokens": 3850 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This is not a true duplicate cluster: the issues span unrelated models, config typing, tokenizer warnings, and an unrelated typo. No soft edge appears to describe the same underlying bug.", + "confidence": 0.96, + "canonical_issue_reason": "If one issue must be used as a representative, #42936 is the most concrete and discussion-rich report; however, it is not actually a duplicate of the others.", + "canonical_pr_reason": null, + "best_issue_reason": "#42936 is the strongest standalone issue in the set, but only as a generic representative\u2014not because it matches the rest of the items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "Both mention normalization-related terms, but one questions Llama4TextL2Norm semantics while the other is a ModernBERT config type-hint bug; different models and different problems." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Mask2former ignore_value being unused is a model-specific loss bug, while kwargs not being passed to loss calculation is a separate API/control-flow issue." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "These are unrelated DeepSeek-V4 gating and Mask2former ignore_value bugs; same broad ML space, not the same code-path problem." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "A Mask2former loss parameter issue is unrelated to a tokenizer regex warning regression." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "Unused ignore_value in a model loss function does not match a typo in a quantization-operation attribute name." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs propagation and a config type-hint mistake are different kinds of bugs in different components." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "ModernBERTConfig norm_eps typing and an orig_conversion.quantization_operation typo are unrelated issues." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type-hint problem is not the same underlying bug as a tokenizer regex warning regression." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "4a0a7b6528f68beb2f1518a7e18ec2bf1699d0fd4efb995dbd8fd278467119f9", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1479, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are not duplicates: one is a specific request about set block decoding, while the other asks for DeepSeek v3.2 support. They describe different features/problems with no shared code-path evidence.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "#41084 is the more concrete, narrowly scoped issue; #43037 is a separate model-support feature request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying requests: block decoding vs DeepSeek v3.2 model support. No overlapping targets, filenames, or concrete bug path suggest a duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "b06bac0bff94ddaeff4c3e5ce9145d8a420a30c3a5a4adb3edd37fd4e6f7917d", + "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 only loosely related by \u201ccustom trainers,\u201d but they describe different trainer behaviors: one is about `remove_unused_column` handling, the other about FLOPS estimation. They are not duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "Issue #43598 is the better cluster representative because it is the broader customizability concern around Trainer behavior; #43600 is a separate FLOPS-accounting problem.", + "canonical_pr_reason": null, + "best_issue_reason": "#43598 is the more suitable global issue anchor since it describes the core trainer customizability gap more directly and broadly, while #43600 is a narrower, distinct follow-up concern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "Revisit `remove_unused_column` in Trainer for better customizability", + "right": "Account for custom trainers when trying to estimate the number of FLOPS", + "accept": false, + "reason": "Both mention custom trainers, but one concerns column-pruning customizability and the other concerns FLOPS estimation. They affect different code paths and are not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "e3ff850f5495f1daff034f4625dc9218a3e0306aac88eccc79fa4f5f6aac953f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1611, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1611, + "estimated_input_tokens": 403, + "estimated_eval_tokens": 1062 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are related only at a very high level: both concern adding Qwen model support to auto classes, but they target different APIs and different model/config variants. They do not look like the same underlying bug or change.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43684 is the broader request (Qwen3-Omni registration for AutoModel and AutoModelForConditionalGeneration) and is the better representative of the auto-class registration theme, but it is not the same task as 44405.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the most general and central of the two; 44405 is a narrower, distinct sequence-classification support request for a different Qwen config.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Reject: 43684 asks for adding Qwen3-Omni registration to AutoModel/AutoModelForConditionalGeneration, while 44405 asks for AutoModelForSequenceClassification support for Qwen3.5 (Qwen3_5Config). Different model family/config and different auto class behavior, so not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "f21028b2c5e49cdf59db79e8df564356f5bcddf6ded65c5a7390f2d2da6c892f", + "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": "Issues 43845, 43846, and 43859 share the exact same generic title \"huggingface \" and form the duplicate cluster; 43835 ('Fett') looks unrelated.", + "confidence": 0.82, + "canonical_issue_reason": "43845 is the earliest issue in the exact-title duplicate set, so it is the best canonical representative.", + "canonical_pr_reason": null, + "best_issue_reason": "43845 is the best overall issue representative because it matches the other two identical-title reports, while 43835 is unrelated.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different titles and no shared targets or other evidence of the same underlying problem." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same exact title and soft similarity; they look like duplicate reports of the same issue." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The cluster summary is mostly grounded, but one soft-edge rationale overstates the evidence: issue 43859 is about 13 hours after 43845/43846, so it is not 'very close' in creation time. If you keep those acceptances, the reasoning should rely only on the identical title and soft similarity, not temporal proximity." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "004a283e5934b2987fd297350411e74b9b1e80dfc6edd361a00067162101eb63", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5785, + "estimated_input_tokens": 1447, + "estimated_eval_tokens": 3150 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster looks like unrelated low-information/spam issues with only superficial title similarity. There is no evidence of a shared underlying bug or change, so none should be deduplicated together.", + "confidence": 0.98, + "canonical_issue_reason": "Issue 44371 is the earliest item and is as generic as the rest, but none of the issues provide enough substance to serve as a meaningful canonical report.", + "canonical_pr_reason": null, + "best_issue_reason": "44371 is the least bad placeholder only because it is earliest; however, the set is too noisy and content-poor to identify a true canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are generic spam placeholders, but there is no concrete evidence they describe the same report." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Identical low-information titles are not enough to prove the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam-like and the other is a documentation suggestion; they do not point to the same problem." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "The titles are unrelated; no shared bug, request, or code path is evident." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "A documentation enhancement and a spam placeholder are not the same issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Different topics with no concrete overlap beyond being low-information issues." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Same generic placeholder title, but no description or target evidence ties them to one underlying report." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Unrelated titles and no explicit shared target or problem statement." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "No substantive common bug/change is visible; similarity is only superficial." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "8f5403be315b4b2a7dc7603ea9f431af87f159fb08388fcc07e3455d285814c0", + "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 have identical titles and similar content, but the packet only supports a soft duplicate hypothesis rather than an exact duplicate. #45145 is the safest canonical issue because it was created first and already has an inbound reference.", + "confidence": 0.78, + "canonical_issue_reason": "#45145 is the earlier report and has an inbound reference, so it is the safest canonical representative among two highly similar issues.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the best issue representative for triage because it is the earliest instance and already referenced elsewhere; the available evidence does not prove a strict duplicate, only strong similarity.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The issues share an identical title and look related, but the packet only provides soft similarity (Jaccard 0.63) with no explicit links, targets, or other evidence proving the same underlying report. That is not strong enough to accept as a duplicate." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The canonical choice (#45145) is grounded by earlier creation time and an inbound reference, but the analysis overstates the evidence for duplication. The packet only shows identical titles and soft similarity with Jaccard 0.63; it does not establish an exact duplicate. Also, the claim that #45145 has \u201cslightly more discussion context\u201d is not supported by the packet (it has 0 discussion activity vs. 1 on #45151)." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45672-2", + "nodes": [ + "issue:45672", + "issue:45674" + ], + "soft_pairs": [ + "issue:45672|issue:45674" + ], + "prepared_review_unit_hash": "a4853145fdabf66fe7820c362fb6bd1dd37936cff9b40bc212ff70afd153bdec", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1668, + "estimated_input_tokens": 417, + "estimated_eval_tokens": 1090 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related only at a very broad level (4-bit inference), but they describe different failures in different code paths: one is a Gemma4/audio-module uint8 + `torch.finfo()` TypeError, the other is a BitsAndBytesConfig `llm_int8_skip_modules`/`lm_head` exclusion AssertionError. They should not be merged as duplicates.", + "confidence": 0.97, + "canonical_issue_reason": "Issue #45674 is the clearer, more generally described bug report: it names the specific configuration interaction, the affected default exclusion behavior, and the resulting assertion path.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45674 is the best representative because it is more precise about the trigger and failure mode, making it easier to triage and fix independently.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Both involve 4-bit inference, but the reported bugs are different: one is a `torch.finfo()` TypeError on uint8 weights in Gemma4 audio modules, the other is an AssertionError caused by `llm_int8_skip_modules` clearing the default `lm_head` exclusion. Different triggers and code paths, so not a duplicate." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 15, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "82a2f5f5d6cd8bc1d2d0169feb6ba16571c6723e5eec40537266c7004168f3d7", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1477, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues appear unrelated: both titles are just different personal names with different dates, and there is no shared description, filename, target, or discussion evidence suggesting a duplicate bug report.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "Different named subjects and different dates; no evidence they describe the same underlying issue or report." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 16, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "fefccf9bea33baae59dc78b6f3f6644645b110e77b4be02e51a423ae00a41b91", + "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-looking closed placeholders with different person-name/date titles, no body, no links, and no shared technical context. There is no basis to treat either as a duplicate of the other.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45764", + "right": "issue:45765", + "accept": false, + "reason": "The titles refer to different names and dates, and there is no issue body, discussion, or linking evidence indicating the same underlying bug or request." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 17, + "component_count": 17, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45869-5", + "nodes": [ + "issue:45869", + "issue:45870", + "issue:45871", + "issue:45872", + "issue:45873" + ], + "soft_pairs": [ + "issue:45869|issue:45870", + "issue:45869|issue:45871", + "issue:45870|issue:45871", + "issue:45870|issue:45872", + "issue:45870|issue:45873", + "issue:45871|issue:45872", + "issue:45871|issue:45873", + "issue:45872|issue:45873" + ], + "prepared_review_unit_hash": "4ecad14438dd50d9f9429f93d1cb83f30115331132ae29876c4fbeebe8950426", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5722, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is not one duplicate set; it splits into two separate exact-duplicate issue pairs: 45870/45871 and 45872/45873. Issue 45869 is only loosely thematically related and should not be merged with either pair.", + "confidence": 0.95, + "canonical_issue_reason": "45870 is the cleanest representative of the first exact-duplicate pair because it matches 45871 verbatim and is the earlier instance. It is not a canonical for the whole cluster, only for its duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue cleanly represents all five items, but 45870 is the best overall representative to keep as the first exact-duplicate issue. If triaging by subcluster, 45872 would be the corresponding representative for the second exact-duplicate pair.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Same broad financial domain, but 45869 is a dataset/sample offer while 45870 is an example issue about prediction with DataForge; not the same underlying request." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Dataset bundle vs example issue; related topic only, not the same concrete bug/change." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Identical titles and likely the same issue reported twice." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Both mention financial time series/DataForge, but one is about a prediction example and the other about a scraping service; different concrete requests." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Different underlying issue: prediction example versus scraping-service request." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different concrete topic and likely separate work items, despite shared keywords." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Prediction example and scraping-service issue are not the same underlying change." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Identical titles and effectively the same issue duplicated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster analysis is grounded in the packet: 45870/45871 and 45872/45873 are the only clearly mergeable duplicate pairs based on identical titles and matching body length, while 45869 is only loosely related. The soft-edge verdicts are conservative and do not overstate evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-15", + "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:46065", + "pull_request:46067" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:41855|pull_request:43424", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:46067", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:46065", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:46065", + "pull_request:43424|pull_request:46067", + "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:43823|pull_request:46067", + "pull_request:43995|pull_request:44827", + "pull_request:43995|pull_request:45213", + "pull_request:44827|pull_request:46065", + "pull_request:44827|pull_request:46067", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:46048", + "pull_request:45170|pull_request:46065", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:44827|pull_request:45655", + "pull_request:46065|pull_request:46067", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "c2430217c36b580b17d982a0524f516a2e9172cd23dbe5c4c48d98b7a61a32c4", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 27, + "serialized_chars": 42112, + "estimated_input_tokens": 10528, + "estimated_eval_tokens": 21312 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 27, + "serialized_chars": 42112, + "estimated_input_tokens": 10528, + "estimated_eval_tokens": 21312 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly noisy and spans unrelated PRs (model additions, docs, tests, kernel/loading fixes). The only clear duplicate/same-change pair is the two `fixed_cross_entropy` patches for the same loss helper.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 43251 is the strongest representative because it directly links issue 43240 and makes the same `fixed_cross_entropy` API change as 43254, but in a slightly more complete/structured way.", + "best_issue_reason": null, + "best_pr_reason": "PR 43251 is the best cluster anchor: it is explicitly issue-linked, targets the core loss helper change, and its duplicate pair (43254) is a near-identical alternative implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "Unrelated PRs: VideoPrism model/docs addition vs an Executorch dynamic-shape test. Same general repo area only, not the same bug/change." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Mistral tokenizer helper methods vs adding MobileLLM. Different models and different code paths." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Tokenizer API fix vs Executorch export test. No shared underlying bug or change." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor auto-loading robustness vs adding MobileLLM. Broad processor/model infrastructure only, not the same fix." + }, + { + "left": "pull_request:43251", + "right": "pull_request:46067", + "accept": false, + "reason": "Both touch loading/loss-related code in the repo, but they fix different problems: cross-entropy kwargs vs base_model_prefix conversion handling." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "Loss helper kwargs fix vs new MobileLLM model addition. Completely different changes." + }, + { + "left": "pull_request:43251", + "right": "pull_request:46065", + "accept": false, + "reason": "Cross-entropy kwargs fix vs testing-utils device detection fix. Unrelated code paths." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Loss helper change vs Mistral4 test/model cleanup. Same broad theme of fixes, but not the same concrete bug." + }, + { + "left": "pull_request:43424", + "right": "pull_request:46065", + "accept": false, + "reason": "Executorch dynamic-shape test vs testing-utils device detection. Different functionality." + }, + { + "left": "pull_request:43424", + "right": "pull_request:46067", + "accept": false, + "reason": "Executorch export test vs conversion-loading prefix handling. No shared change target." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Executorch dynamic-shape test vs Mistral4 test fixes. Both test-oriented, but unrelated code paths." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Executorch test vs MobileLLM model addition. Not the same bug/change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "New MobileLLM model vs config-resolution ordering fix. Different subsystems and issues." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "MobileLLM addition vs Falcon output-interface refactor. Different model families and changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:46067", + "accept": false, + "reason": "MobileLLM addition vs conversion base_model_prefix fix. No common concrete code-path." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-capture refactor vs Mistral4 tests/model fixes. Different models and intent." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactor vs model-creation skill draft. Completely unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46065", + "accept": false, + "reason": "Do not merge just because both are fixes/tests; Mistral4 test fixes and testing-utils device capability handling are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46067", + "accept": false, + "reason": "Mistral4 tests/model work vs base_model_prefix conversion fix. Different underlying problems." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes vs layrnorm->layernorm renaming. No shared bug or mergeable single PR." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46048", + "accept": false, + "reason": "Mistral4 fixes vs TDT loss kernel integration. Different feature/fix scope." + }, + { + "left": "pull_request:45170", + "right": "pull_request:46065", + "accept": false, + "reason": "LayerNorm rename/conversion mapping fix vs testing-utils device properties fix. Unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 fixes vs a new-model skill draft. Not the same change." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM addition vs model-creation skill draft. Different artifact types and purposes." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test fixes vs config-resolution order fix. Different code paths and problems." + }, + { + "left": "pull_request:46065", + "right": "pull_request:46067", + "accept": false, + "reason": "Testing-utils device detection fix vs conversion base_model_prefix fix. Both infra changes, but not the same underlying bug." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Same file and same loss helper (`fixed_cross_entropy`) with the same underlying fix: add supported kwargs/forward them to `nn.functional.cross_entropy` for issue 43240." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it correctly treats the cluster as mostly unrelated noise and only accepts the clear duplicate pair `pull_request:43251`/`pull_request:43254`, which share the same file and issue target `43240`. The rejected soft-edge pairs also look appropriately non-mergeable into a single bugfix PR." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40546-2", + "nodes": [ + "pull_request:40546", + "pull_request:42781" + ], + "soft_pairs": [ + "pull_request:40546|pull_request:42781" + ], + "prepared_review_unit_hash": "645beec4388498c7c542381a57d9b3f374abbd6ec5a90c46cb0947e51b4b718a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 7225, + "estimated_input_tokens": 1807, + "estimated_eval_tokens": 3870 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are about adding VibeVoice support, but PR #42781 is a later, broader realtime follow-up rather than the same concrete change as PR #40546. They overlap heavily on core VibeVoice files, yet the feature scope differs enough that they should not be merged as duplicates.", + "confidence": 0.84, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #42781 is the more comprehensive and newer VibeVoice implementation, covering the realtime path plus the acoustic tokenizer and related generation/model plumbing, so it is the better representative of this cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR #42781 is the strongest standalone candidate because it appears to subsume more of the VibeVoice integration surface and likely reflects the most complete implementation direction.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "They overlap on VibeVoice infrastructure, but #40546 is the initial implementation while #42781 adds a realtime variant and additional tokenizer/generation pieces. That is related work, not the same concrete fix/change, so I would not 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": 3, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-40755-2", + "nodes": [ + "pull_request:40755", + "pull_request:41224" + ], + "soft_pairs": [ + "pull_request:40755|pull_request:41224" + ], + "prepared_review_unit_hash": "42e5168c88d71b4b5f9b570c002b81cbd622ef352af82a0e592d0447bc0ccd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4676, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4676, + "estimated_input_tokens": 1169, + "estimated_eval_tokens": 2594 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two PRs are unrelated feature additions in different model areas: TimesFM covariate forecasting vs DINOv3 image classification support. They do not look like the same underlying change, so the soft duplicate edge should be rejected.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different models and code paths: 40755 adds TimesFM covariate forecasting across timesfm/xreg utilities, while 41224 adds DINOv3 image classification support in auto/modeling docs and DINOv3 code. They are not the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 4, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41356-2", + "nodes": [ + "pull_request:41356", + "pull_request:44339" + ], + "soft_pairs": [ + "pull_request:41356|pull_request:44339" + ], + "prepared_review_unit_hash": "aead1308c167b0bae6ff11bf9358340baa5e76f816618383418b505a10a9cd01", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6050, + "estimated_input_tokens": 1513, + "estimated_eval_tokens": 3282 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two DEIMv2 pull requests target the same model family, but they are not the same change: PR 41356 is an early/basic model + image processor add, while PR 44339 is a much broader follow-up that adds loss code, auto-mappings, conversion tooling, modular files, and more integration work.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44339 is the more complete and representative DEIMv2 implementation; PR 41356 looks like an earlier partial version of the same model bring-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 44339 is the strongest single artifact for the cluster because it subsumes the basic model work and includes the broader integration needed for a full Transformers addition.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41356", + "right": "pull_request:44339", + "accept": false, + "reason": "Same model area, but not the same concrete change: 44339 expands the implementation substantially and adds new code paths beyond the basic PR 41356. They look like related iterations, not mergeable duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 5, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41797-3", + "nodes": [ + "pull_request:41797", + "pull_request:45186", + "pull_request:45630" + ], + "soft_pairs": [ + "pull_request:41797|pull_request:45186", + "pull_request:45186|pull_request:45630" + ], + "prepared_review_unit_hash": "320fd47de973cbb1571e4e4094f51a56fb88e7ce933c748327f650c62454746e", + "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 separate new-model addition PRs for different models (DeepSeek OCR, Isaac, Kimi2-6). They share boilerplate registration/docs patterns, but not the same underlying change or code-path fix, so they should not be clustered as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical duplicate PR: each change adds a different model integration, with distinct files, configs, processors, and model code.", + "best_issue_reason": null, + "best_pr_reason": "PR 45630 is the strongest representative only in the sense that it has the most review activity and a substantial model integration, but it is still not interchangeable with the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different model additions (DeepSeek OCR vs Isaac). Shared docs/auto-registration files are boilerplate, not evidence of the same underlying change or a PR that could be merged into one." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model additions (Isaac vs Kimi2-6) with distinct implementation files and model codepaths. The overlap is broad framework registration, not the same concrete fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42975-2", + "nodes": [ + "pull_request:42975", + "pull_request:42976" + ], + "soft_pairs": [ + "pull_request:42975|pull_request:42976" + ], + "prepared_review_unit_hash": "4a2184db695189253243cfef43ab3212e29458abfe07ec7f943e2e18b0b47e81", + "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 modernize GitHub Actions workflows, but they update different actions and address different change sets: one focuses on Node 24-compatible workflow action upgrades, the other on bumping docker/build-push-action and a few related workflows. They overlap in filenames but are not the same underlying change.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR #42975 is the broader, more coherent workflow-upgrade sweep and is the better representative of the cluster, but it is not a duplicate of #42976.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: both are workflow dependency bumps, but #42975 upgrades core GitHub Actions for Node 24 compatibility while #42976 specifically bumps docker/build-push-action. They touch overlapping files yet fix different action-version migrations and would not plausibly be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-42978-4", + "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": "f9099aabcf4cd6ed22c38e7b5ffc03bfc19bc19bb5c2dffcdd4e1f60c08e5290", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14079, + "estimated_input_tokens": 3520, + "estimated_eval_tokens": 7296 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14079, + "estimated_input_tokens": 3520, + "estimated_eval_tokens": 7296 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Four separate model-addition PRs (ViT NEPA, Molmo, Molmo2, and CTSM) that only look similar because they follow the same Transformers integration template. They touch different model families and code paths, so this is not a duplicate cluster.", + "confidence": 0.99, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: each item introduces a different model integration with distinct files, model classes, and documentation.", + "best_issue_reason": null, + "best_pr_reason": "No best PR for deduplication purposes; the PRs are unrelated changes despite sharing scaffold files like docs and auto-mapping updates.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "ViT NEPA and Molmo are different model additions; shared template files do not indicate the same bug or change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "ViT NEPA and Molmo2 are separate model integrations with different model codepaths and docs." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "ViT NEPA is a vision model addition, while CTSM is a time-series model addition; unrelated changes." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are distinct model families; overlap is limited to standard integration scaffolding." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM touch different model domains and concrete implementations." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are unrelated model additions with no shared underlying bug or fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43291-3", + "nodes": [ + "pull_request:43291", + "pull_request:43665", + "pull_request:44815" + ], + "soft_pairs": [ + "pull_request:43291|pull_request:43665", + "pull_request:43291|pull_request:44815", + "pull_request:43665|pull_request:44815" + ], + "prepared_review_unit_hash": "4c0e1f070d69dd463d44b1527021c081c9576db549a1e3fc18b704674c0c9aa6", + "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": "The three pull requests are not duplicates: one is a Whisper tokenizer/test fix, one is placeholder-like test edits in CLIP/ViT, and one is a substantive FP8 dequant/loading fix. All soft links should be rejected.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the three PRs target unrelated changes, so none should subsume the others.", + "best_issue_reason": null, + "best_pr_reason": "PR 44815 is the strongest standalone change: it has a coherent, substantive code fix across the loading/FP8 path, unlike the other two which are test-only or Whisper-specific.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Whisper tokenizer/timestamp decoding work is unrelated to CLIP/ViT test-assert edits; they do not fix the same bug or change." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "These touch different code paths and problems: Whisper decoding vs FP8 dequant/loading; no plausible single merged fix." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Test-only placeholder assertions in CLIP/ViT are unrelated to the FP8 dequant fix and should 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": 9, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-2", + "nodes": [ + "pull_request:43488", + "pull_request:43532" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:43532" + ], + "prepared_review_unit_hash": "5f07d366db8167e91ab1dc373367d9f2733f72d69d5d7718d668483dc598ac57", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4563, + "estimated_input_tokens": 1141, + "estimated_eval_tokens": 2538 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs, but they are not duplicates: #43488 is a small repo-bot/version-format test PR, while #43532 is a broader CI/workflow and testing-utils change. Shared test-file overlap is incidental.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43532 is the better representative of the cluster because it is broader and more substantive; #43488 is a narrow temporary bot-check PR focused on setup/version formatting.", + "best_issue_reason": null, + "best_pr_reason": "#43532 is the closest thing to a cluster anchor, but neither PR is a strong canonical duplicate target because both are marked '[don't merge]' and appear to be validation/infrastructure changes rather than a single fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Reject: the PRs touch different change sets and code paths. #43488 is mostly setup/version/dependency and a Vit test tweak; #43532 changes CI workflows, testing utilities, and notifications. They do not look like one mergeable fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43612-2", + "nodes": [ + "pull_request:43612", + "pull_request:43613" + ], + "soft_pairs": [ + "pull_request:43612|pull_request:43613" + ], + "prepared_review_unit_hash": "aa2386a531936782064adfd47659907515272d3f746895a160efa2ef57072cea", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6083, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate feature PRs that both add new promptable segmentation pipelines and share generic scaffolding, but they target different concepts, model families, and code paths. They are similar in shape, not the same underlying change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical duplicate PR: 43612 adds Promptable Concept Segmentation, while 43613 adds Promptable Visual Segmentation; they are distinct features with different implementation targets.", + "best_issue_reason": null, + "best_pr_reason": "If one representative is needed, 43613 is the broader/more comprehensive feature PR, but it is not a duplicate of 43612.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different pipelines and feature intents; shared docs/registry/test scaffolding is expected and does not indicate the same concrete bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 11, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43651-2", + "nodes": [ + "pull_request:43651", + "pull_request:43663" + ], + "soft_pairs": [ + "pull_request:43651|pull_request:43663" + ], + "prepared_review_unit_hash": "619e606e478dff7017bb2c882155b166d1a89d047f3549527ac73382aeec4a17", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4290, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4290, + "estimated_input_tokens": 1073, + "estimated_eval_tokens": 2402 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both items modify `src/transformers/trainer.py`, but they solve different problems: 43651 adds a gradient-accumulation loss-scaling hook, while 43663 extracts signature-column filtering for custom/PEFT trainers. Related area, not duplicate change.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "43651 is the stronger representative: it makes a concrete behavior change in `training_step` for loss scaling, whereas 43663 is a separate column-filtering override hook.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "They share the trainer subsystem but not the same underlying bug or code path: one changes GA loss normalization, the other changes signature-column extraction for data filtering. They would not naturally merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 12, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43656-2", + "nodes": [ + "pull_request:43656", + "pull_request:43842" + ], + "soft_pairs": [ + "pull_request:43656|pull_request:43842" + ], + "prepared_review_unit_hash": "c775f3857e2f95759b6dbf96c81476b6a77323daca53255217d3a56ac888a6c3", + "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": "These PRs touch the same file but fix different TypeAdapter-related problems: one is a typing/annotation cleanup in `serve.py`, the other specifically handles `pydantic` being absent. They are not duplicates and should not be merged into one PR.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: the two changes address different runtime/typing failure modes in the CLI, so neither subsumes the other.", + "best_issue_reason": null, + "best_pr_reason": "PR 43842 is the more narrowly targeted fix for the explicit `pydantic`-missing `TypeAdapter` NameError path; PR 43656 is a separate typing-related cleanup/fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Different underlying bugs: 43656 is a typing/future-annotations cleanup in `serve.py`, while 43842 fixes the `TypeAdapter` import/forward-reference failure when `pydantic` is not installed." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44024", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44066|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44722", + "pull_request:44068|pull_request:44116", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44116", + "pull_request:44018|pull_request:44086", + "pull_request:44018|pull_request:44085", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:44071|pull_request:44086", + "pull_request:43997|pull_request:44073", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44056|pull_request:44101", + "pull_request:44073|pull_request:44161", + "pull_request:44059|pull_request:44068", + "pull_request:44018|pull_request:44059", + "pull_request:44101|pull_request:44161", + "pull_request:43997|pull_request:44017", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44018", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44010|pull_request:44073", + "pull_request:44018|pull_request:44129", + "pull_request:43997|pull_request:44074", + "pull_request:43997|pull_request:44129", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154", + "pull_request:44024|pull_request:44076" + ], + "prepared_review_unit_hash": "4531250bdf1eee563ec9f94a9846696eedbc3633cd8250707d635a1d0a43d825", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84505, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 72, + "serialized_chars": 76938, + "estimated_input_tokens": 19235, + "estimated_eval_tokens": 38726 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of independent model-by-model refactors to the new output-tracing/capture_outputs pattern, centered around the shared tracking issue #43979. A few pairs are true near-duplicates within the same model family (notably GPT-Neo and GPT-J/CodeGen), but most cross-model pairs are not the same concrete change.", + "confidence": 0.92, + "canonical_issue_reason": "Issue #43979 is the common umbrella tracker repeatedly referenced by these PRs and appears to be the canonical coordination point for the standardized output-tracing refactor work.", + "canonical_pr_reason": "PR #44722 is the strongest representative: it is a later, more complete GPT-J/CodeGen output-tracing refactor with the same standardized-decorator direction and explicit issue linkage.", + "best_issue_reason": "#43979 is the best global issue anchor because it is explicitly targeted by many of the PRs in this cluster and captures the shared refactor theme.", + "best_pr_reason": "#44722 is the best global PR representative because it clearly implements the standardized output-tracing change in the GPT-J/CodeGen path and appears to be a mature version of that specific refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different models and code paths (CVT/FNet vs GPT-J); same broad tracing theme, but not the same concrete change." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different models (CVT/FNet vs DeBERTa) and unrelated implementation paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both are GPT-J/CodeGen output-tracing refactors with overlapping intent and essentially the same decorator-based change pattern." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "Different families (RegNet/ResNet/RT-DETR vs EfficientNet); same umbrella refactor theme only." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet vs GPT-J/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "GPT-J/CodeGen vs EfficientNet are different model implementations." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 vs DeBERTa; not the same underlying bug/change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen refactor vs MGP-STR refactor; different model code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen vs MPT are different concrete changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both target GPT-Neo output tracing in the same files and look like alternate versions of the same refactor." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are separate model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different code paths despite similar refactor style." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet/RT-DETR backbone refactor vs GPT-J/CodeGen refactor are unrelated." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR vs GPT-J/CodeGen are different model families." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet-based output tracing and GPT-J output tracing are distinct changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are different models and code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet vs MPT; same theme, different implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different model-specific refactors." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert are unrelated concrete changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT vs GPT-J/CodeGen are different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert are different model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are not the same change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different model-specific refactors." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo vs MGP-STR are unrelated concrete code-path changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44086", + "accept": false, + "reason": "MPT vs MGP-STR are different models and fixes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 vs MGP-STR are different concrete changes." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J vs MGP-STR are different model families and code paths." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT vs Flaubert/XLM are different model implementations." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are separate refactors, not one mergeable change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo vs MPT are different model code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "Segformer vs GPT-J/CodeGen are unrelated concrete changes." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "Segformer vs LongT5 are different model-specific refactors." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44101", + "accept": false, + "reason": "VisualBert vs Flaubert/XLM are different concrete changes." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-2 vs GPT-Neo are separate model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44059", + "accept": false, + "reason": "GPT-Neo vs GPT-2 are different code paths." + }, + { + "left": "pull_request:44101", + "right": "pull_request:44161", + "accept": false, + "reason": "Flaubert/XLM vs LongT5 are unrelated model refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44017", + "accept": false, + "reason": "RegNet vs Segformer are different model families." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44056", + "accept": false, + "reason": "RegNet vs MPNet are different concrete changes." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44018", + "accept": false, + "reason": "RegNet vs GPT-Neo are unrelated model-specific refactors." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44074", + "accept": false, + "reason": "RegNet vs TextNet are different code paths." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44161", + "accept": false, + "reason": "RegNet vs LongT5 are unrelated changes." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44129", + "accept": false, + "reason": "MPT vs SpeechT5 are different model implementations." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44071", + "accept": false, + "reason": "SqueezeBert vs MPT are not the same underlying fix." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44073", + "accept": false, + "reason": "SqueezeBert vs VisualBert are different model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-Neo vs SpeechT5 are different code paths." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44018", + "accept": false, + "reason": "SqueezeBert vs GPT-Neo are unrelated model refactors." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44161", + "accept": false, + "reason": "CVT/FNet vs LongT5 are different model implementations." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44017", + "accept": false, + "reason": "CVT/FNet vs Segformer are different concrete changes." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44044", + "accept": false, + "reason": "SqueezeBert vs DeBERTa are separate model-specific refactors." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44074", + "accept": false, + "reason": "DeBERTa vs TextNet are different model code paths." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet and ImageGPT are different models; same general output-tracing theme only." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Both are the same GPT-J/CodeGen standardized output-tracing refactor with heavily overlapping intent and files." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both appear to implement the same GPT-J output-tracing change and could plausibly be merged into one PR." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J vs SpeechT5 are different model families." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet vs RegNet/ResNet/RT-DETR are different code paths." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet vs SpeechT5 are unrelated model-specific changes." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa vs SpeechT5 are different model implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa vs VITS are different concrete changes." + }, + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "FocalNet vs ImageGPT are different models; broad refactor similarity is not enough to treat them as duplicates." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is well grounded in the packet: #43979 is clearly a repeated issue target across the cluster, and #44722 is a reasonable representative for the GPT-J/CodeGen subgroup based on its later date, shared files, and explicit issue link. The soft-edge decisions are mostly conservative cross-model negatives, while the accepted pairs are within the same model family and look mergeable as alternate versions of the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 27, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44129" + ], + "soft_pairs": [ + "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": "79379a6f038f706cb75b22b230c6def9b84d95b29bd4fa255bdf329eda9eedf2", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 77, + "serialized_chars": 84505, + "estimated_input_tokens": 21127, + "estimated_eval_tokens": 42510 + }, + "budget": { + "node_count": 6, + "item_count": 6, + "soft_pair_count": 5, + "serialized_chars": 13067, + "estimated_input_tokens": 3267, + "estimated_eval_tokens": 6790 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are thematically similar PRs for model-by-model migration to standardized output tracing, but they are not duplicates of the same fix/change. Each one targets a different architecture and code path.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44129 is the best cluster anchor: it has an explicit issue target, a clear refactor scope, and is representative of the standardized output-capture migration pattern.", + "best_issue_reason": null, + "best_pr_reason": "PR 44129 is the most suitable representative because it is self-contained, explicitly linked to an issue, and clearly scoped to one model's output-tracing refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "Same refactor theme, but different models and different code paths; not the same underlying change." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "Both modernize output tracing, but they touch different model implementations and are separate migrations." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "Different model-specific refactors; too broad to treat as one duplicate change." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "Both are output-tracing cleanups, but for distinct architectures and forward methods, so not duplicates." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "Shared standardized-output motivation, but they fix separate model implementations and should 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": 15, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44028", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "eb6466aa587c221c1979247d16621b7ec521a86b732ed4e300a1e4a5a9abedcf", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 40, + "serialized_chars": 40173, + "estimated_input_tokens": 10044, + "estimated_eval_tokens": 20344 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs share a common theme\u2014model-specific refactors to output tracing / tuple-return handling\u2014but they touch different model code paths and are not duplicate fixes. I would not merge any of the soft-edge pairs as the same underlying change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "PR 44025 is the clearest representative of the cluster because it applies the output-tracing refactor in a focused way across two closely related files, but it is still not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families and separate forward-path refactors; same broad pattern, not the same change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different models and distinct code paths; both refactor output handling but are not mergeable as one fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Unrelated model implementations; only the tracing refactor pattern matches." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Different architectures and files; this is not the same underlying bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Same output-tracing theme, but the PRs target different model stacks and code paths." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "Separate models with similar refactoring style, not the same concrete fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model code paths; these are parallel refactors, not duplicates." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families and outputs; no shared underlying bug." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Both change output-tracing behavior, but for unrelated model wrappers." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different encoder-decoder model and separate refactor scope." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "Distinct models; same refactoring motif only." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "No shared concrete code path despite similar output-tracing cleanup." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "Different model implementations; not one fix split across PRs." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Related only by refactor style, not by the same bug or code path." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "Separate model code paths with similar API cleanup, not a duplicate change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "Different models and files; same broad subsystem but not same change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "These are independent model-specific refactors, not one mergeable PR." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model families; no evidence they fix the same concrete problem." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "Separate output-tracing refactors in unrelated code paths." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44028", + "accept": false, + "reason": "Falcon/Mamba vs SuperPoint: unrelated implementations and changes." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Different model classes and distinct call sites; not the same underlying fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "Both are refactors around model outputs, but for different models and code paths." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "Different models; similar intent but not a shared concrete bug." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "Distinct model implementations and separate refactor scopes." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "Only the general output-tracing theme overlaps; the code paths are unrelated." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "Different model families; these are parallel refactors, not duplicate fixes." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "Separate encoder/decoder wrappers and different output logic." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "Different models and implementations; no shared concrete bug/change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "Same refactor pattern, but not the same model or code path." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "Unrelated model code; not mergeable as one PR." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model wrappers and separate refactor targets." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "Same broad refactor theme only; no identical underlying issue." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "Different model families and code paths." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "Distinct models; similar output-handling cleanup is not enough to merge." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "Encoder-decoder wrapper vs keypoint model: unrelated changes." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "Different model systems; same theme, not same fix." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "No shared code path or bug; only similar refactoring style." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated; not a duplicate." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "Different models and output semantics; not the same change." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR address different architectures and code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 16, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44662-3", + "nodes": [ + "pull_request:44662", + "pull_request:45075", + "pull_request:45401" + ], + "soft_pairs": [ + "pull_request:44662|pull_request:45401", + "pull_request:44662|pull_request:45075", + "pull_request:45075|pull_request:45401" + ], + "prepared_review_unit_hash": "f82019475c3d468ec8a439a580582ebbfa206281bf99de8b15af9aa18eb6585e", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10910, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10910, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three PRs only look similar at the boilerplate level: they add different models in different modalities (vision-language, OCR, and TTS) with distinct code paths and files. They are not duplicates of one another.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "No single PR is a suitable representative because each change introduces a different model family and implementation path; they should remain separate.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL adds a vision-language model, while Voxtral TTS adds a text-to-speech model; different modalities and concrete implementations, so not the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are separate model additions with different architectures and targets; shared docs/auto-registration files are boilerplate, not duplicate evidence." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 is an OCR model, while Voxtral TTS is a speech synthesis model; they do not fix or add the same underlying code path." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 17, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44979-2", + "nodes": [ + "pull_request:44979", + "pull_request:45363" + ], + "soft_pairs": [ + "pull_request:44979|pull_request:45363" + ], + "prepared_review_unit_hash": "46b5def8d7ad9b9a6fa05b7307450383d1c1f2f4afc8847777ab8cd108eb81e9", + "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 PRs are thematically related to fusion, but they implement different things: #44979 introduces a new generic Module Fusion API, while #45363 adds KernelConfig-based n-to-1 kernel fusion wiring and an example. They are not the same underlying change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45363 is the more concrete, end-user-facing fusion feature PR: it threads KernelConfig through model loading and adds integration code and an example. #44979 is foundational API work for module fusion, not the same change.", + "best_issue_reason": null, + "best_pr_reason": "#45363 best represents the cluster because it has the clearest specific behavior change and broader integration footprint, but it should not be merged as a duplicate of #44979.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion infrastructure, but not the same code-path problem: #44979 adds a new module-fusion API, while #45363 implements KernelConfig-driven n-to-1 fusion across loading/integration code. They could not plausibly be one PR without changing the scope substantially." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45086-2", + "nodes": [ + "pull_request:45086", + "pull_request:45317" + ], + "soft_pairs": [ + "pull_request:45086|pull_request:45317" + ], + "prepared_review_unit_hash": "3d1bf6d211963c912c8755860cca402365a7f39513b6425491cf3922575c082c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests target the same Mistral regex patch bug in `tokenization_utils_tokenizers.py` and make the same fix; the later PR adds tests and looks like the stronger canonical choice.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45317 is the better canonical PR because it applies the same code fix as #45086 and also includes test coverage, making it the more complete change set.", + "best_issue_reason": null, + "best_pr_reason": "PR #45317 is the best overall PR candidate because it addresses the same concrete AttributeError path as #45086 while adding validation in tests, so it is the most merge-ready representative of the fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Accept: both PRs fix the same `_patch_mistral_regex` AttributeError in the same file, with the same underlying code-path change; #45317 is essentially a superset with added tests." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 19, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45115-2", + "nodes": [ + "pull_request:45115", + "pull_request:45569" + ], + "soft_pairs": [ + "pull_request:45115|pull_request:45569" + ], + "prepared_review_unit_hash": "7edc49898e5d011e5ac2c895c87fc28cc76f7ac79d79cd7e4d51aa5a21e7d65f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6066, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two PRs overlap on NemotronH internals, but they target different changes: one refactors NemotronH conversion/model inheritance toward GraniteMoeHybrid compatibility, while the other splits NemotronH into separate dense/sparse model families and updates docs/tests. They are related, but not the same underlying fix/change set.", + "confidence": 0.87, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45569 is the broader, more complete NemotronH family change: it adds the new dense/sparse model variants, wiring, docs, and tests, rather than only a conversion/inheritance refactor.", + "best_issue_reason": null, + "best_pr_reason": "PR #45569 is the best representative of the cluster because it covers the main architectural reshaping of NemotronH into dedicated variants and includes the associated integration work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Both touch NemotronH code, but #45115 is a focused GraniteMoeHybrid-style refactor/conversion mapping update, while #45569 creates separate dense/sparse NemotronH models and updates docs/tests. They are not the same concrete bug or change and would not plausibly merge into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 20, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45332-2", + "nodes": [ + "pull_request:45332", + "pull_request:45333" + ], + "soft_pairs": [ + "pull_request:45332|pull_request:45333" + ], + "prepared_review_unit_hash": "bf090aa1584fc20fb417574f8828d68dcc9ded679ebd517a15dea60691572a5b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5398, + "estimated_input_tokens": 1350, + "estimated_eval_tokens": 2956 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are related feature PRs for heterogeneous-model support, but they are not duplicates: #45333 introduces heterogeneous config primitives, while #45332 adds broader cache/modeling integration and GPT-OSS support.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "If a single representative is needed, #45332 is the broader end-to-end heterogeneous model support PR; #45333 is the narrower config-foundation change it builds on.", + "best_issue_reason": null, + "best_pr_reason": "#45332 is the better global representative for the cluster because it covers the full user-facing heterogeneous-model path, whereas #45333 is only the configuration layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "They share heterogeneity infrastructure, but they are different change sets: #45333 adds per-layer config support, while #45332 adds model/cache behavior and model-specific integration. They are complementary, not the same concrete PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45415-2", + "nodes": [ + "pull_request:45415", + "pull_request:45425" + ], + "soft_pairs": [ + "pull_request:45415|pull_request:45425" + ], + "prepared_review_unit_hash": "b1f01a5a92269bfb47df284710a1454758891e7f5bc3d6c7677ec07f5f85e43d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5513, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5513, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs are typing-related, but they target different changes: 45415 is a broad repo-wide type-checking sweep with config suppressions, while 45425 adds specific typing protocols/helpers for internals. They are not duplicates.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "No true duplicate canonical PR: 45415 is a broad type-checking enablement sweep; 45425 is a narrower typing-infra update. They do not address the same concrete change.", + "best_issue_reason": null, + "best_pr_reason": "45425 is the better representative because it makes a focused code-level typing change in shared helper types, whereas 45415 is mostly an expansive sweep/configuration change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Shared typing files and similar theme aren't enough: 45415 is a large type-checking pass across many modules, while 45425 adds specific typing protocols and helper aliases for modeling/utilities. They are different underlying changes and wouldn't plausibly be merged as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 22, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45513-2", + "nodes": [ + "pull_request:45513", + "pull_request:46084" + ], + "soft_pairs": [ + "pull_request:45513|pull_request:46084" + ], + "prepared_review_unit_hash": "e77e9e03106f298308b3a5c138047666f30e3bfb039fbc2179db0407007ca1ef", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4857, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4857, + "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 both cache-related PRs, but they fix different model families and different code paths. The Mamba2 PR is a focused seq_len>1 use_cache bug fix; the Qwen3.5/Olmo hybrid PR is a broader multi-model linear-attention cached-forward fix. They should not be clustered as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:46084 is the better canonical PR: it is a narrow, explicit fix for Mamba2 use_cache when seq_len > 1, with a direct issue reference (#46032) and a focused diff. The other PR spans multiple models and a different attention path, making it less representative of a single underlying change.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:46084 is the strongest representative of a concrete bug fix because it targets one code path, one model family, and one specific failure mode. pull_request:45513 is broader and less suitable as the global exemplar for this cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Different underlying fixes: 45513 changes cached multi-token forward in Qwen3.5/Olmo hybrid linear attention, while 46084 fixes Mamba2 cuda_kernels_forward for use_cache with seq_len > 1. Similar cache theme, but not the same bug or mergeable into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45548-2", + "nodes": [ + "pull_request:45548", + "pull_request:45662" + ], + "soft_pairs": [ + "pull_request:45548|pull_request:45662" + ], + "prepared_review_unit_hash": "ff485957f394b1fe05227547bf845b9d5089a5100fe98f6c3751c65e49ec9922", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4508, + "estimated_input_tokens": 1127, + "estimated_eval_tokens": 2510 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two EP-related PRs, but they fix different loading bugs: one targets accelerate/ZeRO-3 serialization and distributed_config handling, the other targets FSDP2/rank-0 broadcast overwriting expert parameters.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45662 is the stronger representative of the cluster: it fixes a concrete expert-parameter overwrite path in the model-loading code and spans the relevant loading/integration layers.", + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the best standalone candidate because its bug description is clearer and the fix is more directly tied to a specific incorrect code path; PR 45548 is narrower and addresses a separate accelerate-launch/ZeRO-3 issue.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Both concern expert parallelism, but they fix different problems: 45548 is about accelerate-launch/DeepSpeed ZeRO-3 loading and config serialization, while 45662 is about FSDP2/rank-0 broadcast silently overwriting experts. The code paths and failure modes are distinct." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45639-2", + "nodes": [ + "pull_request:45639", + "pull_request:45645" + ], + "soft_pairs": [ + "pull_request:45639|pull_request:45645" + ], + "prepared_review_unit_hash": "abe5f3b567add0957812a6c2d016dcee23afa71a1f526b76f1f58cb7ae1b1b7c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs target the same xdist collision problem around `captured_info` output from `testing_utils.py`; #45645 is the broader follow-up that includes the core fix plus CI log aggregation, while #45639 is the narrower subset.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45645 is the more complete fix: it includes the xdist-safe per-worker output change in `src/transformers/testing_utils.py` and also updates CI to collect multiple `captured_info*.txt` files, so it subsumes the narrower PR.", + "best_issue_reason": null, + "best_pr_reason": "PR #45645 is the best representative because it addresses the full end-to-end behavior change for xdist-safe debug logs and preserves CI visibility, not just the library-side write-path fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Both PRs fix the same underlying `captured_info` xdist collision in `testing_utils.py`; #45645 extends the same fix with the necessary CI workflow adaptation, so they could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45683-2", + "nodes": [ + "pull_request:45683", + "pull_request:45734" + ], + "soft_pairs": [ + "pull_request:45683|pull_request:45734" + ], + "prepared_review_unit_hash": "eb709b85fdf0aaa42b264faf678be0edc1127137b5c90af86da076f2b207e68b", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4466, + "estimated_input_tokens": 1117, + "estimated_eval_tokens": 2490 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4466, + "estimated_input_tokens": 1117, + "estimated_eval_tokens": 2490 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related but not duplicates: one excludes audio submodules from quantization, while the other makes auto-detected skip keys additive when users pass skip_modules. They touch the same quantizer path and share an issue target, but they fix different underlying bugs.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR for a duplicate cluster: the two PRs address separate behaviors in the same helper, not the same change.", + "best_issue_reason": null, + "best_pr_reason": "45734 is the better representative of the cluster because it fixes the more general control-flow bug in get_modules_to_not_convert and affects any user-supplied skip_modules case.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45683", + "right": "pull_request:45734", + "accept": false, + "reason": "Shared files and issue target are not enough here: 45683 skips audio tower/embed_audio modules to avoid uint8 crashes, while 45734 changes skip_modules handling so default skips remain additive. Different bugs, different fixes." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45737-2", + "nodes": [ + "pull_request:45737", + "pull_request:45738" + ], + "soft_pairs": [ + "pull_request:45737|pull_request:45738" + ], + "prepared_review_unit_hash": "cc2ade73a49ec6a8883a7a24c433988645588bcd049e8aad2bce56b1b24daa1c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4131, + "estimated_input_tokens": 1033, + "estimated_eval_tokens": 2322 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same MusicgenMelody cache initialization bug in `forward()`: replacing `EncoderDecoderCache(DynamicCache, DynamicCache)` with a single `DynamicCache`. PR #45737 is the more complete duplicate because it bundles the fix with a regression test, while #45738 is the fix-only variant.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45737 is the best canonical PR because it contains the same code fix as #45738 plus a regression test, making it the most complete representation of the bug fix.", + "best_issue_reason": null, + "best_pr_reason": "PR #45737 is the strongest overall candidate: it fixes the concrete cache bug and adds a targeted regression test, whereas #45738 only changes the implementation.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45737", + "right": "pull_request:45738", + "accept": true, + "reason": "Same underlying code-path bug in `musicgen_melody` cache setup; the diffs match on the core fix and the test-only addition in #45737 could plausibly live in the same PR as #45738." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The assessment is grounded in the packet: both PRs make the same `musicgen_melody` cache initialization change, and #45737 only adds a regression test on top of that fix. The soft-edge accept is conservative enough because the diffs are mergeable into one PR for the same bugfix." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 27, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-46069-2", + "nodes": [ + "pull_request:46069", + "pull_request:46073" + ], + "soft_pairs": [ + "pull_request:46069|pull_request:46073" + ], + "prepared_review_unit_hash": "e3b94c88cfe283bb4ec42d74ec841b5662d6d4e5b614767f6302310ab811870f", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4282, + "estimated_input_tokens": 1071, + "estimated_eval_tokens": 2398 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4282, + "estimated_input_tokens": 1071, + "estimated_eval_tokens": 2398 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are not duplicates: both PRs add `attn_implementation` dispatch support, but they target different model implementations (`ShieldGemma2` vs `CTRL`) and modify different code paths/files.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the changes are model-specific and do not appear mergeable into one patch or fix the same concrete code-path problem.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a better duplicate representative because they address separate models; if forced, `#46069` is slightly more self-contained, but it should not subsume `#46073`.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46069", + "right": "pull_request:46073", + "accept": false, + "reason": "Both are about attention dispatch support, but they touch different model backends and distinct attention implementations. They are related feature work, not the same underlying bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + } + ] +} diff --git a/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/manifest.json b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..51527b664d9d31618047f509a30ec13cee9755d5 --- /dev/null +++ b/snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260520t000134z", + "artifacts": { + "hybrid": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-20T00:12:12Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260520T000134Z", + "variant": "hybrid" +} diff --git a/snapshots/20260520T000134Z/manifest.json b/snapshots/20260520T000134Z/manifest.json index e7f08473837fdabe77fab28cb03bf79db12d1fb4..f8bf3d44337bf02389a0ed2b96a57ecbb321805e 100644 --- a/snapshots/20260520T000134Z/manifest.json +++ b/snapshots/20260520T000134Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 185 }, "extracted_at": "2026-05-20T00:01:34Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260520t000134z", + "runs": { + "hybrid-model-20260520t000134z": { + "analysis_id": "hybrid-model-20260520t000134z", + "artifacts": { + "hybrid": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260520T000134Z/analysis-runs/hybrid-model-20260520t000134z/manifest.json", + "model": null, + "published_at": "2026-05-20T00:12:12Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260520T000134Z", "watermark": {