diff --git a/analysis/current/analysis-report-hybrid.json b/analysis/current/analysis-report-hybrid.json index d8fc9b5f25a0cada83ff05f32da89548da20cc58..151546ff5202ec2d841d6612d8a326aaed30911a 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": "20260530T180032Z", - "generated_at": "2026-05-30T18:04:56Z", + "snapshot_id": "20260531T000035Z", + "generated_at": "2026-05-31T00:04:30Z", "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 b7c2922c1a8c170455f4372731c6bc3bbc4aa8b9..86c98a9bec8f01283af0ca3e3c03d08ee87a2e02 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": "20260530T180032Z", - "generated_at": "2026-05-30T18:04:56Z", + "snapshot_id": "20260531T000035Z", + "generated_at": "2026-05-31T00:04:30Z", "model": "gpt-5.4-mini?service_tier=flex", "reviews": [ { @@ -13389,8 +13389,8 @@ "review_unit_count": 51, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-10000-437", "nodes": [ @@ -14013,8 +14013,8 @@ "review_unit_count": 51, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-10000-437", "nodes": [ @@ -14346,8 +14346,8 @@ "review_unit_count": 51, "status": "reviewed", "reason": null, - "source": "llm", - "cache_hit": false, + "source": "cache", + "cache_hit": true, "model": "gpt-5.4-mini?service_tier=flex", "cluster_id": "cluster-10000-437", "nodes": [ @@ -17983,160 +17983,160 @@ "pull_request:46048|pull_request:46268", "pull_request:43251|pull_request:43254" ], - "prepared_review_unit_hash": "9e852c7b0727c85710d7b3f2a7b9ce6eb9a55846191989be8de06cf1b2cf748f", + "prepared_review_unit_hash": "597bbbe0dbb0e70ed4f90ee90f7070279d45bba491ba99ec3609ef55def200f1", "component_budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 20, - "serialized_chars": 40300, - "estimated_input_tokens": 10075, - "estimated_eval_tokens": 20406 + "serialized_chars": 40304, + "estimated_input_tokens": 10076, + "estimated_eval_tokens": 20408 }, "budget": { "node_count": 15, "item_count": 15, "soft_pair_count": 20, - "serialized_chars": 40300, - "estimated_input_tokens": 10075, - "estimated_eval_tokens": 20406 + "serialized_chars": 40304, + "estimated_input_tokens": 10076, + "estimated_eval_tokens": 20408 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Only one soft duplicate looks real: the two `fixed_cross_entropy` PRs (43251 and 43254). The rest are unrelated model additions, refactors, docs, or kernel routing changes that share broad subsystems but not the same concrete bug/change.", - "confidence": 0.93, + "summary": "This cluster is mostly heterogeneous: unrelated model additions, tokenizer/API tweaks, export tests, docs, and kernel-routing changes. Only one soft edge looks like a true duplicate/subsumable change: the two fixed_cross_entropy kwargs patches (43251 and 43254).", + "confidence": 0.9, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43251 is the cleaner representative of the duplicate pair: it has the explicit issue target (43240) and implements the same `fixed_cross_entropy` kwargs support as 43254.", + "canonical_pr_reason": "No cluster-wide canonical PR: the items are mostly unrelated. The only near-duplicate pair is 43251/43254, and 43251 is the better representative because it is explicitly tied to issue #43240 and presents the more direct fix.", "best_issue_reason": null, - "best_pr_reason": "PR 43251 is the strongest overall representative of the cluster because it is the only clear duplicate-fix pair, is tied to a tracked issue, and fixes a specific code path in `loss_utils.py`.", + "best_pr_reason": "43251 is the best PR to keep for the loss-kwargs bug because it directly targets the tracked issue and is the stronger representative of the 43251/43254 duplicate pair.", "soft_edge_verdicts": [ { "left": "pull_request:39895", "right": "pull_request:43424", "accept": false, - "reason": "Unrelated work: VideoPrism model integration vs ExecuTorch dynamic-shape export test." + "reason": "VideoPrism model onboarding is unrelated to an executorch dynamic-shape export test." }, { "left": "pull_request:41855", "right": "pull_request:43424", "accept": false, - "reason": "Different bugs/features: Mistral tokenizer methods vs ExecuTorch export coverage." + "reason": "Mistral tokenizer method additions and executorch export testing address different code paths and bugs." }, { "left": "pull_request:41855", "right": "pull_request:43823", "accept": false, - "reason": "Tokenizer API fix for MistralCommon is unrelated to adding MobileLLM." + "reason": "Tokenizer API fixes are unrelated to adding the MobileLLM model." }, { "left": "pull_request:42668", "right": "pull_request:43823", "accept": false, - "reason": "Processor auto-loading robustness vs new MobileLLM model implementation; same area only broadly." + "reason": "Processor/pretrained auto-loading robustness is unrelated to the MobileLLM model implementation." }, { "left": "pull_request:43251", "right": "pull_request:43823", "accept": false, - "reason": "Loss-function kwargs fix is unrelated to MobileLLM model addition." + "reason": "A cross-entropy kwargs fix is unrelated to adding MobileLLM." }, { "left": "pull_request:43251", "right": "pull_request:44827", "accept": false, - "reason": "Different concrete changes: cross-entropy kwargs support vs Mistral4 test/debug changes." + "reason": "Loss utility kwargs handling is unrelated to Mistral4 test fixes." }, { "left": "pull_request:43424", "right": "pull_request:44827", "accept": false, - "reason": "ExecuTorch dynamic-shape export test and Mistral4 test fixes are unrelated." + "reason": "Executorch dynamic-shape export testing is unrelated to Mistral4 test fixes." }, { "left": "pull_request:43424", "right": "pull_request:43823", "accept": false, - "reason": "No shared underlying bug; export test vs model addition." + "reason": "Executorch export tests and MobileLLM model addition are different changes." }, { "left": "pull_request:43823", "right": "pull_request:45655", "accept": false, - "reason": "MobileLLM model addition is unrelated to `cls.config` resolution order fix." + "reason": "Adding MobileLLM is unrelated to the config-resolution ordering fix." }, { "left": "pull_request:43823", "right": "pull_request:43995", "accept": false, - "reason": "Different scope: new MobileLLM model vs Falcon output-capture refactor." + "reason": "MobileLLM model addition and Falcon output-interface refactoring do not fix the same problem." }, { "left": "pull_request:43995", "right": "pull_request:45213", "accept": false, - "reason": "Falcon model refactor is not the same change as adding a model-creation skill." + "reason": "Falcon refactoring and the model-creation skill are unrelated changes." }, { "left": "pull_request:43995", "right": "pull_request:44827", "accept": false, - "reason": "Falcon standardized output interface refactor and Mistral4 test fixes are different code paths." + "reason": "Falcon output-capturing refactor and Mistral4 test fixes are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45170", "accept": false, - "reason": "Mistral4 test fix vs CLIP-family `layrnorm`/`layernorm` rename; unrelated." + "reason": "Mistral4 test fixes are unrelated to the layrnorm-to-layernorm typo/renaming pass." }, { "left": "pull_request:44827", "right": "pull_request:46267", "accept": false, - "reason": "Mistral4 tests and chat parsing updates are distinct changes." + "reason": "Mistral4 test fixes and serve chat parsing updates are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:46048", "accept": false, - "reason": "Mistral4 test work is unrelated to adding the TDT loss kernel." + "reason": "Mistral4 test fixes are unrelated to adding the TDT loss kernel." }, { "left": "pull_request:44827", "right": "pull_request:45655", "accept": false, - "reason": "Mistral4 tests vs config-resolution-order fix; different problems." + "reason": "Mistral4 test fixes and config-resolution ordering changes are unrelated." }, { "left": "pull_request:44827", "right": "pull_request:45213", "accept": false, - "reason": "Test fixes for Mistral4 do not overlap with the model creation skill PR." + "reason": "Mistral4 test fixes are unrelated to the model-creation skill PR." }, { "left": "pull_request:43823", "right": "pull_request:45213", "accept": false, - "reason": "New MobileLLM model code is unrelated to the model-creation skill scaffolding PR." + "reason": "MobileLLM model addition is unrelated to the model-creation skill." }, { "left": "pull_request:46048", "right": "pull_request:46268", "accept": false, - "reason": "Both touch hub-kernel plumbing, but they add different kernel routes for different purposes and are not the same concrete change." + "reason": "Both touch hub-kernel plumbing, but one adds TDT loss kernel support while the other adds ROCm AITER routing; they are different kernels and different fixes." }, { "left": "pull_request:43251", "right": "pull_request:43254", "accept": true, - "reason": "Near-duplicate `fixed_cross_entropy` fixes: both add support for passing kwargs like `weight` and `label_smoothing` into `nn.functional.cross_entropy`." + "reason": "Both PRs patch fixed_cross_entropy to forward supported nn.functional.cross_entropy kwargs for the same underlying issue #43240; one is a narrower variant of the same fix and could plausibly be merged into one PR." } ] }, "evaluator_result": { "accept": true, - "feedback": "The summary is grounded in the packet and stays conservative. The only accepted soft pair, 43251/43254, is a genuine duplicate-fix match: both touch `src/transformers/loss/loss_utils.py`, both add `weight`/`label_smoothing` support to `fixed_cross_entropy`, and both point to the same tracked issue `43240`. The remaining pair rejections are appropriately cautious and do not overclaim shared bug identity; they read as broad subsystem overlap rather than mergeable duplicate fixes." + "feedback": "The summary is grounded in the packet and stays conservative. The only true near-duplicate is 43251/43254, and the mergeability claim is supported by the shared file, shared issue target, and overlapping cross-entropy kwargs fix. The other soft-edge rejections are appropriately cautious and not overstated." }, "evaluator_used": true, "retried": false, @@ -18163,12 +18163,12 @@ "soft_pairs": [ "pull_request:40546|pull_request:42781" ], - "prepared_review_unit_hash": "3ee06d26a25f4313031748b5ff10095b1b7080bc67e9d773f6dd127fbd4a47ac", + "prepared_review_unit_hash": "e96dc70583d4c3bcf638e9beac0db2e47198196eca70291a44361bcd14486aaf", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7226, + "serialized_chars": 7225, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -18176,7 +18176,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 7226, + "serialized_chars": 7225, "estimated_input_tokens": 1807, "estimated_eval_tokens": 3870 }, @@ -18185,18 +18185,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related VibeVoice PRs, but they are not duplicates: one adds the base VibeVoice model integration, while the other adds a separate realtime/acoustic-tokenizer extension.", - "confidence": 0.94, + "summary": "Both items are related VibeVoice model integrations, but they are not the same PR: one is the base VibeVoice implementation, the other adds VibeVoice Realtime and an acoustic tokenizer path. The overlap is expected from shared model scaffolding, not a duplicate change.", + "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "No clear canonical duplicate PR: the scopes differ, with 40546 implementing base VibeVoice and 42781 targeting realtime support plus acoustic-tokenizer pieces.", + "canonical_pr_reason": "PR 40546 is the broader foundational VibeVoice implementation with substantial review activity; it looks like the main integration rather than the specialized realtime follow-up.", "best_issue_reason": null, - "best_pr_reason": "PR 40546 is the better representative of the cluster because it is the broader, more mature base VibeVoice implementation and has substantially more review activity.", + "best_pr_reason": "PR 40546 is the best representative of the cluster because it is the primary VibeVoice model bring-up and covers the core code paths shared by later VibeVoice work.", "soft_edge_verdicts": [ { "left": "pull_request:40546", "right": "pull_request:42781", "accept": false, - "reason": "Different underlying changes: 40546 is the core VibeVoice model integration, while 42781 adds realtime-specific functionality and an acoustic tokenizer. They would not plausibly merge as one duplicate PR." + "reason": "Shared filenames reflect common VibeVoice scaffolding, but 40546 implements the base model while 42781 adds Realtime/acoustic-tokenizer functionality; these are different concrete changes and should not be merged as duplicates." } ] }, @@ -18226,12 +18226,12 @@ "soft_pairs": [ "pull_request:40755|pull_request:41224" ], - "prepared_review_unit_hash": "d685cfbe7c23908a40915b365f18350d823114d494056cdb669c0579aaf4b54c", + "prepared_review_unit_hash": "d12e8776c103ae2f6f70c96c4360f50cde16416ee4b8fd3620436ad6542762b0", "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 }, @@ -18239,7 +18239,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4675, + "serialized_chars": 4676, "estimated_input_tokens": 1169, "estimated_eval_tokens": 2594 }, @@ -18248,18 +18248,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are unrelated: one adds TimesFM covariate forecasting support, the other adds DINOv3 image-classification support. They do not appear to fix the same code-path problem or belong to a single duplicate cluster.", - "confidence": 0.99, + "summary": "The two pull requests are unrelated model-feature additions: one adds covariate forecasting to TimesFM, the other adds image classification support for DINOv3ViT. They do not appear to fix the same bug or implement the same change.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "No canonical PR: these PRs target different models, different code paths, and different user-facing capabilities, so they are not duplicates of one another.", "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "Neither PR is a good global canonical representative for this cluster because the cluster is not a duplicate set; the changes are unrelated.", "soft_edge_verdicts": [ { "left": "pull_request:40755", "right": "pull_request:41224", "accept": false, - "reason": "Different models and different feature areas (TimesFM covariate forecasting vs DINOv3 classification); no shared underlying bug/change, so they should not be merged as duplicates." + "reason": "Different features in different model families (TimesFM covariates vs. DINOv3 image classification); no shared bug or mergeable single fix." } ] }, @@ -18354,7 +18354,7 @@ "pull_request:41797|pull_request:45186", "pull_request:45186|pull_request:45630" ], - "prepared_review_unit_hash": "fbb30c4c0f8907c692a6e3b53f4daf8c63ae4b22a85be405d1850b9bc74ddbe2", + "prepared_review_unit_hash": "c4d970101d2c9d8215176a3dd84f6829411405a359372a39bef79fc285918a36", "component_budget": { "node_count": 3, "item_count": 3, @@ -18376,24 +18376,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are separate model-addition PRs for DeepSeek OCR, Isaac, and Kimi2-6. They share Transformers integration scaffolding, but each targets a different model and code path, so they are not duplicates.", - "confidence": 0.97, + "summary": "These are three separate model-addition PRs for different models (DeepSeek OCR, Isaac, and Kimi2-6). They share the same scaffolding pattern, but they do not fix the same code-path problem and should not be merged as duplicates.", + "confidence": 0.98, "canonical_issue_reason": null, "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": null, + "best_pr_reason": "No duplicate canonical PR exists here; if a representative were needed, Kimi2-6 is the most mature/active PR, but it is still unrelated to the other model additions.", "soft_edge_verdicts": [ { "left": "pull_request:41797", "right": "pull_request:45186", "accept": false, - "reason": "Different model integrations (DeepSeek OCR vs Isaac); overlap is only template/boilerplate files, not the same underlying change." + "reason": "Different model integrations (DeepSeek OCR vs Isaac) with different model files, tests, and implementation details; shared auto-registration/docs changes are just template overlap." }, { "left": "pull_request:45186", "right": "pull_request:45630", "accept": false, - "reason": "Different model integrations (Isaac vs Kimi2-6); shared autos/docs plumbing does not indicate a single mergeable fix or feature." + "reason": "Different model integrations (Isaac vs Kimi2-6). They touch the same infrastructure because all new models need registration, but they are not the same bug/change." } ] }, @@ -18423,7 +18423,7 @@ "soft_pairs": [ "pull_request:42975|pull_request:42976" ], - "prepared_review_unit_hash": "01967bce76526edd05cd395cfda0dd98eaf1fd924f47d26bd935cf9c4a554c21", + "prepared_review_unit_hash": "d1cd92a0c8e528983adfbd6d9246f8f0c7aa329e8232a9eefc2274cf7663c869", "component_budget": { "node_count": 2, "item_count": 2, @@ -18445,18 +18445,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two broad GitHub Actions maintenance PRs overlap heavily in workflow files, but they are not the same change: one is a Node 24 compatibility sweep and the other is a general upgrade-to-latest sweep with different action targets.", - "confidence": 0.87, + "summary": "Two open PRs both touch GitHub Actions workflow maintenance, but they address different upgrades: one updates many official actions for Node 24 compatibility, while the other specifically bumps docker/build-push-action from v5 to v6. They overlap in some workflow files, but the underlying change is not the same.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 42975 is the better representative because it has the clearest concrete purpose (Node 24 compatibility) while still covering many of the same workflow-action updates.", + "canonical_pr_reason": "PR 42975 is the better canonical PR because it is the broader, more directly stated maintenance change: upgrading multiple GitHub Actions to Node 24-compatible versions across many workflows.", "best_issue_reason": null, - "best_pr_reason": "PR 42975 is the strongest single PR in this cluster: it is more specifically motivated, broad enough to represent the workflow-action upgrade work, and not just a generic latest-version bump.", + "best_pr_reason": "PR 42975 is the best representative of the cluster since its title and diff align with the shared workflow-action upgrade theme and it spans the larger, primary compatibility update.", "soft_edge_verdicts": [ { "left": "pull_request:42975", "right": "pull_request:42976", "accept": false, - "reason": "Reject: these are related maintenance PRs, but they do not fix the same underlying bug/change. 42975 is a Node 24 compatibility upgrade across workflows, while 42976 is a separate latest-version bump that updates a different set of actions (notably docker/build-push-action v6). Overlap in workflow files alone is not enough to treat them as duplicates." + "reason": "Reject: these are different changes. 42975 updates several GitHub Actions versions for Node 24 compatibility, while 42976 specifically bumps docker/build-push-action versions in docker image workflows. Shared workflow filenames are not enough to treat them as the same underlying fix." } ] }, @@ -18493,7 +18493,7 @@ "pull_request:43448|pull_request:45490", "pull_request:43451|pull_request:45490" ], - "prepared_review_unit_hash": "e35d919bc9bcffb751ee4615ba51d0f9cf02d86a5f36f4a213d1d7ee3f5ccde8", + "prepared_review_unit_hash": "4d937dd526e546603ee776f5b0606dd0349e55b5edde2cab03ee9a736739c6e3", "component_budget": { "node_count": 4, "item_count": 4, @@ -18515,48 +18515,48 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All four pull requests are separate model additions (ViT NEPA, Molmo, Molmo2, and CTSM). They share only boilerplate areas like docs and auto-registration, not the same underlying bug or change, so this is a false-positive similarity cluster.", - "confidence": 0.99, + "summary": "All four PRs are separate model-addition feature branches (ViT NEPA, Molmo, Molmo2, CTSM). They share generic Hugging Face boilerplate files like docs/toctree and auto registries, but they do not fix the same code-path problem or represent one mergeable duplicate change set.", + "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: these are distinct feature PRs for different model families and code paths, not duplicates.", + "canonical_pr_reason": "No canonical PR: the PRs target different models and different implementation paths, so there is no single duplicate representative.", "best_issue_reason": null, - "best_pr_reason": "No global best PR for deduping purposes; 43451 is the most substantial PR by activity, but it is still unrelated to the others.", + "best_pr_reason": "PR 43451 is the broadest/most complete feature addition, but it is still unrelated to the others; it is not a duplicate canonical choice.", "soft_edge_verdicts": [ { "left": "pull_request:42978", "right": "pull_request:43448", "accept": false, - "reason": "ViT NEPA and Molmo are different model families; the overlap is only in shared docs/auto-registration plumbing." + "reason": "Different model additions (ViT NEPA vs Molmo). Shared auto/docs files are generic scaffolding, not the same underlying change." }, { "left": "pull_request:42978", "right": "pull_request:43451", "accept": false, - "reason": "ViT NEPA vs Molmo2 are unrelated model additions with different implementations and code paths." + "reason": "Different model additions (ViT NEPA vs Molmo2). Similar repository touchpoints do not indicate the same bug or feature." }, { "left": "pull_request:42978", "right": "pull_request:45490", "accept": false, - "reason": "ViT NEPA is a vision model, while CTSM is a time-series model; not the same underlying change." + "reason": "Different model additions (ViT NEPA vs CTSM) with distinct modeling code; only boilerplate overlaps." }, { "left": "pull_request:43448", "right": "pull_request:43451", "accept": false, - "reason": "Molmo and Molmo2 are related by name but still distinct architectures and separate codebases in this repo; shared files are generic integration points only." + "reason": "Molmo and Molmo2 are related by naming but are distinct model implementations with separate configs, processors, and tests." }, { "left": "pull_request:43448", "right": "pull_request:45490", "accept": false, - "reason": "Molmo and CTSM target different domains and fix/add different functionality, so they are not duplicates." + "reason": "Molmo and CTSM are unrelated model integrations; shared docs/auto registry edits are incidental." }, { "left": "pull_request:43451", "right": "pull_request:45490", "accept": false, - "reason": "Molmo2 and CTSM are separate model additions with no common concrete bug or change to merge together." + "reason": "Molmo2 and CTSM are separate model additions touching different concrete code paths, so they should not be merged as duplicates." } ] }, @@ -18589,7 +18589,7 @@ "pull_request:43291|pull_request:44815", "pull_request:43665|pull_request:44815" ], - "prepared_review_unit_hash": "2a984b26b58cb20977f08c13a06feb1ccc65f3585bb1466be92fb6a8308e04e2", + "prepared_review_unit_hash": "cd838f89756a8732579eda3cbfd04b526b32b7f5cf46d5f1a2ce5fb1cac7c248", "component_budget": { "node_count": 3, "item_count": 3, @@ -18611,30 +18611,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These three PRs are not duplicates of one another: one fixes Whisper decoding/tests, one is test-only noise in CLIP/ViT, and one is an FP8 dequant/loading fix. The only apparent similarity is generic \"fix\" wording.", - "confidence": 0.97, + "summary": "No true duplicates here. The three PRs only share vague 'fix' language and some test-file overlap; their concrete code paths are unrelated (Whisper decoding, CLIP/ViT test placeholders, and FP8/Mistral dequantization).", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #44815 is the most substantive and well-scoped change in the set, with a coherent code fix across loading/FP8 quantization paths; the other two are either unrelated or test-only.", + "canonical_pr_reason": "pull_request:44815 is the most substantive and self-contained fix, with real code-path changes across loading/FP8 quantization rather than test-only noise.", "best_issue_reason": null, - "best_pr_reason": "PR #44815 is the best representative change overall because it addresses a concrete implementation bug across the dequantization path and has the richest supporting context.", + "best_pr_reason": "pull_request:44815 is the best representative of the cluster because it contains the clearest functional bug fix and the broadest meaningful implementation changes.", "soft_edge_verdicts": [ { "left": "pull_request:43291", "right": "pull_request:43665", "accept": false, - "reason": "Whisper tokenizer decoding fix vs. unrelated CLIP/ViT test edits; no shared bug or change." + "reason": "Both are test-related, but they target different models and different failure modes; 43291 is Whisper tokenizer decoding, while 43665 is placeholder assertions in CLIP/ViT tests." }, { "left": "pull_request:43291", "right": "pull_request:44815", "accept": false, - "reason": "Whisper batch/timestamp decode logic is unrelated to FP8 dequant/model-loading changes." + "reason": "Different subsystems and different bugs: Whisper decoding/test cleanup versus FP8 dequantization and model-loading changes for Mistral4." }, { "left": "pull_request:43665", "right": "pull_request:44815", "accept": false, - "reason": "Test-only CLIP/ViT edits do not match the FP8 dequant fix; they are not the same underlying change." + "reason": "Shared test-file presence is not enough; 43665 is clearly unrelated test noise, while 44815 fixes a concrete quantization/dequant path." } ] }, @@ -18671,7 +18671,7 @@ "pull_request:45932|pull_request:46100", "pull_request:46100|pull_request:46114" ], - "prepared_review_unit_hash": "2689338da54fc14ddeee095d7adfee471e43485bfd824c73e8957d11ef257706", + "prepared_review_unit_hash": "78bf2c97e96a779794363b9a269d31bb13fa34311ab51f6c5c851bd8958b0344", "component_budget": { "node_count": 5, "item_count": 5, @@ -18693,42 +18693,42 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "This cluster is a set of unrelated \"do not merge\"/test-harness PRs. There is no issue to canonicalize, and none of the soft similarity links are strong enough to treat as duplicates or the same change.", - "confidence": 0.81, + "summary": "These PRs are mostly unrelated dummy/test or CI changes. The only seemingly close pair (45932 and 46100) still targets different code paths and test areas, so this cluster does not form a true duplicate set.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45932 is the most substantive and broad representative in the cluster, with a real-looking cross-model change set and the only pair that even superficially aligns with another PR; the others are narrower test or bot-check PRs.", + "canonical_pr_reason": "No canonical PR: the items span unrelated placeholder workflow, model, and test edits rather than one shared change.", "best_issue_reason": null, - "best_pr_reason": "PR 45932 is the best single representative because it touches real model code and workflows, whereas the others are mostly intentional test noise or CI/debug scaffolding.", + "best_pr_reason": "No single PR is a good global representative because the cluster is not one duplicate change set; the edits are heterogeneous and mostly artificial.", "soft_edge_verdicts": [ { "left": "pull_request:43488", - "right": "pull_request:46114", + "right": "pull_request:43532", "accept": false, - "reason": "Both are intentional test/repo-bot style PRs, but they change different areas and serve different demonstrations; they are not the same underlying bug or fix." + "reason": "Both touch vit tests, but one is a repo-bot/version check PR and the other is CI/workflow plumbing plus model files; not the same underlying bug or fix." }, { "left": "pull_request:43488", - "right": "pull_request:43532", + "right": "pull_request:46114", "accept": false, - "reason": "One checks repo-bot formatting/versioning, the other changes workflow/comment handling and test scaffolding; same broad testing theme, but not the same concrete change." + "reason": "Shared vit test filename is too broad; 43488 is a format/check PR while 46114 is a migration/OTEL test PR with many unrelated edits." }, { "left": "pull_request:43532", "right": "pull_request:46114", "accept": false, - "reason": "Both are demo/test-migration PRs, but they modify different workflows and test paths; no single code-path issue or mergeable shared fix is evident." + "reason": "Both are workflow-heavy test PRs, but they target different automation changes and test edits, not one concrete code-path problem." }, { "left": "pull_request:45932", "right": "pull_request:46100", "accept": false, - "reason": "They both touch ViT-related tests, but 45932 is a broad CI/observability/model patch while 46100 is just injected failing assertions in a test file; not the same underlying bug/change." + "reason": "Despite similar test-migration flavor, 45932 changes model/config/workflow code while 46100 only injects failing Vit test assertions; not mergeable as one fix." }, { "left": "pull_request:46100", "right": "pull_request:46114", "accept": false, - "reason": "Overlap on a ViT test file is incidental; 46114 is a wider migration/OTEL test PR with unrelated CI and model edits, not the same concrete fix as 46100." + "reason": "They share vit test files, but 46114 also changes CI, download, tensor-parallel, and hub/modeling utils; this is not the same underlying change." } ] }, @@ -18758,7 +18758,7 @@ "soft_pairs": [ "pull_request:43612|pull_request:43613" ], - "prepared_review_unit_hash": "4b9e5d739bda6e2c0ac9f3fa7b4b7568264ebd87588d9784b88a8e51b7bdc2d5", + "prepared_review_unit_hash": "3401f7c792da6c9be101261c88e8e486ab67cb708db66a359926012da5a6669a", "component_budget": { "node_count": 2, "item_count": 2, @@ -18780,18 +18780,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs are related but not duplicates: one adds Promptable Concept Segmentation, the other Promptable Visual Segmentation. They share pipeline/docs/registration scaffolding, but the underlying tasks, model coverage, and tests are different.", - "confidence": 0.93, + "summary": "These PRs are related in theme but not duplicates: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share some docs/registry scaffolding, but they target different pipelines, model integrations, and test suites.", + "confidence": 0.96, "canonical_issue_reason": null, - "canonical_pr_reason": "No issue in the cluster; if one PR must be treated as the representative, PR 43613 is slightly broader and more complete, covering more model integrations and test files.", + "canonical_pr_reason": null, "best_issue_reason": null, - "best_pr_reason": "PR 43613 is the stronger standalone representative because it appears to cover a broader visual-segmentation feature set with more model support and test coverage.", + "best_pr_reason": null, "soft_edge_verdicts": [ { "left": "pull_request:43612", "right": "pull_request:43613", "accept": false, - "reason": "Different concrete features: concept segmentation vs visual segmentation. Shared pipeline/docs plumbing is not enough to treat them as the same bug/change." + "reason": "Different concrete features and code paths: concept segmentation vs visual segmentation. Shared documentation and pipeline-registration changes are generic setup, not evidence of the same underlying bug or change." } ] }, @@ -18821,7 +18821,7 @@ "soft_pairs": [ "pull_request:43649|pull_request:46301" ], - "prepared_review_unit_hash": "9f0387759dd198649d3d7d5a09aafabf19999848b33f1693108f01f32502a1c0", + "prepared_review_unit_hash": "44ca84e5cd37c4b3128aabff85acc44b31031ed113e983abd2a46bb74a474baf", "component_budget": { "node_count": 2, "item_count": 2, @@ -18843,18 +18843,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "The two pull requests are not duplicates: one changes CI/failure-reporting workflows and related test utilities, while the other is a test-side tensor-parallel debugging fix. They target different code paths and would not be merged into one PR.", - "confidence": 0.98, + "summary": "These two open PRs are not duplicates: one is a workflow/test infrastructure change around new-failures reporting, while the other is a test/debugging change for tensor-parallel thread/process exit diagnostics. They touch different code paths and should not be merged together.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 43649 is the better canonical representative because it has a specific, descriptive title and a coherent change set around CI/failure reporting; PR 46301 is title-generic and appears unrelated to the other PR.", + "canonical_pr_reason": "PR #43649 is the better canonical PR because it has a concrete, descriptive title and a focused workflow/test infrastructure change, whereas #46301 is generic and appears to be a narrower debugging-oriented update.", "best_issue_reason": null, - "best_pr_reason": "PR 43649 is the strongest standalone PR in the cluster: it is better scoped, easier to understand from the title and diff, and looks like a complete change rather than an ad hoc test/debug patch.", + "best_pr_reason": "PR #43649 is the strongest representative of the cluster because it is more substantively described and more likely to be the intended change, while #46301 is too vague to serve as a good anchor.", "soft_edge_verdicts": [ { "left": "pull_request:43649", "right": "pull_request:46301", "accept": false, - "reason": "Different topics and code paths: 43649 modifies workflow and utility files for failure reporting, while 46301 edits tensor-parallel test code and test fetching logic. They do not look like the same underlying bug/change." + "reason": "Different problems and code paths: #43649 edits CI/workflow scripts and test reporting utilities, while #46301 adds tensor-parallel test diagnostics and process-exit handling. They are not plausibly one merged PR." } ] }, @@ -18884,40 +18884,40 @@ "soft_pairs": [ "pull_request:43651|pull_request:43663" ], - "prepared_review_unit_hash": "cb40658a32d3c317cbbac519a8c7d2acc0ce397af00b5fc3e9ef10cffaccbf2a", + "prepared_review_unit_hash": "1693a39d3589f776ccde23e52a47910e758be83eac8448d202d1fc099ed5d131", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 4292, - "estimated_input_tokens": 1073, - "estimated_eval_tokens": 2402 + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs both touch `trainer.py` and add extensibility hooks, but they address different Trainer behaviors: gradient-accumulation loss scaling vs. signature-based column filtering for PEFT/custom trainers. They are not the same underlying change.", - "confidence": 0.97, + "summary": "These are two distinct trainer extensibility PRs in the same file, but they address different code paths: gradient-accumulation loss scaling vs. signature-column filtering. Similar pattern, not a duplicate change.", + "confidence": 0.95, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43651 is the better representative only because it is a tighter, self-contained fix in the training step path; PR #43663 is a separate customization hook for input-column filtering.", + "canonical_pr_reason": "No single canonical PR for a duplicate cluster: PR 43651 changes loss scaling in training_step, while PR 43663 changes column filtering/signature inspection.", "best_issue_reason": null, - "best_pr_reason": "PR #43651 is the stronger standalone PR for this cluster: it changes a specific code path (`training_step`) with a clear bug-fix intent and minimal scope.", + "best_pr_reason": "No best PR as a duplicate representative; the PRs solve different problems and should be triaged separately.", "soft_edge_verdicts": [ { "left": "pull_request:43651", "right": "pull_request:43663", "accept": false, - "reason": "Do not merge as duplicates: one changes loss scaling during gradient accumulation, the other refactors signature column filtering for model inputs. Shared file and general Trainer extensibility are not enough to indicate the same fix." + "reason": "Different underlying trainer behaviors: one controls gradient accumulation loss normalization, the other controls input column filtering for custom/PEFT trainers. Shared file and similar refactor pattern are not enough to treat them as the same change." } ] }, @@ -18947,7 +18947,7 @@ "soft_pairs": [ "pull_request:43656|pull_request:43842" ], - "prepared_review_unit_hash": "e4e695e90be517e1fad0131d44c8ba4ccf76a766ba6aa732a57540e6e419f72f", + "prepared_review_unit_hash": "17d3ea9804249ac40065f63b84bef3f8103ac7232f331fa57ab611abc1f69503", "component_budget": { "node_count": 2, "item_count": 2, @@ -18969,24 +18969,27 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are related only by touching the same CLI file and a similar TypeAdapter-related area, but they appear to fix different runtime annotation/import problems. I would not merge them as duplicates.", - "confidence": 0.91, + "summary": "The two PRs touch the same file and both relate to annotation/type-related `NameError` risk, but they do not appear to fix the same concrete bug or code path. PR #43656 is a broader `from __future__ import annotations` cleanup with multiple type-hint adjustments, while PR #43842 specifically fixes the `TypeAdapter` import/annotation issue in `_validate_request`.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #43842 is the more concrete and narrowly scoped fix: it directly addresses the TypeAdapter NameError when pydantic is unavailable, with an explicit issue target and a minimal annotation/import change.", + "canonical_pr_reason": "PR #43842 is the more direct and narrowly scoped fix for the reported `TypeAdapter` NameError in `src/transformers/cli/serve.py`, matching the explicit target without the broader annotation cleanup in PR #43656.", "best_issue_reason": null, - "best_pr_reason": "PR #43842 best represents the cluster because it fixes a specific code-path failure in the CLI rather than doing broader annotation cleanup. PR #43656 looks like a different/adjacent typing runtime issue.", + "best_pr_reason": "PR #43842 best fits the concrete runtime failure because it addresses the specific `TypeAdapter` annotation/import problem in the affected function, rather than making a broader module-wide typing change.", "soft_edge_verdicts": [ { "left": "pull_request:43656", "right": "pull_request:43842", "accept": false, - "reason": "Same file and similar symptom, but the fixes target different underlying failures: #43656 is a broader annotation/runtime typing cleanup, while #43842 specifically guards TypeAdapter usage when pydantic is not installed." + "reason": "Related by file and general annotation safety, but not the same underlying bugfix. #43656 is a broad deferred-annotations/type-hint cleanup, whereas #43842 targets a specific `TypeAdapter` NameError in a different code path, so they should not be merged as duplicates." } ] }, - "evaluator_result": null, - "evaluator_used": false, - "retried": false, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports that both PRs touch `src/transformers/cli/serve.py` and address annotation-related runtime `NameError` risk, but the summary overstates the relationship. PR #43656 adds `from __future__ import annotations` and cleans up several unrelated type hints; PR #43842 specifically handles `TypeAdapter` in a different function. That is related, but not clearly the same bugfix or the same affected code path. The soft-edge accept is too strong given the evidence, so this should be rejected as an overreach." + }, + "evaluator_used": true, + "retried": true, "accepted_nontrivial_soft_edge": false, "error_kind": null, "error_message": null @@ -19172,7 +19175,7 @@ "pull_request:44044|pull_request:44129", "pull_request:44044|pull_request:44154" ], - "prepared_review_unit_hash": "45b517c582940c6670641e00b6a28a837e8c4854d007d966c8f95f548991978f", + "prepared_review_unit_hash": "0230e55b264c40d59ffc9140f036c1905ad0b40f56c3249c6612375bee23bb1f", "component_budget": { "node_count": 28, "item_count": 28, @@ -19185,375 +19188,291 @@ "node_count": 27, "item_count": 27, "soft_pair_count": 72, - "serialized_chars": 75092, - "estimated_input_tokens": 18773, - "estimated_eval_tokens": 37802 + "serialized_chars": 75094, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "This cluster is a set of model-specific PRs implementing the same standardized output-tracing migration, mostly for different architectures under issue #43979. I only accepted pairs that clearly target the same concrete model/code path, especially the GPT-J/CodeGen and GPT-Neo duplicates.", - "confidence": 0.87, - "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44722 is the best representative because it is a later, consolidated GPT-J/CodeGen tracing refactor with the clearest standardized-decorator implementation and explicit #43979 linkage.", - "best_issue_reason": null, - "best_pr_reason": "PR 44722 is the strongest single PR to anchor the cluster: it covers the same GPT-J tracing change as the other GPT-J candidates, with broader coverage than the narrower follow-ups.", + "summary": "This cluster is mostly a wave of model-specific refactors to standardized output tracing around issue #43979, not true duplicates across different architectures. The only clear duplicate-like overlaps are within the GPT-Neo and GPT-J refactor series.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43979 is the shared tracking issue repeatedly referenced by the refactor PRs and captures the common output-tracing migration.", + "canonical_pr_reason": "PR #44722 is the strongest representative of the GPT-J/CodeGen subset: explicit issue-linked, broadest same-code-path coverage, and it subsumes the smaller GPT-J-only variants.", + "best_issue_reason": "#43979 is the best issue anchor because it unifies the common standardized output tracing change across the model-specific PRs.", + "best_pr_reason": "PR #44722 is the best single PR representative because it is the most complete GPT-J/CodeGen implementation of the shared tracing refactor.", "soft_edge_verdicts": [ { "left": "pull_request:43996", "right": "pull_request:44085", "accept": false, - "reason": "Different models (CVT/FNet vs GPT-J); only share the broad output-tracing theme." + "reason": "Different model families; same broad refactor theme but not the same concrete code path." }, { "left": "pull_request:43996", "right": "pull_request:44044", "accept": false, - "reason": "Different models and code paths; both are output-tracing refactors, not duplicates." + "reason": "Different architectures and files; only share the issue theme, not a duplicate change." }, { "left": "pull_request:44066", "right": "pull_request:44085", "accept": true, - "reason": "Same GPT-J output-tracing refactor in the same file; 44066 also includes the CodeGen copy, but the underlying GPT-J change is the same." + "reason": "Both target GPT-J output-tracing refactoring in the same file; these are close enough to merge into one PR." }, { "left": "pull_request:44007", "right": "pull_request:44072", "accept": false, - "reason": "RegNet vs EfficientNet; different model implementations." + "reason": "RegNet/ResNet vs EfficientNet are separate model implementations, so this is not the same change." }, { "left": "pull_request:44072", "right": "pull_request:44722", "accept": false, - "reason": "EfficientNet vs GPT-J/CodeGen; unrelated model code." + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths despite similar decorator migration." }, { "left": "pull_request:44066", "right": "pull_request:44072", "accept": false, - "reason": "RegNet/EfficientNet-style CNN refactor vs GPT-J/CodeGen; different code paths." + "reason": "Different model code paths; same output-tracing framework, not the same bug or change." }, { "left": "pull_request:44013", "right": "pull_request:44044", "accept": false, - "reason": "MobileNetV2 vs DeBERTa-v2; different architectures." + "reason": "MobileNetV2 and DeBERTa V2 are unrelated implementations." }, { "left": "pull_request:44066", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J/CodeGen versus MGP-STR; different models and mechanics." + "reason": "GPT-J/CodeGen vs MGP-STR; same pattern, different model-specific code." }, { "left": "pull_request:44066", "right": "pull_request:44071", "accept": false, - "reason": "GPT-J/CodeGen versus MPT; unrelated model code." + "reason": "GPT-J/CodeGen and MPT are separate refactors in different code paths." }, { "left": "pull_request:44018", "right": "pull_request:44068", "accept": true, - "reason": "Same GPT-Neo output-tracing refactor in the same model family." + "reason": "Both are GPT-Neo output-tracing refactors on the same model and file; they look like overlapping implementations of the same change." }, { "left": "pull_request:44018", "right": "pull_request:44066", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; different model families." + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families and code paths." }, { "left": "pull_request:44066", "right": "pull_request:44068", "accept": false, - "reason": "GPT-J/CodeGen vs GPT-Neo; different model families." + "reason": "GPT-J/CodeGen and GPT-Neo are different underlying implementations." }, { "left": "pull_request:44019", "right": "pull_request:44722", "accept": false, - "reason": "ResNet vs GPT-J/CodeGen; different code paths." + "reason": "ResNet and GPT-J/CodeGen are unrelated code paths." }, { "left": "pull_request:44086", "right": "pull_request:44722", "accept": false, - "reason": "MGP-STR vs GPT-J/CodeGen; different models." + "reason": "MGP-STR and GPT-J/CodeGen are separate model-specific refactors." }, { "left": "pull_request:44019", "right": "pull_request:44085", "accept": false, - "reason": "ResNet vs GPT-J; different model implementations." + "reason": "ResNet and GPT-J are different model implementations." }, { "left": "pull_request:44018", "right": "pull_request:44019", "accept": false, - "reason": "GPT-Neo and ResNet are different model refactors, not the same fix." + "reason": "GPT-Neo and ResNet are unrelated code paths." }, { "left": "pull_request:44019", "right": "pull_request:44071", "accept": false, - "reason": "ResNet vs MPT; different output-tracing code." + "reason": "ResNet and MPT are unrelated model refactors." }, { "left": "pull_request:44068", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo vs Flaubert; different model implementations." + "reason": "GPT-Neo vs Flaubert; different models and code paths." }, { "left": "pull_request:44018", "right": "pull_request:44116", "accept": false, - "reason": "GPT-Neo vs Flaubert; different model families." + "reason": "GPT-Neo and Flaubert are unrelated model changes." }, { "left": "pull_request:44068", "right": "pull_request:44722", "accept": false, - "reason": "GPT-Neo vs GPT-J/CodeGen; different model families." + "reason": "GPT-Neo and GPT-J/CodeGen are different model families." }, { "left": "pull_request:44071", "right": "pull_request:44722", "accept": false, - "reason": "MPT vs GPT-J/CodeGen; different code paths." + "reason": "MPT and GPT-J/CodeGen are separate model-specific changes." }, { "left": "pull_request:44018", "right": "pull_request:44085", "accept": false, - "reason": "GPT-Neo vs GPT-J; different model families." + "reason": "GPT-Neo and GPT-J are not the same concrete code-path change." }, { "left": "pull_request:44018", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo vs MGP-STR; different model families." + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." }, { "left": "pull_request:44068", "right": "pull_request:44086", "accept": false, - "reason": "GPT-Neo vs MGP-STR; different model families." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44085", - "accept": false, - "reason": "MPT vs GPT-J; different code paths." + "reason": "GPT-Neo and MGP-STR are different code paths." }, { "left": "pull_request:44059", "right": "pull_request:44086", "accept": false, - "reason": "GPT-2 vs MGP-STR; different models." + "reason": "GPT-2 and MGP-STR share only the high-level tracing theme." }, { "left": "pull_request:44085", "right": "pull_request:44086", "accept": false, - "reason": "GPT-J vs MGP-STR; different code paths." + "reason": "GPT-J and MGP-STR are unrelated model refactors." }, { "left": "pull_request:44098", "right": "pull_request:44101", "accept": false, - "reason": "ViLT vs Flaubert/XLM; different models." + "reason": "ViLT and Flaubert/XLM are different model code paths." }, { "left": "pull_request:44059", "right": "pull_request:44722", "accept": false, - "reason": "GPT-2 vs GPT-J/CodeGen; different model families." + "reason": "GPT-2 and GPT-J/CodeGen are separate implementations." }, { "left": "pull_request:44017", "right": "pull_request:44722", "accept": false, - "reason": "SegFormer vs GPT-J/CodeGen; different models." + "reason": "SegFormer and GPT-J/CodeGen are unrelated models." }, { "left": "pull_request:44017", "right": "pull_request:44161", "accept": false, - "reason": "SegFormer vs LongT5; different code paths." + "reason": "SegFormer and LongT5 are different code paths." }, { "left": "pull_request:44017", "right": "pull_request:44073", "accept": false, - "reason": "SegFormer vs VisualBERT; different model families." + "reason": "SegFormer and VisualBert are separate model changes." }, { "left": "pull_request:44068", "right": "pull_request:44071", "accept": false, - "reason": "GPT-Neo vs MPT; different model families." + "reason": "GPT-Neo and MPT are different model implementations." }, { "left": "pull_request:43997", "right": "pull_request:44073", "accept": false, - "reason": "MPNet vs VisualBERT/XLM; different models." - }, - { - "left": "pull_request:44071", - "right": "pull_request:44086", - "accept": false, - "reason": "MPT vs MGP-STR; different code paths." - }, - { - "left": "pull_request:44074", - "right": "pull_request:44101", - "accept": false, - "reason": "TextNet vs Flaubert/XLM; different architectures." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44018", - "accept": false, - "reason": "MPNet vs GPT-Neo; different model families." + "reason": "RegNet and VisualBert are unrelated." }, { "left": "pull_request:44056", "right": "pull_request:44161", "accept": false, - "reason": "MPNet vs LongT5; different models." + "reason": "MPNet and LongT5 are separate model code paths." }, { - "left": "pull_request:43997", - "right": "pull_request:44161", - "accept": false, - "reason": "MPNet vs LongT5; different models." - }, - { - "left": "pull_request:44074", - "right": "pull_request:44161", - "accept": false, - "reason": "TextNet vs LongT5; different output-tracing implementations." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44161", - "accept": false, - "reason": "GPT-Neo vs LongT5; different model families." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44071", - "accept": false, - "reason": "MPNet vs MPT; different code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44071", - "accept": false, - "reason": "SqueezeBert vs MPT; different models." - }, - { - "left": "pull_request:44018", - "right": "pull_request:44129", - "accept": false, - "reason": "GPT-Neo vs SpeechT5; different code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44073", - "accept": false, - "reason": "SqueezeBert vs VisualBERT; different model families." - }, - { - "left": "pull_request:43997", - "right": "pull_request:44074", + "left": "pull_request:44019", + "right": "pull_request:44085", "accept": false, - "reason": "MPNet vs TextNet; different model families." + "reason": "ResNet and GPT-J are unrelated implementations." }, { - "left": "pull_request:44071", + "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "MPT vs SpeechT5; different model families." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44018", - "accept": false, - "reason": "SqueezeBert vs GPT-Neo; different models." - }, - { - "left": "pull_request:44056", - "right": "pull_request:44068", - "accept": false, - "reason": "MPNet vs GPT-Neo; different code paths." - }, - { - "left": "pull_request:44010", - "right": "pull_request:44044", - "accept": false, - "reason": "SqueezeBert vs DeBERTa-v2; different model families." + "reason": "DeBERTa V2 and SpeechT5 are different model code paths." }, { "left": "pull_request:44044", - "right": "pull_request:44074", + "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa-v2 vs TextNet; different models." + "reason": "DeBERTa V2 and ViTS are unrelated changes." }, { "left": "pull_request:44066", "right": "pull_request:44722", "accept": true, - "reason": "Same GPT-J/CodeGen standardized output-tracing refactor; 44722 looks like the later consolidation of the same change." + "reason": "Same GPT-J output-tracing refactor; 44722 is a broader version of the same change and could absorb 44066." }, { "left": "pull_request:44085", "right": "pull_request:44722", "accept": true, - "reason": "Both are GPT-J output-tracing refactors against the same code path; they could plausibly be merged into one PR." + "reason": "Both are GPT-J tracing refactors on the same file; one is a narrower subset of the other." }, { "left": "pull_request:44085", "right": "pull_request:44129", "accept": false, - "reason": "GPT-J vs SpeechT5; unrelated model implementations." + "reason": "GPT-J and SpeechT5 are unrelated model changes." }, { "left": "pull_request:43996", "right": "pull_request:44007", "accept": false, - "reason": "CVT/FNet vs RegNet; different model families." + "reason": "CVT/FNet and RegNet/ResNet are different model families." }, { "left": "pull_request:43996", "right": "pull_request:44129", "accept": false, - "reason": "CVT/FNet vs SpeechT5; different architectures." + "reason": "CVT/FNet and SpeechT5 are separate code paths." }, { "left": "pull_request:44044", "right": "pull_request:44129", "accept": false, - "reason": "DeBERTa-v2 vs SpeechT5; different code paths." + "reason": "DeBERTa V2 and SpeechT5 are unrelated implementations." }, { "left": "pull_request:44044", "right": "pull_request:44154", "accept": false, - "reason": "DeBERTa-v2 vs VITS; different model families." + "reason": "DeBERTa V2 and ViTS are different model-specific changes." } ] }, "evaluator_result": { "accept": true, - "feedback": "The cluster summary and canonical PR choice are grounded in the packet: the items are indeed standardized output-tracing refactors across model families, mostly linked to issue #43979, and PR 44722 is a reasonable anchor because it is the broader GPT-J/CodeGen consolidation. The soft-edge decisions are conservative overall, and the accepted pairs are plausibly mergeable as single PRs for the same bugfix (notably the GPT-J and GPT-Neo duplicates)." + "feedback": "The summary is grounded in the packet: #43979 is the shared issue anchor, and #44722 is a reasonable representative of the GPT-J/CodeGen subset. The accepted soft-edge pairs are conservative because they stay within the same model family and concrete file path, while the rejected pairs correctly avoid cross-architecture merges. I don\u2019t see evidence of overstated duplication." }, "evaluator_used": true, "retried": false, @@ -19591,7 +19510,7 @@ "pull_request:43997|pull_request:44010", "pull_request:44010|pull_request:44129" ], - "prepared_review_unit_hash": "acf3e73c3e73d18fa57872b674b2224e4d2bad96861f1545adc130ecf6ae2a0b", + "prepared_review_unit_hash": "ff9895bccaac4a2a27dc1ca0e84108f6aa887f4fab9e4b840c08120915c89bc6", "component_budget": { "node_count": 28, "item_count": 28, @@ -19604,57 +19523,57 @@ "node_count": 8, "item_count": 8, "soft_pair_count": 6, - "serialized_chars": 17126, - "estimated_input_tokens": 4282, - "estimated_eval_tokens": 8820 + "serialized_chars": 17124, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": true, "analyst_result": { - "summary": "These are all separate model-specific PRs that follow the same standardized output-tracing migration pattern, but they do not look like duplicates of one another and should not be merged into a single PR cluster.", - "confidence": 0.92, + "summary": "All items are model-specific refactors to standardized output tracing/capture APIs, but they target different architectures and code paths, so they do not look like duplicates of the same change.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44129 is the strongest anchor because it has an explicit issue target and a clearly scoped SpeechT5 output-tracing refactor.", + "canonical_pr_reason": "No single PR spans the whole cluster; this one is a clear, representative standardized-output refactor with an explicit capture_outputs/can_return_tuple migration in a single model family.", "best_issue_reason": null, - "best_pr_reason": "PR 44129 is the most suitable representative PR here: it is tied to a concrete issue and its diff is a focused implementation of the output-capture migration pattern.", + "best_pr_reason": "PR 44073 is the clearest representative of the cluster theme: its title and diff directly describe the standardized output tracing refactor, and it is self-contained and readable as the cluster exemplar.", "soft_edge_verdicts": [ { "left": "pull_request:44024", "right": "pull_request:44076", "accept": false, - "reason": "Both are output-tracing refactors, but for different models and different code paths (FocalNet vs ImageGPT); they do not appear to be the same underlying change." + "reason": "Both are standardized-output refactors, but for different models (FocalNet vs ImageGPT) with different internals; they are related in pattern, not the same underlying bug/change." }, { "left": "pull_request:44073", "right": "pull_request:44074", "accept": false, - "reason": "Both migrate to standardized output capture, but one is VisualBert and the other is TextNet; these are separate model implementations, not the same bug or change." + "reason": "VisualBert and TextNet are separate model implementations; these are parallel refactors to output tracing, not one concrete shared fix." }, { "left": "pull_request:44056", "right": "pull_request:44073", "accept": false, - "reason": "MPNet and VisualBert share the same refactor theme, but the affected code paths are model-specific and not mergeable as one concrete PR." + "reason": "MPNet vs VisualBert touches different forward/output plumbing in different architectures, so they should not be merged as duplicates." }, { "left": "pull_request:44056", "right": "pull_request:44074", "accept": false, - "reason": "These are parallel output-tracing migrations in different models (MPNet vs TextNet), so they are not duplicates." + "reason": "These are distinct model-specific refactors in different code paths; similarity is only at the abstraction level of output capture." }, { "left": "pull_request:43997", "right": "pull_request:44010", "accept": false, - "reason": "RegNet and SqueezeBert are unrelated model implementations; despite similar decorator/output-capture edits, they are not the same underlying fix." + "reason": "RegNet and SqueezeBert are unrelated model implementations; the PRs share a migration pattern but not the same bug or change." }, { "left": "pull_request:44010", "right": "pull_request:44129", "accept": false, - "reason": "SqueezeBert and SpeechT5 touch different model-specific forward paths; the shared theme is too broad to treat them as one duplicate change." + "reason": "SqueezeBert and SpeechT5 address different model-specific output handling changes, so they are not the same concrete PR." } ] }, @@ -19733,268 +19652,274 @@ "pull_request:44028|pull_request:44030", "pull_request:44029|pull_request:44030" ], - "prepared_review_unit_hash": "00b96570c5e63bcc023568ec82e5faed015a5f2879121284781f79e4d4970845", + "prepared_review_unit_hash": "71d50e1d275f0aef8ae214efe6ebcb1dff9a1c825aea96da70d332bed8b2b029", "component_budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39783, - "estimated_input_tokens": 9946, - "estimated_eval_tokens": 20148 + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 }, "budget": { "node_count": 13, "item_count": 13, "soft_pair_count": 39, - "serialized_chars": 39783, - "estimated_input_tokens": 9946, - "estimated_eval_tokens": 20148 + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs share a generic 'output tracing' refactor theme, but they target different model families and code paths, so they are not duplicates of one another.", + "summary": "A set of model-specific output-tracing refactors in different Transformers architectures; they share a theme but not the same underlying code-path change, so they should not be deduplicated together.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 44025 is a good cluster representative because it is a self-contained output-tracing refactor with broader reach across two depth-anything model files, but it is still distinct from the others.", + "canonical_pr_reason": "PR 44025 is the broadest representative of the cluster (depth_anything plus prompt_depth_anything), but the PRs are still separate model-specific refactors rather than duplicates.", "best_issue_reason": null, - "best_pr_reason": "PR 44025 is the best representative of the cluster\u2019s common refactor pattern, but not a duplicate of the other PRs.", + "best_pr_reason": "PR 44025 is the closest exemplar of the shared theme because it spans a core model and its prompt variant, yet it is still not a mergeable duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:43998", "right": "pull_request:44002", "accept": false, - "reason": "Different models and files; same refactor style only." + "reason": "Different model families (timm_backbone vs upernet); same refactor theme only, not the same code-path bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44000", "accept": false, - "reason": "Timm backbone vs vision-text dual encoder are unrelated code paths." + "reason": "Different architectures (timm_backbone vs vision_text_dual_encoder); no shared concrete fix beyond output-tracing cleanup." }, { "left": "pull_request:43998", "right": "pull_request:44001", "accept": false, - "reason": "Different model families; no shared bug/change." + "reason": "Different models (timm_backbone vs univnet); these are separate per-model refactors." }, { "left": "pull_request:43998", "right": "pull_request:44003", "accept": false, - "reason": "Backbone tracing refactor vs Mamba/Falcon-Mamba refactor are separate changes." + "reason": "Different subsystems and code paths (timm_backbone vs mamba/falcon_mamba); not the same bug/change." }, { "left": "pull_request:43998", "right": "pull_request:44029", "accept": false, - "reason": "Different architectures; only the output-tracing pattern matches." + "reason": "Different models (timm_backbone vs rwkv); shared wording only, not a duplicate fix." }, { "left": "pull_request:43999", "right": "pull_request:44001", "accept": false, - "reason": "MobileNetV1 and UnivNet are unrelated implementations." + "reason": "MobileNetV1 and UnivNet are unrelated implementations; same tracing refactor pattern, but not the same change." }, { "left": "pull_request:43999", "right": "pull_request:44002", "accept": false, - "reason": "Different model code paths; not the same change." + "reason": "MobileNetV1 vs UperNet are different model code paths; no single underlying bug." }, { "left": "pull_request:43999", "right": "pull_request:44025", "accept": false, - "reason": "Both refactor tracing, but on different model families and modules." + "reason": "Different model families (MobileNetV1 vs DepthAnything); not mergeable as one PR." }, { "left": "pull_request:43999", "right": "pull_request:44026", "accept": false, - "reason": "MobileNetV1 vs vision-encoder-decoder are separate changes." + "reason": "Different architectures (MobileNetV1 vs VisionEncoderDecoder); only generic output-tracing similarity." }, { "left": "pull_request:43999", "right": "pull_request:44027", "accept": false, - "reason": "Different encoder-decoder stacks; not one concrete fix." + "reason": "Different model code paths (MobileNetV1 vs SpeechEncoderDecoder); not the same concrete fix." }, { "left": "pull_request:44000", "right": "pull_request:44001", "accept": false, - "reason": "Vision-text dual encoder and UnivNet are unrelated." + "reason": "VisionTextDualEncoder and UnivNet are unrelated; they just share the refactor motif." }, { "left": "pull_request:44000", "right": "pull_request:44002", "accept": false, - "reason": "Different model families and forward paths." + "reason": "Different models and runtime paths (vision-text dual encoder vs upernet); not duplicates." }, { "left": "pull_request:44000", "right": "pull_request:44003", "accept": false, - "reason": "Separate model-specific refactors, not a shared bug." + "reason": "VisionTextDualEncoder vs Mamba/FalconMamba are different code bases and problems." }, { "left": "pull_request:44000", "right": "pull_request:44025", "accept": false, - "reason": "Same tracing theme, but different code paths and model families." - }, - { - "left": "pull_request:44000", - "right": "pull_request:44004", - "accept": false, - "reason": "Vision-text dual encoder vs CodeGen are unrelated models." + "reason": "Different model families (vision-text dual encoder vs depth-anything); no shared concrete bug." }, { "left": "pull_request:44001", "right": "pull_request:44002", "accept": false, - "reason": "UnivNet and UperNet do not share a concrete implementation path." + "reason": "UnivNet and UperNet are distinct model implementations; same cleanup pattern only." }, { "left": "pull_request:44001", "right": "pull_request:44003", "accept": false, - "reason": "Different subsystems; no evidence of the same underlying bug." + "reason": "UnivNet vs Mamba/FalconMamba are different code paths; not a duplicate pair." }, { "left": "pull_request:44001", "right": "pull_request:44025", "accept": false, - "reason": "Depth Anything and UnivNet are separate refactors." + "reason": "UnivNet and DepthAnything are unrelated models; no common underlying change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen differ completely; the PRs are not mergeable into one fix." }, { "left": "pull_request:44002", "right": "pull_request:44029", "accept": false, - "reason": "UperNet and RWKV are distinct code paths." + "reason": "UperNet and RWKV are unrelated architectures; only the same output-tracing theme overlaps." }, { "left": "pull_request:44002", "right": "pull_request:44003", "accept": false, - "reason": "Different model families; only the refactor pattern is similar." + "reason": "UperNet vs Mamba/FalconMamba are different model code paths; not the same bug/change." }, { "left": "pull_request:44003", "right": "pull_request:44004", "accept": false, - "reason": "Mamba/Falcon-Mamba and CodeGen fix different forward implementations." + "reason": "Mamba/FalconMamba and CodeGen are different models with different implementation details; no shared concrete fix." }, { "left": "pull_request:43998", "right": "pull_request:44004", "accept": false, - "reason": "Timm backbone and CodeGen are unrelated changes." + "reason": "TimmBackbone and CodeGen are unrelated; only the refactor theme matches." }, { "left": "pull_request:44001", "right": "pull_request:44004", "accept": false, - "reason": "UnivNet and CodeGen touch different model stacks." + "reason": "UnivNet and CodeGen are different subsystems; not a duplicate PR." }, { "left": "pull_request:44002", "right": "pull_request:44004", "accept": false, - "reason": "UperNet and CodeGen are separate model-specific refactors." + "reason": "UperNet and CodeGen are separate model implementations; same theme, different change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "VisionTextDualEncoder and CodeGen are unrelated code paths; no same underlying bug." }, { "left": "pull_request:44025", "right": "pull_request:44026", "accept": false, - "reason": "Both are output-tracing refactors, but for different encoder stacks and files." + "reason": "DepthAnything and VisionEncoderDecoder are different model families; the output-tracing refactor is separate in each." }, { "left": "pull_request:44025", "right": "pull_request:44027", "accept": false, - "reason": "Depth Anything vs speech encoder-decoder are distinct changes." + "reason": "DepthAnything vs SpeechEncoderDecoder are unrelated models; not the same concrete change." }, { "left": "pull_request:44025", "right": "pull_request:44028", "accept": false, - "reason": "Different models; same broad helper usage only." + "reason": "DepthAnything and SuperPoint are different model paths; no mergeable duplicate." }, { "left": "pull_request:44025", "right": "pull_request:44029", "accept": false, - "reason": "Depth Anything and RWKV are unrelated code paths." + "reason": "DepthAnything vs RWKV are different model implementations; same refactor motif only." }, { "left": "pull_request:44025", "right": "pull_request:44030", "accept": false, - "reason": "Different model families; not mergeable into one PR." + "reason": "DepthAnything and DPR are distinct code paths; not the same bug/change." }, { "left": "pull_request:44026", "right": "pull_request:44027", "accept": false, - "reason": "Vision and speech encoder-decoder wrappers are separate implementations." + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are sibling wrappers but still separate code paths; not the same concrete fix." }, { "left": "pull_request:44026", "right": "pull_request:44028", "accept": false, - "reason": "Vision encoder-decoder and SuperPoint are different code paths." + "reason": "VisionEncoderDecoder vs SuperPoint are unrelated models; only generic tracing refactor similarity." }, { "left": "pull_request:44026", "right": "pull_request:44029", "accept": false, - "reason": "Different model families; same refactor motif only." + "reason": "VisionEncoderDecoder and RWKV are different architectures; not duplicates." }, { "left": "pull_request:44026", "right": "pull_request:44030", "accept": false, - "reason": "Vision encoder-decoder and DPR are unrelated changes." + "reason": "VisionEncoderDecoder and DPR are different model paths; no shared underlying bug." }, { "left": "pull_request:44027", "right": "pull_request:44028", "accept": false, - "reason": "Speech encoder-decoder and SuperPoint are not the same fix." + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations; not the same change." }, { "left": "pull_request:44027", "right": "pull_request:44029", "accept": false, - "reason": "Different model architectures and code paths." + "reason": "SpeechEncoderDecoder and RWKV are separate code paths; same cleanup theme only." }, { "left": "pull_request:44027", "right": "pull_request:44030", "accept": false, - "reason": "Speech encoder-decoder vs DPR is not one underlying bug." + "reason": "SpeechEncoderDecoder vs DPR are different model families; not mergeable as one fix." }, { "left": "pull_request:44028", "right": "pull_request:44029", "accept": false, - "reason": "SuperPoint and RWKV are unrelated model implementations." + "reason": "SuperPoint and RWKV are unrelated models; no same concrete bug or change." }, { "left": "pull_request:44028", "right": "pull_request:44030", "accept": false, - "reason": "Different subsystems; only the tracing refactor pattern matches." + "reason": "SuperPoint and DPR are different implementations; only the refactor motif overlaps." }, { "left": "pull_request:44029", "right": "pull_request:44030", "accept": false, - "reason": "RWKV and DPR fix different model code paths." + "reason": "RWKV and DPR are distinct model code paths; not a duplicate pair." } ] }, @@ -20027,52 +19952,52 @@ "pull_request:44662|pull_request:45075", "pull_request:45075|pull_request:45401" ], - "prepared_review_unit_hash": "fcb6170b17e6a9550a20a63400082459e49d6962a729f0df3200ff681e80eb79", + "prepared_review_unit_hash": "4f176dfcee5d238fae6cd2309ba621c0a55075e74a9bd9f02f67cbd30bc8b6f0", "component_budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "budget": { "node_count": 3, "item_count": 3, "soft_pair_count": 3, - "serialized_chars": 10913, - "estimated_input_tokens": 2729, - "estimated_eval_tokens": 5714 + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 }, "overflow_policy": "truncate_then_skip", "trimmed": false, "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three PRs are independent model-addition changes. They share boilerplate docs/auto-registration files, but they do not target the same model, code path, or bug, so none should be merged as duplicates.", + "summary": "Three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS); they overlap on scaffolding files but do not look like the same change.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "No canonical PR: 44662, 45075, and 45401 add different models (PenguinVL, DeepSeek-OCR-2, Voxtral TTS) with distinct implementations and tests.", + "canonical_pr_reason": "No canonical PR: each PR adds a different model family and different implementation/code paths, so they are not duplicates.", "best_issue_reason": null, - "best_pr_reason": "45075 is the most self-contained full model addition, but it is still unrelated to the other two and not a duplicate target.", + "best_pr_reason": "PR #45401 is the most self-contained/referenced (it targets an explicit issue), but it is still just a Voxtral TTS model addition and not a duplicate of the others.", "soft_edge_verdicts": [ { "left": "pull_request:44662", "right": "pull_request:45401", "accept": false, - "reason": "Different model additions for PenguinVL vs Voxtral TTS; shared auto/docs scaffolding is boilerplate, not the same change." + "reason": "PenguinVL vs Voxtral TTS are different model families with different tasks/code paths; shared auto-registration and docs scaffolding are not enough to treat them as the same change." }, { "left": "pull_request:44662", "right": "pull_request:45075", "accept": false, - "reason": "Both add new models, but PenguinVL and DeepSeek-OCR-2 are separate architectures and codepaths, so they are not duplicates." + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model implementations; overlapping repo setup files do not indicate the same underlying bug or feature." }, { "left": "pull_request:45075", "right": "pull_request:45401", "accept": false, - "reason": "DeepSeek-OCR-2 and Voxtral TTS are unrelated model implementations; overlap is only in generic registration/docs files." + "reason": "DeepSeek-OCR-2 (OCR/vision-language) and Voxtral TTS (speech generation) fix/add different concrete capabilities, so they should not be merged as duplicates." } ] }, @@ -20102,7 +20027,7 @@ "soft_pairs": [ "pull_request:44979|pull_request:45363" ], - "prepared_review_unit_hash": "a59286e46c7d735d0c39fb121d687f6c41ccdfa7703054c2048f0201cf5524c4", + "prepared_review_unit_hash": "bbb10481086ac862e35ef5db23838a2f7458671687e6fe339f98a3b74f4d457a", "component_budget": { "node_count": 2, "item_count": 2, @@ -20124,18 +20049,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These two PRs are related but not duplicates: #44979 introduces a new module fusion API and test coverage, while #45363 wires KernelConfig/kernel loading into model code and adds an example for n-to-1 kernel fusion. They address adjacent layers of the feature, not the same concrete change.", - "confidence": 0.93, + "summary": "These PRs are related by the general theme of module/kernel fusion, but they are not duplicates: one introduces a generic module fusion API, while the other implements a specific n-to-1 kernel-fusion path via `KernelConfig` and integration changes.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "#44979 is the more canonical PR for the cluster because it defines the underlying fusion abstraction/API and the core implementation lives there.", + "canonical_pr_reason": "No single canonical PR: #44979 is generic module-fusion infrastructure, while #45363 is a concrete `KernelConfig`-driven kernel-fusion implementation with different scope and code paths.", "best_issue_reason": null, - "best_pr_reason": "#44979 is the best representative PR because it contains the foundational code-path change; #45363 looks like a downstream integration/use-case on top of that API.", + "best_pr_reason": "#45363 is the more concrete and directly user-facing feature implementation; it targets specific integration points (`modeling_utils`, `integrations`, `kernel_config`) rather than just API scaffolding.", "soft_edge_verdicts": [ { "left": "pull_request:44979", "right": "pull_request:45363", "accept": false, - "reason": "Related feature area, but not the same underlying fix/change: #44979 adds the module fusion API itself, while #45363 integrates KernelConfig into model loading and provides an example. They could be merged separately and do not target one identical code path." + "reason": "Related fusion work, but not the same underlying change: #44979 adds a generic module-fusion API, while #45363 implements a specific kernel-fusion mechanism and example. They would not plausibly be merged as one PR." } ] }, @@ -20165,7 +20090,7 @@ "soft_pairs": [ "pull_request:45086|pull_request:45317" ], - "prepared_review_unit_hash": "60a54022aa86cbbe0f7ba8f8c5ea908d5a755051cde136107b54dc3aea819c0b", + "prepared_review_unit_hash": "a40971f848bea24dcd1d5999eb9317972bd75b0daaf3b92d7c47bdb18fce6e7a", "component_budget": { "node_count": 2, "item_count": 2, @@ -20187,18 +20112,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both pull requests target the same Mistral regex patch AttributeError in `tokenization_utils_tokenizers.py` and make the same code-path change from `backend_tokenizer.pre_tokenizer` to `pre_tokenizer`; 45317 is the more complete version because it also includes tests.", + "summary": "Both PRs address the same concrete bug in `_patch_mistral_regex`: an `AttributeError` from accessing `tokenizer.backend_tokenizer.pre_tokenizer` instead of `tokenizer.pre_tokenizer`. They touch the same code path and target the same issue; the second PR is the more complete fix because it adds tests.", "confidence": 0.98, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 and includes an added test file, making it the more complete change set.", + "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 but also includes test coverage, making it the more complete change set for the same bug.", "best_issue_reason": null, - "best_pr_reason": "PR 45317 is the best representative for this cluster: same underlying bug, same fix location, and extra test coverage.", + "best_pr_reason": "PR 45317 is the best representative because it fixes the same underlying AttributeError and adds validation tests, while remaining focused on the same code path.", "soft_edge_verdicts": [ { "left": "pull_request:45086", "right": "pull_request:45317", "accept": true, - "reason": "Same concrete bug and same fix in the same function/file; 45317 appears to be a superset with tests, so these are mergeable duplicates." + "reason": "Same underlying bug and same fix in the same function; 45317 is a superset with tests, so these are duplicate PRs for triage purposes." } ] }, @@ -20228,12 +20153,12 @@ "soft_pairs": [ "pull_request:45115|pull_request:45569" ], - "prepared_review_unit_hash": "ea1faa76471db62f8bdd5bd2039354bbf953e2abebfa94fc66d5979d267cb216", + "prepared_review_unit_hash": "916ae0b5f1abc23e16258a4afd9df30fbe086597b8edf555446e4f5301bb36b5", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6066, + "serialized_chars": 6065, "estimated_input_tokens": 1517, "estimated_eval_tokens": 3290 }, @@ -20241,7 +20166,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 6066, + "serialized_chars": 6065, "estimated_input_tokens": 1517, "estimated_eval_tokens": 3290 }, @@ -20250,18 +20175,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two open PRs both touch NemotronH internals, but they address different changes: one is a conversion/mapping + inheritance refactor, the other is a broader model split into NemotronHDense/Sparse with docs and tests. They are related but not the same change.", - "confidence": 0.89, + "summary": "These PRs overlap on NemotronH internals, but they are not the same change: #45115 is a targeted inheritance/refactor for NemotronH conversion and model wiring, while #45569 is a broader architectural split that introduces dedicated NemotronHDense/NemotronHSparse docs, configs, modeling, and tests. The shared files reflect the common base model area, not a duplicate fix.", + "confidence": 0.91, "canonical_issue_reason": null, - "canonical_pr_reason": "pull_request:45569 is the broader, more complete NemotronH refactor and family split, with model/config/docs/tests updates; it is the better canonical representative for this cluster.", + "canonical_pr_reason": "#45569 is the more complete and representative PR in this cluster because it encompasses the larger NemotronH family restructuring and the new dense/sparse model split, whereas #45115 is a narrower prerequisite-style refactor.", "best_issue_reason": null, - "best_pr_reason": "pull_request:45569 is the strongest standalone PR for triage because it covers the larger architecture update and is more likely to subsume the narrower conversion-mapping refactor.", + "best_pr_reason": "#45569 is the best PR to represent the cluster overall because it carries the main user-facing architectural change; #45115 is a smaller internal refactor and does not appear to fix the same concrete code-path problem.", "soft_edge_verdicts": [ { "left": "pull_request:45115", "right": "pull_request:45569", "accept": false, - "reason": "Shared NemotronH files do not mean the same change: 45115 is mainly checkpoint conversion and inheritance mapping, while 45569 introduces a broader NemotronHDense/Sparse refactor and documentation/test updates. They are not mergeable as one PR without conflating distinct work." + "reason": "Shared NemotronH files are not enough here: #45115 only adjusts conversion mapping and inheritance/refactoring, while #45569 introduces separate NemotronHDense/NemotronHSparse implementations, docs, and tests. They are related but not the same underlying change and would not plausibly merge as one duplicate PR." } ] }, @@ -20291,7 +20216,7 @@ "soft_pairs": [ "pull_request:45332|pull_request:45333" ], - "prepared_review_unit_hash": "e40267f8f80d86aa94928e62bb0d7657eef7672be50c0d14b7b3bac905a6a4aa", + "prepared_review_unit_hash": "6f62d14a7f04022feb8d9910f64e5d515a5b2fb217bcd7537b73768d90cbbab5", "component_budget": { "node_count": 2, "item_count": 2, @@ -20313,18 +20238,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Two related but distinct feature PRs: one adds heterogeneous per-layer config plumbing, the other adds heterogeneous model/cache behavior. They share files because the model PR builds on the config work, but they are not duplicates of the same concrete change.", - "confidence": 0.91, + "summary": "These PRs are closely related, but they are not the same change: one adds heterogeneous config support, while the other adds broader heterogeneous model/runtime support on top of that. The overlap in configuration files/tests reflects dependency, not duplicate scope.", + "confidence": 0.88, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45332 is the broader, more central change: it implements heterogeneous model support across cache/modeling paths and appears to consume the config plumbing from 45333. That makes it the best representative of the cluster.", + "canonical_pr_reason": "PR #45332 is the broader superset: it includes heterogeneous per-layer config handling plus modeling/cache changes, so it better represents the main combined feature work.", "best_issue_reason": null, - "best_pr_reason": "PR 45332 is the best standalone representative because it covers the larger end-to-end feature and is the primary code-path change; 45333 is narrower infrastructure support for that feature.", + "best_pr_reason": "PR #45332 is the best standalone representative because it covers the larger end-to-end heterogeneous support effort rather than only the config layer.", "soft_edge_verdicts": [ { "left": "pull_request:45332", "right": "pull_request:45333", "accept": false, - "reason": "Related feature work, but not the same underlying bug/change. 45333 is config plumbing for per-layer configuration, while 45332 changes cache/modeling behavior to use heterogeneous layer settings. They are complementary and could reasonably land separately, so they should not be merged as duplicates." + "reason": "Related but distinct scope: #45333 is config-only, while #45332 adds broader modeling/cache support and cannot be merged as the same concrete change." } ] }, @@ -20354,7 +20279,7 @@ "soft_pairs": [ "pull_request:45415|pull_request:45425" ], - "prepared_review_unit_hash": "7b28122dcf5cf2b3775efbde0aa231b42a49c71501056c4b21f1d6144318ee47", + "prepared_review_unit_hash": "511e3f8c507e7ec32c9f340a13916df3b43bc1e0e81fde56e8c2a0279d05709e", "component_budget": { "node_count": 2, "item_count": 2, @@ -20376,18 +20301,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both typing-related pull requests, but they are not the same change: one is a broad repo-wide type-checking sweep, the other is a narrower typing follow-up centered on _typing.py/modeling_utils. They may overlap in files, but they do not look mergeable as one duplicate fix.", - "confidence": 0.89, + "summary": "These are both typing-related PRs, but they address different changes: #45415 is a broad type-checking sweep across many files plus pyproject typing-ignore config, while #45425 adds specific typing protocols and model-integration helpers in a narrower area. They are similar in theme, not the same underlying change.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #45425 is the better canonical representative because it is a focused typing change with a clear scope, whereas PR #45415 is a much broader type-checking sweep across many files and config settings.", + "canonical_pr_reason": "#45425 is the more focused, concrete typing change; #45415 is a broad repo-wide type-checking cleanup with different scope and intent.", "best_issue_reason": null, - "best_pr_reason": "PR #45425 is the best single PR for this cluster because it is more self-contained and concrete; PR #45415 is too broad and mixes many unrelated typing adjustments.", + "best_pr_reason": "#45425 is the better representative of a single code-change topic because it introduces specific typing abstractions and targeted integrations, whereas #45415 is a sweeping lint/type cleanup across many files.", "soft_edge_verdicts": [ { "left": "pull_request:45415", "right": "pull_request:45425", "accept": false, - "reason": "Shared typing context and a few filenames, but the PRs address different scopes: #45415 is a large type-checking sweep across many modules, while #45425 adds specific typing protocols/aliases and modeling_utils support. They do not look like the same underlying bug/change." + "reason": "Shared typing theme only. #45415 is a broad type-checking/config sweep across many modules; #45425 adds specific protocols and model-related typing support. They are not the same concrete fix and would not merge cleanly as one PR." } ] }, @@ -20417,7 +20342,7 @@ "soft_pairs": [ "pull_request:45513|pull_request:46084" ], - "prepared_review_unit_hash": "52eb6ce8e8df80c91dba61f80b7ab45b1e2443e9af2926c1d16db8d1f88403a4", + "prepared_review_unit_hash": "5bcf75ac29f6f8c917aa310484afae783d9d502c4ca19b6223e5f247f92a143d", "component_budget": { "node_count": 2, "item_count": 2, @@ -20439,18 +20364,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs address different cached-forward bugs in different model families: PR #45513 fixes multi-token cached forward for OLMO/Qwen linear attention paths, while PR #46084 fixes Mamba2 use_cache behavior when seq_len > 1. They are not duplicates.", + "summary": "Two open PRs with a similar cache-aware decoding theme, but they fix different model families and different code paths: Qwen3.5/Qwen3-next/Olmo hybrid vs. Mamba2. They are not duplicates.", "confidence": 0.97, "canonical_issue_reason": null, - "canonical_pr_reason": "PR #46084 is the cleaner representative because it targets one concrete bug, has an explicit linked issue (#46032), and the diff is narrowly scoped to Mamba2 cached forward handling.", + "canonical_pr_reason": "No single canonical PR: these changes target different bugs in different model implementations rather than one shared fix.", "best_issue_reason": null, - "best_pr_reason": "PR #46084 is the best single PR for the cluster because it is the most self-contained fix with the clearest problem statement and least cross-model breadth.", + "best_pr_reason": "PR 46084 is the cleaner representative of its bug class: it has an explicit issue target (#46032) and a narrowly scoped fix/test for Mamba2 cache handling with seq_len > 1.", "soft_edge_verdicts": [ { "left": "pull_request:45513", "right": "pull_request:46084", "accept": false, - "reason": "Different model implementations and different bugs: 45513 fixes multi-token cached forward in OLMO/Qwen linear attention code paths, while 46084 fixes Mamba2 use_cache when seq_len > 1. They do not look like the same change and would not plausibly merge into one PR." + "reason": "Both involve cached forward logic, but they act on different architectures and different concrete paths; this is a theme match, not the same underlying change." } ] }, @@ -20480,7 +20405,7 @@ "soft_pairs": [ "pull_request:45548|pull_request:45662" ], - "prepared_review_unit_hash": "36b543c693abfbc3b73a661c3f1d95aa5b16b9e9999a844ca23d4dc8d6803b30", + "prepared_review_unit_hash": "c6a0c4f60ad0a9a7d9d66f03287bb9cb114a0937cc6695b7c2d98d3b8eb95227", "component_budget": { "node_count": 2, "item_count": 2, @@ -20502,18 +20427,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are both expert-parallelism-related PRs, but they fix different bugs in different loading paths: one is about preserving distributed_config/has_ep for DeepSpeed ZeRO-3 + accelerate launch, the other is about preventing expert parameters from being overwritten during FSDP2/sharded loading.", + "summary": "These two PRs share an expert-parallelism theme, but they fix different loading bugs in different distributed paths: DeepSpeed ZeRO-3/accelerate launch vs FSDP2 rank-0 broadcast overwriting experts.", "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "No single canonical PR: the changes address separate EP loading defects in different code paths, so they should not be collapsed into one duplicate.", + "canonical_pr_reason": "PR 45662 is the better representative of the cluster because it targets a concrete, multi-file loading bug in the expert-parallel/FSDP2 path with direct code-path fixes.", "best_issue_reason": null, - "best_pr_reason": "pull_request:45662 is the more concrete runtime fix for expert parameters being clobbered during distributed loading, while 45548 is a separate config/serialization and EP-detection change.", + "best_pr_reason": "PR 45662 is the stronger standalone PR: it addresses a specific failure mode, changes the relevant loader/integration code, and has the broader technical scope.", "soft_edge_verdicts": [ { "left": "pull_request:45548", "right": "pull_request:45662", "accept": false, - "reason": "Do not merge as duplicates: 45548 fixes EP + DeepSpeed ZeRO-3/accelerate config handling, while 45662 fixes EP + FSDP2 expert weights being overwritten via rank-0 broadcast. Shared EP context and modeling_utils is not enough to indicate the same underlying bug." + "reason": "Both concern EP loading, but they fix different underlying problems and code paths. 45548 adds distributed_config serialization and a has_ep property for DeepSpeed ZeRO-3/accelerate launch; 45662 prevents expert parameters from being overwritten after FSDP2 sharding. They are related but not the same change." } ] }, @@ -20543,7 +20468,7 @@ "soft_pairs": [ "pull_request:45639|pull_request:45645" ], - "prepared_review_unit_hash": "8ba5d2acc286c66dd78fb5466ec017edb33b3246fa8357cf5f18e01272c0a524", + "prepared_review_unit_hash": "54a222fd9d42d89a0b3adfffb13c6197699d0a7326e7671ec31f9bc19c0ad063", "component_budget": { "node_count": 2, "item_count": 2, @@ -20565,18 +20490,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "Both PRs target the same captured_info/xdist collision problem in testing_utils; 45645 is the broader, more complete fix because it also updates CI log collection to handle multiple captured_info files.", + "summary": "Both PRs address the same xdist/captured_info collision in testing debug artifacts; PR 45645 is the broader, more complete fix, while 45639 is a narrower subset.", "confidence": 0.89, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 45645 is the better representative because it contains the core xdist-safe output-file change plus the downstream CI/workflow handling needed to consume multiple captured_info artifacts.", + "canonical_pr_reason": "PR 45645 is the better canonical PR because it contains the core xdist-safe captured_info fix plus the CI/workflow adjustments needed to consume the new per-worker artifact layout.", "best_issue_reason": null, - "best_pr_reason": "PR 45645 is the strongest single PR for the cluster: it subsumes the utility change from 45639 and extends it to preserve CI debug logs, making it the most complete implementation of the underlying fix.", + "best_pr_reason": "PR 45645 is the best overall PR here since it covers the same underlying bug and includes the downstream handling changes, making it the most complete representative of the fix.", "soft_edge_verdicts": [ { "left": "pull_request:45639", "right": "pull_request:45645", "accept": true, - "reason": "Both PRs address the same underlying captured_info artifact collision under xdist; 45645 is an expanded version of the same fix, not a separate change." + "reason": "Same underlying xdist collision bug for captured_info artifacts; 45645 is a superset that adds the workflow-side log collection changes, so these are plausibly merged into one PR." } ] }, @@ -20608,7 +20533,7 @@ "pull_request:45720|pull_request:46259", "pull_request:46023|pull_request:46259" ], - "prepared_review_unit_hash": "ed518e26376b94d20d68eb0a20bbeec4d3988439ce1fb6e0a7f240e0b7d07c8e", + "prepared_review_unit_hash": "ec48c4c91aa9b458922469d94ef2c2269a42e310411e32afbb2d17229c2455bd", "component_budget": { "node_count": 3, "item_count": 3, @@ -20630,24 +20555,24 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are three distinct open PRs in the same linter/modeling-rules area, but they target different rules and code paths: TRF003 tuple-return cleanup, TRF016 dead do_* flag checks, and TRF018 modeling-rule additions. They are not duplicates of the same underlying change.", - "confidence": 0.95, + "summary": "These PRs are all linter/rule-related, but they target different underlying checks: TRF003 tuple-return behavior, TRF016 dead do_* flags in image/video processors, and TRF018-related modeling-rule additions. The only close pair (46023 vs 46259) shares infra/docs files but not the same bug/change.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": null, + "canonical_pr_reason": "PR 46259 is the best representative of the linter-rule cluster: it is the latest and broadest rule addition, with the clearest shared rule-doc/config footprint.", "best_issue_reason": null, - "best_pr_reason": "No PR is a true cluster canonical; if forced, PR 46023 is the closest representative of the shared modeling-rules/linter theme, but it still fixes a different rule than the others.", + "best_pr_reason": "PR 46259 is the strongest standalone candidate because it adds the most complete rule implementation and touches the widest set of affected model files.", "soft_edge_verdicts": [ { "left": "pull_request:45720", "right": "pull_request:46259", "accept": false, - "reason": "Different linter rules and different code paths: TRF003 tuple-return decorator cleanup in model forwards vs TRF018 image/video processor flag-consumption checks. Shared models are incidental and not mergeable as one PR." + "reason": "Different rule families and code paths: 45720 is about can_return_tuple / forward return handling, while 46259 is about dead do_* preprocessing flags. Same repo area, not the same change." }, { "left": "pull_request:46023", "right": "pull_request:46259", "accept": false, - "reason": "Both touch modeling_rules docs and many model files, but they implement different rule numbers and different behaviors (TRF016 vs TRF018). This is not the same underlying fix." + "reason": "Both are linter-rule updates, but TRF016 and TRF018 target different dead-flag patterns and different model families. Shared docs/config files are not enough to treat them as the same fix." } ] }, @@ -20746,7 +20671,7 @@ "pull_request:46073|pull_request:46196", "pull_request:46154|pull_request:46196" ], - "prepared_review_unit_hash": "6670964f5c5fe45dd8f6101a0eb6f6ba2e7c2780a624a0c1563bed60101de530", + "prepared_review_unit_hash": "07510306d928c2f5e834f787a267a7144ccc17e37e2c20d3bd41e922a3df4957", "component_budget": { "node_count": 3, "item_count": 3, @@ -20768,30 +20693,30 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "All three pull requests are related to enabling SDPA attention dispatch, but they target different model families and code paths, so they are not duplicates of one another.", - "confidence": 0.89, + "summary": "All three pull requests are about enabling SDPA dispatch, but they target different model families and code paths, so they are not duplicates. The broadest and most complete PR is the wav2vec2_conformer/SeamlessM4T one, but the others remain separate changes.", + "confidence": 0.93, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46196 is the broadest and most representative of the cluster: it covers multiple related model implementations and associated tests for SDPA dispatch.", + "canonical_pr_reason": "PR 46196 is the broadest and most developed change, covering multiple related speech/text models and including corresponding tests, so it is the best representative PR in this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR 46196 is the best overall representative because it spans several model variants and appears to be the most comprehensive SDPA-dispatch change in the set.", + "best_pr_reason": "PR 46196 has the widest scope and the most supporting test coverage, making it the strongest single PR candidate for the cluster.", "soft_edge_verdicts": [ { "left": "pull_request:46073", "right": "pull_request:46154", "accept": false, - "reason": "Both are SDPA-dispatch PRs, but one is for CTRL and the other for T5; they modify different model-specific attention paths and would not be merged into a single concrete fix." + "reason": "Both are SDPA-dispatch work, but one is for CTRL and the other for T5; they touch different model implementations and are not the same fix." }, { "left": "pull_request:46073", "right": "pull_request:46196", "accept": false, - "reason": "These cover different model families (CTRL vs wav2vec2_conformer/bert and SeamlessM4T/v2) with separate implementation details, so they are not the same underlying change." + "reason": "These target different model families and code paths (CTRL vs wav2vec2/SeamlessM4T), so they are related by theme only, not by duplicate bug or mergeable change." }, { "left": "pull_request:46154", "right": "pull_request:46196", "accept": false, - "reason": "T5 SDPA support and the multi-model wav2vec2/SeamlessM4T dispatch work are related in theme only; they address distinct code paths and are too different to treat as duplicates." + "reason": "T5 SDPA dispatch is a separate model-specific implementation from wav2vec2/SeamlessM4T SDPA dispatch; they should not be merged as one PR." } ] }, @@ -20821,12 +20746,12 @@ "soft_pairs": [ "pull_request:46126|pull_request:46269" ], - "prepared_review_unit_hash": "6928c0eef65d2d31ee43414c60165e9119cec2f9c1daaf114e6ad553bff1dadd", + "prepared_review_unit_hash": "fbc28c5a4e709e299c8619d729d978b7544290cce05b9f6131fd619f63a20d60", "component_budget": { "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5571, + "serialized_chars": 5570, "estimated_input_tokens": 1393, "estimated_eval_tokens": 3042 }, @@ -20834,7 +20759,7 @@ "node_count": 2, "item_count": 2, "soft_pair_count": 1, - "serialized_chars": 5571, + "serialized_chars": 5570, "estimated_input_tokens": 1393, "estimated_eval_tokens": 3042 }, @@ -20843,18 +20768,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These are not duplicates: PR 46126 is a focused EP/router + Trainer integration change, while PR 46269 is a broad distributed branch base spanning many subsystems and files. The shared distributed filenames are too generic to indicate the same concrete change.", - "confidence": 0.95, + "summary": "Two pull requests only weakly overlap on distributed files, but they are not the same change: one is a focused EP/trainer integration PR, the other is a broad distributed branch-base PR with many unrelated edits.", + "confidence": 0.94, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46126 is the more focused, self-contained change; PR 46269 is a broad base-branch PR touching many unrelated distributed areas, so it is not a good duplicate canonical.", + "canonical_pr_reason": "PR #46126 is the focused, concrete EP + trainer integration change; it has a narrow implementation footprint and a clear purpose, unlike the broad branch-base PR.", "best_issue_reason": null, - "best_pr_reason": "PR 46126 is the best representative of the cluster because it targets a specific EP/Trainer integration path. PR 46269 is too broad and looks like an umbrella/base branch rather than the same fix.", + "best_pr_reason": "PR #46126 is the best representative of the cluster because it targets a specific distributed feature path, whereas #46269 is an umbrella branch-base carrying many unrelated distributed changes.", "soft_edge_verdicts": [ { "left": "pull_request:46126", "right": "pull_request:46269", "accept": false, - "reason": "Do not merge: they do not appear to fix the same concrete code-path problem. 46126 adds RouterParallel/EP behavior and Trainer integration, while 46269 is a large distributed base PR spanning FSDP, tensor parallel, MoE, and core loading changes." + "reason": "Shared distributed filenames do not indicate the same underlying bug or mergeable change. #46126 is a focused EP/trainer integration patch; #46269 is a broad distributed base branch spanning FSDP, CI, integrations, and model files, so they should not be merged as duplicates." } ] }, @@ -20884,7 +20809,7 @@ "soft_pairs": [ "pull_request:46152|pull_request:46207" ], - "prepared_review_unit_hash": "a81b8d8dd248eece191a912c2491cf16a16217612a6033e094382b6eaf4db3cb", + "prepared_review_unit_hash": "2f9fc36c5298bb9fd52f0c9e7d4510960a64880b00bd4ba1b98fe63048508fd3", "component_budget": { "node_count": 2, "item_count": 2, @@ -20906,18 +20831,18 @@ "aggressively_trimmed": false, "split": false, "analyst_result": { - "summary": "These PRs share a broad theme of replacing file-open source inspection with safer source retrieval, but they fix different code paths in different modules and should not be treated as duplicates.", - "confidence": 0.93, + "summary": "Both PRs replace direct source-file opening with safer source/resource inspection, but they target different code paths and different behaviors, so they are related in theme rather than duplicates.", + "confidence": 0.92, "canonical_issue_reason": null, - "canonical_pr_reason": "PR 46152 is the cleaner representative of the shared theme: it changes import_utils to avoid opening its own source file, whereas 46207 is a separate modeling_utils source-inspection tweak.", + "canonical_pr_reason": "PR 46207 is the stronger representative: it has a clearer, narrower concrete behavior change in _can_set_attn_implementation and includes tests, making it the better canonical PR for this cluster.", "best_issue_reason": null, - "best_pr_reason": "PR 46152 is the most central example of the anti-open() refactor pattern in this cluster; 46207 is related in spirit but addresses a different subsystem and code path.", + "best_pr_reason": "PR 46207 is the best standalone example of the cluster\u2019s theme because it cleanly addresses one source-reading heuristic with test coverage; PR 46152 is a separate implementation in a different module.", "soft_edge_verdicts": [ { "left": "pull_request:46152", "right": "pull_request:46207", "accept": false, - "reason": "Different concrete fixes in different modules: import_utils resource loading vs modeling_utils inspect.getsource for attention-implementation gating. They share a style/theme, but not the same underlying bug or a mergeable single PR." + "reason": "Same general pattern (avoid open() on source), but they fix different functions in different files with different semantics: import_utils resource resolution vs modeling_utils attention-implementation detection. They are not the same underlying bug and would not plausibly be merged as one PR." } ] }, diff --git a/analysis/current/manifest.json b/analysis/current/manifest.json index c88029bb5b0fa45be065cd43d9a4cadce322417a..55e6fd9e9224316dc24d4059ba39b1a3b87d7757 100644 --- a/analysis/current/manifest.json +++ b/analysis/current/manifest.json @@ -1,8 +1,8 @@ { - "analysis_id": "hybrid-model-20260530t180032z", + "analysis_id": "hybrid-model-20260531t000035z", "archived_artifacts": { - "hybrid": "snapshots/20260530T180032Z/analysis-runs/hybrid-model-20260530t180032z/analysis-report-hybrid.json", - "hybrid_reviews": "snapshots/20260530T180032Z/analysis-runs/hybrid-model-20260530t180032z/analysis-report-hybrid.llm-reviews.json" + "hybrid": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json" }, "artifacts": { "hybrid": "analysis/current/analysis-report-hybrid.json", @@ -10,9 +10,9 @@ }, "channel": "canonical", "model": null, - "published_at": "2026-05-30T18:04:58Z", + "published_at": "2026-05-31T00:04:31Z", "repo": "huggingface/transformers", "schema_version": 1, - "snapshot_id": "20260530T180032Z", + "snapshot_id": "20260531T000035Z", "variant": "hybrid" } diff --git a/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json new file mode 100644 index 0000000000000000000000000000000000000000..151546ff5202ec2d841d6612d8a326aaed30911a --- /dev/null +++ b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json @@ -0,0 +1,1997 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260531T000035Z", + "generated_at": "2026-05-31T00:04:30Z", + "evidence_quality": "full", + "llm_enrichment": true, + "meta_bugs": [ + { + "cluster_id": "cluster-43979-11", + "summary": "Cluster of 1 issues and 10 PRs centered on issue #43979.", + "status": "open", + "confidence": 0.8, + "canonical_issue_number": 43979, + "canonical_pr_number": 44007, + "issue_numbers": [ + 43979 + ], + "pr_numbers": [ + 43996, + 44007, + 44013, + 44044, + 44066, + 44072, + 44085, + 44129, + 44154, + 44722 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target", + "soft_similarity" + ], + "pr_comparisons": [ + { + "left_pr_number": 43996, + "right_pr_number": 44007, + "code_similarity": 0.179, + "size_similarity": 0.576, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.429, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44013, + "code_similarity": 0.122, + "size_similarity": 0.318, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.392, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44044, + "code_similarity": 0.245, + "size_similarity": 0.864, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.479, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44066, + "code_similarity": 0.225, + "size_similarity": 0.818, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.408, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44072, + "code_similarity": 0.14, + "size_similarity": 0.303, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.528, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44085, + "code_similarity": 0.216, + "size_similarity": 0.783, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44129, + "code_similarity": 0.163, + "size_similarity": 0.643, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.229, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44154, + "code_similarity": 0.153, + "size_similarity": 0.535, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.31, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 43996, + "right_pr_number": 44722, + "code_similarity": 0.225, + "size_similarity": 0.848, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.368, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44013, + "code_similarity": 0.19, + "size_similarity": 0.553, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.531, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44044, + "code_similarity": 0.186, + "size_similarity": 0.667, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.354, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44066, + "code_similarity": 0.188, + "size_similarity": 0.704, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.315, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44072, + "code_similarity": 0.212, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.708, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44085, + "code_similarity": 0.195, + "size_similarity": 0.735, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.318, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44129, + "code_similarity": 0.103, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.191, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44154, + "code_similarity": 0.238, + "size_similarity": 0.93, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.344, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44007, + "right_pr_number": 44722, + "code_similarity": 0.178, + "size_similarity": 0.679, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.28, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44044, + "code_similarity": 0.126, + "size_similarity": 0.368, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.351, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44066, + "code_similarity": 0.127, + "size_similarity": 0.389, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.325, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44072, + "code_similarity": 0.29, + "size_similarity": 0.952, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.667, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44085, + "code_similarity": 0.131, + "size_similarity": 0.406, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.329, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44129, + "code_similarity": 0.07, + "size_similarity": 0.205, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.192, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44154, + "code_similarity": 0.177, + "size_similarity": 0.594, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.389, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44013, + "right_pr_number": 44722, + "code_similarity": 0.118, + "size_similarity": 0.375, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.287, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44066, + "code_similarity": 0.25, + "size_similarity": 0.947, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.404, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44072, + "code_similarity": 0.136, + "size_similarity": 0.351, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.442, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44085, + "code_similarity": 0.24, + "size_similarity": 0.906, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.394, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44129, + "code_similarity": 0.147, + "size_similarity": 0.555, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.243, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44154, + "code_similarity": 0.17, + "size_similarity": 0.62, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.306, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44044, + "right_pr_number": 44722, + "code_similarity": 0.257, + "size_similarity": 0.982, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.402, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44072, + "code_similarity": 0.133, + "size_similarity": 0.37, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.393, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44085, + "code_similarity": 0.763, + "size_similarity": 0.957, + "file_overlap": 0.5, + "area_overlap": 0.825, + "patch_similarity": 0.887, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ] + } + ] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44129, + "code_similarity": 0.145, + "size_similarity": 0.526, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.263, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44154, + "code_similarity": 0.174, + "size_similarity": 0.654, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.286, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44066, + "right_pr_number": 44722, + "code_similarity": 0.907, + "size_similarity": 0.964, + "file_overlap": 1.0, + "area_overlap": 0.808, + "patch_similarity": 0.874, + "shared_filenames": [ + "src/transformers/models/codegen/modeling_codegen.py", + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/codegen/modeling_codegen.py", + "left_ranges": [ + [ + 245, + 266 + ] + ], + "right_ranges": [ + [ + 228, + 234 + ] + ] + }, + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 41 + ], + [ + 174, + 181 + ], + [ + 250, + 257 + ], + [ + 398, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 466 + ], + [ + 471, + 488 + ], + [ + 518, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 606 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44085, + "code_similarity": 0.137, + "size_similarity": 0.387, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.398, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44129, + "code_similarity": 0.074, + "size_similarity": 0.195, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.231, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44154, + "code_similarity": 0.175, + "size_similarity": 0.566, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.414, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44072, + "right_pr_number": 44722, + "code_similarity": 0.124, + "size_similarity": 0.357, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.347, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44129, + "code_similarity": 0.141, + "size_similarity": 0.503, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.272, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44154, + "code_similarity": 0.18, + "size_similarity": 0.684, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.289, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44085, + "right_pr_number": 44722, + "code_similarity": 0.728, + "size_similarity": 0.923, + "file_overlap": 0.5, + "area_overlap": 0.791, + "patch_similarity": 0.78, + "shared_filenames": [ + "src/transformers/models/gptj/modeling_gptj.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/gptj/modeling_gptj.py", + "left_ranges": [ + [ + 33, + 40 + ], + [ + 173, + 180 + ], + [ + 249, + 256 + ], + [ + 397, + 405 + ], + [ + 408, + 419 + ], + [ + 425, + 434 + ], + [ + 459, + 465 + ], + [ + 470, + 489 + ], + [ + 517, + 539 + ], + [ + 553, + 559 + ], + [ + 565, + 574 + ], + [ + 579, + 597 + ], + [ + 600, + 611 + ], + [ + 633, + 639 + ], + [ + 645, + 652 + ], + [ + 657, + 673 + ], + [ + 716, + 728 + ], + [ + 737, + 743 + ], + [ + 748, + 771 + ], + [ + 789, + 794 + ] + ], + "right_ranges": [ + [ + 33, + 42 + ], + [ + 175, + 182 + ], + [ + 251, + 258 + ], + [ + 399, + 420 + ], + [ + 426, + 435 + ], + [ + 460, + 467 + ], + [ + 472, + 489 + ], + [ + 519, + 540 + ], + [ + 554, + 560 + ], + [ + 566, + 575 + ], + [ + 580, + 598 + ], + [ + 601, + 612 + ], + [ + 634, + 640 + ], + [ + 646, + 653 + ], + [ + 658, + 663 + ], + [ + 666, + 674 + ], + [ + 717, + 722 + ], + [ + 738, + 744 + ], + [ + 749, + 772 + ], + [ + 790, + 795 + ] + ] + } + ] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44154, + "code_similarity": 0.099, + "size_similarity": 0.344, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.199, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44129, + "right_pr_number": 44722, + "code_similarity": 0.146, + "size_similarity": 0.545, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.247, + "shared_filenames": [], + "shared_file_areas": [] + }, + { + "left_pr_number": 44154, + "right_pr_number": 44722, + "code_similarity": 0.164, + "size_similarity": 0.631, + "file_overlap": 0.0, + "area_overlap": 0.0, + "patch_similarity": 0.255, + "shared_filenames": [], + "shared_file_areas": [] + } + ] + }, + { + "cluster_id": "cluster-41211-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41211.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41211, + "canonical_pr_number": 44339, + "issue_numbers": [ + 41211 + ], + "pr_numbers": [ + 41356, + 44339 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41356, + "right_pr_number": 44339, + "code_similarity": 0.155, + "size_similarity": 0.094, + "file_overlap": 0.273, + "area_overlap": 0.078, + "patch_similarity": 0.183, + "shared_filenames": [ + "docs/source/en/model_doc/deimv2.md", + "src/transformers/models/deimv2/__init__.py", + "src/transformers/models/deimv2/configuration_deimv2.py", + "src/transformers/models/deimv2/modeling_deimv2.py", + "tests/models/deimv2/__init__.py", + "tests/models/deimv2/test_modeling_deimv2.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/model_doc/deimv2.md", + "left_ranges": [ + [ + 1, + 132 + ] + ], + "right_ranges": [ + [ + 1, + 65 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/__init__.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/deimv2/configuration_deimv2.py", + "left_ranges": [ + [ + 1, + 74 + ] + ], + "right_ranges": [ + [ + 1, + 266 + ] + ] + }, + { + "filename": "tests/models/deimv2/test_modeling_deimv2.py", + "left_ranges": [ + [ + 1, + 15 + ] + ], + "right_ranges": [ + [ + 1, + 1734 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-43240-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #43240.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 43240, + "canonical_pr_number": 43251, + "issue_numbers": [ + 43240 + ], + "pr_numbers": [ + 43251, + 43254 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 43251, + "right_pr_number": 43254, + "code_similarity": 0.794, + "size_similarity": 0.64, + "file_overlap": 1.0, + "area_overlap": 0.667, + "patch_similarity": 0.882, + "shared_filenames": [ + "src/transformers/loss/loss_utils.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/loss/loss_utils.py", + "left_ranges": [ + [ + 30, + 50 + ] + ], + "right_ranges": [ + [ + 30, + 43 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-41115-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #41115.", + "status": "open", + "confidence": 0.55, + "canonical_issue_number": 41115, + "canonical_pr_number": 45613, + "issue_numbers": [ + 41115 + ], + "pr_numbers": [ + 41116, + 45613 + ], + "evidence_types": [ + "closing_reference" + ], + "pr_comparisons": [ + { + "left_pr_number": 41116, + "right_pr_number": 45613, + "code_similarity": 0.797, + "size_similarity": 0.885, + "file_overlap": 0.75, + "area_overlap": 0.831, + "patch_similarity": 0.693, + "shared_filenames": [ + "docs/source/en/_toctree.yml", + "docs/source/en/model_doc/minicpm3.md", + "src/transformers/models/auto/modeling_auto.py", + "src/transformers/models/minicpm3/__init__.py", + "src/transformers/models/minicpm3/configuration_minicpm3.py", + "src/transformers/models/minicpm3/modeling_minicpm3.py", + "src/transformers/models/minicpm3/modular_minicpm3.py", + "tests/models/minicpm3/__init__.py", + "tests/models/minicpm3/test_modeling_minicpm3.py" + ], + "shared_file_areas": [ + { + "filename": "docs/source/en/_toctree.yml", + "left_ranges": [ + [ + 713, + 720 + ] + ], + "right_ranges": [ + [ + 730, + 737 + ] + ] + }, + { + "filename": "docs/source/en/model_doc/minicpm3.md", + "left_ranges": [ + [ + 1, + 67 + ] + ], + "right_ranges": [ + [ + 1, + 45 + ] + ] + }, + { + "filename": "src/transformers/models/auto/modeling_auto.py", + "left_ranges": [ + [ + 285, + 291 + ], + [ + 700, + 706 + ], + [ + 1298, + 1304 + ] + ], + "right_ranges": [ + [ + 720, + 726 + ], + [ + 1331, + 1337 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/__init__.py", + "left_ranges": [ + [ + 1, + 29 + ] + ], + "right_ranges": [ + [ + 1, + 29 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/configuration_minicpm3.py", + "left_ranges": [ + [ + 1, + 141 + ] + ], + "right_ranges": [ + [ + 1, + 126 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 544 + ] + ], + "right_ranges": [ + [ + 1, + 522 + ] + ] + }, + { + "filename": "src/transformers/models/minicpm3/modular_minicpm3.py", + "left_ranges": [ + [ + 1, + 444 + ] + ], + "right_ranges": [ + [ + 1, + 342 + ] + ] + }, + { + "filename": "tests/models/minicpm3/test_modeling_minicpm3.py", + "left_ranges": [ + [ + 1, + 109 + ] + ], + "right_ranges": [ + [ + 1, + 136 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-45647-3", + "summary": "Cluster of 1 issues and 2 PRs centered on issue #45647.", + "status": "open", + "confidence": 0.75, + "canonical_issue_number": 45647, + "canonical_pr_number": 45738, + "issue_numbers": [ + 45647 + ], + "pr_numbers": [ + 45737, + 45738 + ], + "evidence_types": [ + "closing_reference", + "shared_issue_target" + ], + "pr_comparisons": [ + { + "left_pr_number": 45737, + "right_pr_number": 45738, + "code_similarity": 0.526, + "size_similarity": 0.11, + "file_overlap": 0.5, + "area_overlap": 1.0, + "patch_similarity": 0.024, + "shared_filenames": [ + "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py" + ], + "shared_file_areas": [ + { + "filename": "src/transformers/models/musicgen_melody/modeling_musicgen_melody.py", + "left_ranges": [ + [ + 491, + 497 + ] + ], + "right_ranges": [ + [ + 491, + 497 + ] + ] + } + ] + } + ] + }, + { + "cluster_id": "cluster-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 13 discussion comments plus 8 inbound references.", + "score": 164.0 + }, + "best_pr": { + "cluster_id": "cluster-43979-11", + "pr_number": 44007, + "reason": "PR #44007 is the strongest global PR candidate because it is open, belongs to a cluster with 11 artifacts, links to 1 issues, and carries 2 review/discussion events.", + "score": 238.886 + } +} diff --git a/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json new file mode 100644 index 0000000000000000000000000000000000000000..86c98a9bec8f01283af0ca3e3c03d08ee87a2e02 --- /dev/null +++ b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json @@ -0,0 +1,20857 @@ +{ + "schema_version": "1.0", + "repo": "huggingface/transformers", + "snapshot_id": "20260531T000035Z", + "generated_at": "2026-05-31T00:04:30Z", + "model": "gpt-5.4-mini?service_tier=flex", + "reviews": [ + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:24643", + "issue:30277", + "issue:34634", + "issue:34928", + "issue:35545", + "issue:36010", + "issue:36331", + "issue:39290", + "issue:41720", + "issue:41762", + "issue:42915", + "issue:43039", + "issue:43425", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43827", + "issue:43828", + "issue:43901", + "issue:43975", + "issue:44292", + "issue:44322", + "issue:44457", + "issue:44509", + "issue:44512", + "issue:44560", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45081", + "issue:45161", + "issue:45237", + "issue:45464", + "issue:45507", + "issue:45685", + "issue:45812", + "issue:45823", + "issue:45859", + "issue:45874", + "issue:45901", + "issue:45902", + "issue:45920", + "issue:46015", + "issue:46165", + "issue:46294" + ], + "soft_pairs": [ + "issue:44322|issue:45464", + "issue:45237|issue:45685", + "issue:43716|issue:45237", + "issue:43828|issue:45237", + "issue:45237|issue:45507", + "issue:44292|issue:45237", + "issue:30277|issue:35545", + "issue:35545|issue:42915", + "issue:35545|issue:41720", + "issue:45901|issue:46015", + "issue:44509|issue:44512", + "issue:35545|issue:36010", + "issue:44918|issue:46165", + "issue:44805|issue:45823", + "issue:43638|issue:44805", + "issue:43638|issue:46165", + "issue:43596|issue:44805", + "issue:44805|issue:46294", + "issue:44805|issue:45161", + "issue:44560|issue:46165", + "issue:43596|issue:46165", + "issue:43572|issue:46165", + "issue:34634|issue:35545", + "issue:30277|issue:43638", + "issue:43596|issue:43638", + "issue:43975|issue:44457", + "issue:43039|issue:45161", + "issue:44292|issue:44457", + "issue:24643|issue:30277", + "issue:34928|issue:44805", + "issue:45859|issue:45902", + "issue:43638|issue:45161", + "issue:34928|issue:36331", + "issue:43596|issue:45161", + "issue:43716|issue:45507", + "issue:45874|issue:46294", + "issue:39290|issue:45081", + "issue:45823|issue:45874", + "issue:43425|issue:44292", + "issue:34928|issue:41720", + "issue:43828|issue:45161", + "issue:43541|issue:43716", + "issue:43828|issue:44292", + "issue:43716|issue:45685", + "issue:44918|issue:45161", + "issue:43716|issue:44292", + "issue:44292|issue:44918", + "issue:45507|issue:45685", + "issue:43039|issue:44918", + "issue:41762|issue:43638", + "issue:43827|issue:44512", + "issue:43716|issue:44560", + "issue:43828|issue:45685", + "issue:44918|issue:45685", + "issue:43039|issue:43828", + "issue:30277|issue:36331", + "issue:34928|issue:36010", + "issue:45237|issue:46015", + "issue:43039|issue:44805", + "issue:39290|issue:41720", + "issue:41762|issue:43596", + "issue:43901|issue:44512", + "issue:45237|issue:45901", + "issue:45823|issue:46294", + "issue:44841|issue:45823", + "issue:43039|issue:44560", + "issue:43975|issue:46015", + "issue:45812|issue:45920", + "issue:44863|issue:46015" + ], + "prepared_review_unit_hash": "a733d04bd55dd91f50c55b6bb3d9a41dc1782ce889ccd3704fd89476cfd78525", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 69, + "serialized_chars": 48479, + "estimated_input_tokens": 12120, + "estimated_eval_tokens": 24496 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated issue reports with a few true duplicate clusters: ZeRO-3 index-out-of-bounds on model load, a v5 AutoTokenizer token-ID regression, and Qwen3_5Moe rotary-embedding/offload materialization. Most other soft matches are broad-similarity false positives and should stay separate.", + "confidence": 0.84, + "canonical_issue_reason": "The broadest open report for the tokenizer regression cluster: it covers wrong token IDs across multiple model families, making it the best dedupe anchor among the accepted duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "Most comprehensive and actionable issue in the set for the v5 AutoTokenizer token-ID bug; it generalizes the Granite-specific report to the wider affected models.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44322", + "right": "issue:45464", + "accept": false, + "reason": "Different failures: missing config field vs chat/completions streaming API behavior." + }, + { + "left": "issue:45237", + "right": "issue:45685", + "accept": false, + "reason": "Different model/platform bug; AMD GPU failure is unrelated to the MPS histogram Int error." + }, + { + "left": "issue:43716", + "right": "issue:45237", + "accept": false, + "reason": "Different models and code paths; image-preprocessor dtype mismatch is not the GPT-OSS AMD GPU issue." + }, + { + "left": "issue:43828", + "right": "issue:45237", + "accept": false, + "reason": "Different dtype/device problems on different models; not the same bug." + }, + { + "left": "issue:45237", + "right": "issue:45507", + "accept": false, + "reason": "Different failure modes: GPU runtime issue vs invalid method call in a MoE model." + }, + { + "left": "issue:44292", + "right": "issue:45237", + "accept": false, + "reason": "Different models and symptoms; NVFP4 runtime error is not the AMD GPU 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": "Different inference/export stack issues with no shared code path." + }, + { + "left": "issue:35545", + "right": "issue:41720", + "accept": false, + "reason": "ONNX export failure vs auto device-mapping cuda assert; unrelated." + }, + { + "left": "issue:45901", + "right": "issue:46015", + "accept": false, + "reason": "Task crash vs docs/example freshness; not the same underlying bug." + }, + { + "left": "issue:44509", + "right": "issue:44512", + "accept": false, + "reason": "Both are v5 docs cleanups, but they target different removed features and pages." + }, + { + "left": "issue:35545", + "right": "issue:36010", + "accept": false, + "reason": "ONNX export error and GenerationMixin import failure are separate issues." + }, + { + "left": "issue:44918", + "right": "issue:46165", + "accept": false, + "reason": "Different training-related bugs: SFT input-embedding handling vs resuming with trust_remote_code." + }, + { + "left": "issue:44805", + "right": "issue:45823", + "accept": false, + "reason": "Mask-shape IndexError and Gemma4 device mismatch are different problems." + }, + { + "left": "issue:43638", + "right": "issue:44805", + "accept": false, + "reason": "Both are errors, but one is ZeRO-3 empty-index loading and the other is a mask/tensor shape mismatch." + }, + { + "left": "issue:43638", + "right": "issue:46165", + "accept": false, + "reason": "Unrelated training-resume issue; no shared code path with the ZeRO-3 Bert bug." + }, + { + "left": "issue:43596", + "right": "issue:44805", + "accept": false, + "reason": "Different error signatures and mechanisms; not the same bug." + }, + { + "left": "issue:44805", + "right": "issue:46294", + "accept": false, + "reason": "Different multimodal shape mismatch vs chat-template video token mismatch." + }, + { + "left": "issue:44805", + "right": "issue:45161", + "accept": false, + "reason": "Different failures; mask indexing bug is unrelated to GPT-OSS TP support." + }, + { + "left": "issue:44560", + "right": "issue:46165", + "accept": false, + "reason": "Different features entirely; video StopIteration is unrelated to resume/trust_remote_code." + }, + { + "left": "issue:43596", + "right": "issue:46165", + "accept": false, + "reason": "Different training/resume bug, not the ZeRO-3 index error." + }, + { + "left": "issue:43572", + "right": "issue:46165", + "accept": false, + "reason": "Config regression vs training-resume issue; unrelated." + }, + { + "left": "issue:34634", + "right": "issue:35545", + "accept": false, + "reason": "BarkProcessor voice preset handling and ONNX export are unrelated." + }, + { + "left": "issue:30277", + "right": "issue:43638", + "accept": false, + "reason": "Both are distributed/DeepSpeed-related, but they are different failure modes and likely different fixes." + }, + { + "left": "issue:43596", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure on BERT; different model wording, same underlying empty-tensor bug." + }, + { + "left": "issue:43975", + "right": "issue:44457", + "accept": false, + "reason": "Incorrect detokenization and LoRA merge/reload mismatch are different bugs." + }, + { + "left": "issue:43039", + "right": "issue:45161", + "accept": false, + "reason": "Liger-kernel cross_entropy routing and GPT-OSS TP support are unrelated." + }, + { + "left": "issue:44292", + "right": "issue:44457", + "accept": false, + "reason": "Different model/runtime failure vs LoRA save/load consistency issue." + }, + { + "left": "issue:24643", + "right": "issue:30277", + "accept": false, + "reason": "Both mention DeepSpeed, but the concrete errors and code paths are different." + }, + { + "left": "issue:34928", + "right": "issue:44805", + "accept": false, + "reason": "Activation-checkpointing/FSDP tensor recomputation mismatch is unrelated to the mask-shape error." + }, + { + "left": "issue:45859", + "right": "issue:45902", + "accept": true, + "reason": "Same Qwen3_5Moe rotary-embedding/offload state issue; one report describes CPU offload, the other meta-to_empty materialization symptoms." + }, + { + "left": "issue:43638", + "right": "issue:45161", + "accept": false, + "reason": "ZeRO-3 Bert loading bug and GPT-OSS tensor-parallel support issue are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45507", + "accept": false, + "reason": "Different model-specific bugs with no shared code path." + }, + { + "left": "issue:44560", + "right": "issue:46165", + "accept": false, + "reason": "Video embedding failure is unrelated to resume/trust_remote_code behavior." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Different backend/device bugs; autocast dtype mismatch is unrelated to the MPS Int histogram error." + }, + { + "left": "issue:39290", + "right": "issue:45081", + "accept": false, + "reason": "Gemma3 config/vLLM issue and Mistral tokenizer regex crash are unrelated." + }, + { + "left": "issue:45823", + "right": "issue:45874", + "accept": false, + "reason": "Device-mapping mismatch and reverse-embedding lookup cost are different Gemma4 issues." + }, + { + "left": "issue:43425", + "right": "issue:44292", + "accept": false, + "reason": "Torch-version incompatibility and Qwen NVFP4 runtime failure are unrelated." + }, + { + "left": "issue:34928", + "right": "issue:41720", + "accept": false, + "reason": "FSDP/activation-checkpointing mismatch is not the same as Qwen3 device-map cuda assert." + }, + { + "left": "issue:43827", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs regressions, but they cover different removed APIs/commands." + }, + { + "left": "issue:43716", + "right": "issue:44560", + "accept": false, + "reason": "Different multimodal pipelines and different failure modes." + }, + { + "left": "issue:43828", + "right": "issue:45685", + "accept": false, + "reason": "Autocast dtype mismatch is unrelated to the MPS histogram Int limitation." + }, + { + "left": "issue:44918", + "right": "issue:45161", + "accept": false, + "reason": "Different training/runtime issues; no same underlying bug." + }, + { + "left": "issue:43039", + "right": "issue:44918", + "accept": false, + "reason": "Liger kernel cross-entropy routing and Qwen3.5 SFT embedding unpacking are different bugs." + }, + { + "left": "issue:39290", + "right": "issue:41720", + "accept": false, + "reason": "Different models and different failure mechanisms." + }, + { + "left": "issue:41762", + "right": "issue:43638", + "accept": true, + "reason": "Same ZeRO-3 index-0-out-of-bounds loading failure; model names differ, but the underlying empty-index bug is the same." + }, + { + "left": "issue:43901", + "right": "issue:44512", + "accept": false, + "reason": "Docs mention different deprecated behaviors; not one bug." + }, + { + "left": "issue:45237", + "right": "issue:46015", + "accept": false, + "reason": "AMD GPU runtime issue and outdated RAG docs are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the accepted soft-edge pairs are conservative enough from the available evidence. The tokenizer-regression cluster choice is also well-supported by the titles, with 45920 as the broad open anchor and 45812 as the Granite-specific report." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 2, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36010", + "issue:39186", + "issue:39290", + "issue:41093", + "issue:41762", + "issue:43054", + "issue:43296", + "issue:43366", + "issue:43404", + "issue:43425", + "issue:43531", + "issue:43541", + "issue:43572", + "issue:43596", + "issue:43638", + "issue:43716", + "issue:43792", + "issue:43828", + "issue:43854", + "issue:43866", + "issue:43975", + "issue:43994", + "issue:44291", + "issue:44292", + "issue:44387", + "issue:44479", + "issue:44589", + "issue:44805", + "issue:44841", + "issue:44863", + "issue:44918", + "issue:45005", + "issue:45020", + "issue:45070", + "issue:45084", + "issue:45161", + "issue:45362", + "issue:45464", + "issue:45542", + "issue:45685", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45901", + "issue:45902", + "issue:46015", + "issue:46294" + ], + "soft_pairs": [ + "issue:43866|issue:44863", + "issue:44292|issue:46015", + "issue:39290|issue:43531", + "issue:43854|issue:43866", + "issue:41093|issue:43638", + "issue:43792|issue:45901", + "issue:43425|issue:45070", + "issue:43596|issue:45800", + "issue:43975|issue:45901", + "issue:43792|issue:45070", + "issue:45362|issue:45464", + "issue:44292|issue:45901", + "issue:39290|issue:45823", + "issue:43404|issue:43866", + "issue:45464|issue:45685", + "issue:43541|issue:45685", + "issue:43541|issue:43828", + "issue:44841|issue:45084", + "issue:36010|issue:39290", + "issue:45800|issue:45823", + "issue:41093|issue:41762", + "issue:43296|issue:43366", + "issue:43572|issue:45070", + "issue:43541|issue:45161", + "issue:44805|issue:44918", + "issue:44387|issue:45005", + "issue:43828|issue:45464", + "issue:44291|issue:45070", + "issue:43366|issue:45464", + "issue:43531|issue:45070", + "issue:45020|issue:45800", + "issue:43716|issue:46294", + "issue:43541|issue:44589", + "issue:44479|issue:46294", + "issue:41093|issue:43596", + "issue:43054|issue:43994", + "issue:45759|issue:45902", + "issue:45542|issue:45800", + "issue:43716|issue:44918", + "issue:39186|issue:44918" + ], + "prepared_review_unit_hash": "f0c6b0cb4a8b1687b61198b468c970862258acbe9f1833f9b24e460ca7dafc3b", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 40, + "serialized_chars": 38926, + "estimated_input_tokens": 9732, + "estimated_eval_tokens": 19720 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated transformers bug reports, with three clear duplicate-like subgroups: mask-shape IndexError, DeepSpeed ZeRO-3/Bert index-0 failure, and Qwen3.5 video-input regression. I only accepted pairs where the titles strongly indicate the same underlying bug.", + "confidence": 0.78, + "canonical_issue_reason": "issue:41093 is the best issue representative because it is the clearest and most active report for the mask/tensor shape-mismatch IndexError subgroup, and it has a near-exact duplicate in issue:44805.", + "canonical_pr_reason": null, + "best_issue_reason": "Best overall issue in this mixed cluster: issue:41093, since it is a concrete, well-discussed bug report with the strongest duplicate signal among the issues here.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43866", + "right": "issue:44863", + "accept": false, + "reason": "Different models and failure modes: corrupted Ovis2 checkpoint vs NemotronH checkpoint-loading failure." + }, + { + "left": "issue:44292", + "right": "issue:46015", + "accept": false, + "reason": "Unrelated problems: Qwen-3-8B-NVFP4 load/runtime error vs outdated RAG examples." + }, + { + "left": "issue:39290", + "right": "issue:43531", + "accept": false, + "reason": "Both mention sliding-window behavior, but they target different models and different concrete failures." + }, + { + "left": "issue:43854", + "right": "issue:43866", + "accept": false, + "reason": "GLM-4.7 load issue in tests is not the same bug as a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:41093", + "right": "issue:43638", + "accept": false, + "reason": "Both are IndexError reports, but the concrete failure patterns differ: mask-shape mismatch vs ZeRO-3 empty-tensor indexing." + }, + { + "left": "issue:43792", + "right": "issue:45901", + "accept": false, + "reason": "Whisper loading/run failure and table-question-answering crash are unrelated." + }, + { + "left": "issue:43425", + "right": "issue:45070", + "accept": false, + "reason": "Torch-version incompatibility and a pydantic PretrainedConfig regression are different issues." + }, + { + "left": "issue:43596", + "right": "issue:45800", + "accept": false, + "reason": "ZeRO-3/Bert index-0 failure is unrelated to torch/transformers version incompatibility." + }, + { + "left": "issue:43975", + "right": "issue:45901", + "accept": false, + "reason": "Incorrect detokenization and table QA crashing are unrelated bugs." + }, + { + "left": "issue:43792", + "right": "issue:45070", + "accept": false, + "reason": "Whisper load/run failure does not match the PretrainedConfig pydantic regression." + }, + { + "left": "issue:45362", + "right": "issue:45464", + "accept": false, + "reason": "Both involve Qwen3.5 chat usage, but one is a crash with transformers chat and the other is a streaming chat/completions failure; not clearly the same code-path bug." + }, + { + "left": "issue:44292", + "right": "issue:45901", + "accept": false, + "reason": "Qwen-3-8B-NVFP4 runtime error is unrelated to table-question-answering." + }, + { + "left": "issue:39290", + "right": "issue:45823", + "accept": false, + "reason": "Gemma3 sliding_window_pattern and Gemma4 device mismatch are different bugs." + }, + { + "left": "issue:43404", + "right": "issue:43866", + "accept": false, + "reason": "Tied lm_head weights in Mistral3 is unrelated to a corrupted Ovis2 checkpoint." + }, + { + "left": "issue:45464", + "right": "issue:45685", + "accept": false, + "reason": "Streaming chat/completions failure and MPS histogram int support are unrelated." + }, + { + "left": "issue:43541", + "right": "issue:45685", + "accept": false, + "reason": "Mixtral torch-dynamo grouped_mm error is unrelated to an MPS histogram implementation issue." + }, + { + "left": "issue:43541", + "right": "issue:43828", + "accept": false, + "reason": "Grouped_mm tracing failure and autocast dtype mismatch are different bugs." + }, + { + "left": "issue:44841", + "right": "issue:45084", + "accept": false, + "reason": "Voxtral processor failure and non-template-node compile error are unrelated." + }, + { + "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 issues." + }, + { + "left": "issue:41093", + "right": "issue:41762", + "accept": false, + "reason": "Both are IndexErrors, but one is a mask-shape mismatch and the other is a ZeRO-3 zero-sized tensor access during Gemma3 loading." + }, + { + "left": "issue:43296", + "right": "issue:43366", + "accept": false, + "reason": "PaddleOCR-VL load failure and GGUF gpt-oss support are unrelated." + }, + { + "left": "issue:43572", + "right": "issue:45070", + "accept": false, + "reason": "StableLm pad_token_idx regression and PretrainedConfig pydantic regression are different code paths." + }, + { + "left": "issue:43541", + "right": "issue:45161", + "accept": false, + "reason": "Mixtral torch-dynamo grouped_mm error is unrelated to GPT-OSS MoE tensor-parallelism behavior." + }, + { + "left": "issue:44805", + "right": "issue:44918", + "accept": false, + "reason": "Mask-shape IndexError and Qwen3.5 embedding unpacking failure are unrelated." + }, + { + "left": "issue:44387", + "right": "issue:45005", + "accept": false, + "reason": "Int4 OOM regression and tied-weights translation-model issue are unrelated." + }, + { + "left": "issue:43828", + "right": "issue:45464", + "accept": false, + "reason": "Autocast dtype mismatch and streaming chat/completions failure are different bugs." + }, + { + "left": "issue:44291", + "right": "issue:45070", + "accept": false, + "reason": "init_empty_weights unexpected argument and pydantic PretrainedConfig regression are not the same issue." + }, + { + "left": "issue:43366", + "right": "issue:45464", + "accept": false, + "reason": "GGUF gpt-oss support and Qwen3.5 streaming failure are unrelated." + }, + { + "left": "issue:43531", + "right": "issue:45070", + "accept": false, + "reason": "Qwen3-MoE sliding_window issue and PretrainedConfig pydantic regression are unrelated." + }, + { + "left": "issue:45020", + "right": "issue:45800", + "accept": false, + "reason": "Remote_code breakage and torch/transformers version incompatibility are different concerns." + }, + { + "left": "issue:43716", + "right": "issue:46294", + "accept": false, + "reason": "Mistral-3 image-preprocessor dtype mismatch is unrelated to Qwen3.5 video token mismatch." + }, + { + "left": "issue:43541", + "right": "issue:44589", + "accept": false, + "reason": "Grouped_mm tracing failure and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:44479", + "right": "issue:46294", + "accept": true, + "reason": "Both describe the same Qwen3.5/Qwen3.5-MoE video-input regression around video features/tokens and chat-template handling." + }, + { + "left": "issue:41093", + "right": "issue:43596", + "accept": false, + "reason": "Mask-shape mismatch IndexError and ZeRO-3/Bert empty-tensor IndexError are different concrete failures." + }, + { + "left": "issue:43054", + "right": "issue:43994", + "accept": false, + "reason": "Siglip2 embedding quality complaint and Siglip2 nonsensical AutoModel/pipeline outputs may be related in theme, but they are not clearly the same underlying bug." + }, + { + "left": "issue:45759", + "right": "issue:45902", + "accept": false, + "reason": "Composite config unwrap behavior and Qwen3_5Moe rotary embedding materialization bug are unrelated." + }, + { + "left": "issue:45542", + "right": "issue:45800", + "accept": false, + "reason": "TensorBoard-without-TF backend issue is unrelated to torch/transformers compatibility." + }, + { + "left": "issue:43716", + "right": "issue:44918", + "accept": false, + "reason": "Mistral-3 dtype mismatch and Qwen3.5 embedding unpacking failure are unrelated." + }, + { + "left": "issue:39186", + "right": "issue:44918", + "accept": false, + "reason": "FSDP weight-dimension error and Qwen3.5 embedding unpacking failure are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative about the duplicate/relatedness calls. The one accepted pair (44479, 46294) is well supported by the titles, and the canonical issue choice (41093) is reasonable given the near-exact duplicate 44805 and higher discussion activity. No obvious overstatement or risky mergeability claim." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 3, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36331", + "issue:38175", + "issue:39692", + "issue:40990", + "issue:41553", + "issue:41628", + "issue:41762", + "issue:42915", + "issue:42947", + "issue:43054", + "issue:43404", + "issue:43493", + "issue:43644", + "issue:43645", + "issue:43828", + "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:44492", + "issue:44512", + "issue:44530", + "issue:44534", + "issue:44589", + "issue:44863", + "issue:44910", + "issue:44918", + "issue:44928", + "issue:44960", + "issue:45005", + "issue:45237", + "issue:45399", + "issue:45507", + "issue:45632", + "issue:45663", + "issue:45698", + "issue:45701", + "issue:45800", + "issue:45859", + "issue:45902" + ], + "soft_pairs": [ + "issue:45632|issue:45698", + "issue:43645|issue:45399", + "issue:43404|issue:45005", + "issue:40990|issue:44960", + "issue:42915|issue:45399", + "issue:44530|issue:45005", + "issue:43873|issue:45005", + "issue:44360|issue:44512", + "issue:44863|issue:45005", + "issue:44918|issue:45507", + "issue:44492|issue:44512", + "issue:43975|issue:44292", + "issue:44292|issue:45507", + "issue:43950|issue:44534", + "issue:39692|issue:43054", + "issue:43644|issue:43950", + "issue:43828|issue:44928", + "issue:36331|issue:41762", + "issue:41628|issue:45800", + "issue:43872|issue:44589", + "issue:43950|issue:45902", + "issue:43866|issue:44403", + "issue:38175|issue:43054", + "issue:41553|issue:43883", + "issue:43054|issue:45701", + "issue:45663|issue:45902", + "issue:44910|issue:45859", + "issue:42947|issue:44387", + "issue:41553|issue:43881", + "issue:44403|issue:44451", + "issue:43975|issue:45237", + "issue:43054|issue:43493" + ], + "prepared_review_unit_hash": "4bfd60ac419dfb4f859ad7056ccc700089ff15114355951a0650ae9319921e73", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36987, + "estimated_input_tokens": 9247, + "estimated_eval_tokens": 18750 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated model/loading regressions; the only clear duplicate pair is the non-persistent-buffer corruption regression around Transformers v5. The rest are similar at a subsystem/title level but do not look like the same concrete bug.", + "confidence": 0.9, + "canonical_issue_reason": "Issue 43950 is the clearest representative of the non-persistent-buffer regression: it names the exact API (`from_pretrained`) and the failure mode (`register_buffer(persistent=False)` corruption).", + "canonical_pr_reason": null, + "best_issue_reason": "43950 is the best issue anchor because it is the most specific, actionable statement of the underlying bug and matches the confirmed duplicate wording in the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45632", + "right": "issue:45698", + "accept": false, + "reason": "Both involve custom model loading, but one is a cache-path collision for local models and the other is wrong custom-module loading after save/load; not the same concrete bug." + }, + { + "left": "issue:43645", + "right": "issue:45399", + "accept": false, + "reason": "One is a Jupyter custom-model initialization regression; the other is flash-attn fallback logic. Different code paths and symptoms." + }, + { + "left": "issue:43404", + "right": "issue:45005", + "accept": false, + "reason": "Both mention tied weights, but they affect different models and failure modes; too broad to be the same bug." + }, + { + "left": "issue:40990", + "right": "issue:44960", + "accept": false, + "reason": "Completely different models and symptoms: high perplexity on GPT-OSS vs a GLM5 issue." + }, + { + "left": "issue:42915", + "right": "issue:45399", + "accept": false, + "reason": "Qwen3MoE FP8 failure is unrelated to flash-attn fallback gating." + }, + { + "left": "issue:44530", + "right": "issue:45005", + "accept": false, + "reason": "PagedAttentionCache crash vs tied-weights translation model issue; no shared underlying defect." + }, + { + "left": "issue:43873", + "right": "issue:45005", + "accept": false, + "reason": "Quantization/offloading behavior is not the same bug as tied-weights handling in translation models." + }, + { + "left": "issue:44360", + "right": "issue:44512", + "accept": false, + "reason": "DSA/ReLU discussion and a docs note about a removed command are unrelated." + }, + { + "left": "issue:44863", + "right": "issue:45005", + "accept": false, + "reason": "Checkpoint loading for NemotronH is a different problem from tied-weight handling." + }, + { + "left": "issue:44918", + "right": "issue:45507", + "accept": false, + "reason": "TRl SFT embedding unpacking and GraniteMoEHybrid invalid method calls are different failures." + }, + { + "left": "issue:44492", + "right": "issue:44512", + "accept": false, + "reason": "Both are docs-facing, but one is a typo and the other is stale command documentation; not the same issue." + }, + { + "left": "issue:43975", + "right": "issue:44292", + "accept": false, + "reason": "Different models and failures: detokenization bug vs NVFP4 runtime error." + }, + { + "left": "issue:44292", + "right": "issue:45507", + "accept": false, + "reason": "No concrete bug overlap; one is Qwen-3 NVFP4 runtime failure, the other is a GraniteMoEHybrid method issue." + }, + { + "left": "issue:43950", + "right": "issue:44534", + "accept": true, + "reason": "Both describe the same non-persistent-buffer junk/corruption regression in Transformers v5." + }, + { + "left": "issue:39692", + "right": "issue:43054", + "accept": false, + "reason": "Both concern SigLIP2, but one is a docs example/model-processor mismatch and quantization failure while the other is embedding quality regression." + }, + { + "left": "issue:43644", + "right": "issue:43950", + "accept": true, + "reason": "Same underlying regression: Transformers v5 mishandles non-persistent buffers during load/materialization." + }, + { + "left": "issue:43828", + "right": "issue:44928", + "accept": false, + "reason": "Different models and different failure modes: autocast dtype mismatch vs Qwen3.5 gradient explosion from 3D position_ids handling." + }, + { + "left": "issue:36331", + "right": "issue:41762", + "accept": false, + "reason": "Trainer loss signature mismatch and ZeRO-3 load-time IndexError are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:45800", + "accept": false, + "reason": "Import error for AutoImageProcessor is not the same as a torch/transformers version incompatibility." + }, + { + "left": "issue:43872", + "right": "issue:44589", + "accept": false, + "reason": "bitsandbytes keyword-argument incompatibility and missing Float8 storage are different backend issues." + }, + { + "left": "issue:43950", + "right": "issue:45902", + "accept": false, + "reason": "Both touch non-persistent buffers, but one is a from_pretrained regression while the other is a Qwen3_5Moe rotary-embedding materialization bug." + }, + { + "left": "issue:43866", + "right": "issue:44403", + "accept": false, + "reason": "Checkpoint corruption and a generic loading noise report are not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:43054", + "accept": false, + "reason": "Unexpected zero probabilities is not the same as a text-embedding quality regression." + }, + { + "left": "issue:41553", + "right": "issue:43883", + "accept": false, + "reason": "A bad error message for Voxtral tokenizer loading is unrelated to a missing all_tied_weights_keys attribute." + }, + { + "left": "issue:43054", + "right": "issue:45701", + "accept": false, + "reason": "SigLIP2 embedding quality and version-dependent tokenization changes are different problems." + }, + { + "left": "issue:45663", + "right": "issue:45902", + "accept": false, + "reason": "Gemma4 FSDP2 shared_kv_states behavior is unrelated to Qwen3_5Moe inv_freq uninitialized-memory handling." + }, + { + "left": "issue:44910", + "right": "issue:45859", + "accept": false, + "reason": "Both involve Qwen3.5-related internals, but one is flash-attn 3D position_ids handling and the other is CPU-offload incompatibility in rotary embedding." + }, + { + "left": "issue:42947", + "right": "issue:44387", + "accept": false, + "reason": "LoRA gradient checkpointing and int4 CUDA reserved-memory OOM are different regressions." + }, + { + "left": "issue:41553", + "right": "issue:43881", + "accept": false, + "reason": "Voxtral tokenizer error messaging and glm-4v-9b loading failure are unrelated." + }, + { + "left": "issue:44403", + "right": "issue:44451", + "accept": false, + "reason": "Generic loading noise and inability to load a specific model are not the same concrete bug." + }, + { + "left": "issue:43975", + "right": "issue:45237", + "accept": false, + "reason": "Detokenization bug and AMD GPU runtime support issue are different defects." + }, + { + "left": "issue:43054", + "right": "issue:43493", + "accept": false, + "reason": "Both are SigLIP2-related, but one is embedding quality and the other is a HF-vs-JAX implementation discrepancy; not enough to treat as the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The 43950 cluster is clearly supported by the titles: 43950, 43644, and 44534 all describe the same non-persistent-buffer junk/corruption regression in Transformers v5, with 43950 being the most specific anchor. The false soft-edge rejections are also appropriately cautious and do not overclaim equivalence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 4, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36331", + "issue:41093", + "issue:41553", + "issue:41762", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43404", + "issue:43643", + "issue:43742", + "issue:43782", + "issue:43792", + "issue:43824", + "issue:43827", + "issue:43828", + "issue:43854", + "issue:43856", + "issue:43866", + "issue:43872", + "issue:43881", + "issue:43883", + "issue:43940", + "issue:43950", + "issue:44220", + "issue:44291", + "issue:44368", + "issue:44403", + "issue:44488", + "issue:44509", + "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:45685", + "issue:45823", + "issue:45923" + ], + "soft_pairs": [ + "issue:44403|issue:44488", + "issue:43643|issue:45020", + "issue:42947|issue:43856", + "issue:41762|issue:42915", + "issue:45685|issue:45823", + "issue:42491|issue:44368", + "issue:44991|issue:45399", + "issue:43881|issue:43883", + "issue:43824|issue:43872", + "issue:45020|issue:45823", + "issue:44661|issue:45020", + "issue:43828|issue:45823", + "issue:45081|issue:45399", + "issue:43782|issue:44960", + "issue:45020|issue:45356", + "issue:43742|issue:45399", + "issue:43404|issue:43950", + "issue:42915|issue:45020", + "issue:43827|issue:44509", + "issue:43792|issue:44220", + "issue:43872|issue:44291", + "issue:42915|issue:43872", + "issue:43257|issue:43866", + "issue:42947|issue:45923", + "issue:43940|issue:45313", + "issue:36331|issue:41093", + "issue:41553|issue:44991", + "issue:43854|issue:44863", + "issue:44928|issue:45588", + "issue:43257|issue:45305", + "issue:43872|issue:45538", + "issue:41093|issue:44805" + ], + "prepared_review_unit_hash": "58e325d37ab1e8fe16752ce01339f06b75ac0e2808395e956863acb936bf8f79", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 37007, + "estimated_input_tokens": 9252, + "estimated_eval_tokens": 18760 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose set of Transformers loading/regression reports with only a couple of true duplicate pairs; most similar-looking items are different models, different subsystems, or different failure modes.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43872 is the strongest canonical issue: it has a concrete, reproducible root cause (_is_hf_initialized passed into bitsandbytes Int8Params during empty-weight loading) and a near-exact duplicate in issue:44291.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43872 is the best issue to anchor the cluster because it describes a specific code-path failure rather than a broad symptom, and it has the clearest duplicate evidence.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44403", + "right": "issue:44488", + "accept": false, + "reason": "Both are about loading behavior, but one is a generic noise/warning complaint and the other is a concrete model-load failure for a specific checkpoint; not the same bug." + }, + { + "left": "issue:43643", + "right": "issue:45020", + "accept": false, + "reason": "Both mention remote_code, but one is an AutoConfig field-loss issue and the other is a broad regression affecting remote-code models; too different to merge." + }, + { + "left": "issue:42947", + "right": "issue:43856", + "accept": false, + "reason": "Different problems: PEFT LoRA gradient checkpointing vs Qwen3 MoE memory usage. Same family area, not the same underlying bug." + }, + { + "left": "issue:41762", + "right": "issue:42915", + "accept": false, + "reason": "Both are loading failures, but they involve different models and different mechanisms (ZeRO-3 load error vs FineGrainedFP8Config failure)." + }, + { + "left": "issue:45685", + "right": "issue:45823", + "accept": false, + "reason": "Different symptoms and code paths: MPS histogram/int issue vs Gemma4 device-map mismatch during forward." + }, + { + "left": "issue:42491", + "right": "issue:44368", + "accept": false, + "reason": "One is a compatibility break for a trained LoRA model across versions; the other is a warning about tie_word_embeddings configuration." + }, + { + "left": "issue:44991", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer loading for est-roberta and flash-attn fallback gating are unrelated bugs." + }, + { + "left": "issue:43881", + "right": "issue:43883", + "accept": false, + "reason": "Both are model-loading issues, but one is a glm-4v-9b load failure and the other is a missing all_tied_weights_keys attribute; no shared root cause is evident." + }, + { + "left": "issue:43824", + "right": "issue:43872", + "accept": false, + "reason": "Different areas: Qwen2_5_VL import/export exposure vs bitsandbytes Int8Params initialization." + }, + { + "left": "issue:45020", + "right": "issue:45823", + "accept": false, + "reason": "Remote-code regressions and Gemma4 device placement are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45020", + "accept": false, + "reason": "add-new-model-like/tokenizer mapping logic is a distinct code path from remote_code loading regressions." + }, + { + "left": "issue:43828", + "right": "issue:45823", + "accept": false, + "reason": "Autocast dtype mismatch in Phi-tiny-MoE is not the same bug as Gemma4 PLE device mismatch." + }, + { + "left": "issue:45081", + "right": "issue:45399", + "accept": false, + "reason": "Tokenizer regex patch crash and flash-attn fallback checks are separate failures." + }, + { + "left": "issue:43782", + "right": "issue:44960", + "accept": false, + "reason": "Qwen3VL weight_only loading error and GLM5 are different model-specific loading problems." + }, + { + "left": "issue:45020", + "right": "issue:45356", + "accept": false, + "reason": "Remote-code breakage and Kimi tokenizer codec handling are different regressions." + }, + { + "left": "issue:43742", + "right": "issue:45399", + "accept": false, + "reason": "MobileLLM key error and flash-attn fallback gating do not share the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43950", + "accept": false, + "reason": "lm_head tying bug in Mistral3 is unrelated to non-persistent buffer corruption in from_pretrained()." + }, + { + "left": "issue:42915", + "right": "issue:45020", + "accept": false, + "reason": "Qwen3 MoE FineGrainedFP8Config failure is a model/config-specific issue, not the remote_code regression." + }, + { + "left": "issue:43827", + "right": "issue:44509", + "accept": true, + "reason": "Both are the same documentation cleanup: pipeline tasks removed in v5 are still referenced in docs, especially summarization/translation-related pages." + }, + { + "left": "issue:43792", + "right": "issue:44220", + "accept": false, + "reason": "Both involve Whisper/audio loading, but the titles do not show the same concrete failure path; one is a generic model-run failure, the other is a specific feature-extraction function issue." + }, + { + "left": "issue:43872", + "right": "issue:44291", + "accept": true, + "reason": "These describe the same concrete bitsandbytes/empty-weights bug: unexpected _is_hf_initialized being passed into Int8Params during model loading." + }, + { + "left": "issue:42915", + "right": "issue:43872", + "accept": false, + "reason": "Qwen3 MoE FP8 loading and bitsandbytes Int8Params initialization are different failure modes." + }, + { + "left": "issue:43257", + "right": "issue:43866", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed is unrelated to an Ovis2 checkpoint corruption report." + }, + { + "left": "issue:42947", + "right": "issue:45923", + "accept": false, + "reason": "Gradient checkpointing behavior and a missing supports_gradient_checkpointing flag are different issues, even if both touch training configuration." + }, + { + "left": "issue:43940", + "right": "issue:45313", + "accept": false, + "reason": "Both mention ZeRO-3 weight loading for Qwen-family models, but the failures are described differently enough that they do not clearly share one exact root cause." + }, + { + "left": "issue:36331", + "right": "issue:41093", + "accept": false, + "reason": "Different errors and domains: custom trainer loss signature mismatch vs tensor mask shape mismatch." + }, + { + "left": "issue:41553", + "right": "issue:44991", + "accept": false, + "reason": "Voxtral AutoTokenizer error and est-roberta tokenizer load failure are different tokenizer/model regressions." + }, + { + "left": "issue:43854", + "right": "issue:44863", + "accept": false, + "reason": "Unable to load a GLM-4.7-Flash model in tests and NemotronH checkpoint loading are separate model-specific problems." + }, + { + "left": "issue:44928", + "right": "issue:45588", + "accept": false, + "reason": "RLHF gradient explosion from Qwen3.5 position_ids/SDPA behavior is unrelated to flash_attention.py crashing on s_aux=None." + }, + { + "left": "issue:43257", + "right": "issue:45305", + "accept": false, + "reason": "Qwen3 MoE weight conversion under deepspeed/accelerate and GAS gradient averaging with DeepSpeed are different training/loading bugs." + }, + { + "left": "issue:43872", + "right": "issue:45538", + "accept": false, + "reason": "bitsandbytes init_empty_weights incompatibility is unrelated to CLIPTokenizer's model_max_length constant." + }, + { + "left": "issue:41093", + "right": "issue:44805", + "accept": false, + "reason": "These have the same style of IndexError, but they are distinct reports with different contexts and likely different offending code paths." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is conservative and grounded in the packet. The two accepted soft-edge pairs look like genuine duplicates or near-duplicates (43872/44291 and 43827/44509), and the rejected pairs are mostly appropriately cautious given only title/body-level evidence. No mergeability issue applies here because 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": 18, + "review_unit_index": 5, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:24643", + "issue:30064", + "issue:36010", + "issue:38175", + "issue:39692", + "issue:41553", + "issue:41720", + "issue:42491", + "issue:42617", + "issue:42915", + "issue:43317", + "issue:43366", + "issue:43531", + "issue:43550", + "issue:43596", + "issue:43632", + "issue:43638", + "issue:43645", + "issue:43646", + "issue:43720", + "issue:43824", + "issue:43828", + "issue:43950", + "issue:43957", + "issue:43994", + "issue:44155", + "issue:44479", + "issue:44488", + "issue:44530", + "issue:44560", + "issue:44589", + "issue:44661", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44910", + "issue:44918", + "issue:44960", + "issue:44977", + "issue:45030", + "issue:45325", + "issue:45584", + "issue:45663", + "issue:45685", + "issue:45823", + "issue:45834", + "issue:45902" + ], + "soft_pairs": [ + "issue:44479|issue:44560", + "issue:41553|issue:44488", + "issue:44530|issue:44863", + "issue:24643|issue:30064", + "issue:43366|issue:43828", + "issue:45325|issue:45902", + "issue:45663|issue:45823", + "issue:43366|issue:43531", + "issue:43950|issue:45834", + "issue:44560|issue:45685", + "issue:43645|issue:43646", + "issue:43550|issue:44910", + "issue:43366|issue:44589", + "issue:42915|issue:43957", + "issue:44560|issue:44918", + "issue:42617|issue:43366", + "issue:43824|issue:43957", + "issue:36010|issue:42915", + "issue:44661|issue:45823", + "issue:43632|issue:45834", + "issue:38175|issue:43994", + "issue:44155|issue:45584", + "issue:44560|issue:44805", + "issue:43638|issue:44661", + "issue:44877|issue:45030", + "issue:43596|issue:44661", + "issue:44661|issue:44805", + "issue:43317|issue:44756", + "issue:38175|issue:39692", + "issue:42491|issue:43720", + "issue:44960|issue:44977", + "issue:41720|issue:42915" + ], + "prepared_review_unit_hash": "f5eb779007db858617394912c769bc39cdae2a2d6ced2e2a9aedf248205d813f", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37263, + "estimated_input_tokens": 9316, + "estimated_eval_tokens": 18888 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated issues. I only found two plausible duplicate pairs: Transformers 5 custom model initialization (43645/43646) and SigLIP2 bad outputs on the same model family (38175/43994).", + "confidence": 0.84, + "canonical_issue_reason": "No single canonical issue covers the whole mixed set; issue 43646 is the best anchor for the only clear duplicate pair because it states the broader custom-model initialization regression.", + "canonical_pr_reason": null, + "best_issue_reason": "43646 is the strongest global issue anchor here because it generalizes 43645 cleanly; the SigLIP2 pair is a separate duplicate pocket, not the same bug.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44479", + "right": "issue:44560", + "accept": false, + "reason": "Both involve Qwen video behavior, but one is a broad multi-model regression and the other is a specific StopIteration path; not the same bug." + }, + { + "left": "issue:41553", + "right": "issue:44488", + "accept": false, + "reason": "Both are loading failures, but for different models and different failure modes; no shared underlying code-path is evident." + }, + { + "left": "issue:44530", + "right": "issue:44863", + "accept": false, + "reason": "PagedAttentionCache linear_attention crash and NemotronH checkpoint loading are unrelated." + }, + { + "left": "issue:24643", + "right": "issue:30064", + "accept": false, + "reason": "Different subsystems and symptoms; no duplicate relationship." + }, + { + "left": "issue:43366", + "right": "issue:43828", + "accept": false, + "reason": "GGUF architecture support and a torch.autocast dtype mismatch are unrelated." + }, + { + "left": "issue:45325", + "right": "issue:45902", + "accept": false, + "reason": "Both mention rotary embeddings, but they are distinct bugs in different models and code paths." + }, + { + "left": "issue:45663", + "right": "issue:45823", + "accept": false, + "reason": "Both are Gemma4 issues, but FSDP2 shared_kv_states rebuilding and device_map PLE mismatch are different problems." + }, + { + "left": "issue:43366", + "right": "issue:43531", + "accept": false, + "reason": "GGUF architecture support and Qwen3-MoE sliding_window behavior are unrelated." + }, + { + "left": "issue:43950", + "right": "issue:45834", + "accept": false, + "reason": "from_pretrained buffer corruption and Kosmos2.5 long OCR indexing are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:45685", + "accept": false, + "reason": "Qwen3.5 video generation and an MPS histogram int-type error are unrelated." + }, + { + "left": "issue:43645", + "right": "issue:43646", + "accept": true, + "reason": "Same underlying Transformers 5 custom-model initialization regression; 43645 is just a notebook-specific repro." + }, + { + "left": "issue:43550", + "right": "issue:44910", + "accept": false, + "reason": "Different model families and different attention/position-id failures; not mergeable as one bug." + }, + { + "left": "issue:43366", + "right": "issue:44589", + "accept": false, + "reason": "GGUF support and Float8 storage lookup failure are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:43957", + "accept": false, + "reason": "FineGrainedFP8Config failure on Qwen3Moe and meta-device loading regressions are different issues." + }, + { + "left": "issue:44560", + "right": "issue:44918", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a video inference bug and the other is an embedding/unpacking trainer bug." + }, + { + "left": "issue:42617", + "right": "issue:43366", + "accept": false, + "reason": "3d_parallel.py runtime failure and GGUF gpt-oss support are unrelated." + }, + { + "left": "issue:43824", + "right": "issue:43957", + "accept": false, + "reason": "Missing import for Qwen2_5_VLForConditionalGeneration and meta-device loading regressions are different bugs." + }, + { + "left": "issue:36010", + "right": "issue:42915", + "accept": false, + "reason": "GenerationMixin import failure and Qwen3Moe FP8 failure are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:45823", + "accept": false, + "reason": "Tokenizer mapping-name handling and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43632", + "right": "issue:45834", + "accept": false, + "reason": "_is_hf_initialized breakage and Kosmos2.5 long OCR indexing are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43994", + "accept": true, + "reason": "Same SigLIP2 model-family regression with broken outputs; 43994 is the broader reproduction." + }, + { + "left": "issue:44155", + "right": "issue:45584", + "accept": false, + "reason": "AudioFlamingo3 batched inference leakage and Whisper empty-transcription generation are unrelated." + }, + { + "left": "issue:44560", + "right": "issue:44805", + "accept": false, + "reason": "Video StopIteration and a mask shape IndexError are unrelated." + }, + { + "left": "issue:43638", + "right": "issue:44661", + "accept": false, + "reason": "DeepSpeed ZeRO-3 Bert index error and tokenizer-mapping changes are unrelated." + }, + { + "left": "issue:44877", + "right": "issue:45030", + "accept": false, + "reason": "Both are config-loading problems, but they are different validation failures on different models." + }, + { + "left": "issue:43596", + "right": "issue:44661", + "accept": false, + "reason": "ZeRO-3 init Bert IndexError and tokenizer mapping failures are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:44805", + "accept": false, + "reason": "Tokenizer mapping and mask/tensor shape mismatch are unrelated." + }, + { + "left": "issue:43317", + "right": "issue:44756", + "accept": false, + "reason": "Dequantized model offload failure and Strix Halo mmap OOM are different loading issues." + }, + { + "left": "issue:42491", + "right": "issue:43720", + "accept": false, + "reason": "Qwen3 MoE LoRA compatibility and BitNet packed-weight loading are unrelated." + }, + { + "left": "issue:44960", + "right": "issue:44977", + "accept": false, + "reason": "GLM5 and Qwen3.5 flash-attention are different model-specific regressions." + }, + { + "left": "issue:41720", + "right": "issue:42915", + "accept": false, + "reason": "Qwen3 auto device mapping cudaErrorAssert and Qwen3Moe FP8Config failures are different bugs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays conservative and is supported by the packet. The two accepted pairs (43645/43646 and 38175/43994) are plausible same-bug duplicates, and the rejected soft edges are appropriately cautious rather than overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 6, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36010", + "issue:39404", + "issue:39692", + "issue:42491", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43404", + "issue:43425", + "issue:43454", + "issue:43644", + "issue:43645", + "issue:43708", + "issue:43854", + "issue:43856", + "issue:43873", + "issue:43931", + "issue:43957", + "issue:43994", + "issue:44075", + "issue:44155", + "issue:44164", + "issue:44291", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44488", + "issue:44534", + "issue:44756", + "issue:44910", + "issue:44960", + "issue:44991", + "issue:45276", + "issue:45292", + "issue:45313", + "issue:45335", + "issue:45357", + "issue:45362", + "issue:45406", + "issue:45488", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:45859" + ], + "soft_pairs": [ + "issue:44451|issue:44488", + "issue:45313|issue:45357", + "issue:42491|issue:45276", + "issue:43708|issue:44075", + "issue:43644|issue:44534", + "issue:42915|issue:44756", + "issue:45488|issue:45812", + "issue:39692|issue:43994", + "issue:43854|issue:43931", + "issue:43257|issue:43854", + "issue:43856|issue:43873", + "issue:42491|issue:43931", + "issue:43644|issue:43645", + "issue:43856|issue:44387", + "issue:42491|issue:45292", + "issue:44488|issue:44991", + "issue:44910|issue:45588", + "issue:44164|issue:44291", + "issue:45362|issue:45406", + "issue:45276|issue:45335", + "issue:43404|issue:43454", + "issue:36010|issue:39404", + "issue:39692|issue:44960", + "issue:43425|issue:43957", + "issue:44402|issue:44488", + "issue:42947|issue:45704", + "issue:45663|issue:45759", + "issue:45663|issue:45859", + "issue:43873|issue:44387", + "issue:44155|issue:45823", + "issue:44291|issue:44756" + ], + "prepared_review_unit_hash": "f94e5bf39a536df5d44d0712f9937e99cb216902fb0c17fb69f915a6708870bd", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36497, + "estimated_input_tokens": 9125, + "estimated_eval_tokens": 18506 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Almost all candidate edges are related-but-distinct reports; only the Transformers v5 non-persistent buffer junk regression is a clear duplicate pair.", + "confidence": 0.9, + "canonical_issue_reason": "issue:43644 is the clearest, most specific description of the shared regression and is better suited as the canonical issue than the shorter paraphrase.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43644 best captures the underlying bug with the most detail and earliest framing.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44451", + "right": "issue:44488", + "accept": false, + "reason": "Both are model-loading failures, but they reference different BERT models and may stem from different model-specific metadata issues." + }, + { + "left": "issue:45313", + "right": "issue:45357", + "accept": false, + "reason": "Same family, but one is a ZeRO-3 weight-loading bug and the other is incorrect save_pretrained key names for the visual encoder." + }, + { + "left": "issue:42491", + "right": "issue:45276", + "accept": false, + "reason": "Different models and different failures; one is a Qwen3 MoE LoRA compatibility issue, the other is Gemma4 resize_token_embeddings behavior." + }, + { + "left": "issue:43708", + "right": "issue:44075", + "accept": false, + "reason": "Unrelated training-resume math bug vs optimizer argument handling; same training subsystem but not the same defect." + }, + { + "left": "issue:43644", + "right": "issue:44534", + "accept": true, + "reason": "These describe the same Transformers v5 regression where non-persistent buffers are filled with junk; one is just a paraphrased title." + }, + { + "left": "issue:42915", + "right": "issue:44756", + "accept": false, + "reason": "Qwen3 MoE FP8 loading and Strix Halo mmap OOM are unrelated issues." + }, + { + "left": "issue:45488", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is ByteLevel\u2192Metaspace override in LlamaTokenizer and the other is wrong token IDs for Granite models." + }, + { + "left": "issue:39692", + "right": "issue:43994", + "accept": false, + "reason": "Both involve SigLIP2, but one is a doc example/model-processor mismatch and quantization failure while the other reports nonsensical runtime outputs." + }, + { + "left": "issue:43854", + "right": "issue:43931", + "accept": false, + "reason": "Different models and different load-time failures; no sign of the same code-path bug." + }, + { + "left": "issue:43257", + "right": "issue:43854", + "accept": false, + "reason": "Qwen3 MoE deepspeed conversion vs GLM-4.7-Flash unit-test loading are unrelated." + }, + { + "left": "issue:43856", + "right": "issue:43873", + "accept": false, + "reason": "Both touch memory/quantization, but one is Qwen3 MoE training inefficiency and the other is offloading behavior with quantization." + }, + { + "left": "issue:42491", + "right": "issue:43931", + "accept": false, + "reason": "Distinct model families and distinct loading problems." + }, + { + "left": "issue:43644", + "right": "issue:43645", + "accept": false, + "reason": "One is a non-persistent buffer initialization regression; the other is custom model initialization in Jupyter notebooks." + }, + { + "left": "issue:43856", + "right": "issue:44387", + "accept": false, + "reason": "Related to memory under quantization, but one is training-memory inefficiency and the other is int4 CUDA reserved-memory growth leading to OOM." + }, + { + "left": "issue:42491", + "right": "issue:45292", + "accept": false, + "reason": "Different models and different resize_token_embeddings symptoms." + }, + { + "left": "issue:44488", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they concern different models and no shared concrete bug is evident." + }, + { + "left": "issue:44910", + "right": "issue:45588", + "accept": false, + "reason": "Both are flash-attention crashes, but the failure modes differ: packed sequence misinterpretation vs s_aux=None handling." + }, + { + "left": "issue:44164", + "right": "issue:44291", + "accept": false, + "reason": "Save/from_pretrained extra_state handling and init_empty_weights _is_hf_initialized errors are different load/save paths." + }, + { + "left": "issue:45362", + "right": "issue:45406", + "accept": false, + "reason": "Different models and different crash causes (chat path vs Gemma4Processor attribute error)." + }, + { + "left": "issue:45276", + "right": "issue:45335", + "accept": false, + "reason": "Both are resize_token_embeddings regressions, but they hit different architectures and submodules, so they do not clearly describe the same bug." + }, + { + "left": "issue:43404", + "right": "issue:43454", + "accept": false, + "reason": "Similar symptom of untied lm_head, but for different model families and likely separate model-specific fixes." + }, + { + "left": "issue:36010", + "right": "issue:39404", + "accept": false, + "reason": "ImportError for GenerationMixin and Whisper return_language pipeline regression are unrelated." + }, + { + "left": "issue:39692", + "right": "issue:44960", + "accept": false, + "reason": "Different SigLIP2/docs issue versus an unrelated GLM5 report." + }, + { + "left": "issue:43425", + "right": "issue:43957", + "accept": false, + "reason": "Torch version incompatibility and meta-device model-loading breakage are not the same defect." + }, + { + "left": "issue:44402", + "right": "issue:44488", + "accept": false, + "reason": "Tokenizer vocab-size mismatch versus inability to load a specific BERT model; different underlying problems." + }, + { + "left": "issue:42947", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing/LoRA and apex FusedRMSNorm memory leak are unrelated." + }, + { + "left": "issue:45663", + "right": "issue:45759", + "accept": false, + "reason": "Different model families and different code paths: Gemma4 FSDP2 attention vs Qwen composite config unwrapping." + }, + { + "left": "issue:45663", + "right": "issue:45859", + "accept": false, + "reason": "Gemma4 FSDP2 attention state rebuild and Qwen3_5Moe rotary embedding CPU-offload incompatibility are unrelated." + }, + { + "left": "issue:43873", + "right": "issue:44387", + "accept": false, + "reason": "Both mention quantization/memory, but one is offloading behavior and the other is increased reserved memory under int4 quantization." + }, + { + "left": "issue:44155", + "right": "issue:45823", + "accept": false, + "reason": "AudioFlamingo3 track leakage and Gemma4 device mismatch are unrelated." + }, + { + "left": "issue:44291", + "right": "issue:44756", + "accept": false, + "reason": "Unexpected _is_hf_initialized argument and Strix Halo mmap OOM are different issues." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet, and the one accepted edge (43644 \u2194 44534) is clearly supported by the titles and dates. The other soft-edge rejections are conservative and avoid overclaiming duplicate status from loose topical similarity alone. No issue/PR pair in the packet suggests a mergeability problem." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 7, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:39404", + "issue:41720", + "issue:42947", + "issue:43257", + "issue:43335", + "issue:43381", + "issue:43425", + "issue:43611", + "issue:43645", + "issue:43646", + "issue:43708", + "issue:43716", + "issue:43828", + "issue:43854", + "issue:43906", + "issue:43957", + "issue:44155", + "issue:44164", + "issue:44265", + "issue:44292", + "issue:44387", + "issue:44402", + "issue:44451", + "issue:44479", + "issue:44530", + "issue:44589", + "issue:44683", + "issue:44756", + "issue:44805", + "issue:44863", + "issue:44877", + "issue:44898", + "issue:44912", + "issue:44928", + "issue:44960", + "issue:45084", + "issue:45216", + "issue:45276", + "issue:45292", + "issue:45335", + "issue:45588", + "issue:45663", + "issue:45684", + "issue:45698", + "issue:45701", + "issue:45823", + "issue:46050" + ], + "soft_pairs": [ + "issue:44292|issue:44912", + "issue:44960|issue:46050", + "issue:43335|issue:45663", + "issue:44387|issue:44756", + "issue:42947|issue:43381", + "issue:45276|issue:45292", + "issue:43854|issue:45216", + "issue:43381|issue:44928", + "issue:44164|issue:44756", + "issue:44479|issue:44877", + "issue:45588|issue:45663", + "issue:41720|issue:44155", + "issue:45684|issue:45698", + "issue:43957|issue:44756", + "issue:43646|issue:43708", + "issue:45292|issue:45335", + "issue:43645|issue:44164", + "issue:43828|issue:43957", + "issue:44402|issue:44451", + "issue:43425|issue:43828", + "issue:44589|issue:44756", + "issue:43257|issue:44863", + "issue:44683|issue:45823", + "issue:39404|issue:45701", + "issue:43611|issue:43645", + "issue:43425|issue:45823", + "issue:43425|issue:43716", + "issue:44530|issue:45084", + "issue:43906|issue:44530", + "issue:39404|issue:44912", + "issue:44265|issue:44898", + "issue:44479|issue:44805" + ], + "prepared_review_unit_hash": "058d11618cf7d393d8a55eca70fa9037b72e856753d7955c8e9acd3c67fde37a", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36683, + "estimated_input_tokens": 9171, + "estimated_eval_tokens": 18598 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers regressions, with a small duplicate pocket around `resize_token_embeddings` not updating model embeddings. The strongest representative issue is the custom-module save/load regression in `from_pretrained` after `save_pretrained`.", + "confidence": 0.84, + "canonical_issue_reason": "issue:45698 is the broadest and most actionable representative of the custom-model save/load regressions in this set, and it sits at the center of several related loading failures.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45698 is the best issue to keep because it is open, clearly describes a concrete `save_pretrained`/`from_pretrained` failure, and generalizes well to the nearby custom-model loading reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44292", + "right": "issue:44912", + "accept": false, + "reason": "Both are quantization/loading regressions, but they affect different models and failure modes (runtime error vs silent bf16 fallback)." + }, + { + "left": "issue:44960", + "right": "issue:46050", + "accept": false, + "reason": "These are different problems: a vague GLM5 issue versus a quantized-model save/load corruption report." + }, + { + "left": "issue:43335", + "right": "issue:45663", + "accept": false, + "reason": "Completely different bugs: SwitchTransformers sparse-layer creation versus Gemma4 FSDP2 shared-state rebuilding." + }, + { + "left": "issue:44387", + "right": "issue:44756", + "accept": false, + "reason": "Both mention OOM, but the causes are different (int4 reserved memory regression vs mmap on Strix Halo)." + }, + { + "left": "issue:42947", + "right": "issue:43381", + "accept": false, + "reason": "Both involve gradient checkpointing, but one is about PEFT/LoRA ineffectiveness and the other about eval-mode restrictions." + }, + { + "left": "issue:45276", + "right": "issue:45292", + "accept": true, + "reason": "Same underlying `resize_token_embeddings` bug: the Gemma4-specific report and the generic output-embedding report describe the same propagation failure." + }, + { + "left": "issue:43854", + "right": "issue:45216", + "accept": false, + "reason": "Different model-loading regressions with unrelated symptoms and model families." + }, + { + "left": "issue:43381", + "right": "issue:44928", + "accept": false, + "reason": "No shared bug path; one is checkpointing in eval mode, the other is a Qwen3.5 training instability from position IDs/SDPA fallback." + }, + { + "left": "issue:44164", + "right": "issue:44756", + "accept": false, + "reason": "Extra state save/load handling is unrelated to the Strix Halo mmap OOM issue." + }, + { + "left": "issue:44479", + "right": "issue:44877", + "accept": false, + "reason": "Different regressions: video-input handling for Qwen VL models versus strict config loading for granite_speech." + }, + { + "left": "issue:45588", + "right": "issue:45663", + "accept": false, + "reason": "Unrelated failures in flash-attention integration and Gemma4 FSDP2 attention state handling." + }, + { + "left": "issue:41720", + "right": "issue:44155", + "accept": false, + "reason": "Different model-specific correctness bugs with no shared code-path indication." + }, + { + "left": "issue:45684", + "right": "issue:45698", + "accept": false, + "reason": "Both are custom-model save/load adjacent, but one is file-permissions propagation and the other is wrong module loading; not the same bug." + }, + { + "left": "issue:43957", + "right": "issue:44756", + "accept": false, + "reason": "Meta-device loading regressions are not the same issue as Strix Halo mmap OOMs." + }, + { + "left": "issue:43646", + "right": "issue:43708", + "accept": false, + "reason": "Custom model initialization breakage and Trainer max_steps calculation are unrelated." + }, + { + "left": "issue:45292", + "right": "issue:45335", + "accept": true, + "reason": "Same `resize_token_embeddings` propagation failure, expressed as output-embedding versus decoder.embed_tokens updates in different model families." + }, + { + "left": "issue:43645", + "right": "issue:44164", + "accept": false, + "reason": "Both touch custom models, but notebook initialization and extra_state serialization are distinct problems." + }, + { + "left": "issue:43828", + "right": "issue:43957", + "accept": false, + "reason": "Different failure mechanisms: autocast dtype mismatch versus meta-device loading breakage." + }, + { + "left": "issue:44402", + "right": "issue:44451", + "accept": false, + "reason": "Tokenizer vocab mismatch and model loading failure are not the same underlying bug." + }, + { + "left": "issue:43425", + "right": "issue:43828", + "accept": false, + "reason": "Torch version incompatibility and autocast dtype mismatch are separate regressions." + }, + { + "left": "issue:44589", + "right": "issue:44756", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to the mmap/OOM report." + }, + { + "left": "issue:43257", + "right": "issue:44863", + "accept": false, + "reason": "Different model families and different loading failures; no evidence they are the same bug." + }, + { + "left": "issue:44683", + "right": "issue:45823", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 is unrelated to the Gemma4 device-mismatch issue." + }, + { + "left": "issue:39404", + "right": "issue:45701", + "accept": false, + "reason": "Whisper pipeline return_language and tokenization-version changes are separate concerns." + }, + { + "left": "issue:43611", + "right": "issue:43645", + "accept": false, + "reason": "Both are Transformer 5 custom-model regressions, but one is base_model_prefix loading and the other is notebook initialization; not the same concrete bug." + }, + { + "left": "issue:43425", + "right": "issue:45823", + "accept": false, + "reason": "Torch compatibility and Gemma4 device placement are different issues." + }, + { + "left": "issue:43425", + "right": "issue:43716", + "accept": false, + "reason": "Torch compatibility and image preprocessor dtype mismatch are unrelated." + }, + { + "left": "issue:44530", + "right": "issue:45084", + "accept": false, + "reason": "Different failures in attention/cache handling versus template-node compilation." + }, + { + "left": "issue:43906", + "right": "issue:44530", + "accept": false, + "reason": "The isolated reproduction issue is not the same as the Qwen3.5 PagedAttentionCache crash." + }, + { + "left": "issue:39404", + "right": "issue:44912", + "accept": false, + "reason": "Whisper pipeline language return and MXFP4 quantization fallback are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:44898", + "accept": false, + "reason": "torch.export with torch_compilable_check and Perceiver interpolation are different code paths." + }, + { + "left": "issue:44479", + "right": "issue:44805", + "accept": false, + "reason": "Video-input regression and mask shape mismatch are not the same underlying bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: most pairs are reasonably rejected as unrelated, and the `resize_token_embeddings` cluster is the only clearly supported duplicate pocket. The choice of `issue:45698` as the representative save/load issue is conservative and fits the open, concrete custom-module regression reports without overclaiming. No PR mergeability concerns apply here." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 8, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:32090", + "issue:34567", + "issue:36032", + "issue:39404", + "issue:40444", + "issue:40990", + "issue:42915", + "issue:43299", + "issue:43421", + "issue:43425", + "issue:43452", + "issue:43541", + "issue:43582", + "issue:43596", + "issue:43611", + "issue:43632", + "issue:43643", + "issue:43644", + "issue:43646", + "issue:43716", + "issue:43856", + "issue:43901", + "issue:43931", + "issue:43994", + "issue:44079", + "issue:44164", + "issue:44206", + "issue:44220", + "issue:44451", + "issue:44479", + "issue:44488", + "issue:44509", + "issue:44530", + "issue:44589", + "issue:44661", + "issue:44671", + "issue:44683", + "issue:44737", + "issue:44756", + "issue:44811", + "issue:44918", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45584", + "issue:45759", + "issue:45859" + ], + "soft_pairs": [ + "issue:43901|issue:44509", + "issue:44589|issue:45084", + "issue:43425|issue:44918", + "issue:36032|issue:43452", + "issue:44164|issue:45759", + "issue:43299|issue:43931", + "issue:43596|issue:44683", + "issue:44991|issue:45081", + "issue:43994|issue:44079", + "issue:43856|issue:44756", + "issue:44671|issue:44991", + "issue:39404|issue:44671", + "issue:44164|issue:44479", + "issue:44737|issue:45859", + "issue:44488|issue:45081", + "issue:43582|issue:43632", + "issue:44661|issue:44683", + "issue:43611|issue:43644", + "issue:40990|issue:43421", + "issue:32090|issue:39404", + "issue:43716|issue:45084", + "issue:44488|issue:44987", + "issue:43643|issue:44530", + "issue:36032|issue:42915", + "issue:34567|issue:40444", + "issue:44811|issue:45584", + "issue:43541|issue:45084", + "issue:44451|issue:44987", + "issue:42915|issue:44530", + "issue:43644|issue:43646", + "issue:44206|issue:44220" + ], + "prepared_review_unit_hash": "801c192f5a56fdf82327573e8720319ed975932e0805671951a3c036ee872ae4", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36889, + "estimated_input_tokens": 9223, + "estimated_eval_tokens": 18702 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is thematically broad rather than duplicate-heavy: it mixes many Transformers v5 regressions, model-loading failures, tokenizer issues, and a few unrelated audio/docs/multimodal bugs. None of the proposed soft pairs look like the same underlying bug or change.", + "confidence": 0.73, + "canonical_issue_reason": "issue:43611 is the broadest representative of the cluster\u2019s dominant theme: Transformers v5 model-loading regressions. It is more general than the narrower model-specific or component-specific issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best single representative of the cluster because it captures the most central and reusable failure mode among these items: v5 loading behavior breaking for models.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43901", + "right": "issue:44509", + "accept": false, + "reason": "Both are docs-related, but one is about TextClassificationPipeline return_all_scores wording while the other is about removed pipeline tasks in v5; related theme, not the same change." + }, + { + "left": "issue:44589", + "right": "issue:45084", + "accept": false, + "reason": "Different failures in different code paths: missing Float8 storage vs a template-node compilation error." + }, + { + "left": "issue:43425", + "right": "issue:44918", + "accept": false, + "reason": "One is a torch version compatibility issue, the other is a Qwen3.5 input-embedding/TRL trainer failure; unrelated bugs." + }, + { + "left": "issue:36032", + "right": "issue:43452", + "accept": false, + "reason": "T5 tokenizer special-token method conflict and gguf_file loading breakage are separate tokenizer/model-loading problems." + }, + { + "left": "issue:44164", + "right": "issue:45759", + "accept": false, + "reason": "save/from_pretrained extra_state handling and AutoModelForCausalLM.from_config text_config unwrapping are different API regressions." + }, + { + "left": "issue:43299", + "right": "issue:43931", + "accept": false, + "reason": "Both involve Qwen3-VL loading, but they describe different model variants and different breakages; not clearly the same bug." + }, + { + "left": "issue:43596", + "right": "issue:44683", + "accept": false, + "reason": "deepspeed zero3/BertModel indexing and compiled flex_attention on torch>=2.9 are unrelated." + }, + { + "left": "issue:44991", + "right": "issue:45081", + "accept": false, + "reason": "Both are tokenizer load failures, but for different models and different failure mechanisms." + }, + { + "left": "issue:43994", + "right": "issue:44079", + "accept": false, + "reason": "A specific SigLIP2 bad-output issue and a generic ModelOutput key-assignment bug are not the same concrete defect." + }, + { + "left": "issue:43856", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory pressure, but one is Qwen3 MoE training inefficiency and the other is Strix Halo mmap OOM behavior." + }, + { + "left": "issue:44671", + "right": "issue:44991", + "accept": false, + "reason": "CamemBERT masked-LM prediction regression and tokenizer loading for est-roberta are unrelated." + }, + { + "left": "issue:39404", + "right": "issue:44671", + "accept": false, + "reason": "Whisper pipeline return_language regression and CamemBERT masked-LM regression are different model-specific issues." + }, + { + "left": "issue:44164", + "right": "issue:44479", + "accept": false, + "reason": "Extra_state serialization and a video-input regression in Qwen multimodal models do not share the same underlying bug." + }, + { + "left": "issue:44737", + "right": "issue:45859", + "accept": false, + "reason": "Both are device/performance related, but XLNet CPU arange placement and Qwen3_5Moe CPU-offload incompatibility are distinct code paths." + }, + { + "left": "issue:44488", + "right": "issue:45081", + "accept": false, + "reason": "Two separate tokenizer-loading reports for different models and different symptoms." + }, + { + "left": "issue:43582", + "right": "issue:43632", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError and the _is_hf_initialized regression are unrelated." + }, + { + "left": "issue:44661", + "right": "issue:44683", + "accept": false, + "reason": "Model registry generation and compiled flex_attention failures are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43644", + "accept": false, + "reason": "Both are v5 regressions, but one is about base_model_prefix loading and the other about non-persistent buffers; different breakages." + }, + { + "left": "issue:40990", + "right": "issue:43421", + "accept": false, + "reason": "Perplexity on GPT-OSS and runtime post-processor updating are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:39404", + "accept": false, + "reason": "Trainer GPU broadcast TypeError and Whisper pipeline return_language are unrelated." + }, + { + "left": "issue:43716", + "right": "issue:45084", + "accept": false, + "reason": "Mistral-3 image dtype mismatch and template-node compilation error are different failures." + }, + { + "left": "issue:44488", + "right": "issue:44987", + "accept": false, + "reason": "Separate model-loading regressions affecting different repositories and different tokenizer/model paths." + }, + { + "left": "issue:43643", + "right": "issue:44530", + "accept": false, + "reason": "AutoConfig trust_remote_code field loss and PagedAttentionCache linear_attention crash are unrelated." + }, + { + "left": "issue:36032", + "right": "issue:42915", + "accept": false, + "reason": "T5 tokenizer special-token conflict and Qwen3Moe FineGrainedFP8Config failure are unrelated." + }, + { + "left": "issue:34567", + "right": "issue:40444", + "accept": false, + "reason": "TrainerState token-count tracking and Qwen2.5-VL iterable dataset multi-image finetuning are unrelated." + }, + { + "left": "issue:44811", + "right": "issue:45584", + "accept": false, + "reason": "Both concern Whisper, but one is batch_decode skip_special_tokens handling and the other is empty transcription after align_special_tokens; not the same bug." + }, + { + "left": "issue:43541", + "right": "issue:45084", + "accept": false, + "reason": "Mixtral grouped_mm tracing failure and template-node compilation failure are different runtime errors." + }, + { + "left": "issue:44451", + "right": "issue:44987", + "accept": false, + "reason": "Loading vesteinn/ScandiBERT and loading physical-intelligence/fast fail for different reasons and code paths." + }, + { + "left": "issue:43644", + "right": "issue:43646", + "accept": false, + "reason": "Both are v5 regressions, but one is buffer initialization and the other is custom model initialization; not the same underlying change." + }, + { + "left": "issue:44206", + "right": "issue:44220", + "accept": false, + "reason": "Feature-extractor center-arg regression and _torch_extract_fbank_features() issue are related to audio preprocessing but appear to be distinct 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": 18, + "review_unit_index": 9, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36032", + "issue:42175", + "issue:42915", + "issue:43089", + "issue:43262", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43452", + "issue:43482", + "issue:43531", + "issue:43540", + "issue:43632", + "issue:43645", + "issue:43646", + "issue:43742", + "issue:43819", + "issue:43883", + "issue:43994", + "issue:44062", + "issue:44220", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44488", + "issue:44534", + "issue:44589", + "issue:44610", + "issue:44683", + "issue:44756", + "issue:44849", + "issue:44877", + "issue:44987", + "issue:44991", + "issue:45081", + "issue:45084", + "issue:45127", + "issue:45216", + "issue:45325", + "issue:45357", + "issue:45507", + "issue:45987", + "issue:46178" + ], + "soft_pairs": [ + "issue:44464|issue:45987", + "issue:43452|issue:43482", + "issue:43883|issue:44488", + "issue:43317|issue:43482", + "issue:44849|issue:45325", + "issue:36032|issue:43645", + "issue:45084|issue:45507", + "issue:42175|issue:46178", + "issue:43262|issue:43377", + "issue:44987|issue:44991", + "issue:43646|issue:44534", + "issue:43089|issue:45987", + "issue:43404|issue:44466", + "issue:44403|issue:45081", + "issue:43883|issue:44991", + "issue:43322|issue:43540", + "issue:43994|issue:44610", + "issue:42915|issue:45084", + "issue:43645|issue:44534", + "issue:43377|issue:43819", + "issue:44265|issue:44610", + "issue:44451|issue:45081", + "issue:44987|issue:45081", + "issue:44220|issue:44683", + "issue:45216|issue:45357", + "issue:36032|issue:43742", + "issue:42915|issue:44291", + "issue:42915|issue:44589", + "issue:43632|issue:44756", + "issue:44062|issue:44987", + "issue:43404|issue:45127", + "issue:43296|issue:43531", + "issue:43531|issue:44877" + ], + "prepared_review_unit_hash": "1e03fa04a9d249adce3abe87e09e55b737f8f3cfa2eb0a9b4bd532c7f3461b81", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37593, + "estimated_input_tokens": 9399, + "estimated_eval_tokens": 19054 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers regressions that share broad v5/loading similarity, not true duplicates. The only clear duplicate pair is the Qwen3.5 save_pretrained regression (45216/45357).", + "confidence": 0.47, + "canonical_issue_reason": "Issue 45216 is the clearest representative because it describes the core Qwen3.5 save_pretrained corruption, and 45357 reads like a follow-up on the same checkpoint/visual-encoder-key regression.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45216 is the best cluster representative since it has the strongest duplicate linkage in the set and captures the specific regression most directly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44464", + "right": "issue:45987", + "accept": false, + "reason": "Different bugs: chunked generation/compiled forward vs StaticCache sequence-length return type." + }, + { + "left": "issue:43452", + "right": "issue:43482", + "accept": false, + "reason": "Both involve GGUF loading, but the titles point to different failure reports and no shared concrete code-path is clear from the metadata." + }, + { + "left": "issue:43883", + "right": "issue:44488", + "accept": false, + "reason": "Molmo tied-weights attribute error vs a model load failure for cjvt/sleng-bert; unrelated symptoms." + }, + { + "left": "issue:43317", + "right": "issue:43482", + "accept": false, + "reason": "device_map/offload dequantization failure is a different problem from GGUF loading failure." + }, + { + "left": "issue:44849", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen model families and different bugs: hidden-states output vs rope-index temporal scaling." + }, + { + "left": "issue:36032", + "right": "issue:43645", + "accept": false, + "reason": "Tokenizer add_special_tokens conflict is unrelated to custom model initialization in notebooks." + }, + { + "left": "issue:45084", + "right": "issue:45507", + "accept": false, + "reason": "Different errors and different code paths; no evidence they fix the same underlying issue." + }, + { + "left": "issue:42175", + "right": "issue:46178", + "accept": false, + "reason": "Backend-install packaging issue vs backend-mapping error for tensorflow_text; not the same bug." + }, + { + "left": "issue:43262", + "right": "issue:43377", + "accept": false, + "reason": "Audio chat-template sampling-rate default vs MIMI batched-padding-mask mismatch are different issues." + }, + { + "left": "issue:44987", + "right": "issue:44991", + "accept": false, + "reason": "Both are v5 load failures, but they affect different models and likely different loaders." + }, + { + "left": "issue:43646", + "right": "issue:44534", + "accept": false, + "reason": "Custom model initialization breakage is unrelated to non-persistent buffer serialization garbage." + }, + { + "left": "issue:43089", + "right": "issue:45987", + "accept": false, + "reason": "Generation GPU sync overhead is unrelated to StaticCache.get_seq_length contract." + }, + { + "left": "issue:43404", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied lm_head weights, but one is a model tying bug and the other is a serialization inconsistency; not clearly the same concrete defect." + }, + { + "left": "issue:44403", + "right": "issue:45081", + "accept": false, + "reason": "General loading noise vs a Mistral regex patch crash; different failure modes." + }, + { + "left": "issue:43883", + "right": "issue:44991", + "accept": false, + "reason": "Different model-loading failures with no shared underlying bug indicated." + }, + { + "left": "issue:43322", + "right": "issue:43540", + "accept": false, + "reason": "Segmentation fault while loading Llava Next is unrelated to Qwen3OmniMoe video-input validation." + }, + { + "left": "issue:43994", + "right": "issue:44610", + "accept": false, + "reason": "Nonsensical SigLIP2 outputs vs OmDet-Turbo processor resolution mismatch are different issues." + }, + { + "left": "issue:42915", + "right": "issue:45084", + "accept": false, + "reason": "FineGrainedFP8Config failure is unrelated to template-node compilation errors." + }, + { + "left": "issue:43645", + "right": "issue:44534", + "accept": false, + "reason": "Notebook custom-model initialization and junk-filled non-persistent buffers are different regressions." + }, + { + "left": "issue:43377", + "right": "issue:43819", + "accept": false, + "reason": "Missing padding-mask support in MIMI encoder vs DAC forward/from_latents STE mismatch are different code paths." + }, + { + "left": "issue:44265", + "right": "issue:44610", + "accept": false, + "reason": "torch.export/exportability issue is unrelated to processor input-size mismatch." + }, + { + "left": "issue:44451", + "right": "issue:45081", + "accept": false, + "reason": "Model loading failure for ScandiBERT is unrelated to the Mistral tokenizer regex patch crash." + }, + { + "left": "issue:44987", + "right": "issue:45081", + "accept": false, + "reason": "Different models and different failure points; not the same bug." + }, + { + "left": "issue:44220", + "right": "issue:44683", + "accept": false, + "reason": "Feature-extraction helper bug vs compiled flex_attention regression; unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45357", + "accept": true, + "reason": "Same Qwen3.5 save_pretrained regression: both describe incorrect checkpoint serialization/visual-encoder-key handling in the same model family." + }, + { + "left": "issue:36032", + "right": "issue:43742", + "accept": false, + "reason": "Tokenizer special-token conflict vs a MobileLLM key error are unrelated." + }, + { + "left": "issue:42915", + "right": "issue:44291", + "accept": false, + "reason": "Different v5 regressions: FP8 config failure vs init_empty_weights/_is_hf_initialized argument issue." + }, + { + "left": "issue:42915", + "right": "issue:44589", + "accept": false, + "reason": "FP8 config failure is unrelated to missing Float8 storage handling." + }, + { + "left": "issue:43632", + "right": "issue:44756", + "accept": false, + "reason": "_is_hf_initialized flag regression and mmap OOM avoidance are separate issues." + }, + { + "left": "issue:44062", + "right": "issue:44987", + "accept": false, + "reason": "AddedToken special-argument duplication is unrelated to model/tokenizer load failure for fast." + }, + { + "left": "issue:43404", + "right": "issue:45127", + "accept": false, + "reason": "Both touch tied weights, but one is a model-weight tying bug while the other is LoRA merge with extended vocab collapse; not clearly the same defect." + }, + { + "left": "issue:43296", + "right": "issue:43531", + "accept": false, + "reason": "PaddleOCR-VL loading failure and Qwen3-MoE sliding_window bug are different problems." + }, + { + "left": "issue:43531", + "right": "issue:44877", + "accept": false, + "reason": "Sliding_window behavior in Qwen3-MoE is unrelated to granite_speech config strictness." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and the soft-edge verdicts are generally conservative. The only accepted pair, 45216/45357, is well supported by the titles as the same Qwen3.5 save_pretrained regression." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 10, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:33666", + "issue:36032", + "issue:40444", + "issue:40990", + "issue:41553", + "issue:41720", + "issue:42175", + "issue:43296", + "issue:43317", + "issue:43377", + "issue:43381", + "issue:43421", + "issue:43425", + "issue:43482", + "issue:43525", + "issue:43531", + "issue:43582", + "issue:43611", + "issue:43632", + "issue:43646", + "issue:43792", + "issue:43818", + "issue:43856", + "issue:44079", + "issue:44265", + "issue:44291", + "issue:44403", + "issue:44462", + "issue:44479", + "issue:44534", + "issue:44568", + "issue:44589", + "issue:44683", + "issue:44811", + "issue:44829", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45479", + "issue:45491", + "issue:45538", + "issue:45542", + "issue:45663", + "issue:45812", + "issue:45923" + ], + "soft_pairs": [ + "issue:43611|issue:44534", + "issue:36032|issue:41720", + "issue:43425|issue:44403", + "issue:44479|issue:45325", + "issue:40990|issue:44811", + "issue:43792|issue:44589", + "issue:43421|issue:44568", + "issue:44403|issue:44991", + "issue:33666|issue:40444", + "issue:43632|issue:44534", + "issue:44683|issue:45020", + "issue:44079|issue:45663", + "issue:43381|issue:45923", + "issue:44462|issue:45812", + "issue:44291|issue:44589", + "issue:43482|issue:45538", + "issue:44829|issue:45479", + "issue:40444|issue:45325", + "issue:43317|issue:43856", + "issue:43482|issue:43525", + "issue:41553|issue:43582", + "issue:42175|issue:45542", + "issue:43818|issue:45357", + "issue:41720|issue:45081", + "issue:43377|issue:45491", + "issue:43531|issue:44291", + "issue:44265|issue:45072", + "issue:43611|issue:43646", + "issue:42175|issue:43296" + ], + "prepared_review_unit_hash": "b87edc8cfed58005d967db3b66ba1ff830d933116f366a5304ad0fb03ee923a9", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36595, + "estimated_input_tokens": 9149, + "estimated_eval_tokens": 18554 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of unrelated transformer/model-loading regressions, tokenizer bugs, and training/runtime issues. Only one soft pair looks like the same underlying bug: a Transformers v5 model-initialization/loading regression.", + "confidence": 0.47, + "canonical_issue_reason": "issue:43611 is the broadest and most central representative of the shared Transformers v5 loading/initialization regression theme, and it cleanly subsumes the one plausible duplicate pair.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43611 is the best cluster representative because it matches the strongest duplicate evidence and sits at the core of the v5 model-loading breakage pattern.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43611", + "right": "issue:44534", + "accept": false, + "reason": "Both are v5 regressions, but they fail in different ways: base_model_prefix/custom init vs non-persistent buffer handling." + }, + { + "left": "issue:36032", + "right": "issue:41720", + "accept": false, + "reason": "Tokenizer add_special_tokens conflict and a CUDA device-mapping assert are unrelated bugs." + }, + { + "left": "issue:43425", + "right": "issue:44403", + "accept": false, + "reason": "Torch 2.10 compatibility and noisy load logging are different problems." + }, + { + "left": "issue:44479", + "right": "issue:45325", + "accept": false, + "reason": "These are different Qwen VL regressions: video-input handling vs still-image rope position scaling." + }, + { + "left": "issue:40990", + "right": "issue:44811", + "accept": false, + "reason": "WikiText-2 perplexity and Whisper batch_decode token skipping are unrelated code paths." + }, + { + "left": "issue:43792", + "right": "issue:44589", + "accept": false, + "reason": "Whisper runtime failure and Float8 storage lookup error are distinct issues." + }, + { + "left": "issue:43421", + "right": "issue:44568", + "accept": false, + "reason": "Runtime post-processor updates for special tokens and missing BOS/EOS insertion are different tokenizer bugs." + }, + { + "left": "issue:44403", + "right": "issue:44991", + "accept": false, + "reason": "General loading noise and a specific tokenizer-loading regression for EMBEDDIA/est-roberta are not the same bug." + }, + { + "left": "issue:33666", + "right": "issue:40444", + "accept": false, + "reason": "Both are Qwen2-VL training issues, but one is multi-GPU training and the other is iterable-dataset multi-image prompting." + }, + { + "left": "issue:43632", + "right": "issue:44534", + "accept": false, + "reason": "The _is_hf_initialized regression and junk-filled non-persistent buffers are separate Transformers v5 failures." + }, + { + "left": "issue:44683", + "right": "issue:45020", + "accept": false, + "reason": "Compiled flex_attention on torch>=2.9 and remote_code loading breakage are unrelated." + }, + { + "left": "issue:44079", + "right": "issue:45663", + "accept": false, + "reason": "ModelOutput key assignment and Gemma4 shared_kv_states reconstruction are different issues." + }, + { + "left": "issue:43381", + "right": "issue:45923", + "accept": false, + "reason": "Eval-mode gradient checkpointing failure and missing supports_gradient_checkpointing are not the same underlying bug." + }, + { + "left": "issue:44462", + "right": "issue:45812", + "accept": false, + "reason": "Ignoring tokenizer.json and wrong Granite token IDs are both tokenizer regressions but not the same concrete failure." + }, + { + "left": "issue:44291", + "right": "issue:44589", + "accept": false, + "reason": "Unexpected _is_hf_initialized in init_empty_weights and Float8 storage lookup are unrelated." + }, + { + "left": "issue:43482", + "right": "issue:45538", + "accept": false, + "reason": "GGUF loading failure and CLIPTokenizer max_length misuse are unrelated tokenizer/model issues." + }, + { + "left": "issue:44829", + "right": "issue:45479", + "accept": false, + "reason": "Both involve degenerate training, but the model paths and root causes differ." + }, + { + "left": "issue:40444", + "right": "issue:45325", + "accept": false, + "reason": "Multi-image iterable-dataset failure and still-image temporal position scaling are different Qwen2.5-VL bugs." + }, + { + "left": "issue:43317", + "right": "issue:43856", + "accept": false, + "reason": "Device-map/offload loading failure and Qwen3 MoE memory inefficiency are distinct training/runtime problems." + }, + { + "left": "issue:43482", + "right": "issue:43525", + "accept": false, + "reason": "Transformers v5 GGUF loading failure and missing pad_token_id on Llama4Config are separate regressions." + }, + { + "left": "issue:41553", + "right": "issue:43582", + "accept": false, + "reason": "Bad AutoTokenizer error messaging for Voxtral and an AppleSilicon TypeError are unrelated." + }, + { + "left": "issue:42175", + "right": "issue:45542", + "accept": false, + "reason": "Both concern TensorFlow packaging, but the reported failures are different enough to avoid merging as duplicates." + }, + { + "left": "issue:43818", + "right": "issue:45357", + "accept": false, + "reason": "Video-LLaVA temporal-attention/weight-sharing bug and Qwen3.5 save_pretrained key regression are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:45081", + "accept": false, + "reason": "A Qwen3 device-mapping CUDA assert and a Mistral tokenizer regex patch crash are unrelated." + }, + { + "left": "issue:43377", + "right": "issue:45491", + "accept": false, + "reason": "MIMI padding-mask mismatch and Gemma3 mixed-length NaNs are both batching-related but not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:44291", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and init_empty_weights argument handling are unrelated." + }, + { + "left": "issue:44265", + "right": "issue:45072", + "accept": false, + "reason": "torch.export export failures and bfloat16 dtype mismatches are different concrete issues." + }, + { + "left": "issue:43611", + "right": "issue:43646", + "accept": true, + "reason": "Both describe the same Transformers v5 model-initialization/loading regression affecting custom model loading paths." + }, + { + "left": "issue:42175", + "right": "issue:43296", + "accept": false, + "reason": "TensorFlow backend packaging and PaddleOCR-VL loading in vLLM are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Grounded overall. The one accepted pair (43611/43646) is a conservative, mergeable same-bugfix match around Transformers v5 model initialization/loading regressions. The other rejections read 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": 18, + "review_unit_index": 11, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:35707", + "issue:39692", + "issue:40444", + "issue:40990", + "issue:41720", + "issue:42915", + "issue:42947", + "issue:43257", + "issue:43262", + "issue:43296", + "issue:43377", + "issue:43454", + "issue:43482", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43632", + "issue:43644", + "issue:43701", + "issue:43746", + "issue:43761", + "issue:43792", + "issue:43819", + "issue:43881", + "issue:43957", + "issue:43994", + "issue:44079", + "issue:44186", + "issue:44265", + "issue:44291", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44534", + "issue:44568", + "issue:44610", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45325", + "issue:45381", + "issue:45584", + "issue:45759", + "issue:45800", + "issue:45823", + "issue:45834", + "issue:45920", + "issue:45923" + ], + "soft_pairs": [ + "issue:43792|issue:43957", + "issue:43632|issue:45072", + "issue:43994|issue:44898", + "issue:45325|issue:45834", + "issue:44079|issue:44534", + "issue:43454|issue:44466", + "issue:42915|issue:43482", + "issue:40444|issue:45381", + "issue:45325|issue:45381", + "issue:43644|issue:44079", + "issue:43296|issue:45800", + "issue:43761|issue:44079", + "issue:35707|issue:40444", + "issue:44479|issue:45823", + "issue:44291|issue:44877", + "issue:43606|issue:44265", + "issue:44568|issue:45920", + "issue:43701|issue:45325", + "issue:43606|issue:43819", + "issue:41720|issue:45823", + "issue:44186|issue:44265", + "issue:43454|issue:43550", + "issue:43262|issue:43746", + "issue:43881|issue:44488", + "issue:39692|issue:40444", + "issue:40990|issue:45584", + "issue:43454|issue:45072", + "issue:43377|issue:44610", + "issue:43257|issue:45923", + "issue:43572|issue:45759", + "issue:40990|issue:42947" + ], + "prepared_review_unit_hash": "43bf26ef93d1c0dd74f1048820bb2888f3c883f00021137a31488e3d282698cb", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 37187, + "estimated_input_tokens": 9297, + "estimated_eval_tokens": 18850 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose set of unrelated model-loading/regression bugs. There isn\u2019t a strong duplicate group; the closest theme is broad Transformers v5 regressions, but the soft pairs mostly differ in concrete code paths and should stay separate.", + "confidence": 0.32, + "canonical_issue_reason": "issue:45920 is the broadest and most representative issue in the set: it describes a cross-model tokenizer regression affecting multiple families, which fits the cluster\u2019s loose v5-regression theme better than the narrower single-model reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best issue to anchor this cluster because it is open, high-impact, and spans several model families rather than a single model-specific failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43792", + "right": "issue:43957", + "accept": false, + "reason": "Both are load failures, but one is Whisper inference failure and the other is meta-device loading breakage across different models; not the same bug." + }, + { + "left": "issue:43632", + "right": "issue:45072", + "accept": false, + "reason": "Both involve v5 inference regressions, but one is about `_is_hf_initialized` and the other is a bfloat16 dtype mismatch; different code paths." + }, + { + "left": "issue:43994", + "right": "issue:44898", + "accept": false, + "reason": "Both are vision-model issues, but one is bad outputs/loading for SigLIP2 and the other is Perceiver resolution handling; not the same defect." + }, + { + "left": "issue:45325", + "right": "issue:45834", + "accept": false, + "reason": "Both touch multimodal indexing, but one is Qwen2.5-VL temporal position scaling and the other is Kosmos2.5 long OCR index overflow; distinct bugs." + }, + { + "left": "issue:44079", + "right": "issue:44534", + "accept": false, + "reason": "ModelOutput key assignment and non-persistent buffer junk are unrelated internal regressions." + }, + { + "left": "issue:43454", + "right": "issue:44466", + "accept": false, + "reason": "Both mention tied lm_head weights, but one is failure to tie weights and the other is inconsistent serialization behavior; not mergeable as one fix." + }, + { + "left": "issue:42915", + "right": "issue:43482", + "accept": false, + "reason": "Different models and failures: FineGrainedFP8Config on Qwen3Moe vs GGUF loading on Qwen2.5; no shared concrete bug." + }, + { + "left": "issue:40444", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen VL multimodal issues, but one is finetuning with multiple images per prompt and the other is video position-id computation; separate paths." + }, + { + "left": "issue:45325", + "right": "issue:45381", + "accept": false, + "reason": "Related by Qwen2.5-VL position IDs, but one is still-image temporal scaling and the other is video vision_position_ids; different regressions." + }, + { + "left": "issue:43644", + "right": "issue:44079", + "accept": false, + "reason": "Non-persistent buffer initialization and ModelOutput key bookkeeping are different internal behaviors." + }, + { + "left": "issue:43296", + "right": "issue:45800", + "accept": false, + "reason": "One is a specific PaddleOCR-VL load failure in vLLM, the other a broad torch/transformers version incompatibility; not the same issue." + }, + { + "left": "issue:43761", + "right": "issue:44079", + "accept": false, + "reason": "CLIPVision hidden_states regression and ModelOutput key assignment are unrelated." + }, + { + "left": "issue:35707", + "right": "issue:40444", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is a generation bug; the other is multimodal finetuning with multiple images." + }, + { + "left": "issue:44479", + "right": "issue:45823", + "accept": false, + "reason": "Both are multimodal model regressions, but one is Qwen video-input position handling and the other is Gemma4 device-map mismatch; distinct failures." + }, + { + "left": "issue:44291", + "right": "issue:44877", + "accept": false, + "reason": "One is an init_empty_weights/_is_hf_initialized argument breakage, the other a strict config loading issue for granite_speech; different root causes." + }, + { + "left": "issue:43606", + "right": "issue:44265", + "accept": false, + "reason": "CPU offload device mismatch and torch.export/export with torch_compilable_check are separate mechanisms and bugs." + }, + { + "left": "issue:44568", + "right": "issue:45920", + "accept": false, + "reason": "Tokenizer special-token insertion failure is not the same as the broader wrong-token-IDs regression, even if both involve tokenization." + }, + { + "left": "issue:43701", + "right": "issue:45325", + "accept": false, + "reason": "Checkpoint resume key mismatch and Qwen2.5-VL rope position scaling are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43819", + "accept": false, + "reason": "Device-mismatch on CPU offload and DAC latent decoding mismatch are different code paths." + }, + { + "left": "issue:41720", + "right": "issue:45823", + "accept": false, + "reason": "Both are device-related model failures, but one is an A800 cuda assert in Qwen3 and the other is Gemma4 PLE auto-device-map mismatch." + }, + { + "left": "issue:44186", + "right": "issue:44265", + "accept": false, + "reason": "Tokenizer padding/NER crashes and export-time torch_compilable_check failures are unrelated." + }, + { + "left": "issue:43454", + "right": "issue:43550", + "accept": false, + "reason": "lm_head tying/serialization and SDPA torch.compile failures are not the same bug." + }, + { + "left": "issue:43262", + "right": "issue:43746", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting and GraniteSpeech PEFT checkpoint loading are different subsystems." + }, + { + "left": "issue:43881", + "right": "issue:44488", + "accept": false, + "reason": "Different loading failures for different models; no shared concrete root cause is evident." + }, + { + "left": "issue:39692", + "right": "issue:40444", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 and Qwen2.5-VL finetuning failures are unrelated." + }, + { + "left": "issue:40990", + "right": "issue:45584", + "accept": false, + "reason": "Perplexity regression on gpt-oss and Whisper empty-transcription generation failure are separate issues." + }, + { + "left": "issue:43454", + "right": "issue:45072", + "accept": false, + "reason": "AyaVision tied-weight generation bug and a bfloat16 dtype mismatch are different failure modes." + }, + { + "left": "issue:43377", + "right": "issue:44610", + "accept": false, + "reason": "MIMI padding-mask behavior and OmDet-Turbo input-size mismatch are unrelated model/processor bugs." + }, + { + "left": "issue:43257", + "right": "issue:45923", + "accept": false, + "reason": "Qwen3 MoE weight conversion with accelerate/deepspeed and missing gradient-checkpointing flag are different issues." + }, + { + "left": "issue:43572", + "right": "issue:45759", + "accept": false, + "reason": "StableLm pad_token_idx omission and Qwen composite-config unwrapping are separate config-loading problems." + }, + { + "left": "issue:40990", + "right": "issue:42947", + "accept": false, + "reason": "High perplexity on a model and ineffective gradient checkpointing with LoRA are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 12, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:34634", + "issue:35707", + "issue:36331", + "issue:40990", + "issue:41720", + "issue:42175", + "issue:42617", + "issue:42915", + "issue:43295", + "issue:43296", + "issue:43317", + "issue:43322", + "issue:43377", + "issue:43404", + "issue:43450", + "issue:43454", + "issue:43526", + "issue:43550", + "issue:43577", + "issue:43606", + "issue:43708", + "issue:43720", + "issue:43749", + "issue:43873", + "issue:43881", + "issue:43883", + "issue:44008", + "issue:44186", + "issue:44387", + "issue:44423", + "issue:44466", + "issue:44534", + "issue:44610", + "issue:44756", + "issue:44877", + "issue:44898", + "issue:44977", + "issue:44991", + "issue:45072", + "issue:45357", + "issue:45406", + "issue:45632", + "issue:45684", + "issue:45701", + "issue:45704", + "issue:45823", + "issue:46050", + "issue:46291" + ], + "soft_pairs": [ + "issue:43317|issue:43873", + "issue:43377|issue:44898", + "issue:43873|issue:45701", + "issue:43454|issue:43720", + "issue:43296|issue:44991", + "issue:44466|issue:45357", + "issue:41720|issue:44977", + "issue:44991|issue:46291", + "issue:43526|issue:43883", + "issue:43881|issue:44991", + "issue:42617|issue:42915", + "issue:35707|issue:41720", + "issue:43577|issue:43708", + "issue:34634|issue:35707", + "issue:44008|issue:45823", + "issue:43450|issue:45701", + "issue:44877|issue:44991", + "issue:44186|issue:45072", + "issue:43404|issue:45357", + "issue:36331|issue:42915", + "issue:43550|issue:43720", + "issue:42175|issue:46291", + "issue:36331|issue:42617", + "issue:44423|issue:45406", + "issue:44387|issue:45704", + "issue:43873|issue:44756", + "issue:44610|issue:44898", + "issue:44186|issue:44610", + "issue:43749|issue:44534", + "issue:43550|issue:43606", + "issue:43295|issue:45701", + "issue:42915|issue:43317", + "issue:43322|issue:46050", + "issue:45632|issue:45684", + "issue:41720|issue:43322", + "issue:40990|issue:45701", + "issue:41720|issue:42617" + ], + "prepared_review_unit_hash": "ec3fbdeb19be7cc5ae3b07afc927320b57ad6d7827c527c1efc004dc21a3cb94", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 37, + "serialized_chars": 38932, + "estimated_input_tokens": 9733, + "estimated_eval_tokens": 19722 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly unrelated closed issues; the only apparent thematic overlap is a loose offloading/quantization/loading cluster, but no pair looks like the same concrete bug. No PRs are present.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the broadest offloading/quantization umbrella and the closest representative of the weakly related loading/offload subset, but it is not a true duplicate of the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43317", + "right": "issue:43873", + "accept": false, + "reason": "Related to offloading and quantization, but one is a specific dequantized-model load failure and the other is a broad offloading complaint; not the same concrete bug." + }, + { + "left": "issue:43377", + "right": "issue:44898", + "accept": false, + "reason": "Both involve shape/masking-like behavior in processors, but the model families and failure modes are different." + }, + { + "left": "issue:43873", + "right": "issue:45701", + "accept": false, + "reason": "Offloading/quantization vs tokenization/version drift; no shared code-path or bug." + }, + { + "left": "issue:43454", + "right": "issue:43720", + "accept": false, + "reason": "Different problems: tied lm_head weights vs packed-weight unpacking during accelerate loading." + }, + { + "left": "issue:43296", + "right": "issue:44991", + "accept": false, + "reason": "Both are load/import failures, but they concern different subsystems and unrelated root causes." + }, + { + "left": "issue:44466", + "right": "issue:45357", + "accept": false, + "reason": "Both mention weight/serialization correctness, but one is a generic lm_head tying issue and the other is a Qwen3.5 visual-encoder key regression." + }, + { + "left": "issue:41720", + "right": "issue:44977", + "accept": false, + "reason": "Same model family, but one is a device-map cuda assert and the other is flash-attention generation misbehavior; not enough to merge." + }, + { + "left": "issue:44991", + "right": "issue:46291", + "accept": false, + "reason": "Tokenizer loading failure vs kernels package import/version requirement; unrelated." + }, + { + "left": "issue:43526", + "right": "issue:43883", + "accept": false, + "reason": "Different models and bugs: label reduction in an image processor vs missing all_tied_weights_keys on a causal LM." + }, + { + "left": "issue:43881", + "right": "issue:44991", + "accept": false, + "reason": "Both are load-time failures, but one is a model loading issue and the other is a tokenizer package compatibility issue." + }, + { + "left": "issue:42617", + "right": "issue:42915", + "accept": false, + "reason": "Both are model execution/load failures, but for different scripts and distinct causes." + }, + { + "left": "issue:35707", + "right": "issue:41720", + "accept": false, + "reason": "Progressive generation with inputs_embeds/past_key_values is unrelated to Qwen3 device-mapping cuda asserts." + }, + { + "left": "issue:43577", + "right": "issue:43708", + "accept": false, + "reason": "Dtype propagation in BLIP-2 vs Trainer checkpoint resume/max_steps calculation; different code paths." + }, + { + "left": "issue:34634", + "right": "issue:35707", + "accept": false, + "reason": "Voice preset handling in BarkProcessor is unrelated to generation with inputs_embeds and past_key_values." + }, + { + "left": "issue:44008", + "right": "issue:45823", + "accept": false, + "reason": "Both are device/name collision style bugs in multimodal models, but the affected models and failure mechanics differ." + }, + { + "left": "issue:43450", + "right": "issue:45701", + "accept": false, + "reason": "Video processor batch-shape bug vs version-dependent tokenization change; not the same issue." + }, + { + "left": "issue:44877", + "right": "issue:44991", + "accept": false, + "reason": "Strict config loading vs tokenizer loading regression; unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45072", + "accept": false, + "reason": "LayoutLMv2 tokenizer NER/padding crash is unrelated to bfloat16 dtype mismatches in inference." + }, + { + "left": "issue:43404", + "right": "issue:45357", + "accept": false, + "reason": "Both involve tied-weight/save behavior, but one is Mistral3 lm_head tying and the other is Qwen3.5 visual encoder keys." + }, + { + "left": "issue:36331", + "right": "issue:42915", + "accept": false, + "reason": "Trainer custom compute_loss signature mismatch vs Qwen3Moe FineGrainedFP8Config failure; unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43720", + "accept": false, + "reason": "torch.compile/SDPA failure is not the same bug as packed weights not being unpacked during accelerate loading." + }, + { + "left": "issue:42175", + "right": "issue:46291", + "accept": false, + "reason": "Packaging/backend selection issue vs kernels import requirement; unrelated." + }, + { + "left": "issue:36331", + "right": "issue:42617", + "accept": false, + "reason": "Trainer API mismatch vs script execution failure; no shared underlying bug." + }, + { + "left": "issue:44423", + "right": "issue:45406", + "accept": false, + "reason": "Continuous-batching multimodal crash and Gemma4Processor missing _tokenizer are different processor/runtime bugs." + }, + { + "left": "issue:44387", + "right": "issue:45704", + "accept": false, + "reason": "Quantization OOM in Transformers v5 is unrelated to T5's apex RMSNorm memory leak." + }, + { + "left": "issue:43873", + "right": "issue:44756", + "accept": false, + "reason": "Both mention memory/offload concerns, but one is quantization offloading and the other is mmap on Strix Halo OOM; not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:44898", + "accept": false, + "reason": "Different image-processing bugs: wrong fixed size output vs non-default resolution interpolation failure." + }, + { + "left": "issue:44186", + "right": "issue:44610", + "accept": false, + "reason": "Tokenizer crash on batched NER inputs is unrelated to OmDet-Turbo image-size mismatch." + }, + { + "left": "issue:43749", + "right": "issue:44534", + "accept": false, + "reason": "FSDP CPU RAM efficient loading and non-persistent buffer junk are separate v5 loading issues." + }, + { + "left": "issue:43550", + "right": "issue:43606", + "accept": false, + "reason": "Different failures and different models; one is SDPA/torch.compile, the other CPU-offload device mismatch." + }, + { + "left": "issue:43295", + "right": "issue:45701", + "accept": false, + "reason": "Processor.tokenizer regression is unrelated to a version-caused tokenization change report." + }, + { + "left": "issue:42915", + "right": "issue:43317", + "accept": false, + "reason": "Both are load-related model failures, but one is Qwen3Moe FP8 config and the other is offload with dequantized models." + }, + { + "left": "issue:43322", + "right": "issue:46050", + "accept": false, + "reason": "Segmentation fault loading Llava Next models and sinq quantization save/load breakage are unrelated." + }, + { + "left": "issue:45632", + "right": "issue:45684", + "accept": false, + "reason": "Cache-path collision for trust_remote_code is unrelated to read-only permissions propagation in save_pretrained." + }, + { + "left": "issue:41720", + "right": "issue:43322", + "accept": false, + "reason": "Both are model-loading/runtime crashes, but the failures and model families differ." + }, + { + "left": "issue:40990", + "right": "issue:45701", + "accept": false, + "reason": "Perplexity regression on gpt-oss-20b is not the same as a tokenization change across versions." + }, + { + "left": "issue:41720", + "right": "issue:42617", + "accept": false, + "reason": "Qwen3 device-map cuda assert and a script run failure are not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 13, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:29159", + "issue:30064", + "issue:34567", + "issue:34634", + "issue:35707", + "issue:36010", + "issue:36032", + "issue:41720", + "issue:42617", + "issue:42915", + "issue:43316", + "issue:43322", + "issue:43388", + "issue:43421", + "issue:43425", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43572", + "issue:43606", + "issue:43653", + "issue:43720", + "issue:43782", + "issue:43873", + "issue:43881", + "issue:44186", + "issue:44361", + "issue:44492", + "issue:44509", + "issue:44514", + "issue:44530", + "issue:44545", + "issue:44671", + "issue:44743", + "issue:44913", + "issue:45059", + "issue:45081", + "issue:45161", + "issue:45406", + "issue:45464", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:46291" + ], + "soft_pairs": [ + "issue:41720|issue:45161", + "issue:36010|issue:42617", + "issue:43425|issue:46291", + "issue:45081|issue:45812", + "issue:43525|issue:46291", + "issue:43531|issue:43572", + "issue:43316|issue:44913", + "issue:44671|issue:44743", + "issue:43540|issue:43782", + "issue:43421|issue:45812", + "issue:44186|issue:44361", + "issue:43526|issue:43881", + "issue:29159|issue:36032", + "issue:30064|issue:34634", + "issue:45406|issue:45464", + "issue:43550|issue:43653", + "issue:43606|issue:43720", + "issue:44530|issue:46291", + "issue:43421|issue:45701", + "issue:42915|issue:43322", + "issue:43606|issue:43653", + "issue:43531|issue:45759", + "issue:44492|issue:44509", + "issue:34567|issue:35707", + "issue:43388|issue:45059", + "issue:44514|issue:44545", + "issue:43873|issue:45704" + ], + "prepared_review_unit_hash": "b6b40840b2be0eb55877acd78cdba789c4d2c8faf2685a35965fcecff83b44b6", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35093, + "estimated_input_tokens": 8774, + "estimated_eval_tokens": 17804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous singleton issues across unrelated bugs. The only clear duplicate pair is the Qwen2_5_VLProcessor.apply_chat_template padding=False crash (issues 44514 and 44545). No PRs are present.", + "confidence": 0.95, + "canonical_issue_reason": "issue:44545 is the best canonical issue because it exactly matches issue:44514 on the same Qwen2_5_VLProcessor.apply_chat_template batched-input padding=False crash and has slightly stronger report context.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44545 is the strongest representative of the cluster\u2019s only true duplicate pair and is the clearest target for consolidation.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:45161", + "accept": false, + "reason": "Both are model-parallel/dispatch failures, but they affect different models and code paths; not the same bug." + }, + { + "left": "issue:36010", + "right": "issue:42617", + "accept": false, + "reason": "An import error for GenerationMixin is unrelated to failing to run 3d_parallel.py." + }, + { + "left": "issue:43425", + "right": "issue:46291", + "accept": false, + "reason": "Torch 2.10 incompatibility is unrelated to kernels v0.15 requiring version/revision metadata." + }, + { + "left": "issue:45081", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but one is a Mistral regex/backend_tokenizer crash and the other is Granite token ID mis-generation." + }, + { + "left": "issue:43525", + "right": "issue:46291", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to the kernels import/version issue." + }, + { + "left": "issue:43531", + "right": "issue:43572", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and StableLmConfig pad_token_idx are different model/config bugs." + }, + { + "left": "issue:43316", + "right": "issue:44913", + "accept": false, + "reason": "Both involve config/API behavior, but one is Gemma3TextConfig mismatch and the other is GPTNeoX rotary_pct persistence." + }, + { + "left": "issue:44671", + "right": "issue:44743", + "accept": false, + "reason": "CamemBERT masked-LM regression and Qwen3.5 recurrent-state reset are unrelated." + }, + { + "left": "issue:43540", + "right": "issue:43782", + "accept": false, + "reason": "Both involve Qwen3 multimodal loading/processing, but they fail in different concrete paths and are not the same issue." + }, + { + "left": "issue:43421", + "right": "issue:45812", + "accept": false, + "reason": "Runtime special-token post-processor updates and Granite token ID regression are different tokenizer problems." + }, + { + "left": "issue:44186", + "right": "issue:44361", + "accept": false, + "reason": "Different tokenizers, different failure modes, and different task surfaces; not a duplicate." + }, + { + "left": "issue:43526", + "right": "issue:43881", + "accept": false, + "reason": "A BEiT image-processor label reduction bug is unrelated to glm-4v loading failure." + }, + { + "left": "issue:29159", + "right": "issue:36032", + "accept": false, + "reason": "Slow-vs-fast tokenizer inconsistency is broader and not the same as the T5Tokenizer add_special_tokens load conflict." + }, + { + "left": "issue:30064", + "right": "issue:34634", + "accept": false, + "reason": "Void segmentation-map processing and BarkProcessor voice_preset are unrelated processor bugs." + }, + { + "left": "issue:45406", + "right": "issue:45464", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer and Qwen3.5 streaming inference failure are different API paths." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "CPU offload device mismatch in bark-small and BigBirdTokenizer special-token registration are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:43653", + "accept": false, + "reason": "torch.compile SDPA failure in Bamba is unrelated to BigBirdTokenizer decode/special-token behavior." + }, + { + "left": "issue:43606", + "right": "issue:43720", + "accept": false, + "reason": "Both touch loading/offload, but bark-small device mismatch and BitNet packed-weight unpacking are different root causes." + }, + { + "left": "issue:44530", + "right": "issue:46291", + "accept": false, + "reason": "PagedAttentionCache linear_attention group-type failure is unrelated to the kernels version/revision import issue." + }, + { + "left": "issue:42915", + "right": "issue:43322", + "accept": false, + "reason": "Qwen3Moe FP8 config failure and Llava Next segmentation fault are different models and failure modes." + }, + { + "left": "issue:43606", + "right": "issue:43653", + "accept": false, + "reason": "These are not the same bug; one is CPU offload device placement, the other is tokenizer special-token handling." + }, + { + "left": "issue:43531", + "right": "issue:45759", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior and unwrap-text_config on composite multimodal configs are different issues." + }, + { + "left": "issue:44492", + "right": "issue:44509", + "accept": false, + "reason": "A cache-strategy typo and docs mentioning removed pipelines are unrelated documentation/wording issues." + }, + { + "left": "issue:34567", + "right": "issue:35707", + "accept": false, + "reason": "TrainerState token counting and progressive generation with inputs_embeds/past_key_values are unrelated training/generation bugs." + }, + { + "left": "issue:43388", + "right": "issue:45059", + "accept": false, + "reason": "Label truncation in gather_for_metrics and SAM3 text/bbox behavior are different code paths." + }, + { + "left": "issue:44514", + "right": "issue:44545", + "accept": true, + "reason": "Exact duplicate: same Qwen2_5_VLProcessor.apply_chat_template batched-input crash when padding=False." + }, + { + "left": "issue:43873", + "right": "issue:45704", + "accept": false, + "reason": "Quantization offloading issues and T5 apex.FusedRMSNorm memory leak are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet: it identifies the one clearly duplicated pair (44514/44545) and does not overclaim about the many soft matches. The soft-edge rejections are conservative and consistent with the issue titles, and there are no PRs to consolidate." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 14, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:33666", + "issue:34634", + "issue:35707", + "issue:39692", + "issue:41720", + "issue:42490", + "issue:42886", + "issue:43329", + "issue:43381", + "issue:43421", + "issue:43525", + "issue:43531", + "issue:43540", + "issue:43653", + "issue:43746", + "issue:43782", + "issue:43844", + "issue:43873", + "issue:43927", + "issue:43994", + "issue:44062", + "issue:44186", + "issue:44368", + "issue:44451", + "issue:44589", + "issue:44610", + "issue:44625", + "issue:44671", + "issue:44843", + "issue:44898", + "issue:44918", + "issue:44936", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45081", + "issue:45356", + "issue:45357", + "issue:45381", + "issue:45479", + "issue:45588", + "issue:45663", + "issue:45704", + "issue:45759", + "issue:45859", + "issue:45923", + "issue:46294" + ], + "soft_pairs": [ + "issue:42490|issue:43329", + "issue:43421|issue:43927", + "issue:41720|issue:43746", + "issue:44451|issue:44991", + "issue:44898|issue:45072", + "issue:33666|issue:35707", + "issue:45759|issue:45859", + "issue:43531|issue:44589", + "issue:45588|issue:45759", + "issue:44987|issue:45042", + "issue:44368|issue:45357", + "issue:44062|issue:44451", + "issue:43421|issue:43653", + "issue:39692|issue:44610", + "issue:45704|issue:45923", + "issue:45663|issue:45923", + "issue:44918|issue:44936", + "issue:42886|issue:44843", + "issue:43381|issue:43844", + "issue:43421|issue:44186", + "issue:45704|issue:45859", + "issue:34634|issue:41720", + "issue:43525|issue:43531", + "issue:43381|issue:45704", + "issue:45081|issue:45356", + "issue:39692|issue:43873", + "issue:43540|issue:46294", + "issue:44625|issue:45479", + "issue:43782|issue:45381", + "issue:43994|issue:44671" + ], + "prepared_review_unit_hash": "ae61d339e7d0def38040e69268c04424c96bc1f91cae7fec856bd185c32676ea", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 37160, + "estimated_input_tokens": 9290, + "estimated_eval_tokens": 18836 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Most items are unrelated. The only strong duplicate-like pair is the offline tokenizer loading regression: issue 42886 and issue 44843 appear to describe the same HF_HUB_OFFLINE/cache path failure, with 44843 giving the likely root cause in _patch_mistral_regex.", + "confidence": 0.68, + "canonical_issue_reason": "Issue 42886 is the earlier, broader report of the offline tokenizer-cache failure; issue 44843 looks like the more specific root-cause diagnosis for the same symptom.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 42886 is the best representative issue to keep because it captures the user-visible failure cleanly and predates the narrower follow-up report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42490", + "right": "issue:43329", + "accept": false, + "reason": "Different subsystems and failures: local-path import warning vs multimodal token counting bug in video processing." + }, + { + "left": "issue:43421", + "right": "issue:43927", + "accept": false, + "reason": "Both are tokenizer-related, but one is runtime post-processor updates and the other is save/load preservation of custom token IDs; different bugs." + }, + { + "left": "issue:41720", + "right": "issue:43746", + "accept": false, + "reason": "Unrelated model/runtime issues: Qwen3 auto device mapping CUDA assert vs GraniteSpeech PEFT local checkpoint loading." + }, + { + "left": "issue:44451", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading complaints, but they target different models and likely different root causes; not enough evidence of one bug." + }, + { + "left": "issue:44898", + "right": "issue:45072", + "accept": false, + "reason": "Different concrete failures: Perceiver resolution handling vs dtype mismatch in SwitchTransformers/TimmWrapperModel inference." + }, + { + "left": "issue:33666", + "right": "issue:35707", + "accept": false, + "reason": "Completely different topics: Qwen2-VL multi-GPU training vs progressive generation with inputs_embeds/past_key_values." + }, + { + "left": "issue:45759", + "right": "issue:45859", + "accept": false, + "reason": "Different code paths: multimodal config unwrapping vs CPU-offload incompatibility in Qwen3_5MoeTextRotaryEmbedding." + }, + { + "left": "issue:43531", + "right": "issue:44589", + "accept": false, + "reason": "Sliding-window handling in Qwen3-MoE is unrelated to the Float8 storage lookup failure." + }, + { + "left": "issue:45588", + "right": "issue:45759", + "accept": false, + "reason": "Flash-attention sinkless-model crash is unrelated to multimodal config unwrapping." + }, + { + "left": "issue:44987", + "right": "issue:45042", + "accept": false, + "reason": "Different regressions in different layers: loading a specific model vs PIL image processors incorrectly requiring torchvision." + }, + { + "left": "issue:44368", + "right": "issue:45357", + "accept": false, + "reason": "A warning about tie_word_embeddings during LoRA fine-tuning is unrelated to incorrect visual encoder keys in save_pretrained." + }, + { + "left": "issue:44062", + "right": "issue:44451", + "accept": false, + "reason": "AddedToken special-arg construction error is unrelated to ScandiBERT model loading." + }, + { + "left": "issue:43421", + "right": "issue:43653", + "accept": false, + "reason": "Both touch special tokens, but one is about post-processor refresh and the other about BigBirdTokenizer mask-token registration; not the same bug." + }, + { + "left": "issue:39692", + "right": "issue:44610", + "accept": false, + "reason": "Documentation/example mistakes vs an image processor/model resolution mismatch are different issues." + }, + { + "left": "issue:45704", + "right": "issue:45923", + "accept": false, + "reason": "Apex RMSNorm memory leak in T5 is unrelated to a missing supports_gradient_checkpointing flag." + }, + { + "left": "issue:45663", + "right": "issue:45923", + "accept": false, + "reason": "Gemma-4 FSDP2 shared_kv_states KeyError is a different training-time bug than the gradient-checkpointing flag issue." + }, + { + "left": "issue:44918", + "right": "issue:44936", + "accept": false, + "reason": "Different trainer failures: unpacking Qwen3.5 input embeddings vs evaluate() after train()." + }, + { + "left": "issue:42886", + "right": "issue:44843", + "accept": true, + "reason": "Both report the same HF_HUB_OFFLINE tokenizer-loading regression; 44843 identifies the likely root cause in an unconditional model_info() call inside _patch_mistral_regex." + }, + { + "left": "issue:43381", + "right": "issue:43844", + "accept": false, + "reason": "Gradient checkpointing eval-mode restriction is unrelated to abnormal gradient growth under ZeRO-3." + }, + { + "left": "issue:43421", + "right": "issue:44186", + "accept": false, + "reason": "Different tokenizer problems: runtime special-token updates vs LayoutLMv2 NER/padding crashes." + }, + { + "left": "issue:45704", + "right": "issue:45859", + "accept": false, + "reason": "RMSNorm memory leak in T5 is unrelated to Qwen3_5Moe CPU offload behavior." + }, + { + "left": "issue:34634", + "right": "issue:41720", + "accept": false, + "reason": "BarkProcessor voice preset handling has no relation to Qwen3 auto device mapping CUDA asserts." + }, + { + "left": "issue:43525", + "right": "issue:43531", + "accept": false, + "reason": "Missing pad_token_id on Llama4Config is unrelated to the Qwen3-MoE sliding_window issue." + }, + { + "left": "issue:43381", + "right": "issue:45704", + "accept": false, + "reason": "Gradient checkpointing eval-mode issue and T5 RMSNorm memory leak are distinct failures." + }, + { + "left": "issue:45081", + "right": "issue:45356", + "accept": false, + "reason": "Both mention mistral-regex-related tokenizers, but one is a backend_tokenizer AttributeError and the other is a codec-handling regression with a misleading warning; not clearly the same bug." + }, + { + "left": "issue:39692", + "right": "issue:43873", + "accept": false, + "reason": "SigLIP2 doc/example errors are unrelated to quantization offloading behavior." + }, + { + "left": "issue:43540", + "right": "issue:46294", + "accept": false, + "reason": "Both involve Qwen video inputs, but one is a ValueError in Qwen3OmniMoe and the other is an apply_chat_template feature/token mismatch in Qwen3.5-9B; different code paths." + }, + { + "left": "issue:44625", + "right": "issue:45479", + "accept": false, + "reason": "Different model families and bugs: Qwen3.5 num_labels propagation vs generic single-label classification degeneracy." + }, + { + "left": "issue:43782", + "right": "issue:45381", + "accept": false, + "reason": "Weight-only loading error in Qwen3VL is unrelated to Qwen2.5-VL video vision_position_ids." + }, + { + "left": "issue:43994", + "right": "issue:44671", + "accept": false, + "reason": "Different model-specific inference errors: SigLIP2 pipeline misuse vs CamemBERT masked LM regression." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted duplicate-like pair, issue 42886 and issue 44843, is well supported by their titles as the same HF_HUB_OFFLINE tokenizer-loading regression, with 44843 plausibly describing the root cause. The rejected pairs are handled cautiously and do not overclaim duplicates from the available evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 15, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:30064", + "issue:36010", + "issue:36331", + "issue:42915", + "issue:43295", + "issue:43335", + "issue:43388", + "issue:43421", + "issue:43531", + "issue:43540", + "issue:43550", + "issue:43596", + "issue:43618", + "issue:43643", + "issue:43653", + "issue:43697", + "issue:43716", + "issue:43720", + "issue:43746", + "issue:43756", + "issue:43819", + "issue:43873", + "issue:43950", + "issue:44008", + "issue:44062", + "issue:44077", + "issue:44186", + "issue:44220", + "issue:44448", + "issue:44488", + "issue:44625", + "issue:44661", + "issue:44671", + "issue:44811", + "issue:44843", + "issue:44877", + "issue:44898", + "issue:45072", + "issue:45081", + "issue:45183", + "issue:45356", + "issue:45381", + "issue:45479", + "issue:45834", + "issue:45907", + "issue:45987", + "issue:46032", + "issue:46050" + ], + "soft_pairs": [ + "issue:45356|issue:45907", + "issue:30064|issue:36010", + "issue:43596|issue:44220", + "issue:43720|issue:43819", + "issue:43746|issue:46050", + "issue:44077|issue:44625", + "issue:43653|issue:43720", + "issue:44220|issue:44661", + "issue:42915|issue:43746", + "issue:43540|issue:44008", + "issue:43618|issue:43697", + "issue:43550|issue:45072", + "issue:43746|issue:43873", + "issue:43295|issue:45834", + "issue:43550|issue:43819", + "issue:45183|issue:45479", + "issue:43388|issue:46032", + "issue:44186|issue:44898", + "issue:43716|issue:44008", + "issue:43335|issue:43756", + "issue:44062|issue:44488", + "issue:43653|issue:43819", + "issue:43531|issue:43643", + "issue:44843|issue:45081", + "issue:43950|issue:45987", + "issue:43643|issue:44877", + "issue:43421|issue:44811", + "issue:30064|issue:36331", + "issue:44448|issue:44671", + "issue:43540|issue:45381" + ], + "prepared_review_unit_hash": "7dd7c9666aa4c0660ccfe9a55c65d4102c3331714c6a65c7f3fec963bb68cf7e", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "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 a grab bag of unrelated regression reports. Several items are in the tokenizer/config/loading area, but none of the soft pairs look like true duplicates of the same underlying bug or change.", + "confidence": 0.29, + "canonical_issue_reason": "issue:44843 is the cleanest representative of the shared tokenizer-regression theme: a concrete, reproducible from_pretrained/_patch_mistral_regex failure with broad user impact. It is still not a duplicate of the other issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44843 is the most actionable and broadly relevant issue in the set, with a clear root-cause path and user-facing regression.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45356", + "right": "issue:45907", + "accept": false, + "reason": "Different bugs: tokenizer codec / mistral-regex regression vs list_repo_files revision forwarding." + }, + { + "left": "issue:30064", + "right": "issue:36010", + "accept": false, + "reason": "Completely unrelated subsystems: image segmentation processing vs GenerationMixin import error." + }, + { + "left": "issue:43596", + "right": "issue:44220", + "accept": false, + "reason": "Different code paths: DeepSpeed ZeRO3/BertModel init vs fbank feature extraction." + }, + { + "left": "issue:43720", + "right": "issue:43819", + "accept": false, + "reason": "Unrelated model-loading quantization bug vs DAC latent/STE mismatch." + }, + { + "left": "issue:43746", + "right": "issue:46050", + "accept": false, + "reason": "Both involve loading, but one is PEFT checkpoint loading and the other is sinq quantized save/load corruption." + }, + { + "left": "issue:44077", + "right": "issue:44625", + "accept": false, + "reason": "Different model/config issues: optional post_init constraint vs num_labels propagation." + }, + { + "left": "issue:43653", + "right": "issue:43720", + "accept": false, + "reason": "Tokenizer special-token registration bug vs BitNet packed-weight loading bug." + }, + { + "left": "issue:44220", + "right": "issue:44661", + "accept": false, + "reason": "Audio feature extraction bug vs tokenizer mapping-name handling bug." + }, + { + "left": "issue:42915", + "right": "issue:43746", + "accept": false, + "reason": "Qwen3Moe FP8 failure is unrelated to GraniteSpeech PEFT checkpoint loading." + }, + { + "left": "issue:43540", + "right": "issue:44008", + "accept": false, + "reason": "Both multimodal, but different models and distinct failures (video processing vs variable name collision)." + }, + { + "left": "issue:43618", + "right": "issue:43697", + "accept": false, + "reason": "Different behaviors and code paths: missing attentions assignment vs output drift in RTDetrV2." + }, + { + "left": "issue:43550", + "right": "issue:45072", + "accept": false, + "reason": "Both dtype/compile-related, but one is SDPA torch.compile failure and the other is bf16 inference mismatch." + }, + { + "left": "issue:43746", + "right": "issue:43873", + "accept": false, + "reason": "Checkpoint loading with PEFT is unrelated to offloading with quantization." + }, + { + "left": "issue:43295", + "right": "issue:45834", + "accept": false, + "reason": "Different regressions: processor.tokenizer/image routing vs long OCR index error." + }, + { + "left": "issue:43550", + "right": "issue:43819", + "accept": false, + "reason": "Torch.compile/SDPA failure is unrelated to DAC latent decoding mismatch." + }, + { + "left": "issue:45183", + "right": "issue:45479", + "accept": false, + "reason": "Input validation bug vs sequence-classification loss degeneracy; different layers of the stack." + }, + { + "left": "issue:43388", + "right": "issue:46032", + "accept": false, + "reason": "Metrics gathering bug vs Mamba2 cache correctness bug; not the same issue." + }, + { + "left": "issue:44186", + "right": "issue:44898", + "accept": false, + "reason": "Tokenizer crash on NER/padding is unrelated to Perceiver image-resolution handling." + }, + { + "left": "issue:43716", + "right": "issue:44008", + "accept": false, + "reason": "Different multimodal failures in different models and code paths." + }, + { + "left": "issue:43335", + "right": "issue:43756", + "accept": false, + "reason": "SwitchTransformers sparse-layer config bug is unrelated to Smollm3 RoPE layer selection." + }, + { + "left": "issue:44062", + "right": "issue:44488", + "accept": false, + "reason": "AddedToken special-arg duplication is not the same as loading a specific model failing." + }, + { + "left": "issue:43653", + "right": "issue:43819", + "accept": false, + "reason": "Tokenizer special-token registration bug vs DAC forward/from_latents mismatch." + }, + { + "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:44843", + "right": "issue:45081", + "accept": false, + "reason": "Same helper area, but distinct failures: offline model_info call vs missing backend_tokenizer attribute." + }, + { + "left": "issue:43950", + "right": "issue:45987", + "accept": false, + "reason": "Buffer corruption on from_pretrained is unrelated to a cache-length return-type bug." + }, + { + "left": "issue:43643", + "right": "issue:44877", + "accept": false, + "reason": "Both config-related, but one is missing fields on trust_remote_code and the other is strict config blocking granite_speech loading." + }, + { + "left": "issue:43421", + "right": "issue:44811", + "accept": false, + "reason": "Post-processor update bug is not the same as batch_decode ignoring skip_special_tokens." + }, + { + "left": "issue:30064", + "right": "issue:36331", + "accept": false, + "reason": "Image segmentation processing failure vs custom trainer loss signature mismatch." + }, + { + "left": "issue:44448", + "right": "issue:44671", + "accept": false, + "reason": "Different model-specific v4/v5 output regressions; not one shared bug." + }, + { + "left": "issue:43540", + "right": "issue:45381", + "accept": false, + "reason": "Both Qwen video issues, but different models and different symptoms, so not the same underlying bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 16, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28218", + "issue:29159", + "issue:34634", + "issue:36010", + "issue:39692", + "issue:42175", + "issue:43262", + "issue:43322", + "issue:43404", + "issue:43452", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43720", + "issue:43782", + "issue:43818", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43906", + "issue:43994", + "issue:44186", + "issue:44442", + "issue:44479", + "issue:44485", + "issue:44509", + "issue:44561", + "issue:44610", + "issue:44671", + "issue:44805", + "issue:44821", + "issue:44857", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45020", + "issue:45072", + "issue:45081", + "issue:45084", + "issue:45406", + "issue:45584", + "issue:45685", + "issue:45701", + "issue:45834", + "issue:45987", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:39692|issue:45834", + "issue:43577|issue:43818", + "issue:43782|issue:44977", + "issue:45584|issue:45834", + "issue:44821|issue:45084", + "issue:43322|issue:45685", + "issue:43606|issue:45072", + "issue:44479|issue:45834", + "issue:44186|issue:44442", + "issue:43825|issue:43994", + "issue:34634|issue:36010", + "issue:44561|issue:45020", + "issue:44485|issue:44509", + "issue:28218|issue:29159", + "issue:45987|issue:46192", + "issue:43577|issue:43582", + "issue:44610|issue:45072", + "issue:44805|issue:44936", + "issue:43720|issue:45072", + "issue:43452|issue:44991", + "issue:43825|issue:43827", + "issue:43404|issue:43782", + "issue:43582|issue:44857", + "issue:45081|issue:45406", + "issue:42175|issue:45081", + "issue:43906|issue:46209", + "issue:44671|issue:45701", + "issue:43262|issue:43819" + ], + "prepared_review_unit_hash": "2308f5d85fe9c51df0e96eddd087f43d8abbfa7ff333518e3e71a43f49bb602c", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 28, + "serialized_chars": 35584, + "estimated_input_tokens": 8896, + "estimated_eval_tokens": 18048 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This set is not a single duplicate cluster; it spans many unrelated tokenizer, model-loading, vision, audio, and docs regressions. I\u2019d use the broad tokenizer-regression report as the nearest representative, but most soft pairs are not true duplicates.", + "confidence": 0.54, + "canonical_issue_reason": "issue:45701 is the broadest representative: it describes version-driven tokenization changes and has multiple inbound references, which makes it the closest umbrella for the tokenizer-related subset.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45701 is the best overall representative for the cluster\u2019s tokenizer-regression theme, though the cluster is too heterogeneous to be a true duplicate set.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39692", + "right": "issue:45834", + "accept": false, + "reason": "Different products and failure modes: SigLIP2 doc example errors vs Kosmos2.5 OCR index error." + }, + { + "left": "issue:43577", + "right": "issue:43818", + "accept": false, + "reason": "Unrelated bugs: Blip2 dtype handling vs Video-LLaVA missing temporal attention / weight sharing." + }, + { + "left": "issue:43782", + "right": "issue:44977", + "accept": false, + "reason": "Different model families and code paths: Qwen3VL weight_only loading vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:45584", + "right": "issue:45834", + "accept": false, + "reason": "Whisper empty-transcription bug is unrelated to Kosmos2.5 long-ocr index errors." + }, + { + "left": "issue:44821", + "right": "issue:45084", + "accept": false, + "reason": "AutoImageProcessor URL loading and template-compilation TypeError are unrelated failures." + }, + { + "left": "issue:43322", + "right": "issue:45685", + "accept": false, + "reason": "Llava Next segfault vs MPS histogram Int error are different subsystems and symptoms." + }, + { + "left": "issue:43606", + "right": "issue:45072", + "accept": false, + "reason": "CPU offload device mismatch for Bark is not the same as bfloat16 dtype mismatches in SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:44479", + "right": "issue:45834", + "accept": false, + "reason": "Video-input regression for Qwen VL models is unrelated to Kosmos2.5 OCR indexing." + }, + { + "left": "issue:44186", + "right": "issue:44442", + "accept": false, + "reason": "LayoutLMv2 tokenizer padding/NER crash and FastSpeech2Conformer tokenizer loading failure are different tokenizer bugs." + }, + { + "left": "issue:43825", + "right": "issue:43994", + "accept": false, + "reason": "One is an error-message/docs issue about removed pipelines; the other is a model/pipeline output correctness problem." + }, + { + "left": "issue:34634", + "right": "issue:36010", + "accept": false, + "reason": "BarkProcessor voice_preset failure and GenerationMixin import error are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:45020", + "accept": false, + "reason": "Both mention remote_code breakage, but they do not identify the same concrete code-path or fix." + }, + { + "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:28218", + "right": "issue:29159", + "accept": false, + "reason": "Both are tokenizer-related, but one is about added-token spacing while the other is a broader slow/fast inconsistency; not clearly the same bug." + }, + { + "left": "issue:45987", + "right": "issue:46192", + "accept": false, + "reason": "StaticCache return-type bug and return_tensors/text_kwargs precedence are unrelated API issues." + }, + { + "left": "issue:43577", + "right": "issue:43582", + "accept": false, + "reason": "Blip2 dtype state and AppleSilicon caching_allocator_warmup TypeError are different problems." + }, + { + "left": "issue:44610", + "right": "issue:45072", + "accept": false, + "reason": "OmDet-Turbo processor size mismatch is unrelated to bfloat16 dtype mismatches." + }, + { + "left": "issue:44805", + "right": "issue:44936", + "accept": false, + "reason": "A tensor-mask shape IndexError is not the same as trainer.evaluate() failing after train()." + }, + { + "left": "issue:43720", + "right": "issue:45072", + "accept": false, + "reason": "BitNet packed-weight loading failure and generic dtype mismatch issues are different code paths." + }, + { + "left": "issue:43452", + "right": "issue:44991", + "accept": false, + "reason": "Both involve loading/tokenizers, but they are distinct model/package regressions with different symptoms." + }, + { + "left": "issue:43825", + "right": "issue:43827", + "accept": false, + "reason": "Runtime error-message behavior and documentation references are related thematically, but not the same underlying bug/change." + }, + { + "left": "issue:43404", + "right": "issue:43782", + "accept": false, + "reason": "Mistral3 lm_head tying and Qwen3VL weight_only loading are unrelated model-specific bugs." + }, + { + "left": "issue:43582", + "right": "issue:44857", + "accept": false, + "reason": "AppleSilicon warmup TypeError and CUDA AMP loss crash are unrelated hardware/backend issues." + }, + { + "left": "issue:45081", + "right": "issue:45406", + "accept": false, + "reason": "Mistral tokenizer regex patch crash and Gemma4Processor missing _tokenizer are separate attribute-access failures." + }, + { + "left": "issue:42175", + "right": "issue:45081", + "accept": false, + "reason": "Backend extras installation problem is unrelated to Mistral tokenizer regex patching." + }, + { + "left": "issue:43906", + "right": "issue:46209", + "accept": false, + "reason": "An isolated reproduction of one prior issue is not the same as FP8 inference failing on B200." + }, + { + "left": "issue:44671", + "right": "issue:45701", + "accept": false, + "reason": "CamemBERT MLM prediction regression and general tokenization-version changes are related only at a broad tokenizer level, not the same concrete bug." + }, + { + "left": "issue:43262", + "right": "issue:43819", + "accept": false, + "reason": "Audio chat-template sampling-rate defaulting and DAC from_latents STE mismatch are unrelated audio processor bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 17, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:34634", + "issue:36010", + "issue:36331", + "issue:38175", + "issue:39692", + "issue:43257", + "issue:43262", + "issue:43329", + "issue:43454", + "issue:43526", + "issue:43531", + "issue:43550", + "issue:43577", + "issue:43638", + "issue:43644", + "issue:43645", + "issue:43650", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43746", + "issue:43749", + "issue:43819", + "issue:43854", + "issue:43906", + "issue:43927", + "issue:44060", + "issue:44291", + "issue:44368", + "issue:44387", + "issue:44554", + "issue:44589", + "issue:44610", + "issue:44617", + "issue:44811", + "issue:44912", + "issue:44936", + "issue:44977", + "issue:45003", + "issue:45020", + "issue:45042", + "issue:45084", + "issue:45459", + "issue:45538", + "issue:45600", + "issue:45803", + "issue:46285" + ], + "soft_pairs": [ + "issue:43653|issue:44912", + "issue:45003|issue:46285", + "issue:43526|issue:43697", + "issue:44060|issue:44368", + "issue:43650|issue:43906", + "issue:43742|issue:45020", + "issue:45084|issue:45538", + "issue:43329|issue:45600", + "issue:44589|issue:45042", + "issue:43746|issue:44811", + "issue:43644|issue:43749", + "issue:43638|issue:44936", + "issue:43550|issue:44912", + "issue:43819|issue:43927", + "issue:34634|issue:36331", + "issue:44387|issue:44617", + "issue:36010|issue:43645", + "issue:43854|issue:44977", + "issue:39692|issue:44912", + "issue:38175|issue:44610", + "issue:43720|issue:44610", + "issue:45459|issue:45803", + "issue:43526|issue:44554", + "issue:36010|issue:36331", + "issue:43454|issue:43577", + "issue:43531|issue:45042", + "issue:43262|issue:44811", + "issue:43749|issue:44291", + "issue:43257|issue:43329" + ], + "prepared_review_unit_hash": "c98eeff984d4c46577e0f928deab5b9acee59733d3b2b0a8fe1f8c8112401d16", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36627, + "estimated_input_tokens": 9157, + "estimated_eval_tokens": 18570 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is very heterogeneous: the soft pairs mostly share only broad Transformer-regression themes, not the same concrete bug. I would not merge any of the proposed soft edges.", + "confidence": 0.28, + "canonical_issue_reason": "If forced to pick one issue, issue:45020 is the broadest umbrella report in the set (recent-version remote_code breakage), but the cluster as a whole does not form a true duplicate set.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue:45020 is the most general representative of the loading/regression theme, though it is still not a clean canonical for these mostly unrelated reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43653", + "right": "issue:44912", + "accept": false, + "reason": "Different bugs: BigBird tokenizer special-token decoding vs MXFP4 quantization/load fallback." + }, + { + "left": "issue:45003", + "right": "issue:46285", + "accept": false, + "reason": "Unrelated code paths: sys.modules access in modeling_utils vs CLIP text model structure mismatch." + }, + { + "left": "issue:43526", + "right": "issue:43697", + "accept": false, + "reason": "Both are vision/model issues, but one is Beit label reduction and the other is RTDetr output drift." + }, + { + "left": "issue:44060", + "right": "issue:44368", + "accept": false, + "reason": "Both mention tied-weights warnings, but the underlying Qwen models and failure modes differ." + }, + { + "left": "issue:43650", + "right": "issue:43906", + "accept": false, + "reason": "Placeholder text issue vs isolated reproduction of a separate upstream bug." + }, + { + "left": "issue:43742", + "right": "issue:45020", + "accept": false, + "reason": "Specific MobileLLM load key error is not the same concrete bug as broad remote_code breakage." + }, + { + "left": "issue:45084", + "right": "issue:45538", + "accept": false, + "reason": "Compile/template-node error vs CLIP tokenizer max_length issue." + }, + { + "left": "issue:43329", + "right": "issue:45600", + "accept": false, + "reason": "Multimodal token-counting bug vs auto_mappings CI break from removed configs." + }, + { + "left": "issue:44589", + "right": "issue:45042", + "accept": false, + "reason": "Float8 storage lookup failure is unrelated to the torchvision dependency regression." + }, + { + "left": "issue:43746", + "right": "issue:44811", + "accept": false, + "reason": "PEFT/local-checkpoint loading bug vs Whisper batch_decode skip_special_tokens behavior." + }, + { + "left": "issue:43644", + "right": "issue:43749", + "accept": false, + "reason": "Both involve loading/regression symptoms, but one is junk non-persistent buffers and the other is FSDP CPU-RAM-efficient loading." + }, + { + "left": "issue:43638", + "right": "issue:44936", + "accept": false, + "reason": "Different training/eval failures with no shared concrete code path." + }, + { + "left": "issue:43550", + "right": "issue:44912", + "accept": false, + "reason": "torch.compile + SDPA failure is unrelated to MXFP4 quantization load fallback." + }, + { + "left": "issue:43819", + "right": "issue:43927", + "accept": false, + "reason": "DAC forward/from_latents mismatch is unrelated to DiaConfig token-ID persistence." + }, + { + "left": "issue:34634", + "right": "issue:36331", + "accept": false, + "reason": "Bark voice_preset problem vs Trainer compute_loss API change." + }, + { + "left": "issue:44387", + "right": "issue:44617", + "accept": false, + "reason": "Both mention OOM, but the causes and model paths are different." + }, + { + "left": "issue:36010", + "right": "issue:43645", + "accept": false, + "reason": "GenerationMixin import regression vs Jupyter custom-model initialization breakage." + }, + { + "left": "issue:43854", + "right": "issue:44977", + "accept": false, + "reason": "Different models and different failures: GLM-4.7-Flash load test vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:39692", + "right": "issue:44912", + "accept": false, + "reason": "Doc-example errors for SigLIP2 are not the same bug as MXFP4 loading fallback." + }, + { + "left": "issue:38175", + "right": "issue:44610", + "accept": false, + "reason": "Unexpected zero probabilities in SigLIP2 is unrelated to OmDet processor size mismatch." + }, + { + "left": "issue:43720", + "right": "issue:44610", + "accept": false, + "reason": "BitNet packed-weight unpacking bug is unrelated to OmDet input-size mismatch." + }, + { + "left": "issue:45459", + "right": "issue:45803", + "accept": false, + "reason": "Both hide errors with broad exception handling, but they are different functions and failure modes." + }, + { + "left": "issue:43526", + "right": "issue:44554", + "accept": false, + "reason": "Beit label reduction bug is unrelated to the MPS attention correctness issue." + }, + { + "left": "issue:36010", + "right": "issue:36331", + "accept": false, + "reason": "ImportError for GenerationMixin is a different issue from the unexpected compute_loss keyword argument." + }, + { + "left": "issue:43454", + "right": "issue:43577", + "accept": false, + "reason": "AyaVision weight-tying bug and BLIP2 dtype loading bug are distinct." + }, + { + "left": "issue:43531", + "right": "issue:45042", + "accept": false, + "reason": "Qwen3-MoE sliding_window bug is unrelated to the torchvision requirement regression." + }, + { + "left": "issue:43262", + "right": "issue:44811", + "accept": false, + "reason": "Audio chat_template sampling-rate default and Whisper batch_decode behavior are separate processor bugs." + }, + { + "left": "issue:43749", + "right": "issue:44291", + "accept": false, + "reason": "FSDP_CPU_RAM_EFFICIENT_LOADING and init_empty_weights/_is_hf_initialized are different loading-path regressions." + }, + { + "left": "issue:43257", + "right": "issue:43329", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate/deepspeed is unrelated to the multimodal token-count video branch bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 18, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:24643", + "issue:29159", + "issue:33357", + "issue:34567", + "issue:38175", + "issue:40990", + "issue:41720", + "issue:42490", + "issue:42915", + "issue:43257", + "issue:43317", + "issue:43329", + "issue:43450", + "issue:43452", + "issue:43540", + "issue:43577", + "issue:43582", + "issue:43606", + "issue:43643", + "issue:43697", + "issue:43742", + "issue:43927", + "issue:43931", + "issue:44062", + "issue:44291", + "issue:44479", + "issue:44560", + "issue:44568", + "issue:44821", + "issue:44849", + "issue:44898", + "issue:44912", + "issue:44987", + "issue:44991", + "issue:45042", + "issue:45072", + "issue:45137", + "issue:45356", + "issue:45357", + "issue:45381", + "issue:45405", + "issue:45488", + "issue:45538", + "issue:45701", + "issue:45759", + "issue:45859", + "issue:45907" + ], + "soft_pairs": [ + "issue:43643|issue:45759", + "issue:42490|issue:43257", + "issue:43329|issue:43450", + "issue:43606|issue:45859", + "issue:34567|issue:40990", + "issue:44568|issue:45356", + "issue:29159|issue:34567", + "issue:43329|issue:44479", + "issue:42915|issue:43742", + "issue:44849|issue:45701", + "issue:44291|issue:45042", + "issue:43257|issue:43931", + "issue:43452|issue:43582", + "issue:43927|issue:44912", + "issue:42915|issue:44821", + "issue:43697|issue:45357", + "issue:44568|issue:45488", + "issue:33357|issue:34567", + "issue:41720|issue:43540", + "issue:42915|issue:45538", + "issue:44987|issue:45538", + "issue:43317|issue:45538", + "issue:43540|issue:44479", + "issue:44479|issue:45381", + "issue:43540|issue:44560", + "issue:44987|issue:45907", + "issue:45137|issue:45405", + "issue:24643|issue:29159", + "issue:43742|issue:44291", + "issue:43577|issue:45072", + "issue:44062|issue:44991", + "issue:38175|issue:44898" + ], + "prepared_review_unit_hash": "6de693b3d5d7aa928afdbcaa739281073ed3fa33b6807aeeea1bd6ad2da16722", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36870, + "estimated_input_tokens": 9218, + "estimated_eval_tokens": 18692 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous; only one soft edge looks like a true duplicate around the Qwen video-input regression. The rest are distinct tokenizer, loading, vision, and DeepSpeed issues.", + "confidence": 0.81, + "canonical_issue_reason": "No single canonical issue spans this heterogeneous cluster; the only clear duplicate edge is the Qwen video-regression pair.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45701 is the broadest umbrella candidate, but it only loosely covers a tokenizer subset and is not a true global representative.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:45759", + "accept": false, + "reason": "Different config-loading bugs: missing remote-code fields vs text_config unwrapping." + }, + { + "left": "issue:42490", + "right": "issue:43257", + "accept": false, + "reason": "Path-trailing-slash warning and Qwen3 MoE weight conversion are unrelated." + }, + { + "left": "issue:43329", + "right": "issue:43450", + "accept": false, + "reason": "Both involve video handling, but one is token counting and the other is processor output shape." + }, + { + "left": "issue:43606", + "right": "issue:45859", + "accept": false, + "reason": "Both mention CPU offload, but they affect different models and code paths." + }, + { + "left": "issue:34567", + "right": "issue:40990", + "accept": false, + "reason": "Trainer token accounting and perplexity on GPT-OSS are unrelated." + }, + { + "left": "issue:44568", + "right": "issue:45356", + "accept": false, + "reason": "Different tokenizer regressions with different failure modes and models." + }, + { + "left": "issue:29159", + "right": "issue:34567", + "accept": false, + "reason": "Tokenizer slow/fast inconsistency is unrelated to TrainerState token counts." + }, + { + "left": "issue:43329", + "right": "issue:44479", + "accept": true, + "reason": "Same underlying Qwen video-input regression; 43329 pinpoints the broken video branch that 44479 reports broadly." + }, + { + "left": "issue:42915", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3Moe FP8 failure and MobileLLM key error are different loading bugs." + }, + { + "left": "issue:44849", + "right": "issue:45701", + "accept": false, + "reason": "Qwen3.5 hidden-state bug is not the same as a generic tokenization regression." + }, + { + "left": "issue:44291", + "right": "issue:45042", + "accept": false, + "reason": "init_empty_weights argument handling and torchvision import requirements are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:43931", + "accept": false, + "reason": "Both are Qwen3 loading issues, but one is MoE conversion and the other is VL shape mismatch." + }, + { + "left": "issue:43452", + "right": "issue:43582", + "accept": false, + "reason": "GGUF loading and Apple Silicon allocator warmup are unrelated." + }, + { + "left": "issue:43927", + "right": "issue:44912", + "accept": false, + "reason": "Config token-ID persistence and MXFP4 quantization fallback are different bugs." + }, + { + "left": "issue:42915", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3Moe FP8 loading and AutoImageProcessor URL loading are unrelated." + }, + { + "left": "issue:43697", + "right": "issue:45357", + "accept": false, + "reason": "Different regressions: RTDetrV2 output drift vs Qwen3.5 save_pretrained key mapping." + }, + { + "left": "issue:44568", + "right": "issue:45488", + "accept": false, + "reason": "Tokenizer behavior changed, but these are different models and mechanisms." + }, + { + "left": "issue:33357", + "right": "issue:34567", + "accept": false, + "reason": "Mac bus error on CLIP and trainer token accounting are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:43540", + "accept": false, + "reason": "Auto device mapping cuda assert is not the same as Qwen3OmniMoe video processing." + }, + { + "left": "issue:42915", + "right": "issue:45538", + "accept": false, + "reason": "Qwen3Moe FP8 loading and CLIPTokenizer model_max_length are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45538", + "accept": false, + "reason": "Repository loading failure and CLIPTokenizer max length are different issues." + }, + { + "left": "issue:43317", + "right": "issue:45538", + "accept": false, + "reason": "Dequantized-model offload failure is unrelated to tokenizer max length." + }, + { + "left": "issue:43540", + "right": "issue:44479", + "accept": false, + "reason": "Related to video inputs, but one is a processing ValueError and the other is a regression in token counting." + }, + { + "left": "issue:44479", + "right": "issue:45381", + "accept": false, + "reason": "Both are Qwen video regressions, but one is generic video-input failure and the other is wrong vision_position_ids." + }, + { + "left": "issue:43540", + "right": "issue:44560", + "accept": false, + "reason": "Both are video-related, but the failures are different and model-specific." + }, + { + "left": "issue:44987", + "right": "issue:45907", + "accept": false, + "reason": "Loading physical-intelligence/fast and forwarding revision in list_repo_files are unrelated." + }, + { + "left": "issue:45137", + "right": "issue:45405", + "accept": false, + "reason": "DeepSpeed ZeRO3 deque error and PEFT version bump are unrelated." + }, + { + "left": "issue:24643", + "right": "issue:29159", + "accept": false, + "reason": "DeepSpeed weight-dimension error and tokenizer slow/fast inconsistency are unrelated." + }, + { + "left": "issue:43742", + "right": "issue:44291", + "accept": false, + "reason": "MobileLLM key error and init_empty_weights argument handling are different bugs." + }, + { + "left": "issue:43577", + "right": "issue:45072", + "accept": false, + "reason": "Both involve dtype, but one is model loading and the other is bfloat16 inference." + }, + { + "left": "issue:44062", + "right": "issue:44991", + "accept": false, + "reason": "Both are tokenizer-loading failures, but the titles point to different underlying causes." + }, + { + "left": "issue:38175", + "right": "issue:44898", + "accept": false, + "reason": "Zero-probabilities in SigLIP2 and Perceiver image-size handling are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative: it treats the cluster as heterogeneous, avoids overclaiming a canonical representative, and only marks the Qwen video-regression pair as a duplicate-like edge. The other soft-edge rejections are cautious and consistent with the issue titles." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 19, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28282", + "issue:29127", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:36331", + "issue:42175", + "issue:43257", + "issue:43404", + "issue:43452", + "issue:43493", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43646", + "issue:43696", + "issue:43742", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43906", + "issue:43994", + "issue:44062", + "issue:44291", + "issue:44488", + "issue:44589", + "issue:44625", + "issue:44737", + "issue:44756", + "issue:44792", + "issue:44821", + "issue:44877", + "issue:44913", + "issue:44964", + "issue:45042", + "issue:45081", + "issue:45325", + "issue:45357", + "issue:45375", + "issue:45381", + "issue:45405", + "issue:45479", + "issue:45588", + "issue:45600", + "issue:45920", + "issue:45987", + "issue:46121" + ], + "soft_pairs": [ + "issue:44737|issue:45588", + "issue:43257|issue:43696", + "issue:43404|issue:45987", + "issue:34567|issue:36331", + "issue:44062|issue:45081", + "issue:43646|issue:43749", + "issue:44913|issue:46121", + "issue:43493|issue:43994", + "issue:43906|issue:45381", + "issue:44792|issue:44964", + "issue:43749|issue:44756", + "issue:43257|issue:43756", + "issue:44291|issue:44821", + "issue:36010|issue:42175", + "issue:28282|issue:34689", + "issue:42175|issue:43824", + "issue:45042|issue:45081", + "issue:43452|issue:44488", + "issue:45357|issue:45920", + "issue:43742|issue:44589", + "issue:45405|issue:45600", + "issue:28282|issue:29127", + "issue:43643|issue:45375", + "issue:43531|issue:44821", + "issue:43526|issue:45479", + "issue:43756|issue:45325", + "issue:44625|issue:44877" + ], + "prepared_review_unit_hash": "19501d0b7c1a0a933c931ba8c3726d110fd4368303e8710fb0afff9fcc80e33d", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35506, + "estimated_input_tokens": 8877, + "estimated_eval_tokens": 18010 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a grab-bag of distinct Transformers bugs/regressions rather than one tight duplicate cluster. The only plausible overlaps are theme-level (loading, config, tokenizer, vision), but the concrete failure modes differ enough to reject all soft edges.", + "confidence": 0.66, + "canonical_issue_reason": "Issue #45920 is the broadest current regression report in the set, spans multiple affected models, and has inbound references; it is the best umbrella-style issue to represent the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue #45920 has the clearest cross-model impact and enough discussion/references to serve as the most representative issue in this mixed cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44737", + "right": "issue:45588", + "accept": false, + "reason": "Both are performance/runtime bugs, but one is XLNet CPU placement and the other is flash-attention sink handling; different code paths and symptoms." + }, + { + "left": "issue:43257", + "right": "issue:43696", + "accept": false, + "reason": "MoE weight conversion under accelerate/deepspeed is unrelated to a CUDA OOM on GPT-oss." + }, + { + "left": "issue:43404", + "right": "issue:45987", + "accept": false, + "reason": "One is tied weights in Mistral3 image-text generation; the other is a cache length return-type bug." + }, + { + "left": "issue:34567", + "right": "issue:36331", + "accept": false, + "reason": "Training API regressions, but they concern different hooks and arguments (`num_input_tokens_seen` vs `num_items_in_batch`)." + }, + { + "left": "issue:44062", + "right": "issue:45081", + "accept": false, + "reason": "Different tokenizer failures: duplicate `special` kwarg vs missing `backend_tokenizer` in Mistral regex patching." + }, + { + "left": "issue:43646", + "right": "issue:43749", + "accept": false, + "reason": "Config loading with `trust_remote_code` missing fields is not the same as FSDP CPU RAM efficient loading being broken." + }, + { + "left": "issue:44913", + "right": "issue:46121", + "accept": false, + "reason": "Both touch RoPE/config handling, but one is silent config reload fallback while the other is a `TypeError` on JSON-loaded lists." + }, + { + "left": "issue:43493", + "right": "issue:43994", + "accept": false, + "reason": "Both involve SigLIP2, but one is HF-vs-JAX numerical discrepancy and the other is bad results through AutoModel/pipeline; not the same concrete bug." + }, + { + "left": "issue:43906", + "right": "issue:45381", + "accept": false, + "reason": "Both mention vision position ids in a broad sense, but one is an isolated reproduction of an older issue and the other is a Qwen2.5-VL video-input bug." + }, + { + "left": "issue:44792", + "right": "issue:44964", + "accept": false, + "reason": "Different multimodal model failures: a failing Janus image-generation test versus inability to load Phi-4 multimodal instruct." + }, + { + "left": "issue:43749", + "right": "issue:44756", + "accept": false, + "reason": "FSDP loading is a framework feature regression; disabling mmap for Strix Halo is a hardware-specific OOM workaround." + }, + { + "left": "issue:43257", + "right": "issue:43756", + "accept": false, + "reason": "Qwen3 MoE weight conversion and Smollm3 RoPE-layer dropping are unrelated model-specific bugs." + }, + { + "left": "issue:44291", + "right": "issue:44821", + "accept": false, + "reason": "`init_empty_weights` argument handling is unrelated to loading `AutoImageProcessor` from a URL." + }, + { + "left": "issue:36010", + "right": "issue:42175", + "accept": false, + "reason": "Importing `GenerationMixin` and missing TensorFlow in a torch-only install are different dependency/import problems." + }, + { + "left": "issue:28282", + "right": "issue:34689", + "accept": false, + "reason": "PyTorch-missing ImportError and a Llama 3.2 Vision model-loading regression are distinct failure modes." + }, + { + "left": "issue:42175", + "right": "issue:43824", + "accept": false, + "reason": "Backend dependency packaging is unrelated to a missing `Qwen2_5_VLForConditionalGeneration` export." + }, + { + "left": "issue:45042", + "right": "issue:45081", + "accept": false, + "reason": "PIL backend requiring torchvision and Mistral tokenizer regex patching are separate subsystems and bugs." + }, + { + "left": "issue:43452", + "right": "issue:44488", + "accept": false, + "reason": "GGUF loading breakage and a model-loading failure for `cjvt/sleng-bert` are not the same code-path problem." + }, + { + "left": "issue:45357", + "right": "issue:45920", + "accept": false, + "reason": "Both are Qwen-related regressions, but one is save-pretrained key handling and the other is tokenizer ID generation." + }, + { + "left": "issue:43742", + "right": "issue:44589", + "accept": false, + "reason": "A key error loading a specific model is unrelated to a float8 storage lookup TypeError." + }, + { + "left": "issue:45405", + "right": "issue:45600", + "accept": false, + "reason": "PEFT version pinning and stale auto-mappings CI failures are unrelated maintenance issues." + }, + { + "left": "issue:28282", + "right": "issue:29127", + "accept": false, + "reason": "PyTorch import missing versus LayoutLMv3 box-validation messaging are completely different issues." + }, + { + "left": "issue:43643", + "right": "issue:45375", + "accept": false, + "reason": "Both concern missing config fields, but they refer to different mechanisms and models; not enough to treat as one bug." + }, + { + "left": "issue:43531", + "right": "issue:44821", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to `AutoImageProcessor` URL loading." + }, + { + "left": "issue:43526", + "right": "issue:45479", + "accept": false, + "reason": "Both involve labels, but one is image-processor label reduction and the other is sequence-classification loss computation." + }, + { + "left": "issue:43756", + "right": "issue:45325", + "accept": false, + "reason": "Different Qwen multimodal bugs: RoPE layer dropping vs still-image temporal position scaling." + }, + { + "left": "issue:44625", + "right": "issue:44877", + "accept": false, + "reason": "Num-label propagation in Qwen3.5 is a different config bug from strict config blocking granite_speech loading." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 20, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:24643", + "issue:29127", + "issue:29159", + "issue:30064", + "issue:33357", + "issue:33666", + "issue:38175", + "issue:41762", + "issue:43295", + "issue:43452", + "issue:43531", + "issue:43577", + "issue:43582", + "issue:43653", + "issue:43697", + "issue:43720", + "issue:43742", + "issue:43819", + "issue:43906", + "issue:43927", + "issue:44361", + "issue:44442", + "issue:44464", + "issue:44466", + "issue:44484", + "issue:44493", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44743", + "issue:44811", + "issue:44843", + "issue:44898", + "issue:44936", + "issue:44977", + "issue:44991", + "issue:45005", + "issue:45216", + "issue:45290", + "issue:45356", + "issue:45372", + "issue:45381", + "issue:45542", + "issue:45823", + "issue:46050", + "issue:46170", + "issue:46178", + "issue:46202" + ], + "soft_pairs": [ + "issue:43720|issue:44898", + "issue:43697|issue:45216", + "issue:43582|issue:44977", + "issue:44514|issue:45381", + "issue:24643|issue:29127", + "issue:41762|issue:44936", + "issue:44466|issue:45005", + "issue:43452|issue:43577", + "issue:43452|issue:44843", + "issue:43906|issue:46202", + "issue:45372|issue:46170", + "issue:30064|issue:33666", + "issue:43819|issue:44811", + "issue:43295|issue:45356", + "issue:44936|issue:45823", + "issue:44361|issue:44442", + "issue:43653|issue:44361", + "issue:44484|issue:44704", + "issue:38175|issue:43295", + "issue:45542|issue:46178", + "issue:44514|issue:45290", + "issue:43653|issue:44568", + "issue:43577|issue:43697", + "issue:29159|issue:33357", + "issue:44493|issue:46050", + "issue:44843|issue:44991", + "issue:44464|issue:44743", + "issue:43531|issue:43742", + "issue:43653|issue:43927" + ], + "prepared_review_unit_hash": "d674f03f32151f2a37651406be263b6301e59e6ec364a45fd043a73b1ec6110d", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36678, + "estimated_input_tokens": 9170, + "estimated_eval_tokens": 18596 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly heterogeneous. I only see two likely duplicate pairs: the Qwen2_5_VL `apply_chat_template` crash with assistant tool calls and no content, and the v5 tied-weights/lm_head serialization regression. The rest are different bugs or different model-specific failures.", + "confidence": 0.87, + "canonical_issue_reason": "Issue 44514 is the clearest concrete repro for the `apply_chat_template(tokenize=True)` crash; it is more specific than 45290 and describes the exact failing path.", + "canonical_pr_reason": null, + "best_issue_reason": "44514 is the best representative issue in this set because it states a concrete, actionable failure mode and matches its counterpart almost exactly.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43720", + "right": "issue:44898", + "accept": false, + "reason": "Different models and different failure modes; no shared code-path bug." + }, + { + "left": "issue:43697", + "right": "issue:45216", + "accept": false, + "reason": "Both are regressions, but they concern unrelated models and unrelated save/load behavior." + }, + { + "left": "issue:43582", + "right": "issue:44977", + "accept": false, + "reason": "Apple Silicon allocator warmup TypeError is unrelated to Qwen3.5 flash-attention generation." + }, + { + "left": "issue:44514", + "right": "issue:45381", + "accept": false, + "reason": "Same model family, but one is a batched chat-template crash and the other is a video vision-position-id bug; different code paths." + }, + { + "left": "issue:24643", + "right": "issue:29127", + "accept": false, + "reason": "Training/DeepSpeed weight-shape error is unrelated to LayoutLMv3 box-validation messaging." + }, + { + "left": "issue:41762", + "right": "issue:44936", + "accept": false, + "reason": "Gemma3 ZeRO-3 load failure is unrelated to trainer evaluate-after-train behavior." + }, + { + "left": "issue:44466", + "right": "issue:45005", + "accept": true, + "reason": "Both describe the same v5 tied-weights serialization problem: `lm_head.weight`/tied weights being saved inconsistently, especially across model/device setups." + }, + { + "left": "issue:43452", + "right": "issue:43577", + "accept": false, + "reason": "Tokenizer/model loading with gguf_file is unrelated to Blip2 dtype propagation." + }, + { + "left": "issue:43452", + "right": "issue:44843", + "accept": false, + "reason": "Both involve AutoTokenizer loading, but one is gguf_file handling and the other is an offline-mode regression in `_patch_mistral_regex`." + }, + { + "left": "issue:43906", + "right": "issue:46202", + "accept": false, + "reason": "`43906` is only an isolated reproduction reference; the Gemma pipeline roundtrip issue is a different bug." + }, + { + "left": "issue:45372", + "right": "issue:46170", + "accept": false, + "reason": "Gemma processor import failure due to `mistral_common` is unrelated to Windows/ROCm torch.distributed dependency errors." + }, + { + "left": "issue:30064", + "right": "issue:33666", + "accept": false, + "reason": "Void segmentation-map processing and Qwen2-VL multi-GPU training are unrelated." + }, + { + "left": "issue:43819", + "right": "issue:44811", + "accept": false, + "reason": "DAC latent/forward mismatch is unrelated to Whisper batch_decode special-token handling." + }, + { + "left": "issue:43295", + "right": "issue:45356", + "accept": false, + "reason": "Both are tokenizer/processor regressions, but they describe different failures and different affected models." + }, + { + "left": "issue:44936", + "right": "issue:45823", + "accept": false, + "reason": "Trainer lifecycle failure is unrelated to Gemma4 device_map forward mismatch." + }, + { + "left": "issue:44361", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer implementations and different bugs." + }, + { + "left": "issue:43653", + "right": "issue:44361", + "accept": false, + "reason": "BigBird special-token registration and MLukeTokenizer AttributeError are unrelated." + }, + { + "left": "issue:44484", + "right": "issue:44704", + "accept": false, + "reason": "save_pretrained shard-size question is unrelated to AutoProcessor kwarg forwarding." + }, + { + "left": "issue:38175", + "right": "issue:43295", + "accept": false, + "reason": "SigLIP zero-probabilities and processor/tokenizer regression are different issues." + }, + { + "left": "issue:45542", + "right": "issue:46178", + "accept": false, + "reason": "Both mention backend handling, but tensorboard-without-TF and tensorflow_text backend mapping are different bugs." + }, + { + "left": "issue:44514", + "right": "issue:45290", + "accept": true, + "reason": "These appear to be the same crash: `apply_chat_template(tokenize=True)` failing on assistant tool-call messages with no content." + }, + { + "left": "issue:43653", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer special-token problems, but they affect different models and different token types." + }, + { + "left": "issue:43577", + "right": "issue:43697", + "accept": false, + "reason": "Blip2 dtype propagation and RTDetrV2 output differences are unrelated." + }, + { + "left": "issue:29159", + "right": "issue:33357", + "accept": false, + "reason": "Tokenizer consistency and MacOS bus-error CLIP loading are unrelated." + }, + { + "left": "issue:44493", + "right": "issue:46050", + "accept": false, + "reason": "Unexpected position-id keys and quantized save/load breakage are different failure modes." + }, + { + "left": "issue:44843", + "right": "issue:44991", + "accept": false, + "reason": "Offline-mode regression in Mistral regex patching is unrelated to EMBEDDIA tokenizer loading failure." + }, + { + "left": "issue:44464", + "right": "issue:44743", + "accept": false, + "reason": "Both involve generation/cache behavior, but one is compiled-forward chunked generation and the other is Qwen3.5 recurrent-state reset; not the same bug." + }, + { + "left": "issue:43531", + "right": "issue:43742", + "accept": false, + "reason": "Qwen3-MoE sliding-window behavior is unrelated to MobileLLM-125M load key errors." + }, + { + "left": "issue:43653", + "right": "issue:43927", + "accept": false, + "reason": "Special-token registration in BigBirdTokenizer is unrelated to DiaConfig custom token ID persistence." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The grouping is grounded in the packet and the non-matches are handled conservatively. The two accepted soft pairs are plausibly the same bugs from their titles alone: the Qwen2_5_VL chat-template crash and the v5 tied-weights serialization regression. No obvious overstatement beyond the available evidence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 21, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28282", + "issue:32090", + "issue:33357", + "issue:33666", + "issue:34567", + "issue:35141", + "issue:36010", + "issue:36331", + "issue:39692", + "issue:41720", + "issue:43262", + "issue:43295", + "issue:43452", + "issue:43493", + "issue:43504", + "issue:43525", + "issue:43550", + "issue:43572", + "issue:43577", + "issue:43606", + "issue:43643", + "issue:43688", + "issue:43720", + "issue:43742", + "issue:43756", + "issue:43825", + "issue:43906", + "issue:43927", + "issue:43994", + "issue:44361", + "issue:44451", + "issue:44464", + "issue:44466", + "issue:44561", + "issue:44610", + "issue:44821", + "issue:44849", + "issue:44913", + "issue:44977", + "issue:45357", + "issue:45440", + "issue:45491", + "issue:45588", + "issue:45823", + "issue:46002", + "issue:46050", + "issue:46192", + "issue:46209" + ], + "soft_pairs": [ + "issue:41720|issue:43906", + "issue:43550|issue:43927", + "issue:44464|issue:44977", + "issue:43550|issue:44361", + "issue:44977|issue:46209", + "issue:43643|issue:44561", + "issue:32090|issue:34567", + "issue:43577|issue:45588", + "issue:28282|issue:35141", + "issue:43504|issue:43550", + "issue:32090|issue:33666", + "issue:43504|issue:43720", + "issue:45491|issue:46002", + "issue:44466|issue:46050", + "issue:33666|issue:36010", + "issue:43504|issue:44610", + "issue:41720|issue:44464", + "issue:43742|issue:44821", + "issue:43688|issue:45440", + "issue:45823|issue:46050", + "issue:28282|issue:32090", + "issue:44849|issue:46209", + "issue:43262|issue:43295", + "issue:43452|issue:44451", + "issue:28282|issue:33357", + "issue:43720|issue:43927", + "issue:43606|issue:43927", + "issue:43994|issue:46192", + "issue:33666|issue:36331", + "issue:43756|issue:44913", + "issue:43525|issue:43572", + "issue:43720|issue:44361", + "issue:43493|issue:43825", + "issue:44849|issue:45357", + "issue:39692|issue:43493" + ], + "prepared_review_unit_hash": "e7d75091b525885b3c8d4f023c1a67852b9b3b3b629ccb67c791e5962d88b0e7", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 35, + "serialized_chars": 38331, + "estimated_input_tokens": 9583, + "estimated_eval_tokens": 19422 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the issues cover unrelated models, configs, trainer behavior, loading/serialization, and device/runtime failures. None of the soft pairs look like the same underlying bug or change, so I would not deduplicate any of them.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue exists; the set is too diverse and the soft pairs are only superficially similar.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a good global representative because each report targets a different code path or model family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:43906", + "accept": false, + "reason": "Both mention Qwen-related context, but one is a CUDA assert under auto device mapping and the other is an isolated reproduction of a different issue." + }, + { + "left": "issue:43550", + "right": "issue:43927", + "accept": false, + "reason": "Different models and failures: Bamba torch.compile/SDPA versus DiaConfig losing custom token IDs on save/load." + }, + { + "left": "issue:44464", + "right": "issue:44977", + "accept": false, + "reason": "Chunked generation with compiled forward is unrelated to Qwen3.5 flash-attention generation failures." + }, + { + "left": "issue:43550", + "right": "issue:44361", + "accept": false, + "reason": "These are unrelated bugs in different areas: Bamba compiled attention versus MLukeTokenizer task-time AttributeError." + }, + { + "left": "issue:44977", + "right": "issue:46209", + "accept": false, + "reason": "Flash-attention generation bug and FP8 inference failure on B200 are different code paths and hardware-specific issues." + }, + { + "left": "issue:43643", + "right": "issue:44561", + "accept": false, + "reason": "Both involve trust_remote_code, but one is missing fields from AutoConfig and the other is a v5 removal breaking remote models." + }, + { + "left": "issue:32090", + "right": "issue:34567", + "accept": false, + "reason": "Trainer GPU broadcast TypeError and TrainerState.num_input_tokens_seen not updating are distinct trainer bugs." + }, + { + "left": "issue:43577", + "right": "issue:45588", + "accept": false, + "reason": "Blip2 dtype initialization and flash_attention.py crashing on s_aux=None are unrelated failures." + }, + { + "left": "issue:28282", + "right": "issue:35141", + "accept": false, + "reason": "Missing PyTorch ImportError and embedding reinitialization after resize are completely different issues." + }, + { + "left": "issue:43504", + "right": "issue:43550", + "accept": false, + "reason": "Beit pretrained-loading legacy-field bug is unrelated to Bamba torch.compile SDPA behavior." + }, + { + "left": "issue:32090", + "right": "issue:33666", + "accept": false, + "reason": "Trainer broadcast NoneType error is not the same as Qwen2-VL multi-GPU training support." + }, + { + "left": "issue:43504", + "right": "issue:43720", + "accept": false, + "reason": "Legacy field loading in Beit and BitNet packed-weight loading during accelerate are different model-loading bugs." + }, + { + "left": "issue:45491", + "right": "issue:46002", + "accept": false, + "reason": "Gemma3 mixed-length NaNs and classification-head NaNs after checkout/init are different symptoms with different likely causes." + }, + { + "left": "issue:44466", + "right": "issue:46050", + "accept": false, + "reason": "Serialization of tied lm_head weights is unrelated to sinq quantization save/load breakage." + }, + { + "left": "issue:33666", + "right": "issue:36010", + "accept": false, + "reason": "Multi-GPU training for Qwen2-VL is unrelated to the GenerationMixin import error." + }, + { + "left": "issue:43504", + "right": "issue:44610", + "accept": false, + "reason": "Beit legacy-field loading and OmDet processor/model image-size mismatch are unrelated." + }, + { + "left": "issue:41720", + "right": "issue:44464", + "accept": false, + "reason": "CUDA assert with auto device mapping and chunked generation inconsistency are different failures in different execution modes." + }, + { + "left": "issue:43742", + "right": "issue:44821", + "accept": false, + "reason": "MobileLLM key error and AutoImageProcessor-from-URL loading are separate loading paths with different breakages." + }, + { + "left": "issue:43688", + "right": "issue:45440", + "accept": false, + "reason": "Both are MoE-adjacent, but auxiliary-loss normalization and DeepSeekV3MoE divergence are not the same bug." + }, + { + "left": "issue:45823", + "right": "issue:46050", + "accept": false, + "reason": "Gemma4 device-map mismatch and sinq quantization persistence failure are unrelated." + }, + { + "left": "issue:28282", + "right": "issue:32090", + "accept": false, + "reason": "AutoModel missing PyTorch ImportError is unrelated to Trainer _gpu_broadcast_one receiving NoneType." + }, + { + "left": "issue:44849", + "right": "issue:46209", + "accept": false, + "reason": "Qwen3.5 hidden-states bug and FP8 inference on B200 are different model/runtime issues." + }, + { + "left": "issue:43262", + "right": "issue:43295", + "accept": false, + "reason": "Audio chat-template sampling-rate default and processor.tokenizer/image handling regression are unrelated processor bugs." + }, + { + "left": "issue:43452", + "right": "issue:44451", + "accept": false, + "reason": "gguf_file loading breakage and inability to load ScandiBERT are different model/loading failures." + }, + { + "left": "issue:28282", + "right": "issue:33357", + "accept": false, + "reason": "PyTorch missing ImportError and MacOS bus error on CLIP are not the same bug." + }, + { + "left": "issue:43720", + "right": "issue:43927", + "accept": false, + "reason": "BitNet packed-weight loading and DiaConfig custom-token-ID persistence are unrelated." + }, + { + "left": "issue:43606", + "right": "issue:43927", + "accept": false, + "reason": "CPU offload device mismatch in bark-small is unrelated to DiaConfig save/load token ID loss." + }, + { + "left": "issue:43994", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 nonsensical outputs and return_tensors being ignored are different API bugs." + }, + { + "left": "issue:33666", + "right": "issue:36331", + "accept": false, + "reason": "Qwen2-VL multi-GPU training and CustomTrainer.compute_loss signature change are unrelated trainer/model issues." + }, + { + "left": "issue:43756", + "right": "issue:44913", + "accept": false, + "reason": "Smollm3 RoPE-layer dropping and GPTNeoXConfig rotary_pct reload behavior are different configuration/architecture bugs." + }, + { + "left": "issue:43525", + "right": "issue:43572", + "accept": false, + "reason": "Both are missing config fields, but for different models and different fields; not the same underlying defect." + }, + { + "left": "issue:43720", + "right": "issue:44361", + "accept": false, + "reason": "BitNet loading failure and MLukeTokenizer AttributeError are unrelated." + }, + { + "left": "issue:43493", + "right": "issue:43825", + "accept": false, + "reason": "SigLIP2 implementation discrepancy and pipeline translation-task messaging are unrelated." + }, + { + "left": "issue:44849", + "right": "issue:45357", + "accept": false, + "reason": "Hidden-states output bug and incorrect visual-encoder key serialization are different Qwen3.5 issues." + }, + { + "left": "issue:39692", + "right": "issue:43493", + "accept": false, + "reason": "Documentation-example errors for SigLIP2 and HF-vs-JAX implementation discrepancy are related only by model family, not the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 22, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:33357", + "issue:33666", + "issue:39692", + "issue:43257", + "issue:43278", + "issue:43295", + "issue:43299", + "issue:43334", + "issue:43493", + "issue:43504", + "issue:43540", + "issue:43572", + "issue:43575", + "issue:43577", + "issue:43606", + "issue:43646", + "issue:43653", + "issue:43688", + "issue:43749", + "issue:43756", + "issue:43824", + "issue:43844", + "issue:43927", + "issue:44112", + "issue:44291", + "issue:44361", + "issue:44466", + "issue:44479", + "issue:44488", + "issue:44493", + "issue:44554", + "issue:44568", + "issue:44589", + "issue:44625", + "issue:44843", + "issue:44964", + "issue:44977", + "issue:45083", + "issue:45200", + "issue:45229", + "issue:45405", + "issue:45520", + "issue:45701", + "issue:45704", + "issue:45759", + "issue:45812", + "issue:45823", + "issue:46285" + ], + "soft_pairs": [ + "issue:44964|issue:45405", + "issue:43577|issue:44554", + "issue:44479|issue:44625", + "issue:43688|issue:43749", + "issue:44568|issue:45812", + "issue:43540|issue:44977", + "issue:45200|issue:45229", + "issue:44488|issue:44843", + "issue:39692|issue:43295", + "issue:43688|issue:45704", + "issue:44493|issue:46285", + "issue:43756|issue:45083", + "issue:43334|issue:43572", + "issue:43646|issue:44466", + "issue:43493|issue:43844", + "issue:43824|issue:44589", + "issue:33357|issue:33666", + "issue:43334|issue:45759", + "issue:45229|issue:45823", + "issue:44589|issue:45520", + "issue:43927|issue:44361", + "issue:43504|issue:43606", + "issue:43278|issue:43844", + "issue:43572|issue:44291", + "issue:44625|issue:45759", + "issue:43257|issue:43299", + "issue:43575|issue:45405", + "issue:43688|issue:45701", + "issue:43606|issue:44112", + "issue:43504|issue:43653" + ], + "prepared_review_unit_hash": "d0f3a660d73f4f9670cbe6474209ebe9825b4a10cddd95555c0d974ace9fdf15", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36898, + "estimated_input_tokens": 9225, + "estimated_eval_tokens": 18706 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a set of unrelated Transformers bug reports; none of the soft pairs look like the same underlying issue closely enough to merge. I\u2019d keep the Granite tokenization regression as the clearest representative issue in this set.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45812 is the most broadly scoped, high-impact regression report here: it is user-facing, affects all Granite models, and is clearly described as a silent v4\u2192v5 break.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the strongest standalone issue to anchor the cluster because it is concrete, severe, and broadly applicable compared with the more niche or model-specific reports.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44964", + "right": "issue:45405", + "accept": false, + "reason": "One is a Phi-4 multimodal load failure; the other is a packaging/version constraint problem for PEFT. Different bugs and different code paths." + }, + { + "left": "issue:43577", + "right": "issue:44554", + "accept": false, + "reason": "Embedding dtype drift in Blip2 versus an MPS attention correctness issue. No shared failure mechanism." + }, + { + "left": "issue:44479", + "right": "issue:44625", + "accept": false, + "reason": "Video-input regression in Qwen VL models versus num_labels propagation in Qwen3.5 configs. Related area, but not the same defect." + }, + { + "left": "issue:43688", + "right": "issue:43749", + "accept": false, + "reason": "Aux-loss normalization bug versus FSDP CPU RAM efficient loading breakage. Distinct training/runtime problems." + }, + { + "left": "issue:44568", + "right": "issue:45812", + "accept": false, + "reason": "Tokenizer special-token handling for one model is not the same as the Granite-wide token ID regression." + }, + { + "left": "issue:43540", + "right": "issue:44977", + "accept": false, + "reason": "Qwen3OmniMoe video processing ValueError and Qwen3.5 flash-attention generation issues are different failures." + }, + { + "left": "issue:45200", + "right": "issue:45229", + "accept": false, + "reason": "Missing mm_token_type_ids default for text-only fine-tuning versus CUDA OOM in multi-GPU inference." + }, + { + "left": "issue:44488", + "right": "issue:44843", + "accept": false, + "reason": "Loading cjvt/sleng-bert is a model-specific break; HF_HUB_OFFLINE regression is a hub/network-path bug." + }, + { + "left": "issue:39692", + "right": "issue:43295", + "accept": false, + "reason": "Documentation/example errors for SigLIP2 versus a processor.tokenizer API regression. Not the same code-path." + }, + { + "left": "issue:43688", + "right": "issue:45704", + "accept": false, + "reason": "Auxiliary loss normalization in MoE models is unrelated to T5 accidentally using apex.FusedRMSNorm." + }, + { + "left": "issue:44493", + "right": "issue:46285", + "accept": false, + "reason": "Unexpected position-id key warnings and CLIP text-model structure drift are different API/serialization issues." + }, + { + "left": "issue:43756", + "right": "issue:45083", + "accept": false, + "reason": "Smollm3 RoPE layer omission and qwen3_omni_moe feature-length helper behavior are unrelated." + }, + { + "left": "issue:43334", + "right": "issue:43572", + "accept": false, + "reason": "Both involve config fields, but one is Qwen3-VL pad_token_id loading and the other is StableLm pad_token_idx after a 5.0 update." + }, + { + "left": "issue:43646", + "right": "issue:44466", + "accept": false, + "reason": "Custom model initialization breakage is not the same as device-dependent lm_head.weight serialization." + }, + { + "left": "issue:43493", + "right": "issue:43844", + "accept": false, + "reason": "SigLIP2 implementation mismatch versus a ZeRO-3 gradient growth issue; different subsystems and symptoms." + }, + { + "left": "issue:43824", + "right": "issue:44589", + "accept": false, + "reason": "Missing Qwen2.5-VL import and float8 storage lookup failure are unrelated import/runtime errors." + }, + { + "left": "issue:33357", + "right": "issue:33666", + "accept": false, + "reason": "MacOS bus error on CLIP and Qwen2-VL multi-GPU training are clearly different." + }, + { + "left": "issue:43334", + "right": "issue:45759", + "accept": false, + "reason": "Both touch Qwen multimodal config loading, but one is a missing pad_token_id attribute and the other is from_config failing to unwrap text_config." + }, + { + "left": "issue:45229", + "right": "issue:45823", + "accept": false, + "reason": "CUDA OOM in Gemma4 multi-GPU inference is not the same as a device mismatch in PLE forward with device_map=auto." + }, + { + "left": "issue:44589", + "right": "issue:45520", + "accept": false, + "reason": "Float8 storage deserialization failure and flash_attn KeyError on Python 3.13 are separate import/runtime compatibility bugs." + }, + { + "left": "issue:43927", + "right": "issue:44361", + "accept": false, + "reason": "DiaConfig save/load token ID loss and MLukeTokenizer task AttributeError are unrelated tokenizer/config issues." + }, + { + "left": "issue:43504", + "right": "issue:43606", + "accept": false, + "reason": "Legacy field in Beit model loading versus CPU offload device mismatch in bark-small are different model-specific problems." + }, + { + "left": "issue:43278", + "right": "issue:43844", + "accept": false, + "reason": "Embedding dtype change between train/eval is not the same bug as abnormal gradients under HfDeepSpeedConfig + ZeRO-3." + }, + { + "left": "issue:43572", + "right": "issue:44291", + "accept": false, + "reason": "Missing pad_token_idx in StableLmConfig is unrelated to init_empty_weights passing an unexpected _is_hf_initialized argument." + }, + { + "left": "issue:44625", + "right": "issue:45759", + "accept": false, + "reason": "num_labels propagation in Qwen3.5 configs and text_config unwrapping in multimodal configs are adjacent but distinct changes." + }, + { + "left": "issue:43257", + "right": "issue:43299", + "accept": false, + "reason": "Qwen3 MoE weights not converting under accelerate/deepspeed is not the same as Qwen3VL MoE loading breaking in dev." + }, + { + "left": "issue:43575", + "right": "issue:45405", + "accept": false, + "reason": "Tensor-parallel OOM on a Qwen2 model and a PEFT version bump issue have no shared code-path." + }, + { + "left": "issue:43688", + "right": "issue:45701", + "accept": false, + "reason": "Aux-loss normalization in MoE models and a general tokenization-change report are not the same defect." + }, + { + "left": "issue:43606", + "right": "issue:44112", + "accept": false, + "reason": "CPU offload device mismatch in bark-small is separate from a stale CI test in GraniteSpeech." + }, + { + "left": "issue:43504", + "right": "issue:43653", + "accept": false, + "reason": "Pretrained Beit loading with a legacy field and BigBirdTokenizer special-token registration are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 23, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:15354", + "issue:28218", + "issue:29159", + "issue:29942", + "issue:30333", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:38175", + "issue:43232", + "issue:43278", + "issue:43295", + "issue:43450", + "issue:43493", + "issue:43540", + "issue:43572", + "issue:43688", + "issue:43701", + "issue:43844", + "issue:43873", + "issue:43994", + "issue:44186", + "issue:44423", + "issue:44464", + "issue:44493", + "issue:44521", + "issue:44554", + "issue:44610", + "issue:44734", + "issue:44792", + "issue:44849", + "issue:44964", + "issue:44987", + "issue:45072", + "issue:45084", + "issue:45198", + "issue:45200", + "issue:45290", + "issue:45405", + "issue:45406", + "issue:45446", + "issue:45520", + "issue:45584", + "issue:45588", + "issue:45823", + "issue:46050", + "issue:46121", + "issue:46192" + ], + "soft_pairs": [ + "issue:44792|issue:45405", + "issue:44423|issue:44734", + "issue:44464|issue:45584", + "issue:45588|issue:46050", + "issue:29942|issue:30333", + "issue:43994|issue:44493", + "issue:43844|issue:44964", + "issue:28218|issue:34567", + "issue:29159|issue:32090", + "issue:43688|issue:43873", + "issue:44554|issue:45446", + "issue:44521|issue:45290", + "issue:45084|issue:45520", + "issue:15354|issue:38175", + "issue:43540|issue:45200", + "issue:43873|issue:46050", + "issue:45200|issue:45823", + "issue:45072|issue:45198", + "issue:43278|issue:43701", + "issue:43232|issue:44849", + "issue:44186|issue:46192", + "issue:45406|issue:46121", + "issue:28218|issue:33357", + "issue:45823|issue:46192", + "issue:43493|issue:43701", + "issue:43295|issue:43450", + "issue:43295|issue:44610", + "issue:43572|issue:44987" + ], + "prepared_review_unit_hash": "a023d86fc36f61d3806e12e01a102ae42f37c90b4c371a032d7f044aa86bd07d", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36090, + "estimated_input_tokens": 9023, + "estimated_eval_tokens": 18302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft pairs mostly share only broad subsystem keywords (tokenizer, serve, Gemma, etc.) but do not describe the same underlying bug or change. I rejected all proposed edges.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue: the items span many unrelated defects, and none of the soft pairs look like true duplicates.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong global best issue; there isn't a single underlying problem tying these issues together.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44792", + "right": "issue:45405", + "accept": false, + "reason": "Janus test failure vs unreleased PEFT version bump; unrelated." + }, + { + "left": "issue:44423", + "right": "issue:44734", + "accept": false, + "reason": "Both touch serve, but one is a multimodal .to() crash and the other is KV-cache indexing; different bugs." + }, + { + "left": "issue:44464", + "right": "issue:45584", + "accept": false, + "reason": "Chunked compiled generation vs Whisper empty-transcription handling; different code paths." + }, + { + "left": "issue:45588", + "right": "issue:46050", + "accept": false, + "reason": "Flash-attention aux None crash vs quantized save/load regression; unrelated." + }, + { + "left": "issue:29942", + "right": "issue:30333", + "accept": false, + "reason": "Flash Attention 2 test failures vs MLflow failure-reporting bug; unrelated." + }, + { + "left": "issue:43994", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 output quality issue vs unexpected position-id key; not the same defect." + }, + { + "left": "issue:43844", + "right": "issue:44964", + "accept": false, + "reason": "ZeRO-3 gradient inflation vs Phi-4 multimodal loading failure; unrelated." + }, + { + "left": "issue:28218", + "right": "issue:34567", + "accept": false, + "reason": "Added-token spacing bug vs TrainerState token counter not updating; different areas." + }, + { + "left": "issue:29159", + "right": "issue:32090", + "accept": false, + "reason": "Slow/fast tokenizer inconsistency vs Trainer broadcast NoneType error; unrelated." + }, + { + "left": "issue:43688", + "right": "issue:43873", + "accept": false, + "reason": "Aux-loss normalization vs quantization offloading; different problems." + }, + { + "left": "issue:44554", + "right": "issue:45446", + "accept": false, + "reason": "MPS attention correctness bug vs flex_attention version check; unrelated." + }, + { + "left": "issue:44521", + "right": "issue:45290", + "accept": false, + "reason": "All-zero assistant masks vs tool-call/no-content crash in chat templating; distinct bugs." + }, + { + "left": "issue:45084", + "right": "issue:45520", + "accept": false, + "reason": "Template-node compile error vs flash_attn import key error on Python 3.13; unrelated." + }, + { + "left": "issue:15354", + "right": "issue:38175", + "accept": false, + "reason": "TorchScript GeneratorExp export issue vs SigLIP2 zero probabilities; unrelated." + }, + { + "left": "issue:43540", + "right": "issue:45200", + "accept": false, + "reason": "Video input processing failure vs Gemma4 token-type-id defaulting; different bugs." + }, + { + "left": "issue:43873", + "right": "issue:46050", + "accept": false, + "reason": "Quantization offloading bug vs sinq save/load corruption; not the same issue." + }, + { + "left": "issue:45200", + "right": "issue:45823", + "accept": false, + "reason": "Text-only fine-tuning token-id default vs device_map forward mismatch; unrelated." + }, + { + "left": "issue:45072", + "right": "issue:45198", + "accept": false, + "reason": "Bfloat16 dtype mismatch vs Wav2Vec2 save_pretrained/tokenization failure; different code paths." + }, + { + "left": "issue:43278", + "right": "issue:43701", + "accept": false, + "reason": "Embedding dtype change on evaluate vs resume_from_checkpoint key mismatch; unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44849", + "accept": false, + "reason": "Generation kwargs after sync_gpus vs Qwen3.5 output_hidden_states bug; unrelated." + }, + { + "left": "issue:44186", + "right": "issue:46192", + "accept": false, + "reason": "LayoutLMv2 NER padding crash vs return_tensors being ignored; different tokenizer issues." + }, + { + "left": "issue:45406", + "right": "issue:46121", + "accept": false, + "reason": "Gemma4Processor missing _tokenizer in serve vs rope param conversion TypeError; unrelated." + }, + { + "left": "issue:28218", + "right": "issue:33357", + "accept": false, + "reason": "Added-token spacing bug vs CLIP bus error on macOS; unrelated." + }, + { + "left": "issue:45823", + "right": "issue:46192", + "accept": false, + "reason": "Gemma4 device mismatch vs return_tensors/text_kwargs behavior; not the same bug." + }, + { + "left": "issue:43493", + "right": "issue:43701", + "accept": false, + "reason": "SigLIP2 HF/JAX discrepancy vs checkpoint key mismatch; unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43450", + "accept": false, + "reason": "Processor.tokenizer regression vs batched video-shape bug; different failures." + }, + { + "left": "issue:43295", + "right": "issue:44610", + "accept": false, + "reason": "Processor.tokenizer regression vs OmDet-Turbo 640px/224px mismatch; unrelated." + }, + { + "left": "issue:43572", + "right": "issue:44987", + "accept": false, + "reason": "StableLmConfig pad_token_idx regression vs loading physical-intelligence/fast failure; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 24, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:37428", + "issue:38175", + "issue:39692", + "issue:42490", + "issue:42915", + "issue:43262", + "issue:43278", + "issue:43295", + "issue:43334", + "issue:43450", + "issue:43493", + "issue:43525", + "issue:43526", + "issue:43550", + "issue:43572", + "issue:43575", + "issue:43653", + "issue:43696", + "issue:43824", + "issue:43844", + "issue:43856", + "issue:43873", + "issue:43950", + "issue:43957", + "issue:43975", + "issue:44112", + "issue:44442", + "issue:44466", + "issue:44514", + "issue:44521", + "issue:44554", + "issue:44561", + "issue:44898", + "issue:45127", + "issue:45198", + "issue:45200", + "issue:45325", + "issue:45356", + "issue:45381", + "issue:45412", + "issue:45520", + "issue:45759", + "issue:46170", + "issue:46178", + "issue:46192", + "issue:46209", + "issue:46234", + "issue:46285" + ], + "soft_pairs": [ + "issue:39692|issue:46192", + "issue:44554|issue:45356", + "issue:43295|issue:43873", + "issue:43572|issue:43957", + "issue:43950|issue:46285", + "issue:45381|issue:46209", + "issue:44898|issue:45412", + "issue:43550|issue:43844", + "issue:44466|issue:45127", + "issue:45200|issue:45325", + "issue:43450|issue:43575", + "issue:45520|issue:46178", + "issue:37428|issue:43957", + "issue:43334|issue:43525", + "issue:43824|issue:43975", + "issue:42490|issue:43696", + "issue:43278|issue:43856", + "issue:43526|issue:46192", + "issue:38175|issue:43493", + "issue:43653|issue:44112", + "issue:44442|issue:45198", + "issue:42915|issue:43824", + "issue:43975|issue:45520", + "issue:43295|issue:43493", + "issue:38175|issue:45412", + "issue:37428|issue:43824", + "issue:43262|issue:43450", + "issue:44561|issue:46234", + "issue:45759|issue:46285", + "issue:44514|issue:44521", + "issue:45520|issue:46170" + ], + "prepared_review_unit_hash": "f3f4333c3072b2be8eb996319fab9ad96d6585fc17f90fda77a36880fb298738", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "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 mostly a loose mix of unrelated Transformers bug reports; the closest subthemes are multimodal/chat-template regressions, config-attribute load failures, and tokenizer/import issues, but the soft pairs are still too different to merge.", + "confidence": 0.33, + "canonical_issue_reason": "Issue 44521 is the broadest and most central-looking report in the multimodal processor/chat-template subset, which is the closest recurring theme in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "44521 is the best representative issue because it is active, broadly phrased, and centered on a shared multimodal `apply_chat_template` code path rather than a very model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39692", + "right": "issue:46192", + "accept": false, + "reason": "SigLIP2 documentation/example errors and a `return_tensors`/`text_kwargs` behavior bug are different problems in different code paths." + }, + { + "left": "issue:44554", + "right": "issue:45356", + "accept": false, + "reason": "MPS attention correctness and Kimi-K2.5 tokenizer codec regression are unrelated." + }, + { + "left": "issue:43295", + "right": "issue:43873", + "accept": false, + "reason": "Processor.tokenizer regression and quantization/offloading behavior are distinct issues." + }, + { + "left": "issue:43572", + "right": "issue:43957", + "accept": false, + "reason": "Missing `pad_token_idx` in StableLmConfig is not the same as meta-device model loading failures." + }, + { + "left": "issue:43950", + "right": "issue:46285", + "accept": false, + "reason": "Non-persistent buffer corruption in `from_pretrained()` and CLIP text-model structure inconsistency are different regressions." + }, + { + "left": "issue:45381", + "right": "issue:46209", + "accept": false, + "reason": "Qwen2.5-VL video position-id bug and FP8 inference failure on B200 are unrelated." + }, + { + "left": "issue:44898", + "right": "issue:45412", + "accept": false, + "reason": "Perceiver interpolation failure and RT-DETR memory release behavior are different model/runtime problems." + }, + { + "left": "issue:43550", + "right": "issue:43844", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba and ZeRO-3 gradient growth are not the same bug." + }, + { + "left": "issue:44466", + "right": "issue:45127", + "accept": false, + "reason": "Serialization of tied weights and LoRA merge collapse with extended vocabulary are related by theme but not the same concrete change or code path." + }, + { + "left": "issue:45200", + "right": "issue:45325", + "accept": false, + "reason": "Gemma 4 token-type defaults and Qwen2.5-VL temporal position scaling are separate multimodal issues." + }, + { + "left": "issue:43450", + "right": "issue:43575", + "accept": false, + "reason": "Batched video-shape handling and tensor-parallel OOM during model load are unrelated." + }, + { + "left": "issue:45520", + "right": "issue:46178", + "accept": false, + "reason": "`flash_attn` import-key handling on Python 3.13 and a tensorflow_text backend mapping error are different import bugs." + }, + { + "left": "issue:37428", + "right": "issue:43957", + "accept": false, + "reason": "Missing flash-attention helper import and meta-device model loading breakage do not share the same underlying fix." + }, + { + "left": "issue:43334", + "right": "issue:43525", + "accept": false, + "reason": "Both mention missing `pad_token_id`, but they affect different config classes/model families and do not clearly indicate one shared bug." + }, + { + "left": "issue:43824", + "right": "issue:43975", + "accept": false, + "reason": "A missing Qwen2.5-VL export and a DeepSeek detokenization regression are unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43696", + "accept": false, + "reason": "Local-path import warning and GPT-oss OOM are different classes of failure." + }, + { + "left": "issue:43278", + "right": "issue:43856", + "accept": false, + "reason": "Embedding dtype drift and Qwen3 MoE memory inefficiency are separate training/runtime issues." + }, + { + "left": "issue:43526", + "right": "issue:46192", + "accept": false, + "reason": "BeitImageProcessorFast label reduction and ignored `return_tensors` are unrelated processor behaviors." + }, + { + "left": "issue:38175", + "right": "issue:43493", + "accept": false, + "reason": "Both are SigLIP2-related, but one reports zero probabilities and the other an HF-vs-JAX discrepancy; not enough evidence they are the same bug." + }, + { + "left": "issue:43653", + "right": "issue:44112", + "accept": false, + "reason": "BigBird tokenizer special-token registration and GraniteSpeech CI device-override test failure are unrelated." + }, + { + "left": "issue:44442", + "right": "issue:45198", + "accept": false, + "reason": "FastSpeech2Conformer tokenizer loading and Wav2Vec2 save/tokenization failure are different tokenizer issues." + }, + { + "left": "issue:42915", + "right": "issue:43824", + "accept": false, + "reason": "Qwen3MoE FP8 failure and Qwen2.5-VL import error are unrelated." + }, + { + "left": "issue:43975", + "right": "issue:45520", + "accept": false, + "reason": "DeepSeek detokenization regression and `flash_attn` import-key failure are different code paths." + }, + { + "left": "issue:43295", + "right": "issue:43493", + "accept": false, + "reason": "Custom model processor.tokenizer regression and SigLIP2 implementation discrepancy are not the same issue." + }, + { + "left": "issue:38175", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 zero-probabilities and RT-DETR memory leak are unrelated." + }, + { + "left": "issue:37428", + "right": "issue:43824", + "accept": false, + "reason": "Importing `_flash_supports_window_size` and importing Qwen2_5_VLForConditionalGeneration are different missing-symbol problems." + }, + { + "left": "issue:43262", + "right": "issue:43450", + "accept": false, + "reason": "Audio chat-template sampling-rate default and batched video shape handling are unrelated processor bugs." + }, + { + "left": "issue:44561", + "right": "issue:46234", + "accept": false, + "reason": "Removal of `is_torch_fx_available` and missing `is_falcon_mamba_ssm_available` are different missing-utility regressions." + }, + { + "left": "issue:45759", + "right": "issue:46285", + "accept": false, + "reason": "Composite Qwen config unwrapping in `from_config` and CLIP text-model structural inconsistency are not the same fix." + }, + { + "left": "issue:44514", + "right": "issue:44521", + "accept": false, + "reason": "Both are about `apply_chat_template` on multimodal inputs, but one is a batched-input crash and the other produces zero assistant masks; the concrete failure modes differ too much to merge." + }, + { + "left": "issue:45520", + "right": "issue:46170", + "accept": false, + "reason": "`flash_attn` import handling and Windows/ROCm torch.distributed dependency issues are unrelated import problems." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 25, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:29942", + "issue:32090", + "issue:37428", + "issue:39692", + "issue:41720", + "issue:43278", + "issue:43335", + "issue:43388", + "issue:43425", + "issue:43504", + "issue:43526", + "issue:43550", + "issue:43606", + "issue:43611", + "issue:43653", + "issue:43819", + "issue:43825", + "issue:43827", + "issue:43901", + "issue:43931", + "issue:44112", + "issue:44206", + "issue:44351", + "issue:44448", + "issue:44493", + "issue:44610", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44857", + "issue:45083", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45290", + "issue:45310", + "issue:45381", + "issue:45459", + "issue:45478", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45823", + "issue:45859", + "issue:46209", + "issue:46234" + ], + "soft_pairs": [ + "issue:41720|issue:46209", + "issue:44610|issue:44857", + "issue:43819|issue:44112", + "issue:43827|issue:43901", + "issue:43819|issue:45083", + "issue:44206|issue:45584", + "issue:43335|issue:43550", + "issue:44857|issue:45593", + "issue:43606|issue:45083", + "issue:37428|issue:43425", + "issue:44792|issue:45563", + "issue:45127|issue:45245", + "issue:44448|issue:44743", + "issue:45200|issue:45588", + "issue:43335|issue:43653", + "issue:43611|issue:43931", + "issue:45290|issue:45381", + "issue:44855|issue:45083", + "issue:43550|issue:44112", + "issue:43819|issue:44493", + "issue:44206|issue:45823", + "issue:37428|issue:44351", + "issue:29942|issue:32090", + "issue:43335|issue:43504", + "issue:45588|issue:45859", + "issue:43278|issue:43825", + "issue:45459|issue:46234", + "issue:39692|issue:43526", + "issue:43335|issue:45083", + "issue:45310|issue:45478", + "issue:43388|issue:43526", + "issue:39692|issue:44493" + ], + "prepared_review_unit_hash": "01d532bf2363c47fb5a131c171f12558d469f0a5484391f7a89993670a7d0d72", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 32, + "serialized_chars": 36859, + "estimated_input_tokens": 9215, + "estimated_eval_tokens": 18686 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "Mostly a heterogeneous set of unrelated bug reports. The only clear duplicate pair is the Qwen3.5 Moe `from_pretrained` regression; the rest are different code paths or different models/features.", + "confidence": 0.94, + "canonical_issue_reason": "Pick issue:45310 as the canonical issue for the Qwen3.5 Moe `from_pretrained` regression: it is the earlier, fuller report and issue:45478 is a near-exact duplicate.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45310 is the best representative only for the duplicate Qwen3.5 Moe bug; otherwise this cluster is not a single coherent issue family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41720", + "right": "issue:46209", + "accept": false, + "reason": "Different failures: Qwen3 auto device mapping CUDA assert vs FP8 inference on B200. Same hardware theme, but not the same bug." + }, + { + "left": "issue:44610", + "right": "issue:44857", + "accept": false, + "reason": "Different models and code paths: OmDet processor size mismatch vs LwDetrImageLoss AMP crash." + }, + { + "left": "issue:43819", + "right": "issue:44112", + "accept": false, + "reason": "DAC latent/forward mismatch is unrelated to GraniteSpeech stale device override CI failure." + }, + { + "left": "issue:43827", + "right": "issue:43901", + "accept": false, + "reason": "Both mention docs/pipeline behavior, but one is v5 pipeline removal guidance and the other is TextClassificationPipeline `return_all_scores` docs." + }, + { + "left": "issue:43819", + "right": "issue:45083", + "accept": false, + "reason": "DAC STE mismatch is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:44206", + "right": "issue:45584", + "accept": false, + "reason": "LasrFeatureExtractor center-arg regression is unrelated to Whisper empty transcription generation failure." + }, + { + "left": "issue:43335", + "right": "issue:43550", + "accept": false, + "reason": "SwitchTransformers config sparse-layer construction and Bamba torch.compile SDPA failure are different model bugs." + }, + { + "left": "issue:44857", + "right": "issue:45593", + "accept": false, + "reason": "LwDetrImageLoss AMP crash is unrelated to D-FINE auxiliary-loss behavior when denoising is off." + }, + { + "left": "issue:43606", + "right": "issue:45083", + "accept": false, + "reason": "CPU offload device mismatch in bark-small is unrelated to qwen3_omni_moe output-length helper behavior." + }, + { + "left": "issue:37428", + "right": "issue:43425", + "accept": false, + "reason": "Both are version/import compatibility reports, but one is a missing flash-attention symbol and the other is a Torch 2.10 compatibility issue." + }, + { + "left": "issue:44792", + "right": "issue:45563", + "accept": false, + "reason": "Janus image-generation test failure and paged-generate stale warning are different failures with different triggers." + }, + { + "left": "issue:45127", + "right": "issue:45245", + "accept": false, + "reason": "LoRA merge collapse with extended vocab is unrelated to the category-count limit error." + }, + { + "left": "issue:44448", + "right": "issue:44743", + "accept": false, + "reason": "Pegasus v4/v5 output differences are unrelated to Qwen3 modular recurrent-state reset logic." + }, + { + "left": "issue:45200", + "right": "issue:45588", + "accept": false, + "reason": "Gemma 4 `mm_token_type_ids` defaulting issue is unrelated to flash_attention sink-less `s_aux=None` crash." + }, + { + "left": "issue:43335", + "right": "issue:43653", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug and BigBirdTokenizer special-token registration bug are unrelated." + }, + { + "left": "issue:43611", + "right": "issue:43931", + "accept": false, + "reason": "General `base_model_prefix` loading breakage is unrelated to Qwen3-VL-30B-A3B-Instruct weight-shape mismatch." + }, + { + "left": "issue:45290", + "right": "issue:45381", + "accept": false, + "reason": "Chat template tool-call crash is unrelated to qwen2.5-vl video `vision_position_ids` issue." + }, + { + "left": "issue:44855", + "right": "issue:45083", + "accept": false, + "reason": "Python 3.13 `torch.jit.script` import failure is unrelated to qwen3_omni_moe feature-length helper behavior." + }, + { + "left": "issue:43550", + "right": "issue:44112", + "accept": false, + "reason": "Bamba torch.compile SDPA failure is unrelated to GraniteSpeech CI device-override test state." + }, + { + "left": "issue:43819", + "right": "issue:44493", + "accept": false, + "reason": "DAC latent mismatch is unrelated to unexpected position-id keys across models." + }, + { + "left": "issue:44206", + "right": "issue:45823", + "accept": false, + "reason": "LasrFeatureExtractor center-arg crash is unrelated to Gemma4 PLE device-mismatch forward failure." + }, + { + "left": "issue:37428", + "right": "issue:44351", + "accept": false, + "reason": "Different missing imports: `_flash_supports_window_size` vs `HybridCache`." + }, + { + "left": "issue:29942", + "right": "issue:32090", + "accept": false, + "reason": "Flash Attention 2 test failures are unrelated to Trainer `_gpu_broadcast_one` NoneType errors." + }, + { + "left": "issue:43335", + "right": "issue:43504", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction bug is unrelated to Beit pretrained preset legacy-field loading." + }, + { + "left": "issue:45588", + "right": "issue:45859", + "accept": false, + "reason": "Flash attention `s_aux=None` crash is unrelated to Qwen3_5Moe text rotary embedding CPU offload compatibility." + }, + { + "left": "issue:43278", + "right": "issue:43825", + "accept": false, + "reason": "Embedding dtype mismatch in eval is unrelated to the pipeline translation-support error message regression." + }, + { + "left": "issue:45459", + "right": "issue:46234", + "accept": false, + "reason": "Tokenizer protobuf error handling is unrelated to missing `is_falcon_mamba_ssm_available` import helper." + }, + { + "left": "issue:39692", + "right": "issue:43526", + "accept": false, + "reason": "SigLIP2 docs/model-processor mismatch is unrelated to BeitImageProcessorFast `reduce_labels` returning one label." + }, + { + "left": "issue:43335", + "right": "issue:45083", + "accept": false, + "reason": "SwitchTransformers sparse-layer bug and qwen3_omni_moe feature-length helper bug are unrelated." + }, + { + "left": "issue:45310", + "right": "issue:45478", + "accept": true, + "reason": "Same underlying bug: identical Qwen3.5 Moe `from_pretrained` failure on transformers>=5.4.0; 45478 is a duplicate of 45310." + }, + { + "left": "issue:43388", + "right": "issue:43526", + "accept": false, + "reason": "`gather_for_metrics` tuple-label truncation is unrelated to BeitImageProcessorFast label reduction." + }, + { + "left": "issue:39692", + "right": "issue:44493", + "accept": false, + "reason": "SigLIP2 doc/quantization example errors are unrelated to unexpected position-id keys." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The verdicts are conservative and grounded in the packet. The only accepted duplicate pair, issue:45310 and issue:45478, is strongly supported by identical titles and matching regression scope. The rest of the rejections are reasonable distinctions based on different models, code paths, or failure modes, and the summary does not 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": 18, + "review_unit_index": 26, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28218", + "issue:29127", + "issue:29942", + "issue:32090", + "issue:34689", + "issue:35141", + "issue:38175", + "issue:40444", + "issue:42490", + "issue:43278", + "issue:43335", + "issue:43381", + "issue:43412", + "issue:43526", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43611", + "issue:43701", + "issue:43720", + "issue:43746", + "issue:43854", + "issue:43927", + "issue:44112", + "issue:44360", + "issue:44448", + "issue:44493", + "issue:44561", + "issue:44568", + "issue:44779", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45083", + "issue:45198", + "issue:45229", + "issue:45372", + "issue:45491", + "issue:45563", + "issue:45588", + "issue:45593", + "issue:45698", + "issue:45803", + "issue:45823", + "issue:45920", + "issue:46192", + "issue:46209", + "issue:46285" + ], + "soft_pairs": [ + "issue:28218|issue:35141", + "issue:43720|issue:44112", + "issue:44448|issue:44779", + "issue:43335|issue:44112", + "issue:43335|issue:45593", + "issue:42490|issue:43854", + "issue:43606|issue:44857", + "issue:45920|issue:46192", + "issue:38175|issue:44493", + "issue:44360|issue:44561", + "issue:44857|issue:45072", + "issue:44977|issue:45229", + "issue:44448|issue:44977", + "issue:34689|issue:35141", + "issue:43701|issue:45083", + "issue:29127|issue:32090", + "issue:43550|issue:45083", + "issue:43927|issue:45698", + "issue:42490|issue:43575", + "issue:40444|issue:43526", + "issue:29942|issue:35141", + "issue:44561|issue:44779", + "issue:44977|issue:45563", + "issue:44568|issue:45491", + "issue:44857|issue:45588", + "issue:45372|issue:45588", + "issue:43746|issue:46209", + "issue:43412|issue:45588", + "issue:45198|issue:45803", + "issue:43278|issue:43381", + "issue:43611|issue:46285", + "issue:45588|issue:45823" + ], + "prepared_review_unit_hash": "44b79b326a0a7a0dfae1253b820405d02b53643270f237f5420a7a0a8d2aab65", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 37451, + "estimated_input_tokens": 9363, + "estimated_eval_tokens": 18982 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers issues, with a loose theme around v5-era tokenizer/loading regressions. None of the soft pairs are close enough to treat as the same underlying bug/change. The broadest representative issue is the multi-model tokenizer regression report.", + "confidence": 0.43, + "canonical_issue_reason": "issue:45920 is the broadest and most representative issue here: it aggregates a v5 tokenizer regression across multiple model families, which matches the cluster\u2019s main recurring theme better than the narrower single-model reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45920 is the best issue to anchor the cluster because it is broad, current, and captures the dominant tokenizer-regression pattern seen across several related items.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28218", + "right": "issue:35141", + "accept": false, + "reason": "Different bug classes: tokenizer spacing after added tokens vs embedding reinitialization after resize; unrelated code paths." + }, + { + "left": "issue:43720", + "right": "issue:44112", + "accept": false, + "reason": "Packed-weight loading failure and a stale CI device-override test are unrelated." + }, + { + "left": "issue:44448", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions, but they affect different models and failure modes; not the same concrete bug." + }, + { + "left": "issue:43335", + "right": "issue:44112", + "accept": false, + "reason": "Config-layer construction bug vs GraniteSpeech CI test failure; no shared underlying defect." + }, + { + "left": "issue:43335", + "right": "issue:45593", + "accept": false, + "reason": "Sparse layer creation and missing auxiliary losses are unrelated model behaviors." + }, + { + "left": "issue:42490", + "right": "issue:43854", + "accept": false, + "reason": "Local-path trailing-slash warning and GLM-4.7-Flash loading failure are different issues." + }, + { + "left": "issue:43606", + "right": "issue:44857", + "accept": false, + "reason": "CPU offload device mismatch and AMP float16 loss crash are different runtime problems." + }, + { + "left": "issue:45920", + "right": "issue:46192", + "accept": false, + "reason": "Tokenizer ID regression across many models vs silently ignored return_tensors handling; related area, but not the same bug." + }, + { + "left": "issue:38175", + "right": "issue:44493", + "accept": false, + "reason": "Zero probabilities in SigLIP2 and unexpected position-id keys are different symptoms and code paths." + }, + { + "left": "issue:44360", + "right": "issue:44561", + "accept": false, + "reason": "DSA indexer activation issue vs trust_remote_code breakage from removed utility; unrelated." + }, + { + "left": "issue:44857", + "right": "issue:45072", + "accept": false, + "reason": "Different crashes in different models and dtype regimes; not mergeable as one fix." + }, + { + "left": "issue:44977", + "right": "issue:45229", + "accept": false, + "reason": "Flash-attention generation bug vs multi-GPU CUDA OOM; unrelated failure modes." + }, + { + "left": "issue:44448", + "right": "issue:44977", + "accept": false, + "reason": "Different models and behaviors: Pegasus output drift vs Qwen3.5 flash-attention generation issue." + }, + { + "left": "issue:34689", + "right": "issue:35141", + "accept": false, + "reason": "Model-loading breakage for Llama vision vs embedding reinit after resize; separate defects." + }, + { + "left": "issue:43701", + "right": "issue:45083", + "accept": false, + "reason": "Checkpoint key mismatch and a feature-length helper bug are unrelated." + }, + { + "left": "issue:29127", + "right": "issue:32090", + "accept": false, + "reason": "LayoutLMV3 error messaging vs Trainer GPU broadcast type error; not the same bug." + }, + { + "left": "issue:43550", + "right": "issue:45083", + "accept": false, + "reason": "torch.compile/SDPA failure in Bamba vs feature-length helper behavior in Qwen3 Omni MoE." + }, + { + "left": "issue:43927", + "right": "issue:45698", + "accept": false, + "reason": "Both involve save/load, but one is config token IDs and the other is wrong custom module resolution; different root causes." + }, + { + "left": "issue:42490", + "right": "issue:43575", + "accept": false, + "reason": "Local-path import warning and tensor-parallel OOM are unrelated." + }, + { + "left": "issue:40444", + "right": "issue:43526", + "accept": false, + "reason": "Qwen2.5-VL iterable dataset failure and BEiT label reduction bug are unrelated." + }, + { + "left": "issue:29942", + "right": "issue:35141", + "accept": false, + "reason": "Flash Attention 2 test failures and output embedding reinitialization are unrelated." + }, + { + "left": "issue:44561", + "right": "issue:44779", + "accept": false, + "reason": "Removal of is_torch_fx_available and DeepSeek tokenizer regression do not share the same code path." + }, + { + "left": "issue:44977", + "right": "issue:45563", + "accept": false, + "reason": "Flash-attention generation bug and a stale num_return_sequences warning are distinct issues." + }, + { + "left": "issue:44568", + "right": "issue:45491", + "accept": false, + "reason": "Tokenizer special-token handling and Gemma3 NaN embeddings are unrelated." + }, + { + "left": "issue:44857", + "right": "issue:45588", + "accept": false, + "reason": "Different flash-attention-related crashes with different triggers and models." + }, + { + "left": "issue:45372", + "right": "issue:45588", + "accept": false, + "reason": "Gemma 4 processor import failure and sink-less flash_attention AttributeError are separate bugs." + }, + { + "left": "issue:43746", + "right": "issue:46209", + "accept": false, + "reason": "PEFT adapter local-checkpoint load failure and FP8 inference on B200 are unrelated." + }, + { + "left": "issue:43412", + "right": "issue:45588", + "accept": false, + "reason": "Executorch export guard/import support issue vs flash_attention sink-less crash are different problems." + }, + { + "left": "issue:45198", + "right": "issue:45803", + "accept": false, + "reason": "Wav2Vec2 save/tokenization failure and bare-except swallowing errors in Fuyu are unrelated." + }, + { + "left": "issue:43278", + "right": "issue:43381", + "accept": false, + "reason": "Embedding dtype drift and eval-mode gradient checkpointing restriction are different concerns." + }, + { + "left": "issue:43611", + "right": "issue:46285", + "accept": false, + "reason": "Both concern model-loading structure changes, but they target different classes and concrete breakages; too broad to merge." + }, + { + "left": "issue:45588", + "right": "issue:45823", + "accept": false, + "reason": "Flash-attention sink-less crash and Gemma4 PLE device mismatch are different runtime failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 27, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:10000", + "issue:15354", + "issue:25251", + "issue:29127", + "issue:29942", + "issue:30064", + "issue:32090", + "issue:33357", + "issue:34567", + "issue:36010", + "issue:37428", + "issue:39692", + "issue:42490", + "issue:42915", + "issue:42994", + "issue:43065", + "issue:43066", + "issue:43278", + "issue:43575", + "issue:43611", + "issue:43653", + "issue:43873", + "issue:43976", + "issue:43994", + "issue:44186", + "issue:44206", + "issue:44265", + "issue:44361", + "issue:44448", + "issue:44462", + "issue:44466", + "issue:44479", + "issue:44734", + "issue:44743", + "issue:44871", + "issue:44977", + "issue:45198", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45459", + "issue:45563", + "issue:45712", + "issue:46121" + ], + "soft_pairs": [ + "issue:44448|issue:44466", + "issue:36010|issue:37428", + "issue:25251|issue:32090", + "issue:43653|issue:44743", + "issue:45245|issue:45563", + "issue:44186|issue:45198", + "issue:45459|issue:45712", + "issue:43065|issue:45412", + "issue:44361|issue:45198", + "issue:43611|issue:46121", + "issue:33357|issue:39692", + "issue:44871|issue:44977", + "issue:29127|issue:34567", + "issue:45372|issue:45459", + "issue:44206|issue:44479", + "issue:29942|issue:30064", + "issue:42915|issue:42994", + "issue:43976|issue:45440", + "issue:43994|issue:45412", + "issue:43278|issue:43575", + "issue:44265|issue:45198", + "issue:43066|issue:44462", + "issue:10000|issue:15354", + "issue:42490|issue:43873", + "issue:43873|issue:45229", + "issue:44734|issue:45406" + ], + "prepared_review_unit_hash": "733a89599c1ec8d6fef3b551d36a480cef3746312423f7d381532a03f7314d81", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 35040, + "estimated_input_tokens": 8760, + "estimated_eval_tokens": 17776 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All proposed soft edges look like unrelated bugs or regressions rather than true duplicates. The cluster is heterogeneous, so there is no single safe canonical duplicate target; no PRs are present.", + "confidence": 0.96, + "canonical_issue_reason": "No canonical issue: the items span unrelated subsystems and failure modes (tokenizers, generation, export, vision, training, quantization, docs).", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44462 is the clearest standalone bug in the set: it names a specific loader regression, has a concrete failure mode, and is broadly user-facing.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44448", + "right": "issue:44466", + "accept": false, + "reason": "Different bugs: one is generation output changes between v4/v5, the other is serialization of lm_head.weight/tied weights." + }, + { + "left": "issue:36010", + "right": "issue:37428", + "accept": false, + "reason": "Both are ImportErrors, but for different missing symbols in different modules with different fixes." + }, + { + "left": "issue:25251", + "right": "issue:32090", + "accept": false, + "reason": "Pipeline top_k nesting bug vs Trainer NoneType broadcast error; unrelated code paths." + }, + { + "left": "issue:43653", + "right": "issue:44743", + "accept": false, + "reason": "BigBird tokenizer special-token registration vs Qwen recurrent-state reset with cache; not the same issue." + }, + { + "left": "issue:45245", + "right": "issue:45563", + "accept": false, + "reason": "Category-count RuntimeError and stale warning text are unrelated." + }, + { + "left": "issue:44186", + "right": "issue:45198", + "accept": false, + "reason": "LayoutLMv2 NER/batching crash vs Wav2Vec2 save/tokenization failure; different models and failures." + }, + { + "left": "issue:45459", + "right": "issue:45712", + "accept": false, + "reason": "One hides tokenizer errors without protobuf; the other is leftover dummy classes leaking into API surfaces." + }, + { + "left": "issue:43065", + "right": "issue:45412", + "accept": false, + "reason": "Dummy conv in Sam3PixelDecoder vs RT-DETR memory not released; no shared root cause." + }, + { + "left": "issue:44361", + "right": "issue:45198", + "accept": false, + "reason": "MLukeTokenizer AttributeError vs Wav2Vec2 save_pretrained/tokenization failure; unrelated." + }, + { + "left": "issue:43611", + "right": "issue:46121", + "accept": false, + "reason": "base_model_prefix loading regression vs rope validation type handling; separate areas." + }, + { + "left": "issue:33357", + "right": "issue:39692", + "accept": false, + "reason": "MacOS bus error with a community CLIP model vs SigLIP2 doc example errors; different problems." + }, + { + "left": "issue:44871", + "right": "issue:44977", + "accept": false, + "reason": "eos_token_id mismatch is unrelated to flash-attention generation regression." + }, + { + "left": "issue:29127", + "right": "issue:34567", + "accept": false, + "reason": "LayoutLMv3 error-message clarity issue vs TrainerState counter not updating; not duplicates." + }, + { + "left": "issue:45372", + "right": "issue:45459", + "accept": false, + "reason": "Gemma 4 processor loading ImportError vs hidden tokenizer errors behind protobuf guard; distinct bugs." + }, + { + "left": "issue:44206", + "right": "issue:44479", + "accept": false, + "reason": "Feature extractor center-arg regression vs video-input regression for Qwen variants; different code paths." + }, + { + "left": "issue:29942", + "right": "issue:30064", + "accept": false, + "reason": "Flash Attention 2 test failures vs void segmentation map processing; unrelated." + }, + { + "left": "issue:42915", + "right": "issue:42994", + "accept": false, + "reason": "Qwen3Moe FP8 config failure vs quantized model saving failure; separate quantization issues." + }, + { + "left": "issue:43976", + "right": "issue:45440", + "accept": false, + "reason": "Python version compatibility regression vs DeepseekV3MoE divergence from remote implementation." + }, + { + "left": "issue:43994", + "right": "issue:45412", + "accept": false, + "reason": "SigLIP2 wrong outputs vs RT-DETR memory leak; different subsystems." + }, + { + "left": "issue:43278", + "right": "issue:43575", + "accept": false, + "reason": "dtype change during evaluate vs tensor-parallel OOM; not the same bug." + }, + { + "left": "issue:44265", + "right": "issue:45198", + "accept": false, + "reason": "torch.export failure on torch_compilable_check vs Wav2Vec2 save/tokenization failure; unrelated." + }, + { + "left": "issue:43066", + "right": "issue:44462", + "accept": false, + "reason": "Wrong tokenizer decoder type in v5 vs AutoTokenizer ignoring tokenizer.json; both tokenizer-related but different concrete faults." + }, + { + "left": "issue:10000", + "right": "issue:15354", + "accept": false, + "reason": "German DistilBertModel issue vs GeneratorExp unsupported in torch.jit.script; unrelated." + }, + { + "left": "issue:42490", + "right": "issue:43873", + "accept": false, + "reason": "Local-path import warning with trailing slash vs quantization offloading not working; distinct loading issues." + }, + { + "left": "issue:43873", + "right": "issue:45229", + "accept": false, + "reason": "Offloading/quantization behavior vs Gemma4 multi-GPU OOM; different causes and fixes." + }, + { + "left": "issue:44734", + "right": "issue:45406", + "accept": false, + "reason": "KV-cache continuation indexing crash in serve vs Gemma4Processor missing _tokenizer; unrelated runtime failures." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 28, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:29127", + "issue:29942", + "issue:32090", + "issue:33357", + "issue:35141", + "issue:36010", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43278", + "issue:43329", + "issue:43334", + "issue:43381", + "issue:43421", + "issue:43526", + "issue:43531", + "issue:43575", + "issue:43646", + "issue:43653", + "issue:43701", + "issue:43723", + "issue:43756", + "issue:43761", + "issue:43824", + "issue:43994", + "issue:44077", + "issue:44186", + "issue:44279", + "issue:44387", + "issue:44442", + "issue:44554", + "issue:44610", + "issue:44743", + "issue:44811", + "issue:44857", + "issue:44977", + "issue:45072", + "issue:45103", + "issue:45229", + "issue:45245", + "issue:45372", + "issue:45406", + "issue:45412", + "issue:45440", + "issue:45491", + "issue:45593", + "issue:45834", + "issue:45859" + ], + "soft_pairs": [ + "issue:43421|issue:45491", + "issue:43381|issue:43701", + "issue:43653|issue:44442", + "issue:43065|issue:43994", + "issue:44610|issue:45412", + "issue:41720|issue:45229", + "issue:32090|issue:33357", + "issue:43756|issue:45440", + "issue:43278|issue:43329", + "issue:45372|issue:45406", + "issue:29942|issue:36010", + "issue:43526|issue:45834", + "issue:43723|issue:44554", + "issue:43761|issue:45859", + "issue:45440|issue:45593", + "issue:45103|issue:45372", + "issue:43526|issue:44186", + "issue:43575|issue:43701", + "issue:42490|issue:43381", + "issue:43575|issue:44387", + "issue:43526|issue:44857", + "issue:43334|issue:43531", + "issue:44977|issue:45245", + "issue:43824|issue:44279", + "issue:44442|issue:45072", + "issue:29127|issue:35141", + "issue:43646|issue:44077", + "issue:44743|issue:44811" + ], + "prepared_review_unit_hash": "077c0a957c6436a70d041ed7eec27048cbcc43c21d6fc74199282f069afc89b8", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36178, + "estimated_input_tokens": 9045, + "estimated_eval_tokens": 18346 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These are mostly unrelated bug reports across different models, loaders, and runtime paths; the soft-similarity links look superficial, so every candidate edge should be rejected.", + "confidence": 0.95, + "canonical_issue_reason": "No true canonical duplicate emerges from this set; if forced to anchor the cluster, issue:43526 is the most repeated and narrowly scoped report, but it is not the same bug as the others.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue:43526 is the safest representative only because it appears in multiple soft-similarity candidates, but the overall set is too heterogeneous to treat as one duplicate cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43421", + "right": "issue:45491", + "accept": false, + "reason": "Different subsystems: runtime tokenizer post-processor updates vs Gemma3 sliding-window NaNs on mixed-length GPU batches." + }, + { + "left": "issue:43381", + "right": "issue:43701", + "accept": false, + "reason": "Unrelated failures: gradient-checkpointing behavior in eval mode vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43653", + "right": "issue:44442", + "accept": false, + "reason": "Different tokenizer bugs: BigBird special-token registration vs AutoTokenizer failing on FastSpeech2ConformerTokenizer." + }, + { + "left": "issue:43065", + "right": "issue:43994", + "accept": false, + "reason": "Different models and symptoms: a dummy Conv2d in Sam3PixelDecoder vs bad SigLIP2 inference outputs." + }, + { + "left": "issue:44610", + "right": "issue:45412", + "accept": false, + "reason": "Processor input-size mismatch is unrelated to RT-DETR memory not being released after deletion." + }, + { + "left": "issue:41720", + "right": "issue:45229", + "accept": false, + "reason": "Different failure modes and models: Qwen3 auto-device-map cuda assert vs Gemma4 multi-GPU OOM." + }, + { + "left": "issue:32090", + "right": "issue:33357", + "accept": false, + "reason": "Trainer broadcast NoneType error is unrelated to the MacOS bus error on a CLIP community model." + }, + { + "left": "issue:43756", + "right": "issue:45440", + "accept": false, + "reason": "Both involve model parity, but they are different architectures and concrete bugs: Smollm3 RoPE-layer truncation vs DeepseekV3MoE divergence." + }, + { + "left": "issue:43278", + "right": "issue:43329", + "accept": false, + "reason": "Different code paths: dtype drift between train/eval embedding layers vs undefined video multimodal token helpers." + }, + { + "left": "issue:45372", + "right": "issue:45406", + "accept": false, + "reason": "Gemma4 issues, but not the same bug: missing ReasoningEffort import vs missing _tokenizer attribute in serve." + }, + { + "left": "issue:29942", + "right": "issue:36010", + "accept": false, + "reason": "Flash Attention 2 test failures are not the same as the GenerationMixin import breakage." + }, + { + "left": "issue:43526", + "right": "issue:45834", + "accept": false, + "reason": "BeitImageProcessorFast label reduction bug is unrelated to Kosmos2.5 long-OCR index errors." + }, + { + "left": "issue:43723", + "right": "issue:44554", + "accept": false, + "reason": "Tokenizer loading regression and MPS attention correctness bug are different issues." + }, + { + "left": "issue:43761", + "right": "issue:45859", + "accept": false, + "reason": "CLIPVision hidden_states regression is unrelated to Qwen3_5Moe CPU-offload incompatibility." + }, + { + "left": "issue:45440", + "right": "issue:45593", + "accept": false, + "reason": "DeepSeek MoE implementation divergence is unrelated to D-FINE auxiliary-loss handling." + }, + { + "left": "issue:45103", + "right": "issue:45372", + "accept": false, + "reason": "Auto-docstring annotation parsing crash is unrelated to the Gemma4 ReasoningEffort import problem." + }, + { + "left": "issue:43526", + "right": "issue:44186", + "accept": false, + "reason": "Different processors and failure modes: BeitImageProcessorFast label handling vs LayoutLMv2Tokenizer NER/padding crashes." + }, + { + "left": "issue:43575", + "right": "issue:43701", + "accept": false, + "reason": "Model load OOM is unrelated to a resume_from_checkpoint key mismatch." + }, + { + "left": "issue:42490", + "right": "issue:43381", + "accept": false, + "reason": "Import warning on trailing-slash local paths is unrelated to gradient checkpointing in eval mode." + }, + { + "left": "issue:43575", + "right": "issue:44387", + "accept": false, + "reason": "Both mention OOM, but one is tensor-parallel model loading and the other is int4 quantization memory reservation." + }, + { + "left": "issue:43526", + "right": "issue:44857", + "accept": false, + "reason": "Label reduction in BEiT image processing is unrelated to LwDetrImageLoss AMP/CUDA crashes." + }, + { + "left": "issue:43334", + "right": "issue:43531", + "accept": false, + "reason": "Qwen3-VL pad_token_id loading failure and Qwen3-MoE sliding-window behavior are different bugs." + }, + { + "left": "issue:44977", + "right": "issue:45245", + "accept": false, + "reason": "Flash-attention generation bug is unrelated to the categories-cardinality runtime error." + }, + { + "left": "issue:43824", + "right": "issue:44279", + "accept": false, + "reason": "Specific Qwen2.5-VL import failure is not the same as a general dependency issue with transformers." + }, + { + "left": "issue:44442", + "right": "issue:45072", + "accept": false, + "reason": "AutoTokenizer loading failure and dtype mismatches in inference are different problems." + }, + { + "left": "issue:29127", + "right": "issue:35141", + "accept": false, + "reason": "LayoutLMv3 error messaging and token-embedding reinitialization in post_init are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44077", + "accept": false, + "reason": "General Transformers 5.0 custom-init breakage is not the same as the patchtsmixer post_init policy issue." + }, + { + "left": "issue:44743", + "right": "issue:44811", + "accept": false, + "reason": "Qwen3.5 recurrent-state reset and Whisper batch_decode skip_special_tokens handling are unrelated bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 29, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28218", + "issue:32090", + "issue:33290", + "issue:33357", + "issue:34567", + "issue:34689", + "issue:36010", + "issue:38175", + "issue:42175", + "issue:42907", + "issue:42915", + "issue:43262", + "issue:43316", + "issue:43381", + "issue:43452", + "issue:43493", + "issue:43525", + "issue:43550", + "issue:43611", + "issue:43643", + "issue:43720", + "issue:43761", + "issue:43827", + "issue:43873", + "issue:43931", + "issue:44062", + "issue:44188", + "issue:44206", + "issue:44442", + "issue:44464", + "issue:44479", + "issue:44743", + "issue:44871", + "issue:44898", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45216", + "issue:45290", + "issue:45440", + "issue:45491", + "issue:45584", + "issue:45588", + "issue:45698", + "issue:45759", + "issue:45803", + "issue:45907", + "issue:46234" + ], + "soft_pairs": [ + "issue:42915|issue:43931", + "issue:43262|issue:44206", + "issue:44977|issue:45584", + "issue:43452|issue:45588", + "issue:33357|issue:38175", + "issue:44062|issue:45907", + "issue:44464|issue:45491", + "issue:28218|issue:32090", + "issue:33290|issue:34567", + "issue:44442|issue:44898", + "issue:43381|issue:43873", + "issue:43316|issue:43525", + "issue:44964|issue:45440", + "issue:34689|issue:43611", + "issue:32090|issue:33290", + "issue:43720|issue:44442", + "issue:44442|issue:45803", + "issue:44479|issue:45290", + "issue:34689|issue:36010", + "issue:43931|issue:45216", + "issue:43493|issue:43827", + "issue:42175|issue:46234", + "issue:43550|issue:44743", + "issue:43873|issue:44871", + "issue:42907|issue:45698", + "issue:43643|issue:44913", + "issue:43316|issue:45759", + "issue:43761|issue:44188" + ], + "prepared_review_unit_hash": "fcef9c61ab0b0c881e56dddf0c4a6e31e14e30239edacf5d49ce0dfeb6a7afc5", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36261, + "estimated_input_tokens": 9066, + "estimated_eval_tokens": 18388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is not a true duplicate set: the issues span unrelated regressions and feature bugs across tokenization, model loading, quantization, training, audio, docs, and backend utilities. All soft links look like superficial thematic similarity rather than the same underlying defect or change.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42915", + "right": "issue:43931", + "accept": false, + "reason": "Different failures: FineGrainedFP8Config on Qwen3Moe vs shape-mismatch loading for Qwen3-VL-30B; not the same code path." + }, + { + "left": "issue:43262", + "right": "issue:44206", + "accept": false, + "reason": "Audio processor chat-template sampling-rate bug vs LasrFeatureExtractor unsupported-center crash; unrelated components." + }, + { + "left": "issue:44977", + "right": "issue:45584", + "accept": false, + "reason": "Qwen3.5 flash-attention generation issue vs Whisper empty-transcription after special-token alignment; distinct model paths." + }, + { + "left": "issue:43452", + "right": "issue:45588", + "accept": false, + "reason": "gguf_file loading breakage vs flash_attention sink-less s_aux=None crash; different subsystems and failure modes." + }, + { + "left": "issue:33357", + "right": "issue:38175", + "accept": false, + "reason": "MacOS bus error on CLIP load vs SigLIP2 zero probabilities; both vision-related but not the same bug." + }, + { + "left": "issue:44062", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer AddedToken keyword conflict vs list_repo_files revision forwarding in CI; no overlap in code path." + }, + { + "left": "issue:44464", + "right": "issue:45491", + "accept": false, + "reason": "Compiled-forward chunked generation inconsistency vs Gemma3 NaN embeddings with sliding-window attention; different model/bug mechanisms." + }, + { + "left": "issue:28218", + "right": "issue:32090", + "accept": false, + "reason": "Tokenizer added-token spacing issue vs Trainer NoneType GPU broadcast error; unrelated." + }, + { + "left": "issue:33290", + "right": "issue:34567", + "accept": false, + "reason": "AdaFactor/DeepSpeed OOM vs num_input_tokens_seen not updating; not the same defect." + }, + { + "left": "issue:44442", + "right": "issue:44898", + "accept": false, + "reason": "FastSpeech2ConformerTokenizer load failure vs Perceiver non-default-resolution interpolation failure; separate tokenizer vs vision-model bugs." + }, + { + "left": "issue:43381", + "right": "issue:43873", + "accept": false, + "reason": "Gradient checkpointing eval-mode restriction vs offloading with quantization; different behaviors and fixes." + }, + { + "left": "issue:43316", + "right": "issue:43525", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy vs Llama4Config missing pad_token_id; both config issues but not the same field/problem." + }, + { + "left": "issue:44964", + "right": "issue:45440", + "accept": false, + "reason": "Phi-4 multimodal loading regression vs DeepseekV3MoE divergence from remote implementation; distinct model families and causes." + }, + { + "left": "issue:34689", + "right": "issue:43611", + "accept": false, + "reason": "Llama 3.2 Vision model loading breakage vs base_model_prefix loading regression; both load-time issues but different attributes and paths." + }, + { + "left": "issue:32090", + "right": "issue:33290", + "accept": false, + "reason": "Trainer GPU broadcast TypeError vs DeepSpeed AdaFactor OOM; not related beyond training context." + }, + { + "left": "issue:43720", + "right": "issue:44442", + "accept": false, + "reason": "BitNet packed-weight unpacking bug during accelerate loading vs tokenizer load failure for FastSpeech2Conformer; unrelated." + }, + { + "left": "issue:44442", + "right": "issue:45803", + "accept": false, + "reason": "Tokenizer loading failure vs FuyuBatchFeature bare-except error handling; different files and behavior." + }, + { + "left": "issue:44479", + "right": "issue:45290", + "accept": false, + "reason": "Video-input regression for Qwen VL models vs chat-template crash on tool-call assistant messages; different features." + }, + { + "left": "issue:34689", + "right": "issue:36010", + "accept": false, + "reason": "Llama 3.2 Vision loading regression vs GenerationMixin import error; both import/load related but not the same bug." + }, + { + "left": "issue:43931", + "right": "issue:45216", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch vs Qwen3.5 save_pretrained regression; one is load-time, the other save-time." + }, + { + "left": "issue:43493", + "right": "issue:43827", + "accept": false, + "reason": "SigLIP2 implementation discrepancy vs docs still referencing removed pipeline(); one is model math, the other documentation." + }, + { + "left": "issue:42175", + "right": "issue:46234", + "accept": false, + "reason": "Torch-only install missing tensorflow backend vs missing import_utils symbol; packaging/backend availability mismatch, not duplicate." + }, + { + "left": "issue:43550", + "right": "issue:44743", + "accept": false, + "reason": "Bamba torch.compile SDPA failure vs Qwen3.5 recurrent states reset with cache; different model internals." + }, + { + "left": "issue:43873", + "right": "issue:44871", + "accept": false, + "reason": "Quantization offloading issue vs Gemma-3 eos_token_id config mismatch; unrelated." + }, + { + "left": "issue:42907", + "right": "issue:45698", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals vs from_pretrained loading wrong custom module after save_pretrained; both save/load related but different failure points." + }, + { + "left": "issue:43643", + "right": "issue:44913", + "accept": false, + "reason": "trust_remote_code missing fields in AutoConfig return vs GPTNeoX rotary_pct not persisting on reload; separate config serialization bugs." + }, + { + "left": "issue:43316", + "right": "issue:45759", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy vs AutoModelForCausalLM.from_config not unwrapping text_config for multimodal Qwen configs; different config shapes." + }, + { + "left": "issue:43761", + "right": "issue:44188", + "accept": false, + "reason": "CLIPVisionModel hidden_states=None regression vs diverging attention kernels under torch.compile; unrelated code paths." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 30, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:25251", + "issue:28282", + "issue:29127", + "issue:33290", + "issue:33357", + "issue:34689", + "issue:35141", + "issue:41950", + "issue:42617", + "issue:43065", + "issue:43295", + "issue:43316", + "issue:43404", + "issue:43441", + "issue:43475", + "issue:43540", + "issue:43550", + "issue:43575", + "issue:43606", + "issue:43650", + "issue:43701", + "issue:43716", + "issue:43742", + "issue:43825", + "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:44987", + "issue:45137", + "issue:45290", + "issue:45479", + "issue:45584", + "issue:45656", + "issue:45803", + "issue:46170", + "issue:46178", + "issue:46202", + "issue:46209" + ], + "soft_pairs": [ + "issue:45290|issue:46209", + "issue:44855|issue:45137", + "issue:33290|issue:34689", + "issue:44190|issue:44496", + "issue:44568|issue:45479", + "issue:44077|issue:44479", + "issue:43650|issue:46202", + "issue:44987|issue:46178", + "issue:29127|issue:33357", + "issue:25251|issue:28282", + "issue:43295|issue:43825", + "issue:42617|issue:43575", + "issue:43550|issue:43701", + "issue:43606|issue:43701", + "issue:43575|issue:43742", + "issue:33290|issue:35141", + "issue:43316|issue:43716", + "issue:43540|issue:44514", + "issue:33290|issue:45656", + "issue:43316|issue:44877", + "issue:44871|issue:45584", + "issue:44162|issue:44792", + "issue:43295|issue:44871", + "issue:43404|issue:43441", + "issue:45803|issue:46170", + "issue:43065|issue:44617", + "issue:41950|issue:43475" + ], + "prepared_review_unit_hash": "be7ed8666cbb3e378a68d7f761804b61d46346cf0309232150a0071b7342e00a", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 27, + "serialized_chars": 35139, + "estimated_input_tokens": 8785, + "estimated_eval_tokens": 17826 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is noisy and heterogeneous: the soft pairs span unrelated bugs across pipelines, tokenizers, model loading, DeepSpeed, and vision/video models. I found no true duplicate pair, so none of the soft edges should be merged.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43825 is the broadest user-facing regression in the set and has inbound references, so it is the least-bad anchor if one must be chosen.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43825 is the most central and broadly applicable issue here; the rest are mostly unrelated regressions or model-specific failures.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45290", + "right": "issue:46209", + "accept": false, + "reason": "Different bugs: chat-template/tool-call crash vs FP8 inference failure on B200." + }, + { + "left": "issue:44855", + "right": "issue:45137", + "accept": false, + "reason": "Python 3.13 TorchScript parsing error vs DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:33290", + "right": "issue:34689", + "accept": false, + "reason": "DeepSpeed Adafactor OOM vs model-loading regression for Llama 3.2 Vision." + }, + { + "left": "issue:44190", + "right": "issue:44496", + "accept": false, + "reason": "Local dataset loading issue vs unrecognized model/config loading error." + }, + { + "left": "issue:44568", + "right": "issue:45479", + "accept": false, + "reason": "Tokenizer special-token behavior vs degenerate zero-loss classification bug." + }, + { + "left": "issue:44077", + "right": "issue:44479", + "accept": false, + "reason": "Optional post_init policy in patchtsmixer vs video-input regression for Qwen variants." + }, + { + "left": "issue:43650", + "right": "issue:46202", + "accept": false, + "reason": "No clear technical overlap; one is a vague report, the other is a Gemma pipeline roundtrip bug." + }, + { + "left": "issue:44987", + "right": "issue:46178", + "accept": false, + "reason": "Loading a specific model vs backend-mapping error for tensorflow_text." + }, + { + "left": "issue:29127", + "right": "issue:33357", + "accept": false, + "reason": "LayoutLMv3 error-message clarity vs MacOS bus error in CLIP model loading." + }, + { + "left": "issue:25251", + "right": "issue:28282", + "accept": false, + "reason": "Pipeline top_k nesting bug vs missing PyTorch import dependency." + }, + { + "left": "issue:43295", + "right": "issue:43825", + "accept": false, + "reason": "Processor/tokenizer regression vs pipeline translation-task support message regression." + }, + { + "left": "issue:42617", + "right": "issue:43575", + "accept": false, + "reason": "3d_parallel.py failure vs tensor-parallel OOM on Qwen2-57B-A14B-Instruct." + }, + { + "left": "issue:43550", + "right": "issue:43701", + "accept": false, + "reason": "torch.compile/SDPA failure vs resume_from_checkpoint key mismatch." + }, + { + "left": "issue:43606", + "right": "issue:43701", + "accept": false, + "reason": "CPU offload device mismatch vs checkpoint key mismatch; unrelated code paths." + }, + { + "left": "issue:43575", + "right": "issue:43742", + "accept": false, + "reason": "OOM when loading a large Qwen model vs key error loading MobileLLM." + }, + { + "left": "issue:33290", + "right": "issue:35141", + "accept": false, + "reason": "DeepSpeed optimizer OOM vs embedding reinitialization in post_init." + }, + { + "left": "issue:43316", + "right": "issue:43716", + "accept": false, + "reason": "Gemma3TextConfig API discrepancy vs image preprocessor/model dtype mismatch." + }, + { + "left": "issue:43540", + "right": "issue:44514", + "accept": false, + "reason": "Qwen3OmniMoe video ValueError vs batched apply_chat_template padding crash." + }, + { + "left": "issue:33290", + "right": "issue:45656", + "accept": false, + "reason": "OOM with Adafactor/DeepSpeed vs optimizer.step being invoked twice." + }, + { + "left": "issue:43316", + "right": "issue:44877", + "accept": false, + "reason": "Gemma3TextConfig API inconsistency vs strict config loading for granite_speech." + }, + { + "left": "issue:44871", + "right": "issue:45584", + "accept": false, + "reason": "Gemma eos_token_id mismatch vs Whisper empty-transcription generation failure." + }, + { + "left": "issue:44162", + "right": "issue:44792", + "accept": false, + "reason": "ESM2 model breakage vs janus image-generation test failure." + }, + { + "left": "issue:43295", + "right": "issue:44871", + "accept": false, + "reason": "Custom processor/tokenizer regression vs Gemma eos_token_id config inconsistency." + }, + { + "left": "issue:43404", + "right": "issue:43441", + "accept": false, + "reason": "lm_head weight-tying bug vs FlashAttention failure in Ministral-3." + }, + { + "left": "issue:45803", + "right": "issue:46170", + "accept": false, + "reason": "Bare except swallowing interrupts vs Windows/ROCm import dependency problem." + }, + { + "left": "issue:43065", + "right": "issue:44617", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder vs CUDA OOM in Sam3Video." + }, + { + "left": "issue:41950", + "right": "issue:43475", + "accept": false, + "reason": "Video-classification pipeline image-processor lookup vs missing fpn_position_embeddings attribute in Sam3 video output." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 31, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:35141", + "issue:41720", + "issue:42490", + "issue:43065", + "issue:43232", + "issue:43335", + "issue:43388", + "issue:43452", + "issue:43504", + "issue:43572", + "issue:43644", + "issue:43646", + "issue:43673", + "issue:43761", + "issue:43827", + "issue:43931", + "issue:43976", + "issue:43994", + "issue:44060", + "issue:44077", + "issue:44190", + "issue:44242", + "issue:44479", + "issue:44496", + "issue:44534", + "issue:44610", + "issue:44617", + "issue:44734", + "issue:44743", + "issue:44792", + "issue:44855", + "issue:44871", + "issue:44913", + "issue:44964", + "issue:44977", + "issue:45127", + "issue:45200", + "issue:45245", + "issue:45542", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45698", + "issue:45803", + "issue:45987", + "issue:46050", + "issue:46178", + "issue:46234" + ], + "soft_pairs": [ + "issue:43646|issue:44913", + "issue:44871|issue:46050", + "issue:43452|issue:44496", + "issue:45127|issue:45200", + "issue:43761|issue:44479", + "issue:43572|issue:46178", + "issue:43232|issue:43388", + "issue:43504|issue:45698", + "issue:45542|issue:46234", + "issue:44077|issue:44534", + "issue:43673|issue:44743", + "issue:43761|issue:44242", + "issue:44792|issue:44977", + "issue:44617|issue:45584", + "issue:44534|issue:44913", + "issue:44190|issue:44964", + "issue:44792|issue:45600", + "issue:44479|issue:44734", + "issue:44855|issue:45588", + "issue:43827|issue:43994", + "issue:41720|issue:45245", + "issue:43065|issue:44610", + "issue:45803|issue:45987", + "issue:43931|issue:44060", + "issue:35141|issue:42490", + "issue:43644|issue:44913", + "issue:43976|issue:44855", + "issue:43335|issue:44855" + ], + "prepared_review_unit_hash": "e1020ca648dc82dded9b760742c9f84509ab2376fc6a74411f8fd5fc0ff21c95", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36357, + "estimated_input_tokens": 9090, + "estimated_eval_tokens": 18436 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is mostly a loose semantic cluster of unrelated Transformers issues. None of the soft pairs look like true duplicates or the same code-path fix; they span different models, loading bugs, generation bugs, and docs/backends issues.", + "confidence": 0.92, + "canonical_issue_reason": "issue:43646 is the broadest and most central report: a v5 regression in custom model initialization/post-init behavior. It is representative of the cluster\u2019s general loading/initialization theme better than the more model-specific or symptom-specific issues.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43646 is the best single issue to anchor the cluster because it describes a general, actionable regression rather than a narrow model-specific symptom.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43646", + "right": "issue:44913", + "accept": false, + "reason": "Different bugs: one is about custom model initialization/post_init, the other about GPTNeoX rotary_pct not persisting on reload." + }, + { + "left": "issue:44871", + "right": "issue:46050", + "accept": false, + "reason": "Both involve model config/loading, but the failures are different: eos_token_id inconsistency vs quantized model save/load breakage." + }, + { + "left": "issue:43452", + "right": "issue:44496", + "accept": false, + "reason": "Both are loading failures, but one is gguf_file/AutoTokenizer handling and the other is an unrecognized model_type config issue." + }, + { + "left": "issue:45127", + "right": "issue:45200", + "accept": false, + "reason": "Different model families and root causes: LoRA/extended vocabulary collapse vs Gemma 4 mm_token_type_ids defaulting." + }, + { + "left": "issue:43761", + "right": "issue:44479", + "accept": false, + "reason": "Distinct regressions in different models and code paths: CLIPVision hidden_states vs Qwen VL video-input handling." + }, + { + "left": "issue:43572", + "right": "issue:46178", + "accept": false, + "reason": "Unrelated issues: StableLmConfig pad_token_idx vs missing tensorflow_text backend mapping." + }, + { + "left": "issue:43232", + "right": "issue:43388", + "accept": false, + "reason": "Different generation/metrics subsystems and different failure modes; not the same underlying bug." + }, + { + "left": "issue:43504", + "right": "issue:45698", + "accept": false, + "reason": "Both touch model loading, but one is a legacy preset field in BEiT and the other is wrong custom-module resolution after save/load." + }, + { + "left": "issue:45542", + "right": "issue:46234", + "accept": false, + "reason": "Separate import/backend problems: tensorboard-without-TF backend selection vs a missing utility function." + }, + { + "left": "issue:44077", + "right": "issue:44534", + "accept": false, + "reason": "Both mention init-related behavior, but one is an optional post_init API rule and the other is a non-persistent buffer initialization regression." + }, + { + "left": "issue:43673", + "right": "issue:44743", + "accept": false, + "reason": "Different cache bugs in different components: missing GenerationMixin cache in chunked prefill vs recurrent states resetting in modular_qwen3_5." + }, + { + "left": "issue:43761", + "right": "issue:44242", + "accept": false, + "reason": "Completely different issues: hidden_states return value vs MoE load-balancing loss omission." + }, + { + "left": "issue:44792", + "right": "issue:44977", + "accept": false, + "reason": "Different model/runtime failures: janus image-generation test vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:44617", + "right": "issue:45584", + "accept": false, + "reason": "Unrelated symptoms: Sam3Video OOM vs Whisper empty transcription after special-token alignment." + }, + { + "left": "issue:44534", + "right": "issue:44913", + "accept": false, + "reason": "Both are v5 regressions, but one is junk-filled non-persistent buffers and the other is a config field not surviving reload." + }, + { + "left": "issue:44190", + "right": "issue:44964", + "accept": false, + "reason": "Different areas entirely: dataset loading script vs Phi-4 multimodal model loading." + }, + { + "left": "issue:44792", + "right": "issue:45600", + "accept": false, + "reason": "Different failures: janus test case vs broken auto_mappings reference to removed configs." + }, + { + "left": "issue:44479", + "right": "issue:44734", + "accept": false, + "reason": "Different code paths: video-input regression in VL models vs KV-cache continuation bug in serve responses." + }, + { + "left": "issue:44855", + "right": "issue:45588", + "accept": false, + "reason": "Distinct problems: Python 3.13 import parsing/IndentationError vs flash-attention crash on s_aux=None." + }, + { + "left": "issue:43827", + "right": "issue:43994", + "accept": false, + "reason": "Docs leftover pipeline references are not the same as a runtime model-quality regression." + }, + { + "left": "issue:41720", + "right": "issue:45245", + "accept": false, + "reason": "No common underlying bug: Qwen3 auto device mapping CUDA assert vs category-count limit error." + }, + { + "left": "issue:43065", + "right": "issue:44610", + "accept": false, + "reason": "Different model-specific bugs: a dummy Conv2d in Sam3PixelDecoder vs OmDet-Turbo preprocessing/model-size mismatch." + }, + { + "left": "issue:45803", + "right": "issue:45987", + "accept": false, + "reason": "Bare except swallowing errors is unrelated to StaticCache returning a tensor-shaped length." + }, + { + "left": "issue:43931", + "right": "issue:44060", + "accept": false, + "reason": "Different Qwen3-related issues: weight shape mismatch on load vs a tied-weights warning linking the wrong tensors." + }, + { + "left": "issue:35141", + "right": "issue:42490", + "accept": false, + "reason": "Different loading/embedding issues: output embedding reinit after resize vs path-with-trailing-slash import warning." + }, + { + "left": "issue:43644", + "right": "issue:44913", + "accept": false, + "reason": "Both involve v5/config behavior, but they are separate bugs with different symptoms and fixes." + }, + { + "left": "issue:43976", + "right": "issue:44855", + "accept": false, + "reason": "Different failures and environments: version compatibility issue vs a Python 3.13 import parser error." + }, + { + "left": "issue:43335", + "right": "issue:44855", + "accept": false, + "reason": "No overlap in root cause: SwitchTransformers sparse-layer creation vs DebertaV2 import failure on Python 3.13." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 32, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36246", + "issue:38175", + "issue:41628", + "issue:43065", + "issue:43116", + "issue:43295", + "issue:43335", + "issue:43404", + "issue:43479", + "issue:43540", + "issue:43550", + "issue:43650", + "issue:44077", + "issue:44112", + "issue:44186", + "issue:44190", + "issue:44220", + "issue:44246", + "issue:44462", + "issue:44464", + "issue:44521", + "issue:44683", + "issue:44734", + "issue:44737", + "issue:44877", + "issue:44933", + "issue:44938", + "issue:45003", + "issue:45127", + "issue:45216", + "issue:45245", + "issue:45276", + "issue:45357", + "issue:45362", + "issue:45375", + "issue:45381", + "issue:45446", + "issue:45542", + "issue:45563", + "issue:45584", + "issue:45600", + "issue:45632", + "issue:45803", + "issue:45907", + "issue:46082", + "issue:46121", + "issue:46234" + ], + "soft_pairs": [ + "issue:43550|issue:44190", + "issue:45632|issue:46234", + "issue:44077|issue:44877", + "issue:43540|issue:44734", + "issue:44462|issue:45907", + "issue:45127|issue:45357", + "issue:44521|issue:45381", + "issue:43335|issue:44190", + "issue:44737|issue:45803", + "issue:44112|issue:45600", + "issue:43116|issue:44190", + "issue:45276|issue:45584", + "issue:46082|issue:46121", + "issue:43295|issue:45276", + "issue:43479|issue:45375", + "issue:44938|issue:45542", + "issue:45245|issue:45584", + "issue:43650|issue:44220", + "issue:44464|issue:45563", + "issue:36246|issue:41628", + "issue:44186|issue:44734", + "issue:44246|issue:45003", + "issue:43404|issue:45216", + "issue:44683|issue:45446", + "issue:44933|issue:45362", + "issue:38175|issue:43065" + ], + "prepared_review_unit_hash": "6ce56a2caedba91e65bfe153420e106d0d88d3cf460486193343136a50f17248", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 26, + "serialized_chars": 34914, + "estimated_input_tokens": 8729, + "estimated_eval_tokens": 17714 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster looks heterogeneous: these are mostly unrelated issues across different models, APIs, and failure modes. I found no soft-edge pair that is safe to merge as a duplicate.", + "confidence": 0.97, + "canonical_issue_reason": "No true duplicate stand-out here; if forced to pick one representative, issue:44521 is the most active/open report with the most follow-up and a concrete reproducible bug.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44521 is the strongest anchor for the set because it has the most discussion/inbound references and a clearly described multimodal failure path.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43550", + "right": "issue:44190", + "accept": false, + "reason": "Different subsystems and symptoms: SDPA/torch.compile on Bamba vs local dataset loading in an image-classification example." + }, + { + "left": "issue:45632", + "right": "issue:46234", + "accept": false, + "reason": "Cache-path collision for trust_remote_code local models is unrelated to a missing utility export in import_utils." + }, + { + "left": "issue:44077", + "right": "issue:44877", + "accept": false, + "reason": "Both involve config handling, but one is about invalid optional post_init in patchtsmixer and the other about strict loading of granite_speech config." + }, + { + "left": "issue:43540", + "right": "issue:44734", + "accept": false, + "reason": "Qwen3OmniMoe video input validation and serve KV-cache continuation indexing are different code paths and bugs." + }, + { + "left": "issue:44462", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer.json lookup behavior is unrelated to list_repo_files not forwarding revision." + }, + { + "left": "issue:45127", + "right": "issue:45357", + "accept": false, + "reason": "LoRA merge with extended vocab and incorrect visual encoder save keys are separate checkpoint/model-state issues." + }, + { + "left": "issue:44521", + "right": "issue:45381", + "accept": false, + "reason": "Both are multimodal Qwen issues, but assistant mask generation and vision_position_ids are different failures in different paths." + }, + { + "left": "issue:43335", + "right": "issue:44190", + "accept": false, + "reason": "SwitchTransformers config layer creation is unrelated to the image-classification dataset-loading example failure." + }, + { + "left": "issue:44737", + "right": "issue:45803", + "accept": false, + "reason": "CPU tensor construction in XLNet has nothing to do with Fuyu's broad exception handling in tensor conversion." + }, + { + "left": "issue:44112", + "right": "issue:45600", + "accept": false, + "reason": "Both touch CI around speech models, but one is a stale GraniteSpeech device test and the other is a broken auto_mappings reference." + }, + { + "left": "issue:43116", + "right": "issue:44190", + "accept": false, + "reason": "Multi-label empty results in run_classification.py is a different example-script bug than loading a local image dataset." + }, + { + "left": "issue:45276", + "right": "issue:45584", + "accept": false, + "reason": "Gemma4 embedding resize wiring and Whisper empty transcription handling are unrelated model-specific bugs." + }, + { + "left": "issue:46082", + "right": "issue:46121", + "accept": false, + "reason": "LlamaConfig head_dim validation and rope-parameter JSON list handling are distinct config-validation problems." + }, + { + "left": "issue:43295", + "right": "issue:45276", + "accept": false, + "reason": "Processor/tokenizer regression with images is unrelated to Gemma4 embedding/output tensor resizing." + }, + { + "left": "issue:43479", + "right": "issue:45375", + "accept": false, + "reason": "Phi4Multimodal default config initialization and Qwen3_5MoeVision strict-field dropping are different configuration bugs." + }, + { + "left": "issue:44938", + "right": "issue:45542", + "accept": false, + "reason": "Python 3.14 import failure and tensorboard-without-TensorFlow backend handling are not the same issue." + }, + { + "left": "issue:45245", + "right": "issue:45584", + "accept": false, + "reason": "Category cardinality overflow is unrelated to Whisper's empty-transcription generation bug." + }, + { + "left": "issue:43650", + "right": "issue:44220", + "accept": false, + "reason": "Placeholder issue text and fbank feature extraction error are clearly unrelated." + }, + { + "left": "issue:44464", + "right": "issue:45563", + "accept": false, + "reason": "Compiled-forward generation inconsistency and a stale warning for num_return_sequences are different generation bugs." + }, + { + "left": "issue:36246", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but one is a Qwen2.5-VL submodule import and the other is a top-level AutoImageProcessor import problem." + }, + { + "left": "issue:44186", + "right": "issue:44734", + "accept": false, + "reason": "LayoutLMv2 tokenizer crashes and serve KV-cache continuation indexing are unrelated failure modes." + }, + { + "left": "issue:44246", + "right": "issue:45003", + "accept": false, + "reason": "Slow import timing and unsafe sys.modules access are related to import behavior but not the same concrete bug." + }, + { + "left": "issue:43404", + "right": "issue:45216", + "accept": false, + "reason": "lm_head tying in Mistral3 and incorrect Qwen3.5 checkpoint saving are separate weight-sharing/save_pretrained issues." + }, + { + "left": "issue:44683", + "right": "issue:45446", + "accept": false, + "reason": "Both mention flex_attention, but one is a compiled failure on torch>=2.9 and the other is a bad PyTorch version check for AuxRequest import." + }, + { + "left": "issue:44933", + "right": "issue:45362", + "accept": false, + "reason": "Missing image_utils export and Qwen3.5 chat crash are unrelated." + }, + { + "left": "issue:38175", + "right": "issue:43065", + "accept": false, + "reason": "Siglip2 zero probabilities and Sam3PixelDecoder dummy Conv2d are completely different model bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 33, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:32090", + "issue:35141", + "issue:36246", + "issue:38617", + "issue:41950", + "issue:42175", + "issue:42907", + "issue:43295", + "issue:43299", + "issue:43381", + "issue:43388", + "issue:43441", + "issue:43479", + "issue:43525", + "issue:43526", + "issue:43531", + "issue:43643", + "issue:43650", + "issue:43673", + "issue:43688", + "issue:43854", + "issue:43901", + "issue:44016", + "issue:44075", + "issue:44112", + "issue:44220", + "issue:44242", + "issue:44279", + "issue:44336", + "issue:44368", + "issue:44496", + "issue:44561", + "issue:44734", + "issue:44964", + "issue:45042", + "issue:45200", + "issue:45216", + "issue:45335", + "issue:45372", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45593", + "issue:45600", + "issue:45632", + "issue:45759", + "issue:46209", + "issue:46234" + ], + "soft_pairs": [ + "issue:43643|issue:44496", + "issue:44964|issue:45600", + "issue:43854|issue:44964", + "issue:44112|issue:44964", + "issue:45563|issue:45584", + "issue:44734|issue:45632", + "issue:36246|issue:38617", + "issue:44561|issue:45632", + "issue:43295|issue:45335", + "issue:42907|issue:43441", + "issue:43531|issue:45600", + "issue:43526|issue:43901", + "issue:44496|issue:45042", + "issue:41950|issue:44016", + "issue:43441|issue:45588", + "issue:43388|issue:43688", + "issue:43673|issue:44336", + "issue:44075|issue:44368", + "issue:42175|issue:44279", + "issue:43299|issue:45216", + "issue:43901|issue:44496", + "issue:43381|issue:45593", + "issue:44016|issue:44220", + "issue:45335|issue:45584", + "issue:44496|issue:45759", + "issue:45372|issue:46234", + "issue:43650|issue:46209", + "issue:32090|issue:35141", + "issue:43479|issue:43525", + "issue:44242|issue:45200" + ], + "prepared_review_unit_hash": "7b8348485c8b3299f0093c4daec922209f5593c899eeb550e48ae89cc17635c6", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36954, + "estimated_input_tokens": 9239, + "estimated_eval_tokens": 18734 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a loose thematic grouping of unrelated loading/import/model-behavior bugs, not a true duplicate set. None of the soft pairs look like the same underlying bug/change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": "Issue 44964 is the most concrete, user-facing loading regression here and the closest thing to a representative anchor, but the cluster is too heterogeneous to treat it as a true canonical duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43643", + "right": "issue:44496", + "accept": false, + "reason": "Both are config/model-loading failures, but they have different root causes: missing fields with trust_remote_code vs unrecognized model/config model_type." + }, + { + "left": "issue:44964", + "right": "issue:45600", + "accept": false, + "reason": "One is a Phi-4 multimodal model load failure; the other is a CI break from stale auto_mappings references to removed configs." + }, + { + "left": "issue:43854", + "right": "issue:44964", + "accept": false, + "reason": "Different models and failure modes; this is not the same load bug." + }, + { + "left": "issue:44112", + "right": "issue:44964", + "accept": false, + "reason": "GraniteSpeech CI device-override flake is unrelated to Phi-4 multimodal loading." + }, + { + "left": "issue:45563", + "right": "issue:45584", + "accept": false, + "reason": "Both involve generation, but they are different code paths and symptoms: stale warning vs empty-transcription failure after align_special_tokens." + }, + { + "left": "issue:44734", + "right": "issue:45632", + "accept": false, + "reason": "KV-cache continuation crash in serve is unrelated to trust_remote_code cache-path collision." + }, + { + "left": "issue:36246", + "right": "issue:38617", + "accept": false, + "reason": "Both are ImportErrors, but they are for different missing symbols and different subsystems." + }, + { + "left": "issue:44561", + "right": "issue:45632", + "accept": false, + "reason": "Removal of is_torch_fx_available breaking remote-code models is unrelated to cache-path collisions for local models." + }, + { + "left": "issue:43295", + "right": "issue:45335", + "accept": false, + "reason": "Different regressions: processor/tokenizer access and image passing vs resize_token_embeddings not updating decoder embeddings." + }, + { + "left": "issue:42907", + "right": "issue:43441", + "accept": false, + "reason": "Same model family, but different concrete problems: save/dequantization vs FlashAttention load/inference failure." + }, + { + "left": "issue:43531", + "right": "issue:45600", + "accept": false, + "reason": "Qwen3-MoE sliding_window behavior is unrelated to stale auto_mappings config references." + }, + { + "left": "issue:43526", + "right": "issue:43901", + "accept": false, + "reason": "A processor label-reduction bug is unrelated to a docs/behavior mismatch for return_all_scores." + }, + { + "left": "issue:44496", + "right": "issue:45042", + "accept": false, + "reason": "Unrecognized model config and PIL backend torchvision dependency are different bugs." + }, + { + "left": "issue:41950", + "right": "issue:44016", + "accept": false, + "reason": "Pipeline processor lookup and a notebook syntax error are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:45588", + "accept": false, + "reason": "Both mention FlashAttention, but one is a model-specific compatibility issue and the other is an AttributeError on s_aux=None in a different code path." + }, + { + "left": "issue:43388", + "right": "issue:43688", + "accept": false, + "reason": "Different training/eval bugs: gather_for_metrics truncation vs auxiliary-loss normalization." + }, + { + "left": "issue:43673", + "right": "issue:44336", + "accept": false, + "reason": "Chunked-prefill cache handling is unrelated to ANSI codes in loading_report." + }, + { + "left": "issue:44075", + "right": "issue:44368", + "accept": false, + "reason": "Optimizer arguments being ignored is unrelated to a tie_word_embeddings warning in LoRA fine-tuning." + }, + { + "left": "issue:42175", + "right": "issue:44279", + "accept": false, + "reason": "Package extra dependency omission is not the same as a general dependency issue." + }, + { + "left": "issue:43299", + "right": "issue:45216", + "accept": false, + "reason": "Both are Qwen-related, but one is a model-loading regression and the other is a save_pretrained checkpoint regression." + }, + { + "left": "issue:43901", + "right": "issue:44496", + "accept": false, + "reason": "Docs/behavior mismatch for a pipeline option is unrelated to model config loading failure." + }, + { + "left": "issue:43381", + "right": "issue:45593", + "accept": false, + "reason": "Gradient-checkpointing eval-mode restriction is unrelated to D-FINE auxiliary-loss suppression." + }, + { + "left": "issue:44016", + "right": "issue:44220", + "accept": false, + "reason": "A notebook syntax error is unrelated to _torch_extract_fbank_features." + }, + { + "left": "issue:45335", + "right": "issue:45584", + "accept": false, + "reason": "Resize-token-embeddings not propagating is unrelated to Whisper empty-transcription generation failure." + }, + { + "left": "issue:45372", + "right": "issue:46234", + "accept": false, + "reason": "Different missing imports in different libraries/modules; not the same bug." + }, + { + "left": "issue:43650", + "right": "issue:46209", + "accept": false, + "reason": "Placeholder/spam issue and FP8 inference failure are unrelated." + }, + { + "left": "issue:32090", + "right": "issue:35141", + "accept": false, + "reason": "Trainer broadcast TypeError and embedding reinitialization after resize_token_embeddings are different bugs." + }, + { + "left": "issue:43479", + "right": "issue:43525", + "accept": false, + "reason": "Different config classes and different missing/default fields." + }, + { + "left": "issue:44242", + "right": "issue:45200", + "accept": false, + "reason": "Load-balancing loss gating and mm_token_type_ids defaulting are unrelated MoE/multimodal issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 34, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:38175", + "issue:39692", + "issue:41950", + "issue:42994", + "issue:43295", + "issue:43299", + "issue:43317", + "issue:43441", + "issue:43450", + "issue:43577", + "issue:43650", + "issue:43653", + "issue:43824", + "issue:43854", + "issue:43901", + "issue:43976", + "issue:44016", + "issue:44062", + "issue:44279", + "issue:44297", + "issue:44351", + "issue:44462", + "issue:44466", + "issue:44521", + "issue:44617", + "issue:44623", + "issue:44683", + "issue:44749", + "issue:44779", + "issue:44933", + "issue:44987", + "issue:45020", + "issue:45081", + "issue:45216", + "issue:45276", + "issue:45278", + "issue:45325", + "issue:45357", + "issue:45405", + "issue:45542", + "issue:45593", + "issue:45600", + "issue:45712", + "issue:45812", + "issue:45823", + "issue:45834", + "issue:45907", + "issue:46132" + ], + "soft_pairs": [ + "issue:43577|issue:45216", + "issue:38175|issue:44617", + "issue:43299|issue:45357", + "issue:44779|issue:45812", + "issue:43824|issue:44933", + "issue:43295|issue:44779", + "issue:44351|issue:45278", + "issue:41950|issue:45020", + "issue:39692|issue:43901", + "issue:44279|issue:45405", + "issue:44016|issue:44062", + "issue:41950|issue:45823", + "issue:43976|issue:45405", + "issue:43299|issue:43854", + "issue:44683|issue:45542", + "issue:43650|issue:46132", + "issue:44462|issue:45081", + "issue:43976|issue:44987", + "issue:44297|issue:44462", + "issue:43976|issue:44279", + "issue:43450|issue:44279", + "issue:45081|issue:45907", + "issue:44466|issue:45276", + "issue:44521|issue:45325", + "issue:43441|issue:45834", + "issue:42994|issue:43317", + "issue:43653|issue:45593", + "issue:45600|issue:45712", + "issue:44623|issue:44749" + ], + "prepared_review_unit_hash": "3207af5ba69d38d1f263e67c3edc1f06db59969e1eb590bac49f649c3bdde4f5", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36347, + "estimated_input_tokens": 9087, + "estimated_eval_tokens": 18430 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers regression reports (tokenizers, processors, model loading/saving, imports, docs, and a few performance/CI issues). I did not find any soft pair that clearly describes the same concrete bug/change, so no merges are justified.", + "confidence": 0.29, + "canonical_issue_reason": "issue:44462 is the best broad anchor here: it targets the core AutoTokenizer load path and describes a clear regression that could plausibly underlie several nearby tokenizer-related complaints.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45812 is the strongest standalone report: it describes a silent, model-wide token-ID regression affecting all Granite models, which is high impact and well-scoped.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43577", + "right": "issue:45216", + "accept": false, + "reason": "Both involve model serialization/dtype behavior, but they affect different models and different failure modes." + }, + { + "left": "issue:38175", + "right": "issue:44617", + "accept": false, + "reason": "Unrelated bugs: SigLIP probabilities vs Sam3Video OOM." + }, + { + "left": "issue:43299", + "right": "issue:45357", + "accept": false, + "reason": "Different Qwen issues: model loading failure vs incorrect save_pretrained visual encoder keys." + }, + { + "left": "issue:44779", + "right": "issue:45812", + "accept": false, + "reason": "Both are tokenizer regressions, but they appear model-specific and not the same underlying bug." + }, + { + "left": "issue:43824", + "right": "issue:44933", + "accept": false, + "reason": "Both are import problems, but they concern different symbols and code paths." + }, + { + "left": "issue:43295", + "right": "issue:44779", + "accept": false, + "reason": "Processor.tokenizer API regression is not the same as Deepseek tokenizer output corruption." + }, + { + "left": "issue:44351", + "right": "issue:45278", + "accept": false, + "reason": "A specific missing import is not the same as a broad package-wide import regression." + }, + { + "left": "issue:41950", + "right": "issue:45020", + "accept": false, + "reason": "Pipeline image-processor lookup bug is unrelated to remote_code model loading regressions." + }, + { + "left": "issue:39692", + "right": "issue:43901", + "accept": false, + "reason": "Different docs issues with different APIs and symptoms." + }, + { + "left": "issue:44279", + "right": "issue:45405", + "accept": false, + "reason": "General dependency trouble is not the same as a specific PEFT version bump problem." + }, + { + "left": "issue:44016", + "right": "issue:44062", + "accept": false, + "reason": "Notebook syntax error and AddedToken argument conflict are unrelated." + }, + { + "left": "issue:41950", + "right": "issue:45823", + "accept": false, + "reason": "Video pipeline processor selection and Gemma4 device placement are different bugs." + }, + { + "left": "issue:43976", + "right": "issue:45405", + "accept": false, + "reason": "Python version compatibility issue is unrelated to PEFT minimum-version pinning." + }, + { + "left": "issue:43299", + "right": "issue:43854", + "accept": false, + "reason": "Different model-loading failures with no concrete shared code path." + }, + { + "left": "issue:44683", + "right": "issue:45542", + "accept": false, + "reason": "FlashAttention/torch compatibility is unrelated to TensorFlow backend detection." + }, + { + "left": "issue:43650", + "right": "issue:46132", + "accept": false, + "reason": "No meaningful relationship: placeholder issue vs AttentionInterface behavior change." + }, + { + "left": "issue:44462", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer repository loading vs Mistral regex patch crash are different tokenizer bugs." + }, + { + "left": "issue:43976", + "right": "issue:44987", + "accept": false, + "reason": "Both mention version regressions, but the affected loading failures are different and model-specific." + }, + { + "left": "issue:44297", + "right": "issue:44462", + "accept": false, + "reason": "Tokenizer config mismatch on save is not the same as AutoTokenizer ignoring tokenizer.json on load." + }, + { + "left": "issue:43976", + "right": "issue:44279", + "accept": false, + "reason": "No shared underlying bug; one is Python support, the other is dependency handling." + }, + { + "left": "issue:43450", + "right": "issue:44279", + "accept": false, + "reason": "Video processor batching bug is unrelated to dependency issues." + }, + { + "left": "issue:45081", + "right": "issue:45907", + "accept": false, + "reason": "Tokenizer regex patch crash and list_repo_files revision forwarding are unrelated." + }, + { + "left": "issue:44466", + "right": "issue:45276", + "accept": false, + "reason": "Different serialization/embedding bugs with different model families." + }, + { + "left": "issue:44521", + "right": "issue:45325", + "accept": false, + "reason": "Both are multimodal, but assistant mask generation and rope-index scaling are distinct code paths." + }, + { + "left": "issue:43441", + "right": "issue:45834", + "accept": false, + "reason": "FlashAttention failure and OCR index error are unrelated." + }, + { + "left": "issue:42994", + "right": "issue:43317", + "accept": false, + "reason": "Quantized-model saving and dequantized offload loading are different operations and failure points." + }, + { + "left": "issue:43653", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer special-token registration and D-FINE auxiliary-loss behavior are unrelated." + }, + { + "left": "issue:45600", + "right": "issue:45712", + "accept": false, + "reason": "Both are repo-maintenance issues, but they involve different files and different failure modes." + }, + { + "left": "issue:44623", + "right": "issue:44749", + "accept": false, + "reason": "Missing processor save files and slower filtering performance are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 35, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:16998", + "issue:22355", + "issue:41628", + "issue:42491", + "issue:43065", + "issue:43262", + "issue:43299", + "issue:43441", + "issue:43450", + "issue:43525", + "issue:43643", + "issue:43673", + "issue:43723", + "issue:43761", + "issue:43784", + "issue:43881", + "issue:43901", + "issue:43976", + "issue:43994", + "issue:44016", + "issue:44162", + "issue:44188", + "issue:44242", + "issue:44246", + "issue:44261", + "issue:44263", + "issue:44291", + "issue:44295", + "issue:44297", + "issue:44336", + "issue:44361", + "issue:44373", + "issue:44485", + "issue:44496", + "issue:44521", + "issue:44589", + "issue:44617", + "issue:44623", + "issue:44671", + "issue:44683", + "issue:44779", + "issue:44871", + "issue:44898", + "issue:45362", + "issue:45397", + "issue:45542", + "issue:45593", + "issue:45823" + ], + "soft_pairs": [ + "issue:44623|issue:45397", + "issue:43065|issue:44898", + "issue:44261|issue:44263", + "issue:44361|issue:45593", + "issue:44671|issue:44779", + "issue:44016|issue:45823", + "issue:43441|issue:44683", + "issue:43901|issue:43994", + "issue:43723|issue:44162", + "issue:43901|issue:44246", + "issue:43525|issue:43881", + "issue:43450|issue:44617", + "issue:44297|issue:45397", + "issue:43525|issue:43643", + "issue:43784|issue:45542", + "issue:44016|issue:44291", + "issue:44188|issue:44336", + "issue:43262|issue:44521", + "issue:44589|issue:45362", + "issue:41628|issue:43976", + "issue:43673|issue:43761", + "issue:44336|issue:44373", + "issue:16998|issue:22355", + "issue:42491|issue:43299", + "issue:44246|issue:44496", + "issue:44242|issue:45593", + "issue:44295|issue:45397", + "issue:44246|issue:44871", + "issue:44336|issue:44485" + ], + "prepared_review_unit_hash": "62058780b43ccde73f8c7b312ee5450605f5e4b211be46285a8abf00c5d24f9b", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36081, + "estimated_input_tokens": 9021, + "estimated_eval_tokens": 18298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is highly heterogeneous; the soft pairs mostly share only superficial topical overlap, not the same underlying bug or change. I would not deduplicate any of them and there is no good PR representative here.", + "confidence": 0.95, + "canonical_issue_reason": "No clear canonical issue: the items span unrelated regressions across loading, tokenizers, processors, attention kernels, docs, and model-specific behavior.", + "canonical_pr_reason": null, + "best_issue_reason": "No single issue is a strong global representative because the cluster is not centered on one code path or one bug family.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44623", + "right": "issue:45397", + "accept": false, + "reason": "Both are model-loading related, but one is missing processor save files and the other is a zero3/from_pretrained failure; different code paths." + }, + { + "left": "issue:43065", + "right": "issue:44898", + "accept": false, + "reason": "Both mention vision/model components, but one is a dummy Conv2d in Sam3PixelDecoder and the other is a Perceiver interpolation failure." + }, + { + "left": "issue:44261", + "right": "issue:44263", + "accept": false, + "reason": "Different subsystems: MLA q_a_layernorm precision config vs GlmMoeDsaIndexer torch.split behavior." + }, + { + "left": "issue:44361", + "right": "issue:45593", + "accept": false, + "reason": "Tokenizer/task AttributeError and missing auxiliary losses are unrelated bugs." + }, + { + "left": "issue:44671", + "right": "issue:44779", + "accept": false, + "reason": "Both are v5 regressions, but one affects CamemBERT masked LM outputs and the other Deepseek tokenizer behavior." + }, + { + "left": "issue:44016", + "right": "issue:45823", + "accept": false, + "reason": "Notebook syntax error and Gemma4 PLE device mismatch are unrelated." + }, + { + "left": "issue:43441", + "right": "issue:44683", + "accept": false, + "reason": "Both involve attention acceleration, but FlashAttention failure and compiled flex_attention failure are different concrete problems." + }, + { + "left": "issue:43901", + "right": "issue:43994", + "accept": false, + "reason": "Docs mismatch for return_all_scores is unrelated to SigLIP2 producing bad predictions." + }, + { + "left": "issue:43723", + "right": "issue:44162", + "accept": false, + "reason": "AutoTokenizer loading issue and ESM2 breakage are unrelated." + }, + { + "left": "issue:43901", + "right": "issue:44246", + "accept": false, + "reason": "Documentation mismatch and slow import are not the same bug." + }, + { + "left": "issue:43525", + "right": "issue:43881", + "accept": false, + "reason": "Both are model-loading failures, but for different models and different missing-field symptoms." + }, + { + "left": "issue:43450", + "right": "issue:44617", + "accept": false, + "reason": "Incorrect batched video shape and CUDA OOM in Sam3Video are not the same issue." + }, + { + "left": "issue:44297", + "right": "issue:45397", + "accept": false, + "reason": "Tokenizer save metadata mismatch is unrelated to Gemma4 zero3 loading." + }, + { + "left": "issue:43525", + "right": "issue:43643", + "accept": false, + "reason": "A missing pad_token_id attribute and trust_remote_code dropping fields are distinct config bugs." + }, + { + "left": "issue:43784", + "right": "issue:45542", + "accept": false, + "reason": "Import NameError for sentence-transformers and undefined tf backend error are unrelated." + }, + { + "left": "issue:44016", + "right": "issue:44291", + "accept": false, + "reason": "Notebook syntax error and init_empty_weights argument incompatibility are unrelated." + }, + { + "left": "issue:44188", + "right": "issue:44336", + "accept": false, + "reason": "Attention kernel divergence and ANSI output in loading_report are unrelated." + }, + { + "left": "issue:43262", + "right": "issue:44521", + "accept": false, + "reason": "Both involve apply_chat_template, but one is audio sampling-rate defaulting and the other is multimodal assistant mask generation." + }, + { + "left": "issue:44589", + "right": "issue:45362", + "accept": false, + "reason": "Storage type import failure and Qwen3.5 chat crash are unrelated." + }, + { + "left": "issue:41628", + "right": "issue:43976", + "accept": false, + "reason": "AutoImageProcessor import error and Python version compatibility are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:43761", + "accept": false, + "reason": "Different v5 regressions affecting GenerationMixin cache vs CLIPVisionModel hidden_states." + }, + { + "left": "issue:44336", + "right": "issue:44373", + "accept": false, + "reason": "ANSI code emission and a wrong docstring for position_ids are unrelated." + }, + { + "left": "issue:16998", + "right": "issue:22355", + "accept": false, + "reason": "DeBERTa model_max_length question and missing transformers.onnx module are unrelated." + }, + { + "left": "issue:42491", + "right": "issue:43299", + "accept": false, + "reason": "Both mention Qwen3 MoE, but one is LoRA reuse across versions and the other is base model loading breakage." + }, + { + "left": "issue:44246", + "right": "issue:44496", + "accept": false, + "reason": "Slow import and unrecognized model/config model_type are unrelated." + }, + { + "left": "issue:44242", + "right": "issue:45593", + "accept": false, + "reason": "Both concern auxiliary losses, but they are for different model families and different gating flags." + }, + { + "left": "issue:44295", + "right": "issue:45397", + "accept": false, + "reason": "Reading position_ids after buffer registration is unrelated to Gemma4 zero3 loading." + }, + { + "left": "issue:44246", + "right": "issue:44871", + "accept": false, + "reason": "Import latency and eos_token_id config inconsistency are unrelated." + }, + { + "left": "issue:44336", + "right": "issue:44485", + "accept": false, + "reason": "ANSI output in loading_report and GLM-5 RoPE implementation are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 36, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36246", + "issue:41950", + "issue:42757", + "issue:42886", + "issue:43065", + "issue:43232", + "issue:43257", + "issue:43262", + "issue:43352", + "issue:43408", + "issue:43526", + "issue:43596", + "issue:43673", + "issue:43824", + "issue:43901", + "issue:43976", + "issue:44162", + "issue:44220", + "issue:44242", + "issue:44246", + "issue:44295", + "issue:44336", + "issue:44351", + "issue:44496", + "issue:44561", + "issue:44749", + "issue:44779", + "issue:44857", + "issue:44877", + "issue:44964", + "issue:44987", + "issue:45003", + "issue:45081", + "issue:45137", + "issue:45200", + "issue:45250", + "issue:45292", + "issue:45362", + "issue:45375", + "issue:45412", + "issue:45459", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45701", + "issue:45759", + "issue:46123", + "issue:46132" + ], + "soft_pairs": [ + "issue:43824|issue:43976", + "issue:41950|issue:44220", + "issue:36246|issue:42757", + "issue:43976|issue:44964", + "issue:36246|issue:44351", + "issue:42886|issue:46132", + "issue:44779|issue:45292", + "issue:44242|issue:44857", + "issue:45081|issue:45362", + "issue:43673|issue:44561", + "issue:44295|issue:44749", + "issue:43352|issue:45250", + "issue:43901|issue:45003", + "issue:44162|issue:45200", + "issue:43526|issue:45003", + "issue:44496|issue:45003", + "issue:45412|issue:46123", + "issue:45292|issue:45584", + "issue:43262|issue:44246", + "issue:45292|issue:45701", + "issue:36246|issue:43596", + "issue:43257|issue:45137", + "issue:45375|issue:45759", + "issue:44877|issue:45375", + "issue:45561|issue:45563", + "issue:43232|issue:44336", + "issue:44987|issue:45459", + "issue:43065|issue:43408" + ], + "prepared_review_unit_hash": "51b59eed482f8561fbc6780150ea1376dde5d9c81002f8bf5bcb6c075c134a3c", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 36089, + "estimated_input_tokens": 9023, + "estimated_eval_tokens": 18302 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is a noisy mix of unrelated issues spanning imports, generation, tokenization, configs, and DeepSpeed; none of the soft pairs looks like the same underlying bug or fix. No PRs are present.", + "confidence": 0.92, + "canonical_issue_reason": "No single canonical issue is a safe duplicate representative here; the items are too heterogeneous and the soft links are only superficial similarity.", + "canonical_pr_reason": null, + "best_issue_reason": "No issue stands out as the global representative because there is no coherent common bug across the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43824", + "right": "issue:43976", + "accept": false, + "reason": "Different problems: a missing Qwen2.5-VL export vs a Python-version compatibility failure." + }, + { + "left": "issue:41950", + "right": "issue:44220", + "accept": false, + "reason": "Video-classification image-processor lookup and audio feature extraction are unrelated code paths." + }, + { + "left": "issue:36246", + "right": "issue:42757", + "accept": false, + "reason": "Missing Qwen2.5-VL image processor import is unrelated to huggingface_hub's is_offline_mode import error." + }, + { + "left": "issue:43976", + "right": "issue:44964", + "accept": false, + "reason": "Python support/versioning issue vs a specific multimodal model-loading regression." + }, + { + "left": "issue:36246", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols in different modules with different causes." + }, + { + "left": "issue:42886", + "right": "issue:46132", + "accept": false, + "reason": "Offline cache loading failure and AttentionInterface.register behavior changes are separate behaviors." + }, + { + "left": "issue:44779", + "right": "issue:45292", + "accept": false, + "reason": "Tokenizer regression and output-embedding resize propagation are distinct bugs." + }, + { + "left": "issue:44242", + "right": "issue:44857", + "accept": false, + "reason": "MoE load-balancing loss handling is unrelated to the LwDetrImageLoss AMP crash." + }, + { + "left": "issue:45081", + "right": "issue:45362", + "accept": false, + "reason": "Mistral regex patch failure and Qwen chat crash do not share the same concrete code path." + }, + { + "left": "issue:43673", + "right": "issue:44561", + "accept": false, + "reason": "Generation cache handling during chunked prefill is unrelated to trust_remote_code breakage from a removed helper." + }, + { + "left": "issue:44295", + "right": "issue:44749", + "accept": false, + "reason": "A buffer access IndexError and a slowdown after upgrade are not the same bug." + }, + { + "left": "issue:43352", + "right": "issue:45250", + "accept": false, + "reason": "Unsupported Flash Attention message for Nemotron is not the same as a generic Flash Attention issue." + }, + { + "left": "issue:43901", + "right": "issue:45003", + "accept": false, + "reason": "Docs mismatch about return_all_scores is unrelated to unsafe sys.modules access." + }, + { + "left": "issue:44162", + "right": "issue:45200", + "accept": false, + "reason": "ESM2 breakage and Gemma 4 token-id defaults are different model-specific regressions." + }, + { + "left": "issue:43526", + "right": "issue:45003", + "accept": false, + "reason": "BEiT reduce_labels truncation is unrelated to sys.modules access in modeling_utils." + }, + { + "left": "issue:44496", + "right": "issue:45003", + "accept": false, + "reason": "Unrecognized model/config loading is not the same failure as unsafe sys.modules lookup." + }, + { + "left": "issue:45412", + "right": "issue:46123", + "accept": false, + "reason": "RT-DETR memory retention and MaskGenerationPipeline partial-batch dropping are separate issues." + }, + { + "left": "issue:45292", + "right": "issue:45584", + "accept": false, + "reason": "Embedding resize propagation and Whisper empty-transcription generation are different code paths." + }, + { + "left": "issue:43262", + "right": "issue:44246", + "accept": false, + "reason": "Audio chat-template sample-rate defaulting is unrelated to import slowness." + }, + { + "left": "issue:45292", + "right": "issue:45701", + "accept": false, + "reason": "Embedding resize behavior is not the same as a version-dependent tokenization change." + }, + { + "left": "issue:36246", + "right": "issue:43596", + "accept": false, + "reason": "Qwen2.5-VL import failure and DeepSpeed zero3/BertModel IndexError are unrelated." + }, + { + "left": "issue:43257", + "right": "issue:45137", + "accept": false, + "reason": "Qwen3 MoE weight conversion under accelerate+deepspeed is different from a Zero3 deque underflow." + }, + { + "left": "issue:45375", + "right": "issue:45759", + "accept": false, + "reason": "Missing config field under strict handling and text_config unwrapping for composite configs are different bugs." + }, + { + "left": "issue:44877", + "right": "issue:45375", + "accept": false, + "reason": "Both involve config handling, but they concern different models and different failure modes." + }, + { + "left": "issue:45561", + "right": "issue:45563", + "accept": false, + "reason": "pytest-xdist file races and a stale generate warning are unrelated." + }, + { + "left": "issue:43232", + "right": "issue:44336", + "accept": false, + "reason": "Generation kwargs update logic and ANSI-code leakage in loading_report are unrelated." + }, + { + "left": "issue:44987", + "right": "issue:45459", + "accept": false, + "reason": "Model-loading failure and tokenizer protobuf error handling are separate issues." + }, + { + "left": "issue:43065", + "right": "issue:43408", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is not the same bug as a sam3_video/sam3_tracker model-type mismatch warning." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 37, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:42886", + "issue:42994", + "issue:43475", + "issue:43482", + "issue:43540", + "issue:43646", + "issue:43653", + "issue:43673", + "issue:43701", + "issue:43827", + "issue:43931", + "issue:44060", + "issue:44077", + "issue:44162", + "issue:44188", + "issue:44297", + "issue:44361", + "issue:44368", + "issue:44466", + "issue:44479", + "issue:44483", + "issue:44623", + "issue:44734", + "issue:44749", + "issue:44869", + "issue:44871", + "issue:44877", + "issue:44977", + "issue:44995", + "issue:45003", + "issue:45137", + "issue:45200", + "issue:45229", + "issue:45230", + "issue:45335", + "issue:45356", + "issue:45397", + "issue:45561", + "issue:45563", + "issue:45584", + "issue:45588", + "issue:45600", + "issue:45656", + "issue:45987", + "issue:46082", + "issue:46132", + "issue:46170", + "issue:46202" + ], + "soft_pairs": [ + "issue:45987|issue:46082", + "issue:44995|issue:45200", + "issue:44466|issue:45335", + "issue:44479|issue:46170", + "issue:43475|issue:43540", + "issue:45397|issue:45656", + "issue:44483|issue:46202", + "issue:45137|issue:45600", + "issue:43653|issue:44162", + "issue:44995|issue:45588", + "issue:44368|issue:44977", + "issue:44368|issue:45563", + "issue:44877|issue:46170", + "issue:43931|issue:44368", + "issue:42886|issue:45229", + "issue:43673|issue:44734", + "issue:44060|issue:44077", + "issue:45003|issue:45561", + "issue:45584|issue:46170", + "issue:44297|issue:44623", + "issue:44869|issue:45356", + "issue:44361|issue:44749", + "issue:43646|issue:44162", + "issue:44871|issue:46132", + "issue:43673|issue:43827", + "issue:44749|issue:45656", + "issue:44623|issue:45656", + "issue:43701|issue:44749", + "issue:44188|issue:46202", + "issue:42994|issue:43482", + "issue:45230|issue:45397" + ], + "prepared_review_unit_hash": "5ec68d9ef8b9e1aca9157a3bb17dca6213d16f18aa10d7b53dda023166e55be5", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36924, + "estimated_input_tokens": 9231, + "estimated_eval_tokens": 18718 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous and the soft pairs are mostly thematic rather than true duplicates. I would not merge any of the candidate edges; they point to different bugs, code paths, or models.", + "confidence": 0.97, + "canonical_issue_reason": "No single canonical issue: these items cover unrelated bugs across tokenizers, generation, multimodal models, serving, and training utilities.", + "canonical_pr_reason": null, + "best_issue_reason": "No clear best duplicate target for the cluster; issue 45561 has the most cross-reference activity, but it is not representative of the other issues.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45987", + "right": "issue:46082", + "accept": false, + "reason": "StaticCache return-type bug vs LlamaConfig head_dim validation; different subsystems and failure modes." + }, + { + "left": "issue:44995", + "right": "issue:45200", + "accept": false, + "reason": "GlmMoeDsa stale indexer on second forward is unrelated to Gemma 4 token-type defaults." + }, + { + "left": "issue:44466", + "right": "issue:45335", + "accept": false, + "reason": "Both mention tied embeddings, but one is save/serialization behavior and the other is resize_token_embeddings propagation." + }, + { + "left": "issue:44479", + "right": "issue:46170", + "accept": false, + "reason": "Qwen video regression and Windows ROCm import/dependency issue are unrelated." + }, + { + "left": "issue:43475", + "right": "issue:43540", + "accept": false, + "reason": "Different multimodal model bugs with no shared code path indicated." + }, + { + "left": "issue:45397", + "right": "issue:45656", + "accept": false, + "reason": "ZeRO3 from_pretrained loading problem is distinct from a double optimizer-step bug in deepspeed." + }, + { + "left": "issue:44483", + "right": "issue:46202", + "accept": false, + "reason": "OpenAI chat completions API rejection is unrelated to Gemma pipeline roundtrip tokenization." + }, + { + "left": "issue:45137", + "right": "issue:45600", + "accept": false, + "reason": "ZeRO3 deque error and removed-config CI breakage are unrelated." + }, + { + "left": "issue:43653", + "right": "issue:44162", + "accept": false, + "reason": "Tokenizer special-token registration bug is not the same as the ESM2 breakage report." + }, + { + "left": "issue:44995", + "right": "issue:45588", + "accept": false, + "reason": "Stale indexer cache crash and flash-attention s_aux=None AttributeError are different code paths." + }, + { + "left": "issue:44368", + "right": "issue:44977", + "accept": false, + "reason": "A tied-embeddings warning during fine-tuning is not the same as a flash-attention generation regression." + }, + { + "left": "issue:44368", + "right": "issue:45563", + "accept": false, + "reason": "Both are warnings, but they concern different generation APIs and different bugs." + }, + { + "left": "issue:44877", + "right": "issue:46170", + "accept": false, + "reason": "Strict config loading for granite_speech is unrelated to the Windows ROCm import failure." + }, + { + "left": "issue:43931", + "right": "issue:44368", + "accept": false, + "reason": "Qwen3-VL weight-shape mismatch is unrelated to a tie_word_embeddings warning." + }, + { + "left": "issue:42886", + "right": "issue:45229", + "accept": false, + "reason": "Offline cache-loading failure and multi-GPU CUDA OOM are unrelated." + }, + { + "left": "issue:43673", + "right": "issue:44734", + "accept": false, + "reason": "Missing GenerationMixin cache during chunked_prefill is a different bug from server-side KV-cache tensor indexing." + }, + { + "left": "issue:44060", + "right": "issue:44077", + "accept": false, + "reason": "Qwen3-Next tied-weights warning and patchtsmixer post_init policy are unrelated." + }, + { + "left": "issue:45003", + "right": "issue:45561", + "accept": false, + "reason": "sys.modules access bug and pytest-xdist captured_info.txt race are different issues." + }, + { + "left": "issue:45584", + "right": "issue:46170", + "accept": false, + "reason": "Whisper empty-transcription failure is unrelated to the Windows ROCm dependency problem." + }, + { + "left": "issue:44297", + "right": "issue:44623", + "accept": false, + "reason": "tokenizer.save_pretrained config mismatch and processor.save_pretrained missing files are related only at a high level, not the same concrete bug." + }, + { + "left": "issue:44869", + "right": "issue:45356", + "accept": false, + "reason": "Whisper trailing replacement-character crash and Kimi-K2.5 codec regression are different tokenizer bugs." + }, + { + "left": "issue:44361", + "right": "issue:44749", + "accept": false, + "reason": "MLukeTokenizer AttributeError and a performance regression after upgrade are unrelated." + }, + { + "left": "issue:43646", + "right": "issue:44162", + "accept": false, + "reason": "A broad transformers v5 initialization breakage does not match the specific ESM2 failure report." + }, + { + "left": "issue:44871", + "right": "issue:46132", + "accept": false, + "reason": "Gemma eos_token_id inconsistency is unrelated to AttentionInterface.register behavior changes." + }, + { + "left": "issue:43673", + "right": "issue:43827", + "accept": false, + "reason": "Generation cache bug and docs referencing removed pipeline() are unrelated." + }, + { + "left": "issue:44749", + "right": "issue:45656", + "accept": false, + "reason": "Filtering slowdown after upgrade and a double optimizer-step bug are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45656", + "accept": false, + "reason": "Missing processor save files and deepspeed optimizer double-step are unrelated." + }, + { + "left": "issue:43701", + "right": "issue:44749", + "accept": false, + "reason": "resume_from_checkpoint key mismatch is unrelated to the data-length slowdown regression." + }, + { + "left": "issue:44188", + "right": "issue:46202", + "accept": false, + "reason": "torch.compile attention-kernel divergence is unrelated to Gemma pipeline roundtrip behavior." + }, + { + "left": "issue:42994", + "right": "issue:43482", + "accept": false, + "reason": "Quantized model saving failure and GGUF loading failure are opposite directions and likely different serialization paths." + }, + { + "left": "issue:45230", + "right": "issue:45397", + "accept": false, + "reason": "Generic bug report provides no evidence of the same Gemma-4 ZeRO3 loading issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 38, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28282", + "issue:30990", + "issue:35141", + "issue:36010", + "issue:41628", + "issue:42175", + "issue:42371", + "issue:42673", + "issue:42831", + "issue:42898", + "issue:42994", + "issue:43232", + "issue:43278", + "issue:43377", + "issue:43475", + "issue:43525", + "issue:43643", + "issue:43673", + "issue:43704", + "issue:43824", + "issue:43901", + "issue:44038", + "issue:44222", + "issue:44242", + "issue:44351", + "issue:44496", + "issue:44568", + "issue:44623", + "issue:44661", + "issue:44792", + "issue:44933", + "issue:44964", + "issue:45081", + "issue:45092", + "issue:45103", + "issue:45137", + "issue:45310", + "issue:45375", + "issue:45381", + "issue:45406", + "issue:45478", + "issue:45561", + "issue:45600", + "issue:45712", + "issue:46077", + "issue:46123", + "issue:46202" + ], + "soft_pairs": [ + "issue:28282|issue:30990", + "issue:43475|issue:43643", + "issue:43475|issue:45381", + "issue:44038|issue:44623", + "issue:42371|issue:45092", + "issue:43232|issue:43673", + "issue:41628|issue:44933", + "issue:43475|issue:44661", + "issue:42994|issue:43525", + "issue:45375|issue:45478", + "issue:46077|issue:46123", + "issue:45081|issue:45103", + "issue:45310|issue:45375", + "issue:45406|issue:46202", + "issue:42673|issue:43704", + "issue:41628|issue:44351", + "issue:44964|issue:45137", + "issue:42994|issue:43824", + "issue:44222|issue:45310", + "issue:36010|issue:41628", + "issue:44038|issue:45310", + "issue:42831|issue:44222", + "issue:42175|issue:45712", + "issue:44496|issue:45561", + "issue:43377|issue:44242", + "issue:42898|issue:44568", + "issue:45561|issue:45600", + "issue:43901|issue:45561", + "issue:43232|issue:44792", + "issue:30990|issue:35141", + "issue:43278|issue:45137" + ], + "prepared_review_unit_hash": "9ffc59c6223e8459e9c66a9cffa02763925d90aef37dee3cf460dcb8a86549a9", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 31, + "serialized_chars": 36414, + "estimated_input_tokens": 9104, + "estimated_eval_tokens": 18464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is heterogeneous overall, but it does contain two clear duplicate families: issue:42673 \u2194 issue:43704 (Qwen3ForCausalLM VRAM leak in multiple dataloader threads) and issue:45310 \u2194 issue:45478 (Qwen3.5 Moe from_pretrained error). The rest of the soft links look like conservative rejections.", + "confidence": 0.88, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster because it spans two separate duplicate families; if one representative must be chosen, issue:42673 is the stronger document for the VRAM-leak family, while issue:45310 is the counterpart for the Qwen3.5 Moe loading family.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42673 is the best-documented and most active issue overall, but only for one duplicate family. The cluster also has a separate, equally clear duplicate family centered on issue:45310/issue:45478, so 42673 should not be treated as the sole representative of the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:28282", + "right": "issue:30990", + "accept": false, + "reason": "Different failure modes: a PyTorch import error versus Sentence Transformers getting stuck while loading." + }, + { + "left": "issue:43475", + "right": "issue:43643", + "accept": false, + "reason": "Different model paths and bugs: missing SAM vision encoder attribute versus missing AutoConfig fields with trust_remote_code." + }, + { + "left": "issue:43475", + "right": "issue:45381", + "accept": false, + "reason": "Unrelated model-specific bugs: SAM 3 vision output attribute error versus Qwen2.5-VL video position-id issues." + }, + { + "left": "issue:44038", + "right": "issue:44623", + "accept": false, + "reason": "Different surfaces: Qwen3-VL-Moe loading versus processor.save_pretrained missing files." + }, + { + "left": "issue:42371", + "right": "issue:45092", + "accept": false, + "reason": "Packaging/backend setup issue versus remote-code meta-initialization incompatibility; not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:43673", + "accept": false, + "reason": "Both involve generation internals, but the concrete code paths differ: sync_gpus/_update_model_kwargs_for_generation versus chunked_prefill cache handling." + }, + { + "left": "issue:41628", + "right": "issue:44933", + "accept": false, + "reason": "Both are import-related, but they concern different missing symbols and different modules." + }, + { + "left": "issue:43475", + "right": "issue:44661", + "accept": false, + "reason": "Different problems: SAM 3 output attribute error versus add-new-model-like failing in TOKENIZER_MAPPING_NAMES." + }, + { + "left": "issue:42994", + "right": "issue:43525", + "accept": false, + "reason": "Different bug classes: quantized model saving failure versus Llama4Config missing pad_token_id." + }, + { + "left": "issue:45375", + "right": "issue:45478", + "accept": false, + "reason": "Same model family, but one is a missing config field and the other is a from_pretrained loading error; too different to merge." + }, + { + "left": "issue:46077", + "right": "issue:46123", + "accept": false, + "reason": "Different subsystems: Gemma4 attention-mask construction versus MaskGenerationPipeline final-batch bookkeeping." + }, + { + "left": "issue:45081", + "right": "issue:45103", + "accept": false, + "reason": "Unrelated AttributeErrors in different areas: tokenizer regex patching versus auto-docstring kwargs processing." + }, + { + "left": "issue:45310", + "right": "issue:45375", + "accept": false, + "reason": "Related family, but not the same concrete bug: Qwen3.5 Moe loading error versus a vision-config field being dropped by strict parsing." + }, + { + "left": "issue:45406", + "right": "issue:46202", + "accept": false, + "reason": "Different Gemma-related issues: processor missing _tokenizer versus pipeline roundtrip failure on the underscore token." + }, + { + "left": "issue:42673", + "right": "issue:43704", + "accept": true, + "reason": "Exact duplicate title and same VRAM leak in Qwen3ForCausalLM when used in multiple dataloader threads." + }, + { + "left": "issue:41628", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but they are for different exported objects and do not indicate the same underlying bug." + }, + { + "left": "issue:44964", + "right": "issue:45137", + "accept": false, + "reason": "Different failures: multimodal model loading versus a DeepSpeed ZeRO3 deque underflow." + }, + { + "left": "issue:42994", + "right": "issue:43824", + "accept": false, + "reason": "Saving quantized models is unrelated to an import error for Qwen2_5_VLForConditionalGeneration." + }, + { + "left": "issue:44222", + "right": "issue:45310", + "accept": false, + "reason": "Same broad model area, but one is FP8 save_pretrained behavior and the other is a from_pretrained loading error." + }, + { + "left": "issue:36010", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different API symbols and likely different code paths." + }, + { + "left": "issue:44038", + "right": "issue:45310", + "accept": false, + "reason": "Different models and symptoms: Qwen3-VL-Moe issue versus Qwen3.5 Moe loading error." + }, + { + "left": "issue:42831", + "right": "issue:44222", + "accept": false, + "reason": "Accuracy regression with FineGrainedFP8 is not the same as FP8 save_pretrained failing." + }, + { + "left": "issue:42175", + "right": "issue:45712", + "accept": false, + "reason": "Both touch packaging/torch-related surfaces, but one is missing TensorFlow in the torch extra and the other is dummy PT objects leaking into the API." + }, + { + "left": "issue:44496", + "right": "issue:45561", + "accept": false, + "reason": "Unrelated issues: unrecognized model/config loading versus a pytest-xdist file race." + }, + { + "left": "issue:43377", + "right": "issue:44242", + "accept": false, + "reason": "Different model bugs: missing padding-mask support in MIMI encoder versus omitted load-balancing loss when router logits are disabled." + }, + { + "left": "issue:42898", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer behavior changes in v5, but they affect different behaviors and likely require different fixes." + }, + { + "left": "issue:45561", + "right": "issue:45600", + "accept": false, + "reason": "A concurrency race in testing utilities is unrelated to stale references in auto_mappings.py." + }, + { + "left": "issue:43901", + "right": "issue:45561", + "accept": false, + "reason": "Docs/behavior mismatch in a pipeline is unrelated to a pytest-xdist race." + }, + { + "left": "issue:43232", + "right": "issue:44792", + "accept": false, + "reason": "Generation kwargs handling and a Janus image-generation test failure are different issues." + }, + { + "left": "issue:30990", + "right": "issue:35141", + "accept": false, + "reason": "Loading hang versus embedding reinitialization after resizing token embeddings are different bugs." + }, + { + "left": "issue:43278", + "right": "issue:45137", + "accept": false, + "reason": "Different failures: dtype drift during evaluate versus a DeepSpeed ZeRO3 deque error." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports two clear duplicate pairs, not just one: issue:42673 \u2194 issue:43704 and issue:45310 \u2194 issue:45478. Because of that, the claim that 42673 is the best representative of the only clearly duplicated bug overstates the evidence. The rest of the conservative rejections look reasonable, but the cluster summary/canonical framing should acknowledge both duplicate families." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 39, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28282", + "issue:30333", + "issue:33290", + "issue:34689", + "issue:35141", + "issue:36331", + "issue:42175", + "issue:42222", + "issue:42831", + "issue:42898", + "issue:43065", + "issue:43232", + "issue:43479", + "issue:43723", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43976", + "issue:44016", + "issue:44060", + "issue:44075", + "issue:44079", + "issue:44188", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44448", + "issue:44568", + "issue:44623", + "issue:44734", + "issue:44779", + "issue:44933", + "issue:45092", + "issue:45103", + "issue:45125", + "issue:45200", + "issue:45245", + "issue:45310", + "issue:45356", + "issue:45405", + "issue:45656", + "issue:45712", + "issue:45812", + "issue:46123", + "issue:46132", + "issue:46231" + ], + "soft_pairs": [ + "issue:42222|issue:45200", + "issue:44623|issue:45310", + "issue:30333|issue:33290", + "issue:43065|issue:46123", + "issue:44188|issue:44373", + "issue:43232|issue:44188", + "issue:42898|issue:45812", + "issue:43784|issue:43824", + "issue:43723|issue:44568", + "issue:42898|issue:44779", + "issue:42898|issue:45356", + "issue:43874|issue:45092", + "issue:44734|issue:45103", + "issue:44016|issue:46231", + "issue:44075|issue:46231", + "issue:44060|issue:45125", + "issue:42898|issue:44448", + "issue:44295|issue:45656", + "issue:45405|issue:45712", + "issue:42175|issue:44933", + "issue:44448|issue:46132", + "issue:44222|issue:44297", + "issue:44933|issue:45712", + "issue:43479|issue:44079", + "issue:43976|issue:44933", + "issue:44297|issue:45656", + "issue:30333|issue:34689", + "issue:44222|issue:44623", + "issue:42831|issue:44623", + "issue:45245|issue:46132", + "issue:30333|issue:36331", + "issue:28282|issue:30333", + "issue:30333|issue:35141" + ], + "prepared_review_unit_hash": "c8f893a020afb3e91166c5ec0f437c3b6eddc3d6e75423658dbfa620f2de7bc2", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 33, + "serialized_chars": 37117, + "estimated_input_tokens": 9280, + "estimated_eval_tokens": 18816 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a set of unrelated Transformers issues with superficial lexical overlap (many tokenizer/v5/regression topics). I do not see any true duplicate pair; the best representative issue is the broad v5 tokenizer regression around `clean_up_tokenization_spaces`.", + "confidence": 0.28, + "canonical_issue_reason": "No single canonical duplicate issue emerges: the items span unrelated bugs across model loading, training, tokenization, generation, packaging, and docs. If forced to anchor the cluster, issue 42898 is the broadest v5 tokenizer regression representative.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42898 is the most central representative by similarity, but it is still not a duplicate of the other issues; it best fits the cluster\u2019s loose v5/tokenizer regression theme.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:42222", + "right": "issue:45200", + "accept": false, + "reason": "Different subsystems: VitPose model import/breakage vs Gemma 4 multimodal token-type defaults." + }, + { + "left": "issue:44623", + "right": "issue:45310", + "accept": false, + "reason": "Both involve save/load flows, but one is processor.save_pretrained missing files and the other is a Qwen3.5 MoE from_pretrained failure; not the same bug." + }, + { + "left": "issue:30333", + "right": "issue:33290", + "accept": false, + "reason": "MLflow job-reporting failure vs DeepSpeed Adafactor OOM; unrelated training issues." + }, + { + "left": "issue:43065", + "right": "issue:46123", + "accept": false, + "reason": "Dummy Conv2d in Sam3PixelDecoder is unrelated to MaskGenerationPipeline final-batch handling." + }, + { + "left": "issue:44188", + "right": "issue:44373", + "accept": false, + "reason": "torch.compile attention-kernel divergence is unrelated to a docstring correction for position_ids." + }, + { + "left": "issue:43232", + "right": "issue:44188", + "accept": false, + "reason": "Generation kwargs update ordering vs attention-kernel branching under torch.compile; different code paths and symptoms." + }, + { + "left": "issue:42898", + "right": "issue:45812", + "accept": false, + "reason": "Both are v5 tokenizer regressions, but one is clean_up_tokenization_spaces behavior and the other is Granite token ID mapping; not the same concrete bug." + }, + { + "left": "issue:43784", + "right": "issue:43824", + "accept": false, + "reason": "Sentence-transformers import NameError vs missing Qwen2.5-VL export; distinct import failures." + }, + { + "left": "issue:43723", + "right": "issue:44568", + "accept": false, + "reason": "AutoTokenizer loading issue vs add_special_tokens not adding BOS/EOS for a specific tokenizer; different tokenizer bugs." + }, + { + "left": "issue:42898", + "right": "issue:44779", + "accept": false, + "reason": "Both are tokenizer regressions in v5, but they target different models and failure modes." + }, + { + "left": "issue:42898", + "right": "issue:45356", + "accept": false, + "reason": "Kimi-K2.5 codec handling/warning regression is separate from clean_up_tokenization_spaces behavior change." + }, + { + "left": "issue:43874", + "right": "issue:45092", + "accept": false, + "reason": "Missing image-patch method in a GLM image processor vs InternVL2 meta-initialization incompatibility; unrelated multimodal issues." + }, + { + "left": "issue:44734", + "right": "issue:45103", + "accept": false, + "reason": "KV-cache continuation crash in serve vs auto-docstring crash with future annotations; different components." + }, + { + "left": "issue:44016", + "right": "issue:46231", + "accept": false, + "reason": "Notebook syntax error is unrelated to a documentation parameter-name mismatch." + }, + { + "left": "issue:44075", + "right": "issue:46231", + "accept": false, + "reason": "Optimizer SGD arguments being ignored is unrelated to the set_training docs typo." + }, + { + "left": "issue:44060", + "right": "issue:45125", + "accept": false, + "reason": "Wrong tied-weights warning in Qwen3-Next is not the same as missing `_tp_plan` for Qwen3_5Moe." + }, + { + "left": "issue:42898", + "right": "issue:44448", + "accept": false, + "reason": "Both involve v4\u2192v5 output changes, but Pegasus generation differences are not the same bug as tokenization cleanup behavior." + }, + { + "left": "issue:44295", + "right": "issue:45656", + "accept": false, + "reason": "Position_ids buffer read error is unrelated to optimizer step being called twice with DeepSpeed." + }, + { + "left": "issue:45405", + "right": "issue:45712", + "accept": false, + "reason": "PEFT version pin issue is unrelated to leftover dummy classes in `dummy_pt_objects.py`." + }, + { + "left": "issue:42175", + "right": "issue:44933", + "accept": false, + "reason": "TensorFlow missing from a torch install extra is unrelated to a nonexistent import from image_utils." + }, + { + "left": "issue:44448", + "right": "issue:46132", + "accept": false, + "reason": "Pegasus output regression is unrelated to AttentionInterface.register changing function behavior." + }, + { + "left": "issue:44222", + "right": "issue:44297", + "accept": false, + "reason": "FP8 save_pretrained issue for MoE is separate from tokenizer_class mismatch in tokenizer config." + }, + { + "left": "issue:44933", + "right": "issue:45712", + "accept": false, + "reason": "image_utils import error and dummy PT class cleanup are different packaging/import problems." + }, + { + "left": "issue:43479", + "right": "issue:44079", + "accept": false, + "reason": "Phi4Multimodal config initialization bug is unrelated to ModelOutput key assignment when values were previously None." + }, + { + "left": "issue:43976", + "right": "issue:44933", + "accept": false, + "reason": "Python version compatibility issue is unrelated to the image_utils import problem." + }, + { + "left": "issue:44297", + "right": "issue:45656", + "accept": false, + "reason": "Tokenizer config class mismatch has nothing to do with DeepSpeed optimizer double-step behavior." + }, + { + "left": "issue:30333", + "right": "issue:34689", + "accept": false, + "reason": "MLflow training-job reporting bug is unrelated to Llama 3.2 Vision model loading breakage." + }, + { + "left": "issue:44222", + "right": "issue:44623", + "accept": false, + "reason": "MoE FP8 save_pretrained bug is not the same as processor.save_pretrained missing files." + }, + { + "left": "issue:42831", + "right": "issue:44623", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue is unrelated to processor save_pretrained missing files." + }, + { + "left": "issue:45245", + "right": "issue:46132", + "accept": false, + "reason": "Category-count runtime error is unrelated to AttentionInterface.register behavior changes." + }, + { + "left": "issue:30333", + "right": "issue:36331", + "accept": false, + "reason": "MLflow job reporting and CustomTrainer compute_loss signature mismatch are different training issues." + }, + { + "left": "issue:28282", + "right": "issue:30333", + "accept": false, + "reason": "AutoModel import error without PyTorch vs MLflow reporting bug; unrelated environment/training issues." + }, + { + "left": "issue:30333", + "right": "issue:35141", + "accept": false, + "reason": "MLflow failure reporting and embedding reinitialization in post_init are unrelated bugs." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 40, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:22355", + "issue:28282", + "issue:30990", + "issue:38175", + "issue:41628", + "issue:42757", + "issue:42831", + "issue:42907", + "issue:43122", + "issue:43232", + "issue:43479", + "issue:43644", + "issue:43723", + "issue:43761", + "issue:43824", + "issue:43873", + "issue:44190", + "issue:44206", + "issue:44222", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44360", + "issue:44373", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44514", + "issue:44623", + "issue:44829", + "issue:44869", + "issue:44871", + "issue:44913", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45092", + "issue:45103", + "issue:45310", + "issue:45357", + "issue:45406", + "issue:45834", + "issue:46002", + "issue:46050", + "issue:46082", + "issue:46209" + ], + "soft_pairs": [ + "issue:44190|issue:46082", + "issue:43479|issue:44869", + "issue:45071|issue:46082", + "issue:41628|issue:42757", + "issue:44206|issue:45103", + "issue:44297|issue:45310", + "issue:43723|issue:44977", + "issue:44263|issue:45092", + "issue:43122|issue:46209", + "issue:43873|issue:44945", + "issue:43232|issue:45834", + "issue:44222|issue:44484", + "issue:44373|issue:44485", + "issue:43479|issue:43644", + "issue:44295|issue:44623", + "issue:44483|issue:45406", + "issue:43761|issue:46082", + "issue:43723|issue:44871", + "issue:45092|issue:45357", + "issue:30990|issue:38175", + "issue:44263|issue:44360", + "issue:44261|issue:45092", + "issue:42907|issue:46050", + "issue:44514|issue:45103", + "issue:44829|issue:46002", + "issue:43479|issue:44913", + "issue:42831|issue:45310", + "issue:22355|issue:28282", + "issue:41628|issue:43824", + "issue:44263|issue:44373" + ], + "prepared_review_unit_hash": "62e68b6a5cf0af73761d5670e1d17fa973831321a5a7d75c2c307a5c324ddc87", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 30, + "serialized_chars": 35805, + "estimated_input_tokens": 8952, + "estimated_eval_tokens": 18160 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a loose pile of unrelated Transformers issues that share only broad regression/import/config language; none of the soft pairs look like true duplicates. No PRs are present.", + "confidence": 0.88, + "canonical_issue_reason": "issue:45092 is the clearest representative of the cluster\u2019s broad v5 regression / initialization theme and has a concrete repro path; the rest are mostly separate bugs.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45092 is the most actionable standalone issue with a specific failure mode and modern v5 context, making it the best representative if one must be chosen.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44190", + "right": "issue:46082", + "accept": false, + "reason": "Local dataset loading in a training script vs LlamaConfig head_dim validation; different code paths and failures." + }, + { + "left": "issue:43479", + "right": "issue:44869", + "accept": false, + "reason": "Multimodal config defaulting bug vs Whisper word-timestamp decode crash; unrelated models and subsystems." + }, + { + "left": "issue:45071", + "right": "issue:46082", + "accept": false, + "reason": "PretrainedConfig type-checking regression vs explicit head_dim validation in LlamaConfig; not the same bug." + }, + { + "left": "issue:41628", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but for different symbols/packages and likely different missing exports or version mismatches." + }, + { + "left": "issue:44206", + "right": "issue:45103", + "accept": false, + "reason": "Feature-extractor center-arg crash vs auto_docstring AttributeError under future annotations; unrelated failures." + }, + { + "left": "issue:44297", + "right": "issue:45310", + "accept": false, + "reason": "Tokenizer class mismatch on save vs Qwen3.5 MoE from_pretrained error; different save/load paths and symptoms." + }, + { + "left": "issue:43723", + "right": "issue:44977", + "accept": false, + "reason": "AutoTokenizer loading issue vs flash-attention generation bug; different functionality and code paths." + }, + { + "left": "issue:44263", + "right": "issue:45092", + "accept": false, + "reason": "torch.split return-value issue in a DSA indexer vs remote-code meta-init incompatibility; unrelated." + }, + { + "left": "issue:43122", + "right": "issue:46209", + "accept": false, + "reason": "Tokenization changes across versions vs FP8 inference on B200; different layers of the stack." + }, + { + "left": "issue:43873", + "right": "issue:44945", + "accept": false, + "reason": "Quantized offloading behavior vs pipeline-parallelism output correctness; same broad area, not the same bug." + }, + { + "left": "issue:43232", + "right": "issue:45834", + "accept": false, + "reason": "Generation kwargs update problem vs OCR long-input index error; separate model behaviors." + }, + { + "left": "issue:44222", + "right": "issue:44484", + "accept": false, + "reason": "FP8 save_pretrained bug vs max_shard_size default question; not the same underlying issue." + }, + { + "left": "issue:44373", + "right": "issue:44485", + "accept": false, + "reason": "Docstring mismatch for position_ids vs GLM-5 RoPE implementation discussion; unrelated." + }, + { + "left": "issue:43479", + "right": "issue:43644", + "accept": false, + "reason": "Config initialization defaults vs non-persistent buffer corruption; different bug classes." + }, + { + "left": "issue:44295", + "right": "issue:44623", + "accept": false, + "reason": "position_ids buffer read error vs processor.save_pretrained missing files; different serialization problems." + }, + { + "left": "issue:44483", + "right": "issue:45406", + "accept": false, + "reason": "Chat completions request rejection vs Gemma4Processor missing _tokenizer in serve; unrelated runtime failures." + }, + { + "left": "issue:43761", + "right": "issue:46082", + "accept": false, + "reason": "CLIP hidden_states regression vs LlamaConfig head_dim validation; different models and symptoms." + }, + { + "left": "issue:43723", + "right": "issue:44871", + "accept": false, + "reason": "Tokenizer loading issue vs eos_token_id config inconsistency; both config-related but distinct." + }, + { + "left": "issue:45092", + "right": "issue:45357", + "accept": false, + "reason": "Meta-init incompatibility for old checkpoints vs incorrect visual encoder keys on save_pretrained; same model family but different code paths." + }, + { + "left": "issue:30990", + "right": "issue:38175", + "accept": false, + "reason": "Sentence Transformers loading hang vs unexpected zero probabilities in SigLIP2; unrelated." + }, + { + "left": "issue:44263", + "right": "issue:44360", + "accept": false, + "reason": "Both mention the DSA indexer, but one is about torch.split outputs and the other about a missing ReLU; not the same bug." + }, + { + "left": "issue:44261", + "right": "issue:45092", + "accept": false, + "reason": "MLA layernorm epsilon precision issue vs checkpoint/meta-init incompatibility; different underlying problems." + }, + { + "left": "issue:42907", + "right": "issue:46050", + "accept": false, + "reason": "Dequantized save bug for specific models vs sinq quantized model save/load breakage; similar theme but not same defect." + }, + { + "left": "issue:44514", + "right": "issue:45103", + "accept": false, + "reason": "Batched chat-template crash vs auto_docstring crash from future annotations; unrelated functionality." + }, + { + "left": "issue:44829", + "right": "issue:46002", + "accept": false, + "reason": "flash_attention_3 training degeneration vs NaNs after checkout+init; different symptoms and likely different causes." + }, + { + "left": "issue:43479", + "right": "issue:44913", + "accept": false, + "reason": "Both touch config handling, but one is default initialization for multimodal configs and the other is rotary_pct not persisting on reload." + }, + { + "left": "issue:42831", + "right": "issue:45310", + "accept": false, + "reason": "FineGrainedFP8 accuracy issue vs Qwen3.5 MoE from_pretrained error; unrelated FP8/model-loading bugs." + }, + { + "left": "issue:22355", + "right": "issue:28282", + "accept": false, + "reason": "transformers.onnx missing vs PyTorch-not-found import error; different dependency and module issues." + }, + { + "left": "issue:41628", + "right": "issue:43824", + "accept": false, + "reason": "Different missing transformer imports for different classes/models; both import errors but not the same fix." + }, + { + "left": "issue:44263", + "right": "issue:44373", + "accept": false, + "reason": "DSA indexer runtime behavior vs docstring typo; 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": 18, + "review_unit_index": 41, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:30990", + "issue:33357", + "issue:39401", + "issue:41628", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42886", + "issue:42907", + "issue:42994", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43408", + "issue:43475", + "issue:43550", + "issue:43576", + "issue:43646", + "issue:43723", + "issue:43756", + "issue:43784", + "issue:43937", + "issue:44038", + "issue:44060", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44295", + "issue:44297", + "issue:44373", + "issue:44442", + "issue:44464", + "issue:44514", + "issue:44568", + "issue:44704", + "issue:44779", + "issue:44945", + "issue:44964", + "issue:45200", + "issue:45278", + "issue:45290", + "issue:45593", + "issue:45600", + "issue:45753", + "issue:46002", + "issue:46082", + "issue:46132" + ], + "soft_pairs": [ + "issue:39401|issue:44568", + "issue:42831|issue:44038", + "issue:42886|issue:43066", + "issue:42886|issue:42994", + "issue:42757|issue:45278", + "issue:44945|issue:45753", + "issue:44464|issue:46082", + "issue:44117|issue:44704", + "issue:43576|issue:43784", + "issue:43646|issue:46002", + "issue:42371|issue:44263", + "issue:43550|issue:46132", + "issue:30990|issue:33357", + "issue:43232|issue:45593", + "issue:44295|issue:44297", + "issue:44704|issue:45290", + "issue:43723|issue:44442", + "issue:44261|issue:44373", + "issue:42907|issue:44945", + "issue:43723|issue:44779", + "issue:43784|issue:45600", + "issue:41628|issue:45278", + "issue:42907|issue:43937", + "issue:43756|issue:44060", + "issue:43408|issue:43475", + "issue:43122|issue:44514", + "issue:43116|issue:45200", + "issue:42907|issue:44964" + ], + "prepared_review_unit_hash": "339a79c2ab4dc4a11931622b68154ab4090eb89791b3adec89422e7174e922f6", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 28, + "serialized_chars": 35648, + "estimated_input_tokens": 8912, + "estimated_eval_tokens": 18080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers v5 regression reports. The only plausible duplicate here is the AutoTokenizer loading regression pair (43723/44442); the rest are different bugs in different subsystems or model families.", + "confidence": 0.79, + "canonical_issue_reason": "issue:43723 is the broadest, most central issue in the only likely duplicate pair: a generic AutoTokenizer.from_pretrained loading regression in v5.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43723 best represents the cluster\u2019s only true duplicate theme because it describes the underlying tokenizer-loading failure at the general code-path level.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:39401", + "right": "issue:44568", + "accept": false, + "reason": "Both are tokenizer bugs, but one is offset_mapping for Qwen3 and the other is missing BOS/EOS insertion for mdeberta; different code paths and symptoms." + }, + { + "left": "issue:42831", + "right": "issue:44038", + "accept": false, + "reason": "Different model-specific failures: one is an FP8 accuracy issue, the other is a transformers 5.0/Qwen3-VL-Moe bug." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Offline cache loading failure vs wrong tokenizer decoder type; related area but not the same bug." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Tokenizer cache loading failure and quantized model save failure are unrelated change paths." + }, + { + "left": "issue:42757", + "right": "issue:45278", + "accept": false, + "reason": "One is a specific missing huggingface_hub symbol, the other is a broad set of import errors after upgrade; not one concrete defect." + }, + { + "left": "issue:44945", + "right": "issue:45753", + "accept": false, + "reason": "Pipeline-parallelism wrong output and an infinite loop on a specific image are different multimodal/runtime failures." + }, + { + "left": "issue:44464", + "right": "issue:46082", + "accept": false, + "reason": "Chunked generation inconsistency with compiled forward is unrelated to LlamaConfig head_dim validation." + }, + { + "left": "issue:44117", + "right": "issue:44704", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES None handling and AutoProcessor kwargs forwarding are different loader bugs." + }, + { + "left": "issue:43576", + "right": "issue:43784", + "accept": false, + "reason": "Broken env command and sentence-transformers import NameError are distinct regressions." + }, + { + "left": "issue:43646", + "right": "issue:46002", + "accept": false, + "reason": "Custom model initialization breakage and NaNs in classification heads are different failures with different triggers." + }, + { + "left": "issue:42371", + "right": "issue:44263", + "accept": false, + "reason": "TF32 settings guidance and a torch.split return-value bug are unrelated." + }, + { + "left": "issue:43550", + "right": "issue:46132", + "accept": false, + "reason": "torch.compile/SDPA failure and AttentionInterface.register behavior change are different attention-related bugs." + }, + { + "left": "issue:30990", + "right": "issue:33357", + "accept": false, + "reason": "Both mention loading, but one is Sentence Transformers hanging and the other is a MacOS bus error on a CLIP model." + }, + { + "left": "issue:43232", + "right": "issue:45593", + "accept": false, + "reason": "Generation kwargs update after sync_gpus and missing auxiliary losses in D-FINE are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:44297", + "accept": false, + "reason": "Reading a registered position_ids buffer and tokenizer_class mismatch on save_pretrained are different tokenizer/model serialization issues." + }, + { + "left": "issue:43723", + "right": "issue:44442", + "accept": true, + "reason": "Same underlying bug class: AutoTokenizer.from_pretrained loading fails in v5, with 44442 looking like a specific tokenizer instance of the broader regression." + }, + { + "left": "issue:44261", + "right": "issue:44373", + "accept": false, + "reason": "A precision error from missing rms_norm_eps is not the same as a wrong docstring for position_ids." + }, + { + "left": "issue:42907", + "right": "issue:44945", + "accept": false, + "reason": "Saving dequantized Ministrals/Devstrals and incorrect pipeline-parallel output are different code-path problems." + }, + { + "left": "issue:43723", + "right": "issue:44779", + "accept": false, + "reason": "Tokenizer loading failure and changed tokenization output are related only broadly; they do not describe the same defect." + }, + { + "left": "issue:43784", + "right": "issue:45600", + "accept": false, + "reason": "Import NameError in sentence-transformers and stale auto_mappings references are separate import/CI issues." + }, + { + "left": "issue:41628", + "right": "issue:45278", + "accept": false, + "reason": "Missing AutoImageProcessor export may be one example of broader import breakage, but the reports are not specific enough to treat as the same bug." + }, + { + "left": "issue:42907", + "right": "issue:43937", + "accept": false, + "reason": "Quantized save failure and invalid GenerationConfig are unrelated." + }, + { + "left": "issue:43756", + "right": "issue:44060", + "accept": false, + "reason": "Smollm3 RoPE-layer mismatch and Qwen3-Next tied-weights warning are different model-configuration issues." + }, + { + "left": "issue:43408", + "right": "issue:43475", + "accept": false, + "reason": "Model-type warning for sam3_video/sam3_tracker and missing fpn_position_embeddings are distinct SAM3 issues." + }, + { + "left": "issue:43122", + "right": "issue:44514", + "accept": false, + "reason": "Different-tokenization regression and apply_chat_template batching crash are separate tokenizer/processor bugs." + }, + { + "left": "issue:43116", + "right": "issue:45200", + "accept": false, + "reason": "Empty multi-label classification results and mm_token_type_ids default handling are unrelated example/model issues." + }, + { + "left": "issue:44704", + "right": "issue:45290", + "accept": false, + "reason": "AutoProcessor cached_file kwargs forwarding and assistant-message chat-template crashes are different processor bugs." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Model loading failure for Phi-4 multimodal and general import errors after upgrade are not the same defect." + }, + { + "left": "issue:42886", + "right": "issue:43066", + "accept": false, + "reason": "Tokenizer cache/offline loading and decoder-type mismatch are different failures." + }, + { + "left": "issue:42886", + "right": "issue:42994", + "accept": false, + "reason": "Tokenizer cache/offline loading and quantized save failure are unrelated." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary stays grounded in the packet: it characterizes the cluster as mostly unrelated v5 regressions and only elevates the 43723/44442 tokenizer-loading pair, which is a reasonable conservative duplicate call from the titles alone. The soft-edge rejections are also cautious and do not overclaim sameness across clearly different bug classes." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 42, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:22355", + "issue:28218", + "issue:29159", + "issue:30990", + "issue:36296", + "issue:39401", + "issue:42222", + "issue:42371", + "issue:42757", + "issue:42831", + "issue:42907", + "issue:43066", + "issue:43116", + "issue:43122", + "issue:43232", + "issue:43441", + "issue:43452", + "issue:43611", + "issue:43784", + "issue:43824", + "issue:43874", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44038", + "issue:44075", + "issue:44222", + "issue:44295", + "issue:44297", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44485", + "issue:44488", + "issue:44521", + "issue:44625", + "issue:44704", + "issue:44779", + "issue:44829", + "issue:44936", + "issue:45216", + "issue:45245", + "issue:45357", + "issue:45446", + "issue:45478", + "issue:46002", + "issue:46231" + ], + "soft_pairs": [ + "issue:44625|issue:44829", + "issue:44360|issue:44485", + "issue:43232|issue:45245", + "issue:43122|issue:44521", + "issue:44038|issue:44297", + "issue:28218|issue:30990", + "issue:43122|issue:44779", + "issue:44038|issue:44295", + "issue:42907|issue:43452", + "issue:36296|issue:43116", + "issue:44038|issue:44222", + "issue:39401|issue:44488", + "issue:45216|issue:45478", + "issue:43824|issue:44351", + "issue:39401|issue:44521", + "issue:43784|issue:45446", + "issue:22355|issue:28218", + "issue:42757|issue:44351", + "issue:22355|issue:29159", + "issue:43122|issue:43906", + "issue:43992|issue:44704", + "issue:43066|issue:44779", + "issue:44355|issue:46231", + "issue:43937|issue:44485", + "issue:43611|issue:46002", + "issue:42371|issue:43874", + "issue:42222|issue:43441", + "issue:43976|issue:45446", + "issue:44075|issue:44936", + "issue:42831|issue:44297", + "issue:45357|issue:45478", + "issue:44038|issue:45478" + ], + "prepared_review_unit_hash": "19fd17166a948a63719b437709116577cb72f51606c2c2679581aa99d0299e8d", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 32, + "serialized_chars": 36691, + "estimated_input_tokens": 9173, + "estimated_eval_tokens": 18602 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "These items are mostly distinct bugs spanning tokenization regressions, model import/load failures, training issues, and documentation problems. I do not see any soft pair that clearly describes the same underlying fix.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43122 is the most broadly phrased and representative tokenizer regression here, centered on version-to-version behavior changes rather than a model-specific edge case.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43122 is the best standalone issue candidate because it is concrete, reproducible, and general enough to represent the tokenizer-regression theme without being overly model-specific.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44625", + "right": "issue:44829", + "accept": false, + "reason": "Different models and different failure modes: config propagation for Qwen3.5 vs degenerate training with flash_attention_3." + }, + { + "left": "issue:44360", + "right": "issue:44485", + "accept": false, + "reason": "Unrelated topics: DSA/ReLU discussion vs GLM-5 RoPE implementation." + }, + { + "left": "issue:43232", + "right": "issue:45245", + "accept": false, + "reason": "Generation-state bug vs category cardinality RuntimeError; no shared code path." + }, + { + "left": "issue:43122", + "right": "issue:44521", + "accept": false, + "reason": "Both involve token-related behavior, but one is a tokenizer regression and the other is multimodal assistant masks in chat templating." + }, + { + "left": "issue:44038", + "right": "issue:44297", + "accept": false, + "reason": "Qwen3-VL-Moe loading issue vs tokenizer save_pretrained class metadata mismatch; different bugs." + }, + { + "left": "issue:28218", + "right": "issue:30990", + "accept": false, + "reason": "Tokenizer spacing bug vs Sentence Transformers loading hang; clearly unrelated." + }, + { + "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 merge as one bug." + }, + { + "left": "issue:44038", + "right": "issue:44295", + "accept": false, + "reason": "Model loading failure vs position_ids buffer access error; different code paths." + }, + { + "left": "issue:42907", + "right": "issue:43452", + "accept": false, + "reason": "Dequantized Ministral/Devstral save failure vs gguf_file loading breakage; unrelated mechanisms." + }, + { + "left": "issue:36296", + "right": "issue:43116", + "accept": false, + "reason": "Tensor-parallel training bug vs example-script multi-label classification output bug; different subsystems." + }, + { + "left": "issue:44038", + "right": "issue:44222", + "accept": false, + "reason": "Different issues around Qwen3-VL-Moe/FP8 save_pretrained; no evidence they are the same concrete defect." + }, + { + "left": "issue:39401", + "right": "issue:44488", + "accept": false, + "reason": "Qwen3 tokenizer offset mapping bug vs loading cjvt/sleng-bert failure; unrelated." + }, + { + "left": "issue:45216", + "right": "issue:45478", + "accept": false, + "reason": "Both touch Qwen3.5 and save/load flows, but one is save_pretrained checkpoint corruption and the other is from_pretrained loading error; too different to treat as one bug." + }, + { + "left": "issue:43824", + "right": "issue:44351", + "accept": false, + "reason": "Different missing symbols from different modules; import errors are not the same bug." + }, + { + "left": "issue:39401", + "right": "issue:44521", + "accept": false, + "reason": "Tokenizer offset_mapping regression vs multimodal assistant mask failure; different concrete behavior." + }, + { + "left": "issue:43784", + "right": "issue:45446", + "accept": false, + "reason": "Sentence-transformers import NameError vs flex_attention version check; unrelated." + }, + { + "left": "issue:22355", + "right": "issue:28218", + "accept": false, + "reason": "onnx module import failure vs added-token spacing bug; unrelated." + }, + { + "left": "issue:42757", + "right": "issue:44351", + "accept": false, + "reason": "Missing huggingface_hub symbol vs missing transformers symbol; different packages and causes." + }, + { + "left": "issue:22355", + "right": "issue:29159", + "accept": false, + "reason": "onnx import failure vs slow/fast tokenizer inconsistency; not the same bug." + }, + { + "left": "issue:43122", + "right": "issue:43906", + "accept": false, + "reason": "Version-dependent tokenization differences vs reproduction of another tracked issue; no clear shared defect." + }, + { + "left": "issue:43992", + "right": "issue:44704", + "accept": false, + "reason": "UMT5 weight loading vs AutoProcessor kwargs forwarding; different APIs and failures." + }, + { + "left": "issue:43066", + "right": "issue:44779", + "accept": false, + "reason": "Both concern tokenizer behavior in v5, but one is decoder-type metadata and the other is incorrect Deepseek tokenization results; not the same fix." + }, + { + "left": "issue:44355", + "right": "issue:46231", + "accept": false, + "reason": "Compiled Python file errors vs documentation parameter-name mismatch; unrelated." + }, + { + "left": "issue:43937", + "right": "issue:44485", + "accept": false, + "reason": "GLM-5 generation config validity vs GLM-5 RoPE implementation; different concrete issues." + }, + { + "left": "issue:43611", + "right": "issue:46002", + "accept": false, + "reason": "base_model_prefix loading regression vs NaNs in classification heads; different failure modes." + }, + { + "left": "issue:42371", + "right": "issue:43874", + "accept": false, + "reason": "TF32 settings guidance vs missing image-patch-count method; unrelated." + }, + { + "left": "issue:42222", + "right": "issue:43441", + "accept": false, + "reason": "VitPose model breakage vs Ministral flash-attention failure; different models and code paths." + }, + { + "left": "issue:43976", + "right": "issue:45446", + "accept": false, + "reason": "Python version compatibility issue vs flex_attention import check; unrelated." + }, + { + "left": "issue:44075", + "right": "issue:44936", + "accept": false, + "reason": "Optimizer argument handling vs trainer.evaluate after train; different parts of training stack." + }, + { + "left": "issue:42831", + "right": "issue:44297", + "accept": false, + "reason": "FP8 accuracy issue vs tokenizer class metadata mismatch; unrelated." + }, + { + "left": "issue:45357", + "right": "issue:45478", + "accept": false, + "reason": "Qwen3.5 save_pretrained regression vs Qwen3.5 from_pretrained error; related model family but not the same concrete bug." + }, + { + "left": "issue:44038", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model variants and different load failures; not enough overlap for one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 43, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:22355", + "issue:29127", + "issue:33453", + "issue:38617", + "issue:39401", + "issue:41628", + "issue:42175", + "issue:42222", + "issue:42673", + "issue:43064", + "issue:43116", + "issue:43122", + "issue:43381", + "issue:43421", + "issue:43450", + "issue:43493", + "issue:43673", + "issue:43825", + "issue:43827", + "issue:43937", + "issue:43986", + "issue:44117", + "issue:44291", + "issue:44380", + "issue:44410", + "issue:44466", + "issue:44625", + "issue:44779", + "issue:44829", + "issue:44938", + "issue:44945", + "issue:44977", + "issue:45071", + "issue:45072", + "issue:45081", + "issue:45083", + "issue:45216", + "issue:45278", + "issue:45310", + "issue:45405", + "issue:45446", + "issue:45563", + "issue:45588", + "issue:45753", + "issue:46002", + "issue:46077", + "issue:46178", + "issue:46298" + ], + "soft_pairs": [ + "issue:43116|issue:43825", + "issue:43493|issue:45753", + "issue:45083|issue:45446", + "issue:43116|issue:43493", + "issue:43937|issue:45563", + "issue:22355|issue:29127", + "issue:33453|issue:39401", + "issue:38617|issue:45278", + "issue:44625|issue:46002", + "issue:39401|issue:44779", + "issue:44380|issue:46077", + "issue:44117|issue:45588", + "issue:42175|issue:44938", + "issue:43064|issue:43673", + "issue:43827|issue:45446", + "issue:43381|issue:44945", + "issue:43450|issue:43986", + "issue:43937|issue:44977", + "issue:44466|issue:46002", + "issue:45405|issue:45446", + "issue:44117|issue:45081", + "issue:42673|issue:45072", + "issue:43122|issue:46298", + "issue:44410|issue:45310", + "issue:44291|issue:45071", + "issue:44829|issue:45216", + "issue:39401|issue:43421", + "issue:38617|issue:41628", + "issue:42222|issue:46178" + ], + "prepared_review_unit_hash": "4e24711b2060327a5908a53bd251084c915780c0462d27ae1a0b8cd9d571ff59", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 29, + "serialized_chars": 36360, + "estimated_input_tokens": 9090, + "estimated_eval_tokens": 18436 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab-bag of unrelated Transformers regressions and feature bugs; the soft pairs share broad topical similarity but not the same underlying defect. I would not merge any of the candidate pairs.", + "confidence": 0.95, + "canonical_issue_reason": "If an issue must anchor the cluster, issue 45278 is the broadest umbrella: it covers multiple import breakages after upgrading to v5.5.0 and is the closest to a generic regression representative among the items.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the best representative issue only because it is the widest-scoped and most cluster-like report; the rest are too specific or unrelated to serve as a better canonical duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43116", + "right": "issue:43825", + "accept": false, + "reason": "Different bugs: multi-label classification example returns empty results, while the other is a pipeline() v5 translation-task error message issue." + }, + { + "left": "issue:43493", + "right": "issue:45753", + "accept": false, + "reason": "Both mention Qwen3.5, but one is a SigLIP2 implementation discrepancy and the other is an image-specific infinite loop; not the same defect." + }, + { + "left": "issue:45083", + "right": "issue:45446", + "accept": false, + "reason": "Different code paths: qwen3_omni_moe feature-extract length helper vs flex_attention aux-request version check." + }, + { + "left": "issue:43116", + "right": "issue:43493", + "accept": false, + "reason": "Unrelated model areas and symptoms: example-script classification output vs SigLIP2 implementation mismatch." + }, + { + "left": "issue:43937", + "right": "issue:45563", + "accept": false, + "reason": "GenerationConfig validation failure is not the same as a stale warning emitted by paged generate()." + }, + { + "left": "issue:22355", + "right": "issue:29127", + "accept": false, + "reason": "Import error for transformers.onnx versus a LayoutLMv3 error-message clarity issue; different functionality entirely." + }, + { + "left": "issue:33453", + "right": "issue:39401", + "accept": false, + "reason": "Tokenizer loading regression is broad and version-related, but the other is a Qwen3 offset_mapping bug; not the same bug." + }, + { + "left": "issue:38617", + "right": "issue:45278", + "accept": false, + "reason": "Both are import-related regressions, but one is a specific missing symbol and the other is a broad multi-import failure report; not the same concrete fix." + }, + { + "left": "issue:44625", + "right": "issue:46002", + "accept": false, + "reason": "Qwen3.5 num_labels propagation bug is unrelated to NaNs in classification heads after checkout/init." + }, + { + "left": "issue:39401", + "right": "issue:44779", + "accept": false, + "reason": "Both affect tokenization, but one is offset_mapping in Qwen3 and the other is incorrect Deepseek tokenization; different model-specific issues." + }, + { + "left": "issue:44380", + "right": "issue:46077", + "accept": false, + "reason": "GPT2 attention scaling under SDPA/FlashAttention is distinct from Gemma4 building causal masks when bidirectional attention is requested." + }, + { + "left": "issue:44117", + "right": "issue:45588", + "accept": false, + "reason": "TOKENIZER_MAPPING_NAMES None handling is unrelated to flash_attention.py crashing on s_aux=None for sink-less models." + }, + { + "left": "issue:42175", + "right": "issue:44938", + "accept": false, + "reason": "TF not included in pip install '.[torch]' is a packaging/backend issue, not a Python 3.14 import failure." + }, + { + "left": "issue:43064", + "right": "issue:43673", + "accept": false, + "reason": "Wrong optimizer states on nonzero ranks in training is unrelated to missing GenerationMixin cache during chunked prefill." + }, + { + "left": "issue:43827", + "right": "issue:45446", + "accept": false, + "reason": "Documentation still referencing pipeline() is not the same as the incorrect PyTorch version check for AuxRequest import." + }, + { + "left": "issue:43381", + "right": "issue:44945", + "accept": false, + "reason": "Gradient checkpointing in eval mode and incorrect LLM output under pipeline parallelism are different runtime behaviors and code paths." + }, + { + "left": "issue:43450", + "right": "issue:43986", + "accept": false, + "reason": "Video processor batch shape bug is unrelated to AutoProcessor crash when torchvision is missing." + }, + { + "left": "issue:43937", + "right": "issue:44977", + "accept": false, + "reason": "Both involve generation/Qwen3.5, but one is invalid GenerationConfig and the other is flash-attention generation failure; different root causes." + }, + { + "left": "issue:44466", + "right": "issue:46002", + "accept": false, + "reason": "lm_head.weight serialization inconsistency is unrelated to NaNs in classification heads upon checkout/init." + }, + { + "left": "issue:45405", + "right": "issue:45446", + "accept": false, + "reason": "Released-version pinning problem for PEFT is unrelated to the AuxRequest PyTorch version check." + }, + { + "left": "issue:44117", + "right": "issue:45081", + "accept": false, + "reason": "Tokenizer mapping None handling does not match the Mistral regex patch crash on missing backend_tokenizer." + }, + { + "left": "issue:42673", + "right": "issue:45072", + "accept": false, + "reason": "VRAM leak in Qwen3ForCausalLM threads is unrelated to CI dtype mismatches for SwitchTransformers/TimmWrapperModel." + }, + { + "left": "issue:43122", + "right": "issue:46298", + "accept": false, + "reason": "Tokenizer behavior changed across versions is unrelated to a noisy logging message." + }, + { + "left": "issue:44410", + "right": "issue:45310", + "accept": false, + "reason": "Missing attn_qkv/attn_gate projections in qwen3next layer 0 is unrelated to Qwen3.5 Moe from_pretrained loading error." + }, + { + "left": "issue:44291", + "right": "issue:45071", + "accept": false, + "reason": "init_empty_weights TypeError from unexpected _is_hf_initialized argument is unrelated to PretrainedConfig type-checking breakage." + }, + { + "left": "issue:44829", + "right": "issue:45216", + "accept": false, + "reason": "FlashAttention_3 degenerate training is not the same as Qwen3.5 save_pretrained producing incorrect checkpoints." + }, + { + "left": "issue:39401", + "right": "issue:43421", + "accept": false, + "reason": "Qwen3 tokenizer offset_mapping bug is unrelated to TokenizersBackend not updating post-processors when special tokens change." + }, + { + "left": "issue:38617", + "right": "issue:41628", + "accept": false, + "reason": "Both are import errors, but they concern different missing symbols/modules and different fixes." + }, + { + "left": "issue:42222", + "right": "issue:46178", + "accept": false, + "reason": "Broken vitpose models are unrelated to the backend mapping error for tensorflow_text." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 44, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:38617", + "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:43441", + "issue:43452", + "issue:43577", + "issue:43742", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43937", + "issue:44038", + "issue:44075", + "issue:44117", + "issue:44220", + "issue:44261", + "issue:44263", + "issue:44360", + "issue:44410", + "issue:44483", + "issue:44484", + "issue:44485", + "issue:44493", + "issue:44496", + "issue:44829", + "issue:44877", + "issue:44964", + "issue:44977", + "issue:44987", + "issue:45071", + "issue:45278", + "issue:45310", + "issue:45464", + "issue:45478", + "issue:45542", + "issue:45656", + "issue:46172", + "issue:46231" + ], + "soft_pairs": [ + "issue:43408|issue:43742", + "issue:44877|issue:46231", + "issue:44484|issue:45310", + "issue:43937|issue:44496", + "issue:43066|issue:43122", + "issue:44964|issue:45278", + "issue:44483|issue:45464", + "issue:44075|issue:45656", + "issue:42371|issue:44261", + "issue:42222|issue:45542", + "issue:43012|issue:43577", + "issue:44410|issue:45478", + "issue:42175|issue:42222", + "issue:38617|issue:44220", + "issue:43097|issue:44493", + "issue:43874|issue:44261", + "issue:41628|issue:45071", + "issue:44263|issue:44485", + "issue:45071|issue:45542", + "issue:42673|issue:44977", + "issue:42673|issue:43906", + "issue:44263|issue:46172", + "issue:43012|issue:43408", + "issue:44360|issue:46172", + "issue:44484|issue:45478", + "issue:43441|issue:44829", + "issue:42371|issue:42831", + "issue:43931|issue:44038", + "issue:43335|issue:45071", + "issue:43097|issue:43452", + "issue:44117|issue:44987" + ], + "prepared_review_unit_hash": "1e2c806f15b481354ffe1ab89caacc6c2ee8ef5233d9f9411c33f83670ef051d", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 31, + "serialized_chars": 36646, + "estimated_input_tokens": 9162, + "estimated_eval_tokens": 18580 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft pairs mostly share broad themes like imports, model loading, tokenization, or numeric precision, but not the same concrete bug or code path. I would not merge any of the suggested pairs as duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "No single canonical issue truly fits this set; the items span distinct regressions. If forced to pick the broadest umbrella, issue 45278 is the closest because it covers many import failures after upgrading, but it still does not subsume the rest.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45278 is the best representative only in a very loose sense because its title is broad enough to describe a class of upgrade-related import breakages. It is not a true duplicate hub for the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43408", + "right": "issue:43742", + "accept": false, + "reason": "Different model-loading problems: SAM3 type mismatch warning vs MobileLLM key error." + }, + { + "left": "issue:44877", + "right": "issue:46231", + "accept": false, + "reason": "One is a config-loading strictness bug; the other is a docs parameter-name mismatch." + }, + { + "left": "issue:44484", + "right": "issue:45310", + "accept": false, + "reason": "Unrelated: shard-size behavior in save_pretrained vs Qwen3.5 MoE from_pretrained failure." + }, + { + "left": "issue:43937", + "right": "issue:44496", + "accept": false, + "reason": "Different layers of failure: GenerationConfig validation vs unrecognized model/config loading." + }, + { + "left": "issue:43066", + "right": "issue:43122", + "accept": false, + "reason": "Both tokenizer-related, but one is decoder-type metadata and the other is changed tokenization output; too weak to treat as the same bug." + }, + { + "left": "issue:44964", + "right": "issue:45278", + "accept": false, + "reason": "Specific Phi-4 multimodal load failure vs a broad report of many import errors after upgrade." + }, + { + "left": "issue:44483", + "right": "issue:45464", + "accept": false, + "reason": "Different API paths and symptoms: general chat/completions rejection vs streaming inference failure on Qwen3.5-0.8B." + }, + { + "left": "issue:44075", + "right": "issue:45656", + "accept": false, + "reason": "Separate optimizer bugs: SGD args ignored vs optimizer.step being called twice with deepspeed." + }, + { + "left": "issue:42371", + "right": "issue:44261", + "accept": false, + "reason": "TF32 API warning and MLA RMS-ep precision issue are different numeric/config regressions." + }, + { + "left": "issue:42222", + "right": "issue:45542", + "accept": false, + "reason": "VitPose model breakage is unrelated to the missing-TensorFlow backend error." + }, + { + "left": "issue:43012", + "right": "issue:43577", + "accept": false, + "reason": "Both involve dtype/precision, but one is a compile warning and the other is incorrect dtype propagation when loading Blip2." + }, + { + "left": "issue:44410", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen model bugs: missing projections in qwen3next vs a Qwen3.5 MoE load error." + }, + { + "left": "issue:42175", + "right": "issue:42222", + "accept": false, + "reason": "TensorFlow extra-install issue and broken VitPose models are unrelated." + }, + { + "left": "issue:38617", + "right": "issue:44220", + "accept": false, + "reason": "ImportError for layer_type_validation is unrelated to the fbank feature-extraction issue." + }, + { + "left": "issue:43097", + "right": "issue:44493", + "accept": false, + "reason": "A removed config field and unexpected position-id keys are different migration regressions." + }, + { + "left": "issue:43874", + "right": "issue:44261", + "accept": false, + "reason": "Missing image-processor method vs MLA layernorm epsilon precision error are different subsystems." + }, + { + "left": "issue:41628", + "right": "issue:45071", + "accept": false, + "reason": "AutoImageProcessor import failure and PretrainedConfig type-checking breakage are separate API regressions." + }, + { + "left": "issue:44263", + "right": "issue:44485", + "accept": false, + "reason": "GlmMoeDsaIndexer torch.split behavior and GLM-5 RoPE implementation are distinct internal bugs." + }, + { + "left": "issue:45071", + "right": "issue:45542", + "accept": false, + "reason": "PretrainedConfig type checking and undefined tf backend errors do not share a concrete code path." + }, + { + "left": "issue:42673", + "right": "issue:44977", + "accept": false, + "reason": "VRAM leak in dataloader threads vs Qwen3.5 flash-attention generation failure are different runtime bugs." + }, + { + "left": "issue:42673", + "right": "issue:43906", + "accept": false, + "reason": "43906 is a reproduction of another issue, but it is not the same as a Qwen3ForCausalLM VRAM leak." + }, + { + "left": "issue:44263", + "right": "issue:46172", + "accept": false, + "reason": "Different model internals: torch.split return handling vs a comb.to(dtype).transpose bug." + }, + { + "left": "issue:43012", + "right": "issue:43408", + "accept": false, + "reason": "A bfloat16 compile warning is unrelated to the sam3_video/sam3_tracker type warning." + }, + { + "left": "issue:44360", + "right": "issue:46172", + "accept": false, + "reason": "DSA indexer missing ReLU and deepseek-v4 dtype/transpose are unrelated changes." + }, + { + "left": "issue:44484", + "right": "issue:45478", + "accept": false, + "reason": "save_pretrained shard-size behavior and Qwen3.5 MoE loading error are not the same bug." + }, + { + "left": "issue:43441", + "right": "issue:44829", + "accept": false, + "reason": "Both mention flash attention, but one is a Ministral-3 failure and the other is degenerate training in sequence classification; not the same code path." + }, + { + "left": "issue:42371", + "right": "issue:42831", + "accept": false, + "reason": "TF32 configuration warning and FineGrainedFP8 accuracy regression are different precision issues." + }, + { + "left": "issue:43931", + "right": "issue:44038", + "accept": false, + "reason": "Different Qwen3-VL model failures with different symptoms and likely different root causes." + }, + { + "left": "issue:43335", + "right": "issue:45071", + "accept": false, + "reason": "SwitchTransformers sparse-layer construction and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43452", + "accept": false, + "reason": "Removed tie_embeddings behavior and gguf_file loading breakage are separate regressions." + }, + { + "left": "issue:44117", + "right": "issue:44987", + "accept": false, + "reason": "Tokenizer mapping returning None and a model-loading failure for physical-intelligence/fast are different issues." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 45, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:38617", + "issue:42617", + "issue:42673", + "issue:42757", + "issue:42890", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43408", + "issue:43502", + "issue:43550", + "issue:43873", + "issue:43874", + "issue:43906", + "issue:43931", + "issue:43976", + "issue:43986", + "issue:43992", + "issue:44038", + "issue:44062", + "issue:44117", + "issue:44261", + "issue:44263", + "issue:44315", + "issue:44351", + "issue:44368", + "issue:44410", + "issue:44484", + "issue:44485", + "issue:44704", + "issue:44933", + "issue:44945", + "issue:44964", + "issue:45103", + "issue:45200", + "issue:45290", + "issue:45341", + "issue:45372", + "issue:45375", + "issue:45440", + "issue:45561", + "issue:45588", + "issue:45859", + "issue:46050", + "issue:46172", + "issue:46231", + "issue:46298" + ], + "soft_pairs": [ + "issue:44933|issue:46231", + "issue:43874|issue:44263", + "issue:43408|issue:44368", + "issue:43976|issue:44945", + "issue:43986|issue:44484", + "issue:45440|issue:46172", + "issue:43097|issue:46050", + "issue:43097|issue:45588", + "issue:43064|issue:44315", + "issue:42673|issue:45200", + "issue:38617|issue:42757", + "issue:44062|issue:44117", + "issue:44410|issue:45375", + "issue:42890|issue:46298", + "issue:44038|issue:44410", + "issue:43931|issue:44410", + "issue:43502|issue:43992", + "issue:38617|issue:44351", + "issue:45341|issue:45859", + "issue:43097|issue:43873", + "issue:44261|issue:44485", + "issue:44964|issue:45341", + "issue:44704|issue:45103", + "issue:43986|issue:44117", + "issue:42617|issue:45341", + "issue:43066|issue:43906", + "issue:43986|issue:45372", + "issue:43986|issue:45290", + "issue:45341|issue:45588", + "issue:43208|issue:43550", + "issue:45341|issue:45561", + "issue:43986|issue:45341", + "issue:43992|issue:44484" + ], + "prepared_review_unit_hash": "1494d8f79a16cc1d33762fe8575d9b130fa55154b7f9a9d3cce5b50f643195c9", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 33, + "serialized_chars": 37524, + "estimated_input_tokens": 9381, + "estimated_eval_tokens": 19018 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "No duplicate pairs look like the same underlying bug/change. The soft matches are mostly superficial title-level similarity across different subsystems, error types, or unrelated docs/test issues. Best representative issue is the broad open quantization/offloading bug.", + "confidence": 0.93, + "canonical_issue_reason": "issue:43873 is the broadest, currently open, user-impacting runtime bug in the set, with multiple references and a clear actionable failure mode.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:43873 is the best standalone issue to keep as the representative: it is open, broadly scoped, and tied to concrete behavior rather than a narrow import/warning/docs problem.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44933", + "right": "issue:46231", + "accept": false, + "reason": "Nonexistent import error vs documentation parameter-name mismatch; unrelated problems." + }, + { + "left": "issue:43874", + "right": "issue:44263", + "accept": false, + "reason": "Different GLM failures in different paths: image patch counting vs torch.split return handling." + }, + { + "left": "issue:43408", + "right": "issue:44368", + "accept": false, + "reason": "SAM model-type warning vs tie_word_embeddings warning; different models and causes." + }, + { + "left": "issue:43976", + "right": "issue:44945", + "accept": false, + "reason": "Python compatibility/install issue vs incorrect pipeline-parallel output; unrelated failure modes." + }, + { + "left": "issue:43986", + "right": "issue:44484", + "accept": false, + "reason": "Missing torchvision crash in AutoProcessor vs save_pretrained shard-size question; no shared bug." + }, + { + "left": "issue:45440", + "right": "issue:46172", + "accept": false, + "reason": "Different DeepSeek model bugs in separate code paths and model versions." + }, + { + "left": "issue:43097", + "right": "issue:46050", + "accept": false, + "reason": "Removed config field vs quantization serialization/deserialization breakage; not the same bug." + }, + { + "left": "issue:43097", + "right": "issue:45588", + "accept": false, + "reason": "Removed config field warning vs flash-attention sink-less crash; unrelated behavior." + }, + { + "left": "issue:43064", + "right": "issue:44315", + "accept": false, + "reason": "FSDP/PEFT optimizer state corruption vs Liger-kernel application with model_init; different training issues." + }, + { + "left": "issue:42673", + "right": "issue:45200", + "accept": false, + "reason": "VRAM leak in threaded dataloaders vs missing multimodal token IDs default; distinct bugs." + }, + { + "left": "issue:38617", + "right": "issue:42757", + "accept": false, + "reason": "Two different missing imports from different modules and dependency layers." + }, + { + "left": "issue:44062", + "right": "issue:44117", + "accept": false, + "reason": "AddedToken keyword collision vs tokenizer mapping None-handling; separate tokenizer bugs." + }, + { + "left": "issue:44410", + "right": "issue:45375", + "accept": false, + "reason": "Missing Qwen projections vs missing config field silently dropped; different model/config issues." + }, + { + "left": "issue:42890", + "right": "issue:46298", + "accept": false, + "reason": "Seed-related flaky test failure vs noisy logging message; not the same underlying problem." + }, + { + "left": "issue:44038", + "right": "issue:44410", + "accept": false, + "reason": "Qwen3-VL-Moe issue vs qwen3next missing projections; different models and code paths." + }, + { + "left": "issue:43931", + "right": "issue:44410", + "accept": false, + "reason": "Model weight-shape mismatch on load vs missing projections in qwen3next; unrelated." + }, + { + "left": "issue:43502", + "right": "issue:43992", + "accept": false, + "reason": "local_files_only network leakage vs missing embed_tokens weight on load; different loading bugs." + }, + { + "left": "issue:38617", + "right": "issue:44351", + "accept": false, + "reason": "Missing import of layer_type_validation vs missing HybridCache import; only superficially similar." + }, + { + "left": "issue:45341", + "right": "issue:45859", + "accept": false, + "reason": "Testing utility bug vs CPU-offload incompatibility in rotary embedding; unrelated." + }, + { + "left": "issue:43097", + "right": "issue:43873", + "accept": false, + "reason": "Removed tie_embeddings config issue vs quantization offloading failure; different affected paths." + }, + { + "left": "issue:44261", + "right": "issue:44485", + "accept": false, + "reason": "RMS norm epsilon precision discussion vs GLM RoPE implementation; different math/config topics." + }, + { + "left": "issue:44964", + "right": "issue:45341", + "accept": false, + "reason": "Model loading regression vs testing_utils bug; no shared code-path problem." + }, + { + "left": "issue:44704", + "right": "issue:45103", + "accept": false, + "reason": "cached_file kwargs forwarding bug vs auto-docstring annotation parsing crash; unrelated." + }, + { + "left": "issue:43986", + "right": "issue:44117", + "accept": false, + "reason": "Processor loading without torchvision vs tokenizer mapping None handling; distinct subsystems." + }, + { + "left": "issue:42617", + "right": "issue:45341", + "accept": false, + "reason": "3d_parallel execution failure vs testing utility bug; unrelated." + }, + { + "left": "issue:43066", + "right": "issue:43906", + "accept": false, + "reason": "Wrong tokenizer decoder type vs isolated reproduction of another issue; not the same concrete bug." + }, + { + "left": "issue:43986", + "right": "issue:45372", + "accept": false, + "reason": "Missing torchvision dependency crash vs mistral_common ReasoningEffort import break; different import failures." + }, + { + "left": "issue:43986", + "right": "issue:45290", + "accept": false, + "reason": "Processor loading crash vs chat-template tokenization crash; different code paths." + }, + { + "left": "issue:45341", + "right": "issue:45588", + "accept": false, + "reason": "Testing utility bug vs flash-attention sink-less crash; no overlap beyond being bugs." + }, + { + "left": "issue:43208", + "right": "issue:43550", + "accept": false, + "reason": "xLSTM training blockers vs Bamba torch.compile/SDPA failure; different models and causes." + }, + { + "left": "issue:45341", + "right": "issue:45561", + "accept": false, + "reason": "Both mention testing utilities, but one is a minor bug and the other is an xdist race; not the same failure." + }, + { + "left": "issue:43986", + "right": "issue:45341", + "accept": false, + "reason": "Processor loading crash vs testing utility bug; unrelated." + }, + { + "left": "issue:43992", + "right": "issue:44484", + "accept": false, + "reason": "Missing encoder weights on load vs max_shard_size documentation/behavior question; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 46, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36683", + "issue:38617", + "issue:42490", + "issue:42757", + "issue:42907", + "issue:42994", + "issue:43012", + "issue:43064", + "issue:43066", + "issue:43097", + "issue:43208", + "issue:43299", + "issue:43475", + "issue:43502", + "issue:43526", + "issue:43550", + "issue:43618", + "issue:43673", + "issue:43761", + "issue:43792", + "issue:43824", + "issue:43825", + "issue:43867", + "issue:43901", + "issue:44038", + "issue:44162", + "issue:44222", + "issue:44230", + "issue:44368", + "issue:44380", + "issue:44483", + "issue:44514", + "issue:44655", + "issue:44683", + "issue:44938", + "issue:45276", + "issue:45290", + "issue:45478", + "issue:45600", + "issue:45698", + "issue:45712", + "issue:45753", + "issue:46077", + "issue:46123", + "issue:46172", + "issue:46178", + "issue:46209", + "issue:46298" + ], + "soft_pairs": [ + "issue:43012|issue:43550", + "issue:43825|issue:44655", + "issue:43012|issue:44368", + "issue:45712|issue:46298", + "issue:42907|issue:44655", + "issue:42907|issue:45753", + "issue:43097|issue:46298", + "issue:44162|issue:46172", + "issue:43792|issue:46123", + "issue:44938|issue:46178", + "issue:44483|issue:44514", + "issue:43208|issue:43526", + "issue:44222|issue:45478", + "issue:43012|issue:44683", + "issue:42490|issue:43012", + "issue:42757|issue:43824", + "issue:45600|issue:46298", + "issue:38617|issue:43502", + "issue:45698|issue:46172", + "issue:44038|issue:44230", + "issue:43673|issue:46123", + "issue:44483|issue:45290", + "issue:43064|issue:44380", + "issue:43618|issue:43761", + "issue:43299|issue:43867", + "issue:43066|issue:46209", + "issue:36683|issue:43475", + "issue:45276|issue:46077", + "issue:42994|issue:44655", + "issue:43901|issue:44655" + ], + "prepared_review_unit_hash": "84a7b1646435ef549dc13a0496da8ef5ce58ae7170e80d4d836d2630b00cca52", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 30, + "serialized_chars": 36321, + "estimated_input_tokens": 9081, + "estimated_eval_tokens": 18418 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The pairs are mostly superficial title-similarity matches, not the same underlying bug or change. I found no safe duplicate merges among them.", + "confidence": 0.95, + "canonical_issue_reason": "No single canonical issue stands out: the items span unrelated regressions, import errors, model-specific bugs, and docs/UX issues, so there is no safe duplicate anchor.", + "canonical_pr_reason": null, + "best_issue_reason": "If one issue must represent the set, issue:45698 has the strongest activity signal, but it still does not unify the cluster and is not a true canonical duplicate.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43012", + "right": "issue:43550", + "accept": false, + "reason": "Compile warning vs a torch.compile+SDPA failure; different code paths and symptoms." + }, + { + "left": "issue:43825", + "right": "issue:44655", + "accept": false, + "reason": "Pipeline task-message wording issue vs pipeline serialization failure; unrelated bugs." + }, + { + "left": "issue:43012", + "right": "issue:44368", + "accept": false, + "reason": "Both mention warnings, but one is a bfloat16 compile warning and the other is a Qwen fine-tuning config warning." + }, + { + "left": "issue:45712", + "right": "issue:46298", + "accept": false, + "reason": "Left is leftover dummy-class cleanup; right is noisy logging. Not the same bug." + }, + { + "left": "issue:42907", + "right": "issue:44655", + "accept": false, + "reason": "Quantized/dequantized model save failure vs Pipeline.save_pretrained failure; different objects and paths." + }, + { + "left": "issue:42907", + "right": "issue:45753", + "accept": false, + "reason": "Save/export bug vs an inference infinite-loop bug; no shared underlying defect." + }, + { + "left": "issue:43097", + "right": "issue:46298", + "accept": false, + "reason": "Removed API compatibility issue vs generic logging noise; unrelated." + }, + { + "left": "issue:44162", + "right": "issue:46172", + "accept": false, + "reason": "ESM2 breakage vs a DeepSeek tensor operation bug; different models and failures." + }, + { + "left": "issue:43792", + "right": "issue:46123", + "accept": false, + "reason": "Whisper load failure vs partial-batch dropping in MaskGenerationPipeline; different code paths." + }, + { + "left": "issue:44938", + "right": "issue:46178", + "accept": false, + "reason": "Python 3.14 import/load issue vs backend-mapping validation error; unrelated." + }, + { + "left": "issue:44483", + "right": "issue:44514", + "accept": false, + "reason": "Server /v1/chat/completions rejection vs Qwen2.5-VL chat-template batching crash; different failures." + }, + { + "left": "issue:43208", + "right": "issue:43526", + "accept": false, + "reason": "xLSTM training bugs vs BeitImageProcessorFast label reduction; no shared concrete defect." + }, + { + "left": "issue:44222", + "right": "issue:45478", + "accept": false, + "reason": "FP8 save_pretrained problem vs Qwen3.5-MoE from_pretrained load error; both MoE-related but distinct." + }, + { + "left": "issue:43012", + "right": "issue:44683", + "accept": false, + "reason": "PyTorch warning during compile vs flex_attention compile failure; not the same bug." + }, + { + "left": "issue:42490", + "right": "issue:43012", + "accept": false, + "reason": "Local-path trailing-slash import warning vs bfloat16 compile warning; unrelated." + }, + { + "left": "issue:42757", + "right": "issue:43824", + "accept": false, + "reason": "huggingface_hub import error vs transformers model import error; different missing symbols." + }, + { + "left": "issue:45600", + "right": "issue:46298", + "accept": false, + "reason": "Broken auto_mappings CI references vs generic logging noise; not the same underlying issue." + }, + { + "left": "issue:38617", + "right": "issue:43502", + "accept": false, + "reason": "Missing import from configuration_utils vs unintended network access with local_files_only=True; unrelated." + }, + { + "left": "issue:45698", + "right": "issue:46172", + "accept": false, + "reason": "Custom module reload/save mismatch vs DeepSeek tensor op failure; different subsystems." + }, + { + "left": "issue:44038", + "right": "issue:44230", + "accept": false, + "reason": "Qwen3-VL-Moe loading regression vs FP8 inference-support request; not the same concrete bug." + }, + { + "left": "issue:43673", + "right": "issue:46123", + "accept": false, + "reason": "Generation cache missing in v5 vs final partial-batch result loss; different functionality." + }, + { + "left": "issue:44483", + "right": "issue:45290", + "accept": false, + "reason": "Chat-completions endpoint rejection vs assistant tool-call template crash; unrelated." + }, + { + "left": "issue:43064", + "right": "issue:44380", + "accept": false, + "reason": "FSDP/PEFT optimizer-state bug vs GPT2 attention-scaling being ignored; different paths." + }, + { + "left": "issue:43618", + "right": "issue:43761", + "accept": false, + "reason": "Missing CLIPOutput attentions assignment vs CLIPVisionModel hidden_states regression; separate output fields." + }, + { + "left": "issue:43299", + "right": "issue:43867", + "accept": false, + "reason": "Qwen3VL-Moe loading breakage vs state_dict sorting load error; not the same failure." + }, + { + "left": "issue:43066", + "right": "issue:46209", + "accept": false, + "reason": "Tokenizer decoder type regression vs FP8 inference failure on B200; unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43475", + "accept": false, + "reason": "Gemma3Config vocab_size attr missing vs SAM3 video output attr missing; different model families and bugs." + }, + { + "left": "issue:45276", + "right": "issue:46077", + "accept": false, + "reason": "Embedding resize not propagating vs bidirectional-attention mask construction; different Gemma4 issues." + }, + { + "left": "issue:42994", + "right": "issue:44655", + "accept": false, + "reason": "Quantized model saving failure vs saving Pipeline objects; both save-related but not the same bug." + }, + { + "left": "issue:43901", + "right": "issue:44655", + "accept": false, + "reason": "Docs behavior mismatch vs Pipeline.save_pretrained failure; unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 47, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:28282", + "issue:33453", + "issue:36010", + "issue:36296", + "issue:36683", + "issue:41669", + "issue:42757", + "issue:42890", + "issue:43064", + "issue:43097", + "issue:43299", + "issue:43352", + "issue:43441", + "issue:43502", + "issue:43525", + "issue:43575", + "issue:43611", + "issue:43618", + "issue:43867", + "issue:43881", + "issue:43906", + "issue:43937", + "issue:43976", + "issue:43992", + "issue:44117", + "issue:44242", + "issue:44246", + "issue:44355", + "issue:44380", + "issue:44485", + "issue:44492", + "issue:44625", + "issue:44655", + "issue:44855", + "issue:44938", + "issue:45216", + "issue:45310", + "issue:45357", + "issue:45375", + "issue:45478", + "issue:45479", + "issue:45561", + "issue:45753", + "issue:46077", + "issue:46082", + "issue:46132", + "issue:46202", + "issue:46285" + ], + "soft_pairs": [ + "issue:36010|issue:42757", + "issue:44625|issue:46077", + "issue:43352|issue:43937", + "issue:43611|issue:44655", + "issue:43867|issue:45216", + "issue:46077|issue:46082", + "issue:43502|issue:44485", + "issue:36683|issue:43525", + "issue:43618|issue:45216", + "issue:36683|issue:44242", + "issue:44380|issue:46132", + "issue:36683|issue:43881", + "issue:43906|issue:45753", + "issue:43299|issue:45753", + "issue:43352|issue:43976", + "issue:43992|issue:45310", + "issue:43441|issue:44380", + "issue:43352|issue:45478", + "issue:44355|issue:44855", + "issue:43867|issue:46202", + "issue:43867|issue:45375", + "issue:44380|issue:45479", + "issue:43352|issue:44380", + "issue:36683|issue:44117", + "issue:41669|issue:44246", + "issue:43618|issue:44380", + "issue:43097|issue:43352", + "issue:42890|issue:45561", + "issue:43064|issue:44492", + "issue:43976|issue:44938", + "issue:43867|issue:45357", + "issue:43992|issue:45478", + "issue:36296|issue:43575", + "issue:43064|issue:44655", + "issue:28282|issue:33453", + "issue:43618|issue:46285" + ], + "prepared_review_unit_hash": "9d5dc177862e5aa74f80f82034720fc16981e459c6e07903259f58549f6714b7", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 36, + "serialized_chars": 38139, + "estimated_input_tokens": 9535, + "estimated_eval_tokens": 19326 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a grab bag of unrelated Transformers bug reports. The only clear duplicate-like pair is the import-time slowdown reports (41669/44246); the rest differ by model, API, or failure mode.", + "confidence": 0.93, + "canonical_issue_reason": "issue:41669 is the most concrete root-cause report and directly matches the only accepted duplicate-like pair: slow `transformers` import due to `import *` usage in models.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:41669 is the best representative issue because it names the specific performance regression and likely fix target, whereas 44246 is the broader symptom report.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36010", + "right": "issue:42757", + "accept": false, + "reason": "Both are import errors, but they involve different missing symbols (`AutoModel`/PyTorch vs `is_offline_mode`/huggingface_hub) and different root causes." + }, + { + "left": "issue:44625", + "right": "issue:46077", + "accept": false, + "reason": "Different models and bugs: Qwen3.5 label propagation vs Gemma4 attention-mask construction." + }, + { + "left": "issue:43352", + "right": "issue:43937", + "accept": false, + "reason": "Both are model-loading/runtime errors, but one is FlashAttention support for Nemotron and the other is an invalid GenerationConfig for GLM-5." + }, + { + "left": "issue:43611", + "right": "issue:44655", + "accept": false, + "reason": "`base_model_prefix` loading regression and pipeline save_pretrained are unrelated code paths." + }, + { + "left": "issue:43867", + "right": "issue:45216", + "accept": false, + "reason": "Both affect saving/loading, but one is state_dict ordering/model load failure and the other is an incorrect Qwen3.5 checkpoint save regression." + }, + { + "left": "issue:46077", + "right": "issue:46082", + "accept": false, + "reason": "Gemma4 attention-mask logic and LlamaConfig head_dim validation are different issues." + }, + { + "left": "issue:43502", + "right": "issue:44485", + "accept": false, + "reason": "Local-files-only network leakage and GLM-5 RoPE discussion are unrelated." + }, + { + "left": "issue:36683", + "right": "issue:43525", + "accept": false, + "reason": "Similar shape of bug, but different models and missing config fields (`vocab_size` vs `pad_token_id`)." + }, + { + "left": "issue:43618", + "right": "issue:45216", + "accept": false, + "reason": "CLIP attentions regression and Qwen3.5 save_pretrained checkpoint corruption are not the same bug." + }, + { + "left": "issue:36683", + "right": "issue:44242", + "accept": false, + "reason": "Different failure modes: missing config attribute versus MoE load-balance loss omission." + }, + { + "left": "issue:44380", + "right": "issue:46132", + "accept": false, + "reason": "One is backend-specific attention scaling, the other is behavior change in AttentionInterface.register." + }, + { + "left": "issue:36683", + "right": "issue:43881", + "accept": false, + "reason": "Different models and symptoms; Gemma3Config missing vocab_size is not the same as glm-4v-9b loading failure." + }, + { + "left": "issue:43906", + "right": "issue:45753", + "accept": false, + "reason": "An isolated reproduction of an older issue and a Qwen3_5 image loop bug are different problems." + }, + { + "left": "issue:43299", + "right": "issue:45753", + "accept": false, + "reason": "Qwen3VL MoE loading failure and Qwen3_5 infinite-loop generation are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:43976", + "accept": false, + "reason": "FlashAttention support for a model and Python-version compatibility are distinct issues." + }, + { + "left": "issue:43992", + "right": "issue:45310", + "accept": false, + "reason": "Different models and missing weights/config path; both loading problems but not the same concrete bug." + }, + { + "left": "issue:43441", + "right": "issue:44380", + "accept": false, + "reason": "Both mention attention backends, but the model-specific FlashAttention failure and GPT2 attention scaling regression are different code paths." + }, + { + "left": "issue:43352", + "right": "issue:45478", + "accept": false, + "reason": "Same broad topic (Qwen/FlashAttention complaints) but different model/version and failure details." + }, + { + "left": "issue:44355", + "right": "issue:44855", + "accept": false, + "reason": "Compiled-file import errors and Python 3.13 `torch.jit.script` parsing failure are unrelated." + }, + { + "left": "issue:43867", + "right": "issue:46202", + "accept": false, + "reason": "State_dict-sorted load failure and Gemma pipeline roundtrip on `\u2581` are different bugs." + }, + { + "left": "issue:43867", + "right": "issue:45375", + "accept": false, + "reason": "Load-order issue versus Qwen3.5 config field being dropped by `@strict`; different underlying causes." + }, + { + "left": "issue:44380", + "right": "issue:45479", + "accept": false, + "reason": "Attention backend scaling bug and single-label classification zero-loss bug are unrelated." + }, + { + "left": "issue:43352", + "right": "issue:44380", + "accept": false, + "reason": "Both touch attention code, but they target different models and distinct backend behaviors." + }, + { + "left": "issue:36683", + "right": "issue:44117", + "accept": false, + "reason": "Missing config attr in one model and tokenizer mapping None-handling in another are not the same issue." + }, + { + "left": "issue:41669", + "right": "issue:44246", + "accept": true, + "reason": "Both report slow `transformers` import; 41669 identifies the likely cause (`import *` in models) and 44246 reports the same slowdown symptom." + }, + { + "left": "issue:43618", + "right": "issue:46285", + "accept": false, + "reason": "CLIP attentions regression and CLIP text-model structural inconsistency are related only by model family, not by the same bug." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only accepted pair, 41669/44246, is plausibly the same import-slowdown bug, and the remaining soft-edge rejections do not overclaim equivalence." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 48, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:30333", + "issue:30990", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:36296", + "issue:38617", + "issue:42548", + "issue:42757", + "issue:42831", + "issue:42890", + "issue:43010", + "issue:43299", + "issue:43502", + "issue:43576", + "issue:43618", + "issue:43723", + "issue:43824", + "issue:43827", + "issue:43874", + "issue:44062", + "issue:44112", + "issue:44222", + "issue:44315", + "issue:44351", + "issue:44355", + "issue:44360", + "issue:44368", + "issue:44387", + "issue:44556", + "issue:44655", + "issue:44749", + "issue:44857", + "issue:44938", + "issue:44961", + "issue:44964", + "issue:44977", + "issue:45071", + "issue:45125", + "issue:45278", + "issue:45375", + "issue:45440", + "issue:45468", + "issue:45478", + "issue:45600", + "issue:45656", + "issue:45850", + "issue:46132" + ], + "soft_pairs": [ + "issue:43618|issue:44857", + "issue:44655|issue:44938", + "issue:43618|issue:44977", + "issue:44360|issue:45440", + "issue:42890|issue:44964", + "issue:43502|issue:44062", + "issue:42890|issue:44112", + "issue:42890|issue:45600", + "issue:44222|issue:45125", + "issue:43576|issue:46132", + "issue:42548|issue:44351", + "issue:44355|issue:44749", + "issue:45125|issue:45478", + "issue:30333|issue:33453", + "issue:44387|issue:44556", + "issue:45125|issue:45375", + "issue:43010|issue:45278", + "issue:30990|issue:31795", + "issue:43723|issue:44556", + "issue:43502|issue:44222", + "issue:42831|issue:43874", + "issue:43010|issue:45850", + "issue:43502|issue:44961", + "issue:43010|issue:44368", + "issue:30333|issue:36296", + "issue:44355|issue:45071", + "issue:43827|issue:44961", + "issue:44355|issue:44655", + "issue:44315|issue:44360", + "issue:33453|issue:34689", + "issue:43299|issue:44556", + "issue:42757|issue:43576", + "issue:43576|issue:45071", + "issue:33453|issue:36296", + "issue:43010|issue:45656", + "issue:43576|issue:43824", + "issue:31795|issue:38617", + "issue:44961|issue:45468" + ], + "prepared_review_unit_hash": "a2d24a2b7dd065fa1437c93c451225456e26c259edf958004a70dd5e1bc122c3", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 38, + "serialized_chars": 38612, + "estimated_input_tokens": 9653, + "estimated_eval_tokens": 19562 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The set is broadly heterogeneous: most items are unrelated v5 regressions, import errors, loading issues, or test/docs complaints. I don\u2019t see any soft pair that clearly shares the same concrete underlying bug or fix path.", + "confidence": 0.87, + "canonical_issue_reason": "issue:45278 is the broadest umbrella report in the set, covering the general v5 upgrade/import-breakage theme better than the more specific symptom reports.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45278 is the most triage-useful anchor because it is broad, upgrade-focused, and closest to a reusable umbrella for related regressions.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43618", + "right": "issue:44857", + "accept": false, + "reason": "Different failures: a missing CLIPOutput attentions assignment vs an AMP/CUDA loss crash in LwDetrImageLoss." + }, + { + "left": "issue:44655", + "right": "issue:44938", + "accept": false, + "reason": "One is Pipeline.save_pretrained, the other is Python 3.14 import/load failure; no shared code path." + }, + { + "left": "issue:43618", + "right": "issue:44977", + "accept": false, + "reason": "Different model paths and symptoms: CLIP output fields vs Qwen3.5 flash-attention generation." + }, + { + "left": "issue:44360", + "right": "issue:45440", + "accept": false, + "reason": "DSA indexer/ReLU discussion is unrelated to DeepseekV3MoE behavioral divergence." + }, + { + "left": "issue:42890", + "right": "issue:44964", + "accept": false, + "reason": "A flaky SamHQ integration test is unrelated to loading microsoft/Phi-4-multimodal-instruct." + }, + { + "left": "issue:43502", + "right": "issue:44062", + "accept": false, + "reason": "Local-files-only network leakage and AddedToken argument duplication are different bugs." + }, + { + "left": "issue:42890", + "right": "issue:44112", + "accept": false, + "reason": "Different CI issues: missing set_seed in SamHQ tests vs a stale GraniteSpeech device override test." + }, + { + "left": "issue:42890", + "right": "issue:45600", + "accept": false, + "reason": "SamHQ test seeding flakiness and auto_mappings.py references to removed configs are unrelated." + }, + { + "left": "issue:44222", + "right": "issue:45125", + "accept": false, + "reason": "FP8 save_pretrained on MoE and missing _tp_plan for Qwen3_5MoE are different failure modes." + }, + { + "left": "issue:43576", + "right": "issue:46132", + "accept": false, + "reason": "Broken `transformers env` CLI and AttentionInterface.register behavior change are separate areas." + }, + { + "left": "issue:42548", + "right": "issue:44351", + "accept": false, + "reason": "Both are import errors, but for different symbols and likely different export breakages." + }, + { + "left": "issue:44355", + "right": "issue:44749", + "accept": false, + "reason": "Compiled Python file errors and a Chinese report about slower filtering after upgrade are not the same bug." + }, + { + "left": "issue:45125", + "right": "issue:45478", + "accept": false, + "reason": "Both mention Qwen3.5 MoE, but one is tensor-parallel planning and the other is from_pretrained loading; too different to merge." + }, + { + "left": "issue:30333", + "right": "issue:33453", + "accept": false, + "reason": "MLflow job-status reporting and tokenizer-loading regression are unrelated subsystems." + }, + { + "left": "issue:44387", + "right": "issue:44556", + "accept": false, + "reason": "CUDA reserved-memory/OOM under int4 quantization is not the same as checkpoint reload failure after upgrade." + }, + { + "left": "issue:45125", + "right": "issue:45375", + "accept": false, + "reason": "Missing _tp_plan and missing deepstack_visual_indexes are distinct Qwen3_5Moe issues." + }, + { + "left": "issue:43010", + "right": "issue:45278", + "accept": false, + "reason": "Cache/layer no_grad decoration is unrelated to broad import errors after upgrade." + }, + { + "left": "issue:30990", + "right": "issue:31795", + "accept": false, + "reason": "Stuck Sentence Transformers loading is not the same as a documentation clarification issue." + }, + { + "left": "issue:43723", + "right": "issue:44556", + "accept": false, + "reason": "Tokenizer AutoTokenizer.from_pretrained failure and checkpoint reload regression overlap on loading, but not the same concrete bug." + }, + { + "left": "issue:43502", + "right": "issue:44222", + "accept": false, + "reason": "Unexpected network calls and FP8 MoE save_pretrained are different code paths." + }, + { + "left": "issue:42831", + "right": "issue:43874", + "accept": false, + "reason": "FineGrainedFP8 accuracy and a missing image-processor method causing token-count errors are unrelated." + }, + { + "left": "issue:43010", + "right": "issue:45850", + "accept": false, + "reason": "No-grad decoration for update methods and a generic report that v5 breaks many models are not the same issue." + }, + { + "left": "issue:43502", + "right": "issue:44961", + "accept": false, + "reason": "Local_files_only network requests and an empty 'racoon' issue have no apparent connection." + }, + { + "left": "issue:43827", + "right": "issue:44961", + "accept": false, + "reason": "Docs still referencing pipeline() after removals is unrelated to the 'racoon' placeholder issue." + }, + { + "left": "issue:44355", + "right": "issue:45071", + "accept": false, + "reason": "Compiled-file errors and PreTrainedConfig type-checking regressions are different problems." + }, + { + "left": "issue:44355", + "right": "issue:44655", + "accept": false, + "reason": "Compiled-file execution errors are unrelated to saving Pipeline objects." + }, + { + "left": "issue:44315", + "right": "issue:44360", + "accept": false, + "reason": "Liger Kernel application with model_init and a DSA indexer/ReLU discussion are different topics." + }, + { + "left": "issue:33453", + "right": "issue:34689", + "accept": false, + "reason": "Tokenizer loading regression and Llama 3.2 90B Vision model loading breakage are both loading-related but not the same bug." + }, + { + "left": "issue:43299", + "right": "issue:44556", + "accept": false, + "reason": "Qwen3VL MoE loading and checkpoint reload failures after upgrade are distinct model-specific regressions." + }, + { + "left": "issue:42757", + "right": "issue:43576", + "accept": false, + "reason": "Missing `is_offline_mode` import and broken `transformers env` CLI are unrelated." + }, + { + "left": "issue:43576", + "right": "issue:45071", + "accept": false, + "reason": "CLI breakage and PretrainedConfig type checking are different surfaces and code paths." + }, + { + "left": "issue:33453", + "right": "issue:36296", + "accept": false, + "reason": "Tokenizer loading regression is unrelated to tensor-parallel training bugs." + }, + { + "left": "issue:43010", + "right": "issue:44368", + "accept": false, + "reason": "No-grad cache updates and a tie_word_embeddings warning in Qwen3.5 LoRA are unrelated." + }, + { + "left": "issue:31795", + "right": "issue:38617", + "accept": false, + "reason": "Documentation confusion about forward arguments and an ImportError for layer_type_validation are not the same underlying bug." + }, + { + "left": "issue:44961", + "right": "issue:45468", + "accept": false, + "reason": "A placeholder/empty issue and a Gemma-4 audio positional-encoding bug are clearly unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 49, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:36296", + "issue:41628", + "issue:41669", + "issue:42548", + "issue:42890", + "issue:43010", + "issue:43352", + "issue:43408", + "issue:43525", + "issue:43526", + "issue:43572", + "issue:43576", + "issue:43673", + "issue:43901", + "issue:43976", + "issue:44038", + "issue:44222", + "issue:44230", + "issue:44246", + "issue:44273", + "issue:44295", + "issue:44297", + "issue:44315", + "issue:44351", + "issue:44373", + "issue:44393", + "issue:44492", + "issue:44556", + "issue:44623", + "issue:44704", + "issue:44908", + "issue:44938", + "issue:44961", + "issue:45003", + "issue:45071", + "issue:45092", + "issue:45125", + "issue:45230", + "issue:45278", + "issue:45341", + "issue:45362", + "issue:45542", + "issue:45753", + "issue:45850", + "issue:46095", + "issue:46209", + "issue:46218" + ], + "soft_pairs": [ + "issue:44222|issue:44230", + "issue:43010|issue:43976", + "issue:43576|issue:44938", + "issue:41628|issue:42548", + "issue:44908|issue:44961", + "issue:44315|issue:46209", + "issue:36296|issue:43901", + "issue:36296|issue:43526", + "issue:44623|issue:45230", + "issue:44273|issue:45542", + "issue:44038|issue:45125", + "issue:44273|issue:45003", + "issue:44393|issue:45071", + "issue:44230|issue:46095", + "issue:43576|issue:44556", + "issue:44373|issue:44961", + "issue:44393|issue:45753", + "issue:43525|issue:45850", + "issue:41669|issue:43673", + "issue:44556|issue:45092", + "issue:43572|issue:45850", + "issue:45362|issue:45850", + "issue:41669|issue:46218", + "issue:44246|issue:44273", + "issue:42890|issue:44908", + "issue:43408|issue:44315", + "issue:44704|issue:44908", + "issue:43352|issue:44393", + "issue:43976|issue:44393", + "issue:44297|issue:45230", + "issue:43576|issue:44908", + "issue:44295|issue:45230", + "issue:44908|issue:45071", + "issue:41669|issue:44351", + "issue:41669|issue:45341", + "issue:45278|issue:45850", + "issue:43673|issue:44492" + ], + "prepared_review_unit_hash": "fad3bec65d8fd622d60d8b2359c89700bde351daac2721063993745f70a678c7", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 47, + "item_count": 47, + "soft_pair_count": 37, + "serialized_chars": 37406, + "estimated_input_tokens": 9352, + "estimated_eval_tokens": 18960 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly about Transformers v5 import/lazy-loading regressions and related API compatibility issues. There are no PRs in the set. I would anchor the cluster on the broad lazy-loading/import symptom report, while treating the soft pairs as mostly similar-but-not-duplicate edge cases.", + "confidence": 0.63, + "canonical_issue_reason": "issue:44273 is the broadest and most central report here: it describes lazy loading being broken, which plausibly underlies several of the import-related failures in the cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:44273 is the best issue to represent the cluster because it captures the shared failure mode at a high level, not just one specific symbol or model.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44222", + "right": "issue:44230", + "accept": false, + "reason": "Both mention FP8/MoE, but one is about save_pretrained and the other about inference support; different concrete failures." + }, + { + "left": "issue:43010", + "right": "issue:43976", + "accept": false, + "reason": "Cache update no_grad and Python version incompatibility are unrelated bugs." + }, + { + "left": "issue:43576", + "right": "issue:44938", + "accept": false, + "reason": "Both are version/load problems, but one is the v5 env command and the other is Python 3.14 import/load failure; too different." + }, + { + "left": "issue:41628", + "right": "issue:42548", + "accept": false, + "reason": "Both are top-level import errors, but they target different missing symbols and there is not enough evidence they are the same bug." + }, + { + "left": "issue:44908", + "right": "issue:44961", + "accept": false, + "reason": "Scheduler kwargs handling and an unrelated generic issue title are not the same bug." + }, + { + "left": "issue:44315", + "right": "issue:46209", + "accept": false, + "reason": "Liger Kernel application and FP8 inference on B200 are separate code paths." + }, + { + "left": "issue:36296", + "right": "issue:43901", + "accept": false, + "reason": "Tensor parallel training and pipeline docs are unrelated." + }, + { + "left": "issue:36296", + "right": "issue:43526", + "accept": false, + "reason": "Tensor parallel training and BeitImageProcessorFast label reduction are unrelated." + }, + { + "left": "issue:44623", + "right": "issue:45230", + "accept": false, + "reason": "A specific processor.save_pretrained file bug and a generic bug report do not indicate the same underlying issue." + }, + { + "left": "issue:44273", + "right": "issue:45542", + "accept": false, + "reason": "Lazy loading regressions and missing TensorFlow backend handling are different problems." + }, + { + "left": "issue:44038", + "right": "issue:45125", + "accept": false, + "reason": "Generic Qwen3-VL/MoE breakage and missing tensor-parallel plan are not the same concrete defect." + }, + { + "left": "issue:44273", + "right": "issue:45003", + "accept": false, + "reason": "Both touch import-time behavior, but unsafe sys.modules access is a different root cause than lazy loading not working properly." + }, + { + "left": "issue:44393", + "right": "issue:45071", + "accept": false, + "reason": "Qwen3-VL bbox output errors and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:44230", + "right": "issue:46095", + "accept": false, + "reason": "Both are FP8/MoE-adjacent, but inference support and a weight conversion question are not the same bug." + }, + { + "left": "issue:43576", + "right": "issue:44556", + "accept": false, + "reason": "Both involve version upgrades, but the env command breakage and checkpoint reload incompatibility are different issues." + }, + { + "left": "issue:44373", + "right": "issue:44961", + "accept": false, + "reason": "A docstring typo and an unrelated issue title are not duplicates." + }, + { + "left": "issue:44393", + "right": "issue:45753", + "accept": false, + "reason": "2D bounding-box output errors and an infinite-loop image case are different failures in the same model family." + }, + { + "left": "issue:43525", + "right": "issue:45850", + "accept": false, + "reason": "Specific pad_token_id missing in Llama4Config vs a vague 'breaks too many models' report; not the same concrete bug." + }, + { + "left": "issue:41669", + "right": "issue:43673", + "accept": false, + "reason": "Import-star cleanup/performance and missing GenerationMixin cache during chunked prefill are different problems." + }, + { + "left": "issue:44556", + "right": "issue:45092", + "accept": false, + "reason": "Both are v5 compatibility complaints, but one is general checkpoint reload failure and the other is remote-code/meta-init incompatibility." + }, + { + "left": "issue:43572", + "right": "issue:45850", + "accept": false, + "reason": "A missing pad_token_idx regression is too specific to be the same as a broad 'many models break' report." + }, + { + "left": "issue:45362", + "right": "issue:45850", + "accept": false, + "reason": "Qwen3.5 chat crash and a broad v5 breakage report are not the same underlying defect." + }, + { + "left": "issue:41669", + "right": "issue:46218", + "accept": false, + "reason": "Import performance cleanup and failure to import a specific model module are not the same bug." + }, + { + "left": "issue:44246", + "right": "issue:44273", + "accept": false, + "reason": "Slow import timing and broken lazy loading may be related, but the evidence is not strong enough to treat them as duplicates." + }, + { + "left": "issue:42890", + "right": "issue:44908", + "accept": false, + "reason": "Test flakiness from missing set_seed and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:43408", + "right": "issue:44315", + "accept": false, + "reason": "Model-type warning during sam3 instantiation and Liger Kernel application are unrelated." + }, + { + "left": "issue:44704", + "right": "issue:44908", + "accept": false, + "reason": "AutoProcessor kwargs forwarding and scheduler kwargs handling are different APIs." + }, + { + "left": "issue:43352", + "right": "issue:44393", + "accept": false, + "reason": "Flash Attention 2 support error for Nemotron and Qwen3-VL bbox hallucination/error are unrelated." + }, + { + "left": "issue:43976", + "right": "issue:44393", + "accept": false, + "reason": "Python version incompatibility and Qwen3-VL output errors are unrelated." + }, + { + "left": "issue:44297", + "right": "issue:45230", + "accept": false, + "reason": "Tokenizer save_pretrained metadata mismatch and a generic bug report are not the same defect." + }, + { + "left": "issue:43576", + "right": "issue:44908", + "accept": false, + "reason": "Env command breakage and scheduler kwargs handling are unrelated." + }, + { + "left": "issue:44295", + "right": "issue:45230", + "accept": false, + "reason": "Position_ids buffer access error and generic bug report are not the same issue." + }, + { + "left": "issue:44908", + "right": "issue:45071", + "accept": false, + "reason": "Scheduler kwargs handling and PretrainedConfig type checking are unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44351", + "accept": false, + "reason": "Import-star cleanup and HybridCache import failure are different symbol/export problems." + }, + { + "left": "issue:41669", + "right": "issue:45341", + "accept": false, + "reason": "Import performance cleanup and a testing_utils bug are unrelated." + }, + { + "left": "issue:45278", + "right": "issue:45850", + "accept": false, + "reason": "Many import errors after upgrade and a vague 'breaks too many models' report overlap broadly, but not enough to prove the same underlying bug." + }, + { + "left": "issue:43673", + "right": "issue:44492", + "accept": false, + "reason": "Chunked prefill cache behavior and a typo in cache strategies are unrelated." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 50, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:31515", + "issue:31795", + "issue:33453", + "issue:34689", + "issue:41669", + "issue:42371", + "issue:42913", + "issue:43066", + "issue:43298", + "issue:43352", + "issue:43502", + "issue:43519", + "issue:43525", + "issue:43572", + "issue:43576", + "issue:43606", + "issue:43704", + "issue:43827", + "issue:43874", + "issue:43976", + "issue:44077", + "issue:44261", + "issue:44263", + "issue:44273", + "issue:44315", + "issue:44351", + "issue:44360", + "issue:44393", + "issue:44485", + "issue:44492", + "issue:44623", + "issue:44655", + "issue:44829", + "issue:44861", + "issue:44908", + "issue:44998", + "issue:45230", + "issue:45290", + "issue:45310", + "issue:45468", + "issue:45478", + "issue:45850", + "issue:46018", + "issue:46095", + "issue:46143", + "issue:46144", + "issue:46172", + "issue:46218" + ], + "soft_pairs": [ + "issue:46143|issue:46144", + "issue:43874|issue:45850", + "issue:44393|issue:45478", + "issue:43976|issue:46218", + "issue:44077|issue:44861", + "issue:43827|issue:44908", + "issue:31795|issue:33453", + "issue:41669|issue:44492", + "issue:44315|issue:44829", + "issue:42371|issue:44492", + "issue:43576|issue:44273", + "issue:44655|issue:44861", + "issue:44360|issue:45468", + "issue:45230|issue:45310", + "issue:44273|issue:44908", + "issue:43576|issue:46218", + "issue:43827|issue:44492", + "issue:46018|issue:46172", + "issue:43519|issue:44485", + "issue:43519|issue:44908", + "issue:41669|issue:43704", + "issue:31795|issue:34689", + "issue:31515|issue:31795", + "issue:44485|issue:45468", + "issue:43704|issue:44485", + "issue:43298|issue:46095", + "issue:45850|issue:46218", + "issue:43502|issue:43519", + "issue:42371|issue:43704", + "issue:43519|issue:44623", + "issue:43519|issue:43704", + "issue:43606|issue:45468", + "issue:44263|issue:45468", + "issue:44261|issue:45468", + "issue:44351|issue:46218", + "issue:43352|issue:46218", + "issue:42913|issue:43066", + "issue:44908|issue:44998", + "issue:44861|issue:45290", + "issue:43525|issue:44861", + "issue:43704|issue:44998", + "issue:43572|issue:44861", + "issue:41669|issue:44998", + "issue:43066|issue:44998" + ], + "prepared_review_unit_hash": "c116c538ccd78e8981ae4674ddde9cf9118b64f6ac882f44255f77de003f9490", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 48, + "item_count": 48, + "soft_pair_count": 44, + "serialized_chars": 40118, + "estimated_input_tokens": 10030, + "estimated_eval_tokens": 20316 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "The cluster is mostly a heterogeneous mix of unrelated Transformers issues; none of the soft pairs look like true duplicates. The strongest commonality is broad v5/model-loading regression chatter, but it is not coherent enough to merge into one canonical bug.", + "confidence": 0.89, + "canonical_issue_reason": "issue:45850 is the broadest umbrella report about Transformers v5 breaking many models, so it is the closest thing to a cluster anchor, though the cluster is still too mixed for a true duplicate canonical.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:45850 is the most representative high-level complaint in the set, but it is too vague to be a precise duplicate target.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:46143", + "right": "issue:46144", + "accept": false, + "reason": "Related RoFormer area, but one is missing kwargs passthrough and the other bypasses the attention interface; not the same concrete bug." + }, + { + "left": "issue:43874", + "right": "issue:45850", + "accept": false, + "reason": "One is a specific GLM46V attribute error; the other is a broad meta-complaint about many v5 regressions." + }, + { + "left": "issue:44393", + "right": "issue:45478", + "accept": false, + "reason": "Different Qwen3.5-VL problems: bounding-box output error vs from_pretrained failure." + }, + { + "left": "issue:43976", + "right": "issue:46218", + "accept": false, + "reason": "Python compatibility/versioning issue vs missing Qwen3_5 import; different failure modes and likely different fixes." + }, + { + "left": "issue:44077", + "right": "issue:44861", + "accept": false, + "reason": "PatchTSMixer post_init policy change vs tied-weights key crash; unrelated code paths." + }, + { + "left": "issue:43827", + "right": "issue:44908", + "accept": false, + "reason": "Docs referencing pipeline() vs scheduler kwargs ignored; no shared bug." + }, + { + "left": "issue:31795", + "right": "issue:33453", + "accept": false, + "reason": "Confusing forward docs and tokenizer loading regression are both about usage/loading, but not the same underlying defect." + }, + { + "left": "issue:41669", + "right": "issue:44492", + "accept": false, + "reason": "Import-star performance issue vs cache-strategy typo; clearly different." + }, + { + "left": "issue:44315", + "right": "issue:44829", + "accept": false, + "reason": "Liger kernel not applied with model_init vs Flash Attention 3 training degeneration; different mechanisms." + }, + { + "left": "issue:42371", + "right": "issue:44492", + "accept": false, + "reason": "TF32 API settings guidance vs cache strategy typo; unrelated." + }, + { + "left": "issue:43576", + "right": "issue:44273", + "accept": false, + "reason": "Broken transformers env command vs lazy loading malfunction; different surfaces and causes." + }, + { + "left": "issue:44655", + "right": "issue:44861", + "accept": false, + "reason": "Pipeline save_pretrained issue vs tied weight key AttributeError; not the same bug." + }, + { + "left": "issue:44360", + "right": "issue:45468", + "accept": false, + "reason": "Both mention MLA/DSA-ish internals, but one is a missing ReLU in the indexer and the other is Gemma-4 audio positional encoding." + }, + { + "left": "issue:45230", + "right": "issue:45310", + "accept": false, + "reason": "Generic bug report vs Qwen3.5 MoE from_pretrained error; no concrete overlap." + }, + { + "left": "issue:44273", + "right": "issue:44908", + "accept": false, + "reason": "Lazy loading behavior vs scheduler kwargs handling; separate features." + }, + { + "left": "issue:43576", + "right": "issue:46218", + "accept": false, + "reason": "Broken env CLI vs missing Qwen3_5 import; unrelated." + }, + { + "left": "issue:43827", + "right": "issue:44492", + "accept": false, + "reason": "Docs/pipeline references and a cache-strategy typo do not describe the same defect." + }, + { + "left": "issue:46018", + "right": "issue:46172", + "accept": false, + "reason": "DeepSeek-V4 gating issue vs a tensor conversion/transpose bug; different model code paths." + }, + { + "left": "issue:43519", + "right": "issue:44485", + "accept": false, + "reason": "Qwen3VL timestamp calculation and GLM-5 RoPE implementation are distinct multimodal/model-internal bugs." + }, + { + "left": "issue:43519", + "right": "issue:44908", + "accept": false, + "reason": "Processor timestamp bug vs scheduler kwargs bug; unrelated." + }, + { + "left": "issue:41669", + "right": "issue:43704", + "accept": false, + "reason": "Import-star slowdown and VRAM leak in dataloader threads are different issues." + }, + { + "left": "issue:31795", + "right": "issue:34689", + "accept": false, + "reason": "Docs confusion vs Llama 3.2 Vision model loading regression; not duplicates." + }, + { + "left": "issue:31515", + "right": "issue:31795", + "accept": false, + "reason": "Both are around loading/docs, but one is slow checkpoint loading and the other is forward-API documentation confusion." + }, + { + "left": "issue:44485", + "right": "issue:45468", + "accept": false, + "reason": "Different model families and bugs: GLM-5 RoPE vs Gemma-4 audio positional encoding." + }, + { + "left": "issue:43704", + "right": "issue:44485", + "accept": false, + "reason": "VRAM leak in multithreaded dataloading vs RoPE implementation bug; no overlap." + }, + { + "left": "issue:43298", + "right": "issue:46095", + "accept": false, + "reason": "Continuous batching audio-model support vs DeepSeek-V4 weight conversion/readability question; different topics." + }, + { + "left": "issue:45850", + "right": "issue:46218", + "accept": false, + "reason": "Broad v5 breakage complaint vs a specific missing Qwen3_5 import error." + }, + { + "left": "issue:43502", + "right": "issue:43519", + "accept": false, + "reason": "local_files_only network-leak issue vs Qwen3VL timestamp calculation bug; distinct." + }, + { + "left": "issue:42371", + "right": "issue:43704", + "accept": false, + "reason": "TF32 API settings guidance vs multithreaded VRAM leak; unrelated." + }, + { + "left": "issue:43519", + "right": "issue:44623", + "accept": false, + "reason": "Processor timestamp math bug vs processor.save_pretrained missing files; different save/load areas." + }, + { + "left": "issue:43519", + "right": "issue:43704", + "accept": false, + "reason": "Timestamp calculation in a processor vs VRAM leak under dataloader threads; no shared root cause." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-star performance issue vs unrelated placeholder issue title 'Unemployment'." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Wrong tokenizer decoder type vs unrelated placeholder issue title 'Unemployment'." + }, + { + "left": "issue:44908", + "right": "issue:44998", + "accept": false, + "reason": "Scheduler kwargs bug vs unrelated placeholder issue title 'Unemployment'." + }, + { + "left": "issue:44861", + "right": "issue:45290", + "accept": false, + "reason": "Tied-weight key AttributeError vs chat template crash on tool-call assistant messages; different code paths." + }, + { + "left": "issue:43525", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_id in config vs tied-weight key crash; not the same defect." + }, + { + "left": "issue:43704", + "right": "issue:44998", + "accept": false, + "reason": "VRAM leak in threads vs unrelated placeholder issue title 'Unemployment'." + }, + { + "left": "issue:43572", + "right": "issue:44861", + "accept": false, + "reason": "Missing pad_token_idx in config vs tied-weight key crash; unrelated." + }, + { + "left": "issue:41669", + "right": "issue:44998", + "accept": false, + "reason": "Import-star performance issue vs unrelated placeholder issue title 'Unemployment'." + }, + { + "left": "issue:43066", + "right": "issue:44998", + "accept": false, + "reason": "Tokenizer decoder type bug vs unrelated placeholder issue title 'Unemployment'." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 1, + "component_count": 18, + "review_unit_index": 51, + "review_unit_count": 51, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10000-437", + "nodes": [ + "issue:30333", + "issue:31515", + "issue:33453", + "issue:36296", + "issue:37934", + "issue:38617", + "issue:42936", + "issue:43240", + "issue:43298", + "issue:43668", + "issue:43717", + "issue:43813", + "issue:44031", + "issue:44230", + "issue:44623", + "issue:44998", + "issue:45310", + "issue:46018", + "issue:46144", + "issue:46218" + ], + "soft_pairs": [ + "issue:31515|issue:38617", + "issue:44230|issue:44623", + "issue:44998|issue:46218", + "issue:30333|issue:31515", + "issue:31515|issue:36296", + "issue:44230|issue:45310", + "issue:31515|issue:33453", + "issue:43298|issue:44230", + "issue:43717|issue:46144", + "issue:42936|issue:46018", + "issue:43668|issue:44031", + "issue:42936|issue:43240", + "issue:43240|issue:46144", + "issue:42936|issue:44031", + "issue:42936|issue:46144", + "issue:42936|issue:43813", + "issue:43240|issue:43668", + "issue:43668|issue:43813", + "issue:37934|issue:43668", + "issue:42936|issue:43668" + ], + "prepared_review_unit_hash": "2c20a396467164677e5f7dfd48e2f8706d75c3aee660c71077af405b90b41163", + "component_budget": { + "node_count": 437, + "item_count": 437, + "soft_pair_count": 1611, + "serialized_chars": 834644, + "estimated_input_tokens": 208661, + "estimated_eval_tokens": 417578 + }, + "budget": { + "node_count": 20, + "item_count": 20, + "soft_pair_count": 20, + "serialized_chars": 17052, + "estimated_input_tokens": 4263, + "estimated_eval_tokens": 8782 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is heterogeneous: the soft-similarity pairs overlap only on broad model/loading/tokenizer language, not the same concrete bug or change. No pair is a safe duplicate match.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:31515", + "right": "issue:38617", + "accept": false, + "reason": "Checkpoint loading slowness and an ImportError in configuration_utils are unrelated code paths." + }, + { + "left": "issue:44230", + "right": "issue:44623", + "accept": false, + "reason": "FP8 inference support for Qwen models is unrelated to missing files from processor.save_pretrained()." + }, + { + "left": "issue:44998", + "right": "issue:46218", + "accept": false, + "reason": "These titles describe unrelated problems; one is nonsensical/off-topic, the other is a Qwen import failure." + }, + { + "left": "issue:30333", + "right": "issue:31515", + "accept": false, + "reason": "MLFlow job-status reporting after failure is unrelated to slow from_pretrained checkpoint loading." + }, + { + "left": "issue:31515", + "right": "issue:36296", + "accept": false, + "reason": "Checkpoint load performance and tensor-parallel training bugs do not describe the same failure." + }, + { + "left": "issue:44230", + "right": "issue:45310", + "accept": false, + "reason": "Both mention Qwen3.5 MoE, but one is FP8 support for inference and the other is a from_pretrained regression." + }, + { + "left": "issue:31515", + "right": "issue:33453", + "accept": false, + "reason": "Slow checkpoint loading and tokenizer-loading regression are different bugs." + }, + { + "left": "issue:43298", + "right": "issue:44230", + "accept": false, + "reason": "Continuous batching support for audio models is unrelated to FP8 Qwen model support." + }, + { + "left": "issue:43717", + "right": "issue:46144", + "accept": false, + "reason": "Mamba init_weights behavior and RoFormer attention-interface usage are different implementation issues." + }, + { + "left": "issue:42936", + "right": "issue:46018", + "accept": false, + "reason": "Mask2former ignore_value handling and DeepSeek-V4 shared-expert gating are unrelated model-specific bugs." + }, + { + "left": "issue:43668", + "right": "issue:44031", + "accept": false, + "reason": "A config type-hint typo is not the same as tokenizer regex warning behavior." + }, + { + "left": "issue:42936", + "right": "issue:43240", + "accept": false, + "reason": "Ignoring a Mask2former value and kwargs not reaching loss calculation are different defects." + }, + { + "left": "issue:43240", + "right": "issue:46144", + "accept": false, + "reason": "Loss-function kwargs propagation has no overlap with RoFormer attention implementation." + }, + { + "left": "issue:42936", + "right": "issue:44031", + "accept": false, + "reason": "These are unrelated: Mask2former ignore_value handling versus tokenizer regex warnings." + }, + { + "left": "issue:42936", + "right": "issue:46144", + "accept": false, + "reason": "Mask2former ignore_value and RoFormer attention-interface problems are different subsystems and bugs." + }, + { + "left": "issue:42936", + "right": "issue:43813", + "accept": false, + "reason": "A Mask2former loss-value issue is unrelated to a typo in quantization_operation." + }, + { + "left": "issue:43240", + "right": "issue:43668", + "accept": false, + "reason": "Loss kwargs propagation and a ModernBERT type-hint issue are not the same change." + }, + { + "left": "issue:43668", + "right": "issue:43813", + "accept": false, + "reason": "Incorrect type annotation and a typo in another symbol name are distinct issues." + }, + { + "left": "issue:37934", + "right": "issue:43668", + "accept": false, + "reason": "RMSNorm semantics for Llama4TextL2Norm are unrelated to ModernBERT norm_eps typing." + }, + { + "left": "issue:42936", + "right": "issue:43668", + "accept": false, + "reason": "Mask2former ignore_value handling does not match a ModernBERT config type-hint bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 2, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-10519-3", + "nodes": [ + "issue:10519", + "issue:11005", + "issue:11307" + ], + "soft_pairs": [ + "issue:10519|issue:11307", + "issue:10519|issue:11005", + "issue:11005|issue:11307" + ], + "prepared_review_unit_hash": "cc6db42238218ac85a7ca0fa9d7062c8d3b4ccdbd63edc62ce2bf8dcc44c55d1", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2877, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 2877, + "estimated_input_tokens": 720, + "estimated_eval_tokens": 1696 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These three issues are about unrelated feature requests in different parts of the library: token truncation behavior, scheduler functionality, and Wav2Vec2 word timing offsets. They do not describe the same underlying bug or change, so none should be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": "No canonical issue: the titles and descriptions point to three distinct requests with different code paths and goals.", + "canonical_pr_reason": null, + "best_issue_reason": "No single best issue candidate because there is no duplicate set here; each issue targets a different feature area.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:10519", + "right": "issue:11307", + "accept": false, + "reason": "Truncation option request and Wav2Vec2 timing offsets are unrelated feature requests in different components." + }, + { + "left": "issue:10519", + "right": "issue:11005", + "accept": false, + "reason": "Token truncation behavior and ReduceLROnPlateau-like scheduler functionality are separate problems with no shared code path." + }, + { + "left": "issue:11005", + "right": "issue:11307", + "accept": false, + "reason": "Scheduler feature request and Wav2Vec2 word offset request concern different subsystems and do not look like the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 3, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-13244-3", + "nodes": [ + "issue:13244", + "issue:15980", + "issue:16618" + ], + "soft_pairs": [ + "issue:13244|issue:16618", + "issue:15980|issue:16618" + ], + "prepared_review_unit_hash": "838e9e84a34f8b21d4da7ea1d262d0adfc6047e50ef5e565f7fc4833d694b693", + "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": "No clear duplicate cluster: 13244 is unrelated, and 15980 vs 16618 only overlap at a broad \"model loading/download\" level. The private-model auth/error-message report and the generic \"can't load bert-base-uncased\" report do not look like the same underlying bug.", + "confidence": 0.89, + "canonical_issue_reason": "No strong canonical duplicate stands out; if forced, 16618 is the broadest issue, but it does not clearly subsume the others.", + "canonical_pr_reason": null, + "best_issue_reason": "16618 is the most general and central of the three, but it still appears to describe a different failure mode than 15980 and is unrelated to 13244.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:13244", + "right": "issue:16618", + "accept": false, + "reason": "Different topics entirely: Tapas tokenization vs. model loading failure. Same broad library, not the same bug." + }, + { + "left": "issue:15980", + "right": "issue:16618", + "accept": false, + "reason": "Both concern model download/load errors, but 15980 is specifically a private-model login/auth error while 16618 is a generic inability to load bert-base-uncased; 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": 4, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-26350-2", + "nodes": [ + "issue:26350", + "issue:33260" + ], + "soft_pairs": [ + "issue:26350|issue:33260" + ], + "prepared_review_unit_hash": "7ab7a7b3204dfa2d2d0d2ea2b6df2c57fdb6e6eda22129df32fcc548feaa0adb", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1590, + "estimated_input_tokens": 398, + "estimated_eval_tokens": 1052 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two separate community-contribution issues for different features: Flash Attention 2 support vs GGUF support. They share only a generic contribution framing, not the same underlying bug or change request.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:26350", + "right": "issue:33260", + "accept": false, + "reason": "Different requested capabilities and code paths: Flash Attention 2 architecture support is unrelated to GGUF support. Similar wording about community contributions is too broad to treat as 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": 5, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-27088-8", + "nodes": [ + "issue:27088", + "issue:28936", + "issue:38435", + "issue:43834", + "issue:44365", + "issue:44370", + "issue:46222", + "issue:46226" + ], + "soft_pairs": [ + "issue:27088|issue:44370", + "issue:27088|issue:46222", + "issue:27088|issue:44365", + "issue:27088|issue:43834", + "issue:27088|issue:38435", + "issue:27088|issue:28936", + "issue:28936|issue:43834", + "issue:28936|issue:44365", + "issue:28936|issue:38435", + "issue:28936|issue:44370", + "issue:38435|issue:44370", + "issue:38435|issue:46222", + "issue:38435|issue:44365", + "issue:38435|issue:43834", + "issue:38435|issue:46226", + "issue:43834|issue:44370", + "issue:43834|issue:46222", + "issue:43834|issue:44365", + "issue:43834|issue:46226", + "issue:44365|issue:44370", + "issue:44365|issue:46222", + "issue:44365|issue:46226", + "issue:44370|issue:46222", + "issue:44370|issue:46226", + "issue:46222|issue:46226" + ], + "prepared_review_unit_hash": "940aaa18b4ee3a8962be8e8fc31f23c076d542695a415d37a3210c24adee3c04", + "component_budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 25, + "serialized_chars": 13686, + "estimated_input_tokens": 3422, + "estimated_eval_tokens": 7100 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 25, + "serialized_chars": 13686, + "estimated_input_tokens": 3422, + "estimated_eval_tokens": 7100 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The cluster is dominated by i18n translation-request issues. The explicit language-specific issues are clearly separate requests, and the templated placeholder issues are too ambiguous to safely merge without a concrete language target.", + "confidence": 0.68, + "canonical_issue_reason": "issue:46222 is the newest open issue and the best representative of the repeated i18n translation-request template in this cluster.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:46222 is the most current open issue among the near-identical templated entries, so it is the best single representative if one issue must anchor the cluster.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:27088", + "right": "issue:44370", + "accept": false, + "reason": "Different language-request issue versus a templated placeholder entry; no explicit target or shared artifact evidence that they are the same request." + }, + { + "left": "issue:27088", + "right": "issue:46222", + "accept": false, + "reason": "Turkish translation request does not match the ambiguous templated entry as a concrete duplicate." + }, + { + "left": "issue:27088", + "right": "issue:44365", + "accept": false, + "reason": "Different language target; similarity is only at the generic i18n translation-template level." + }, + { + "left": "issue:27088", + "right": "issue:43834", + "accept": false, + "reason": "Distinct translation request; the shared wording is too broad to treat as the same issue." + }, + { + "left": "issue:27088", + "right": "issue:38435", + "accept": false, + "reason": "Turkish and Romanian translation requests are separate issues, not the same underlying change." + }, + { + "left": "issue:27088", + "right": "issue:28936", + "accept": false, + "reason": "Turkish and Spanish are different language targets, so this is not a duplicate." + }, + { + "left": "issue:28936", + "right": "issue:43834", + "accept": false, + "reason": "Spanish request versus an ambiguous templated entry; no concrete evidence of the same underlying issue." + }, + { + "left": "issue:28936", + "right": "issue:44365", + "accept": false, + "reason": "Different language target; the overlap is only the generic i18n docs template." + }, + { + "left": "issue:28936", + "right": "issue:38435", + "accept": false, + "reason": "Spanish and Romanian translation requests are separate issues." + }, + { + "left": "issue:28936", + "right": "issue:44370", + "accept": false, + "reason": "Spanish request does not match the templated entry as a clear duplicate." + }, + { + "left": "issue:38435", + "right": "issue:44370", + "accept": false, + "reason": "Romanian request versus a generic template entry; too little concrete evidence to merge." + }, + { + "left": "issue:38435", + "right": "issue:46222", + "accept": false, + "reason": "Romanian translation request is a separate language-specific issue, not the same underlying request." + }, + { + "left": "issue:38435", + "right": "issue:44365", + "accept": false, + "reason": "Different language target; the similarity is only template-level." + }, + { + "left": "issue:38435", + "right": "issue:43834", + "accept": false, + "reason": "Romanian request and the placeholder-titled issue are not demonstrably the same bug/change." + }, + { + "left": "issue:38435", + "right": "issue:46226", + "accept": false, + "reason": "Romanian and Thai translation requests are distinct issues." + }, + { + "left": "issue:43834", + "right": "issue:44370", + "accept": false, + "reason": "Both look like template-matched translation requests, but there is no concrete language target or issue linkage proving they are the same request." + }, + { + "left": "issue:43834", + "right": "issue:46222", + "accept": false, + "reason": "Near-identical template text is not enough here; this could still be a separate language request." + }, + { + "left": "issue:43834", + "right": "issue:44365", + "accept": false, + "reason": "Ambiguous placeholder issues with no explicit target language; reject as potential distinct requests." + }, + { + "left": "issue:43834", + "right": "issue:38435", + "accept": false, + "reason": "The explicit Romanian request is not proven to be the same as the placeholder-titled issue." + }, + { + "left": "issue:44365", + "right": "issue:44370", + "accept": false, + "reason": "Extremely similar template text, but lacking a concrete target language or issue linkage, so do not merge." + }, + { + "left": "issue:44365", + "right": "issue:46222", + "accept": false, + "reason": "Template similarity alone is insufficient to treat these as the same underlying issue." + }, + { + "left": "issue:44365", + "right": "issue:46226", + "accept": false, + "reason": "Placeholder template issue and Thai-language request are not clearly the same request." + }, + { + "left": "issue:44370", + "right": "issue:46222", + "accept": false, + "reason": "These are only similar at the generic template level; no concrete evidence they are duplicates." + }, + { + "left": "issue:44370", + "right": "issue:46226", + "accept": false, + "reason": "Generic template issue versus Thai translation request; not a safe duplicate match." + }, + { + "left": "issue:46222", + "right": "issue:46226", + "accept": false, + "reason": "Placeholder-titled translation issue and Thai-language request are distinct enough that a duplicate merge would be unsafe." + } + ] + }, + "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": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-36817-16", + "nodes": [ + "issue:36817", + "issue:36879", + "issue:37015", + "issue:41115", + "issue:41211", + "issue:42503", + "issue:42738", + "issue:43671", + "issue:43837", + "issue:43909", + "issue:44121", + "issue:44205", + "issue:45027", + "issue:45177", + "issue:45322", + "issue:46133" + ], + "soft_pairs": [ + "issue:36817|issue:41211", + "issue:36817|issue:43671", + "issue:36817|issue:36879", + "issue:36879|issue:41211", + "issue:36879|issue:43909", + "issue:36879|issue:44121", + "issue:36879|issue:43837", + "issue:36879|issue:43671", + "issue:37015|issue:43837", + "issue:37015|issue:44121", + "issue:37015|issue:43909", + "issue:36879|issue:37015", + "issue:37015|issue:42503", + "issue:41115|issue:43837", + "issue:41115|issue:44121", + "issue:41115|issue:42503", + "issue:41115|issue:45027", + "issue:41211|issue:43671", + "issue:42503|issue:43837", + "issue:42503|issue:43671", + "issue:42503|issue:42738", + "issue:42738|issue:45027", + "issue:43671|issue:43837", + "issue:43671|issue:45027", + "issue:43671|issue:45177", + "issue:43671|issue:44121", + "issue:43837|issue:43909", + "issue:43837|issue:45322", + "issue:43909|issue:44205", + "issue:43671|issue:43909", + "issue:44121|issue:45322", + "issue:43837|issue:44121", + "issue:43837|issue:45027", + "issue:37015|issue:45027", + "issue:43837|issue:45177", + "issue:45322|issue:46133" + ], + "prepared_review_unit_hash": "67f4eb186b5a24dbb5e67d21309d24e4bfc19b207194024888954b222bf5b0d6", + "component_budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21658, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "budget": { + "node_count": 16, + "item_count": 16, + "soft_pair_count": 36, + "serialized_chars": 21658, + "estimated_input_tokens": 5415, + "estimated_eval_tokens": 11086 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly a loose set of model-request issues across different modalities (text, vision, audio, ASR/TTS, detection). The titles are thematically similar, but none look like true duplicates of the same concrete request.", + "confidence": 0.31, + "canonical_issue_reason": "issue:42738 is the most generic, cross-cutting model-architecture request in the set and is the best broad anchor for the BERT-family subset, though the overall cluster is only loosely related.", + "canonical_pr_reason": null, + "best_issue_reason": "issue:42738 best represents the broad 'add support for a model/config variant' theme that loosely ties the cluster together.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:36817", + "right": "issue:41211", + "accept": false, + "reason": "Different models and tasks: EuroBert config vs DEIMv2 object detection." + }, + { + "left": "issue:36817", + "right": "issue:43671", + "accept": false, + "reason": "Text model config request vs Qwen3 TTS support; same library area, different change." + }, + { + "left": "issue:36817", + "right": "issue:36879", + "accept": false, + "reason": "EuroBert config vs RF-DETR model; unrelated model families." + }, + { + "left": "issue:36879", + "right": "issue:41211", + "accept": false, + "reason": "Both are detection-related, but RF-DETR and DEIMv2 are distinct architectures and requests." + }, + { + "left": "issue:36879", + "right": "issue:43909", + "accept": false, + "reason": "Object detection model vs audio model request; not the same underlying change." + }, + { + "left": "issue:36879", + "right": "issue:44121", + "accept": false, + "reason": "RF-DETR addition is unrelated to OpenAI weight-sparse transformer support." + }, + { + "left": "issue:36879", + "right": "issue:43837", + "accept": false, + "reason": "Detection model request vs Qwen3 ASR support; different modality and code paths." + }, + { + "left": "issue:36879", + "right": "issue:43671", + "accept": false, + "reason": "Detection model request vs Qwen3 TTS support; only broad topical overlap." + }, + { + "left": "issue:37015", + "right": "issue:43837", + "accept": false, + "reason": "NeoBERT text-model request vs Qwen3 ASR support; different model family and modality." + }, + { + "left": "issue:37015", + "right": "issue:44121", + "accept": false, + "reason": "NeoBERT addition and sparse-transformer support are unrelated model requests." + }, + { + "left": "issue:37015", + "right": "issue:43909", + "accept": false, + "reason": "NeoBERT text model vs audio model; no shared concrete change." + }, + { + "left": "issue:36879", + "right": "issue:37015", + "accept": false, + "reason": "RF-DETR detection request and NeoBERT request are different model families." + }, + { + "left": "issue:37015", + "right": "issue:42503", + "accept": false, + "reason": "NeoBERT vs ModernVBERT; both text-model-ish but distinct requests." + }, + { + "left": "issue:41115", + "right": "issue:43837", + "accept": false, + "reason": "MiniCPM3 architecture request vs Qwen3 ASR support; different model and modality." + }, + { + "left": "issue:41115", + "right": "issue:44121", + "accept": false, + "reason": "MiniCPM3 support and sparse-transformer support do not target the same code path." + }, + { + "left": "issue:41115", + "right": "issue:42503", + "accept": false, + "reason": "MiniCPM3 vs ModernVBERT; both are model additions, not duplicates." + }, + { + "left": "issue:41115", + "right": "issue:45027", + "accept": false, + "reason": "MiniCPM3 request vs Voxtral TTS support; different model families and functionality." + }, + { + "left": "issue:41211", + "right": "issue:43671", + "accept": false, + "reason": "DEIMv2 detection request vs Qwen3 TTS support; different underlying change." + }, + { + "left": "issue:42503", + "right": "issue:43837", + "accept": false, + "reason": "ModernVBERT model addition vs Qwen3 ASR support; unrelated model targets." + }, + { + "left": "issue:42503", + "right": "issue:43671", + "accept": false, + "reason": "ModernVBERT vs Qwen3 TTS; same general area, not the same request." + }, + { + "left": "issue:42503", + "right": "issue:42738", + "accept": false, + "reason": "ModernVBERT addition and BERT-like models with RoPE are not the same concrete model request." + }, + { + "left": "issue:42738", + "right": "issue:45027", + "accept": false, + "reason": "BERT-like RoPE support request vs Voxtral TTS support; unrelated modalities." + }, + { + "left": "issue:43671", + "right": "issue:43837", + "accept": false, + "reason": "Qwen3 TTS and Qwen3 ASR share a family but request different capabilities and code paths." + }, + { + "left": "issue:43671", + "right": "issue:45027", + "accept": false, + "reason": "Both are TTS-related, but Qwen3 TTS and Voxtral TTS are different models and changes." + }, + { + "left": "issue:43671", + "right": "issue:45177", + "accept": false, + "reason": "TTS support request vs DeepSeek-OCR2; different model class and use case." + }, + { + "left": "issue:43671", + "right": "issue:44121", + "accept": false, + "reason": "TTS support request vs sparse-transformer request; no same underlying bug/change." + }, + { + "left": "issue:43837", + "right": "issue:43909", + "accept": false, + "reason": "ASR support request vs audio model addition; related area but different model and implementation." + }, + { + "left": "issue:43837", + "right": "issue:45322", + "accept": false, + "reason": "ASR support request vs vision-language encoder request; different modality and code path." + }, + { + "left": "issue:43909", + "right": "issue:44205", + "accept": false, + "reason": "Audio model request vs SAM3-LiteText; distinct model families." + }, + { + "left": "issue:43671", + "right": "issue:43909", + "accept": false, + "reason": "TTS model request vs audio model request; not a duplicate." + }, + { + "left": "issue:44121", + "right": "issue:45322", + "accept": false, + "reason": "Sparse-transformer model request vs EUPE perception encoder request; unrelated models." + }, + { + "left": "issue:43837", + "right": "issue:44121", + "accept": false, + "reason": "Qwen3 ASR support and weight-sparse transformer support are different changes." + }, + { + "left": "issue:43837", + "right": "issue:45027", + "accept": false, + "reason": "ASR support request vs Voxtral TTS support; same audio umbrella, different concrete request." + }, + { + "left": "issue:37015", + "right": "issue:45027", + "accept": false, + "reason": "NeoBERT text-model request vs Voxtral TTS support; unrelated." + }, + { + "left": "issue:43837", + "right": "issue:45177", + "accept": false, + "reason": "ASR support request vs OCR model addition; different modality and code path." + }, + { + "left": "issue:45322", + "right": "issue:46133", + "accept": false, + "reason": "Both are vision-language encoder/pretraining requests, but EUPE and TIPSv2 are distinct models and not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 7, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-41084-2", + "nodes": [ + "issue:41084", + "issue:43037" + ], + "soft_pairs": [ + "issue:41084|issue:43037" + ], + "prepared_review_unit_hash": "9b1b684bae0bfde421bb2e6658719c5fc885d026d41eb5478a35213bbc9049fd", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1480, + "estimated_input_tokens": 370, + "estimated_eval_tokens": 996 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are not duplicates: one is about Set Block Decoding, the other about DeepSeek v3.2 support. They mention different product areas and different requested changes.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:41084", + "right": "issue:43037", + "accept": false, + "reason": "Different underlying requests: decoding behavior vs model support; no indication they describe the same bug or change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 8, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43598-2", + "nodes": [ + "issue:43598", + "issue:43600" + ], + "soft_pairs": [ + "issue:43598|issue:43600" + ], + "prepared_review_unit_hash": "77bd21d27fdc318e321cc64bb1bf59dd8057cca98476f77e414092cbeff7ab08", + "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 Trainer customization, but they describe different problems: unused-column handling vs FLOPS estimation for custom trainers. They should not be deduplicated.", + "confidence": 0.96, + "canonical_issue_reason": "Issue 43598 is the more concrete Trainer customization request; 43600 is a separate metrics/accounting concern.", + "canonical_pr_reason": null, + "best_issue_reason": "43598 is the better cluster representative because it is a specific, actionable Trainer behavior change rather than a broader estimation question.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43598", + "right": "issue:43600", + "accept": false, + "reason": "Different underlying changes: one asks to revisit `remove_unused_column`, the other asks to account for custom trainers in FLOPS estimation. Shared Trainer context is too broad to treat as the same bug." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 9, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43684-2", + "nodes": [ + "issue:43684", + "issue:44405" + ], + "soft_pairs": [ + "issue:43684|issue:44405" + ], + "prepared_review_unit_hash": "e02adba0bf8c1b93f20813215517dcb4e3d9e4d9b30e24d1674b2e5896965e9b", + "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": "Two closed issues request different Qwen-related enhancements: one for Qwen3-Omni auto-registration, the other for Qwen3.5 sequence classification support. They are related by model family but not the same underlying change.", + "confidence": 0.93, + "canonical_issue_reason": "Issue 43684 is the broader request and the better representative if a single issue must be chosen, but it does not duplicate issue 44405.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 43684 is the more general auto-model registration request; issue 44405 is a separate, narrower head-support request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43684", + "right": "issue:44405", + "accept": false, + "reason": "Different model variants and different capabilities requested: auto-registration for Qwen3-Omni vs sequence classification support for Qwen3.5." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 10, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43835-4", + "nodes": [ + "issue:43835", + "issue:43845", + "issue:43846", + "issue:43859" + ], + "soft_pairs": [ + "issue:43835|issue:43845", + "issue:43835|issue:43846", + "issue:43835|issue:43859", + "issue:43845|issue:43846", + "issue:43845|issue:43859", + "issue:43846|issue:43859" + ], + "prepared_review_unit_hash": "7ec0fbd37750b201c40434c948a24af5ff4887e14431d59bfbbcfcefec1770cc", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4262, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 4262, + "estimated_input_tokens": 1066, + "estimated_eval_tokens": 2388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "One outlier issue (\u201cFett\u201d) appears unrelated; the three \u201chuggingface\u201d issues are highly likely duplicates of the same sparse report and should cluster together.", + "confidence": 0.77, + "canonical_issue_reason": "Issue 43859 is the best representative among the duplicate-looking \u201chuggingface\u201d reports because it has the same title as the others and the only discussion activity in the set.", + "canonical_pr_reason": null, + "best_issue_reason": "43859 is the strongest cluster anchor: same title as 43845/43846, similar minimal content, and slightly more activity than the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:43835", + "right": "issue:43845", + "accept": false, + "reason": "Different title and no evidence of the same underlying problem; this does not look like the same report." + }, + { + "left": "issue:43835", + "right": "issue:43846", + "accept": false, + "reason": "Different title and no shared concrete problem details; likely unrelated." + }, + { + "left": "issue:43835", + "right": "issue:43859", + "accept": false, + "reason": "Different title and no concrete overlap beyond both being short issues." + }, + { + "left": "issue:43845", + "right": "issue:43846", + "accept": true, + "reason": "Same title (\u201chuggingface \u201d) and near-identical sparse issue shape, so they likely describe the same underlying report." + }, + { + "left": "issue:43845", + "right": "issue:43859", + "accept": true, + "reason": "Same title and very similar minimal metadata/body pattern; likely duplicate reports." + }, + { + "left": "issue:43846", + "right": "issue:43859", + "accept": true, + "reason": "Same title and near-identical sparse report structure; likely the same underlying issue." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The cluster summary is grounded in the packet: 43835 has a different title, while 43845/43846/43859 all share the same title and similarly sparse metadata. The soft-edge acceptances for the three hugggingface issues are conservative enough given the identical titles and close similarity scores, and the choice of 43859 as canonical is supported by its extra discussion activity." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 11, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-44371-5", + "nodes": [ + "issue:44371", + "issue:44418", + "issue:44572", + "issue:44573", + "issue:44937" + ], + "soft_pairs": [ + "issue:44371|issue:44572", + "issue:44371|issue:44573", + "issue:44371|issue:44418", + "issue:44371|issue:44937", + "issue:44418|issue:44572", + "issue:44418|issue:44573", + "issue:44572|issue:44573", + "issue:44572|issue:44937", + "issue:44573|issue:44937" + ], + "prepared_review_unit_hash": "9863e338842f69b97a7fd336923b6fc8153e1ae8dc27a4b2075d6e3453ad8125", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 9, + "serialized_chars": 5794, + "estimated_input_tokens": 1449, + "estimated_eval_tokens": 3154 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues do not appear to describe the same underlying bug or change; they are mostly spam/generic noise with no concrete shared problem statement.", + "confidence": 0.96, + "canonical_issue_reason": "No issue is a credible canonical: the titles are either spam, a generic documentation suggestion, or an unrelated promotional phrase, with no concrete bug description to anchor deduplication.", + "canonical_pr_reason": null, + "best_issue_reason": "No strong best issue candidate exists for deduping this cluster; issue 44937 is slightly more substantive-looking by title, but it still does not indicate the same problem as the others.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:44371", + "right": "issue:44572", + "accept": false, + "reason": "Both are spam-like titles; no evidence they refer to the same real issue." + }, + { + "left": "issue:44371", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam-like titles; no shared concrete bug or change." + }, + { + "left": "issue:44371", + "right": "issue:44418", + "accept": false, + "reason": "One is spam, the other is a generic documentation suggestion; not the same underlying issue." + }, + { + "left": "issue:44371", + "right": "issue:44937", + "accept": false, + "reason": "Spam title vs unrelated promotional/title phrase; no duplicate signal." + }, + { + "left": "issue:44418", + "right": "issue:44572", + "accept": false, + "reason": "Generic documentation suggestion and spam are not the same issue." + }, + { + "left": "issue:44418", + "right": "issue:44573", + "accept": false, + "reason": "Generic documentation suggestion and spam are not the same issue." + }, + { + "left": "issue:44572", + "right": "issue:44573", + "accept": false, + "reason": "Both are spam-like, but there is no evidence of the same underlying bug or change." + }, + { + "left": "issue:44572", + "right": "issue:44937", + "accept": false, + "reason": "Spam title vs unrelated promotional/title phrase; no concrete overlap." + }, + { + "left": "issue:44573", + "right": "issue:44937", + "accept": false, + "reason": "Spam title vs unrelated promotional/title phrase; no concrete overlap." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 12, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45145-2", + "nodes": [ + "issue:45145", + "issue:45151" + ], + "soft_pairs": [ + "issue:45145|issue:45151" + ], + "prepared_review_unit_hash": "bdb45e14b5ba358573eba1a8493b7435f7e562cdfc696a63b26dad55bbd55e4c", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1646, + "estimated_input_tokens": 412, + "estimated_eval_tokens": 1080 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two closed issues have identical titles and strong body similarity, but there is not enough linking evidence to confidently treat them as a duplicate pair; #45145 is the best canonical representative.", + "confidence": 0.89, + "canonical_issue_reason": "#45145 is the better canonical issue because it was created slightly earlier and has an inbound reference, while matching the same title and highly similar content as #45151.", + "canonical_pr_reason": null, + "best_issue_reason": "#45145 is the strongest issue representative for the cluster because it is the earliest matching report and already has a bit more discussion linkage.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45145", + "right": "issue:45151", + "accept": false, + "reason": "The evidence only shows the same title and a soft text-similarity signal; there are no shared files, explicit targets, or direct links to ground a confident true-duplicate claim." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "Rejecting because the soft-edge verdict overstates the evidence. The packet supports only same title, similar size, and a soft_similarity signal (Jaccard ~0.63) with no shared files/targets or explicit links; it does not ground a confident \u2018true duplicate\u2019 or \u2018near-identical bodies\u2019 claim. The canonical issue choice is fine, but the duplicate verdict should be more conservative." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 13, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45295-2", + "nodes": [ + "issue:45295", + "issue:45373" + ], + "soft_pairs": [], + "prepared_review_unit_hash": "f5fd95fada2f530ab0999e343c17c16266cde0c7182bb22509972ca44827cd49", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 0, + "serialized_chars": 1286, + "estimated_input_tokens": 322, + "estimated_eval_tokens": 900 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues describe the same missing Gemma 4 sequence-classification support; the later, more specific open issue is the better cluster representative.", + "confidence": 0.94, + "canonical_issue_reason": "issue #45373 is the clearest canonical tracker: it is open, explicitly names the missing class `Gemma4ForSequenceClassification`, and states the module-level gap relative to Gemma 2/3.", + "canonical_pr_reason": null, + "best_issue_reason": "issue #45373 best captures the concrete request and likely remaining work, while #45295 is a shorter earlier duplicate with less detail and is already closed.", + "best_pr_reason": null, + "soft_edge_verdicts": [] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 14, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "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": "66b7c7713c06921f91b625ff9e9e3f40ceb804acb03b06d9886d9d81aa28b4c1", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1670, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1670, + "estimated_input_tokens": 418, + "estimated_eval_tokens": 1092 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two issues are related to 4-bit inference and quantization behavior, but they describe different failures and different code paths: one is a Gemma4 audio-module `torch.finfo()` TypeError on `uint8` weights, the other is a `BitsAndBytesConfig` skip-module regression that drops the default `lm_head` exclusion and triggers an AssertionError.", + "confidence": 0.93, + "canonical_issue_reason": "Issue #45674 is the better representative because it is open, more directly framed as a configuration regression, and appears easier to track as an actionable bug report.", + "canonical_pr_reason": null, + "best_issue_reason": "#45674 is the best issue for the cluster since it names the specific 4-bit inference regression and likely reflects the active bug being investigated; #45672 is a separate, narrower Gemma4/audio failure.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45672", + "right": "issue:45674", + "accept": false, + "reason": "Both are 4-bit inference bugs, but the failures are different: `torch.finfo()` on `uint8` audio weights versus `llm_int8_skip_modules` clearing the default `lm_head` exclusion and causing an AssertionError. Shared subsystem alone is not enough to treat them as 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": 15, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45762-2", + "nodes": [ + "issue:45762", + "issue:45763" + ], + "soft_pairs": [ + "issue:45762|issue:45763" + ], + "prepared_review_unit_hash": "afc1660cb246fe71680915d2acda69eab5ff7f51b4b6ba92e69994a4d302e209", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1476, + "estimated_input_tokens": 369, + "estimated_eval_tokens": 994 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "The two issues are not duplicates; they are separate name/date entries with no shared technical content or linking evidence.", + "confidence": 0.96, + "canonical_issue_reason": "No clear canonical issue: both are unrelated, contentless personal-name entries with different names and dates.", + "canonical_pr_reason": null, + "best_issue_reason": "Neither issue is a good duplicate anchor because there is no demonstrated underlying bug, feature request, or shared subject.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45762", + "right": "issue:45763", + "accept": false, + "reason": "The titles only share a similar personal-name/date pattern; there is no evidence they describe the same underlying issue 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": 16, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45764-2", + "nodes": [ + "issue:45764", + "issue:45765" + ], + "soft_pairs": [ + "issue:45764|issue:45765" + ], + "prepared_review_unit_hash": "612a302576ebc80880c99e59aef076a38a83682ba4bbb2267d45dd7e522b57bd", + "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 closed issues have only superficial similarity in title structure and appear to be unrelated personal-name entries, not duplicates of the same bug or task.", + "confidence": 0.94, + "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": "Reject: the titles are different named entities with different dates and no shared problem description, targets, or repository context; this does not look like the same underlying issue." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "issue", + "component_index": 17, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45810-2", + "nodes": [ + "issue:45810", + "issue:46295" + ], + "soft_pairs": [ + "issue:45810|issue:46295" + ], + "prepared_review_unit_hash": "ee191d2f679a0c04688dec32200905a8e2c96cc943e3536b96f26465c81883c2", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1541, + "estimated_input_tokens": 386, + "estimated_eval_tokens": 1028 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 1541, + "estimated_input_tokens": 386, + "estimated_eval_tokens": 1028 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These issues are unrelated: one requests a new Qwen3_5 token classification/value-model class, while the other asks for FP8 training support. No duplicate or same-change signal is present.", + "confidence": 0.98, + "canonical_issue_reason": "Issue 45810 is the more specific, concrete feature request; 46295 is a separate training-capability request.", + "canonical_pr_reason": null, + "best_issue_reason": "45810 is the best representative issue because it names a specific missing model class and use case, making it more actionable than the broader FP8 training request.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45810", + "right": "issue:46295", + "accept": false, + "reason": "Different requests in different areas: model-class support vs FP8 training support. They do not appear to 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": 18, + "component_count": 18, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-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": "f09cd8f24015a8968014e1026d60e3fc907f8605274600ed68c149415ab35cfb", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5723, + "estimated_input_tokens": 1431, + "estimated_eval_tokens": 3118 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 8, + "serialized_chars": 5723, + "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 contains three separate issue topics: a dataset sales/sample post, an 'Example: Financial time series prediction with DataForge' pair, and a 'DataForge: Financial time series + scraping service' pair. Only the exact-title duplicates within the latter two topic pairs look like true duplicates.", + "confidence": 0.96, + "canonical_issue_reason": "No single issue cleanly represents the whole cluster because it mixes unrelated topics. If forced to pick one anchor, issue 45870 is the best representative of the exact duplicate 'Example: Financial time series prediction with DataForge' pair because it is the earlier, more active copy.", + "canonical_pr_reason": null, + "best_issue_reason": "Issue 45870 is the best global issue anchor only in the narrow sense that it is one of the exact duplicates; however, the cluster overall is too heterogeneous for a strong single canonical issue.", + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "issue:45869", + "right": "issue:45870", + "accept": false, + "reason": "Different topics: dataset bundle/sample post versus an example walkthrough about financial time series prediction." + }, + { + "left": "issue:45869", + "right": "issue:45871", + "accept": false, + "reason": "Different topics: dataset bundle/sample post versus an example walkthrough about financial time series prediction." + }, + { + "left": "issue:45870", + "right": "issue:45871", + "accept": true, + "reason": "Exact same title and essentially the same issue content; these are duplicate reports of the same example request." + }, + { + "left": "issue:45870", + "right": "issue:45872", + "accept": false, + "reason": "Related financial domain, but one is an example prediction writeup and the other is a scraping-service integration request; not the same underlying issue." + }, + { + "left": "issue:45870", + "right": "issue:45873", + "accept": false, + "reason": "Related financial domain, but one is an example prediction writeup and the other is a scraping-service integration request; not the same underlying issue." + }, + { + "left": "issue:45871", + "right": "issue:45872", + "accept": false, + "reason": "Different concrete requests: example prediction walkthrough versus scraping-service integration." + }, + { + "left": "issue:45871", + "right": "issue:45873", + "accept": false, + "reason": "Different concrete requests: example prediction walkthrough versus scraping-service integration." + }, + { + "left": "issue:45872", + "right": "issue:45873", + "accept": true, + "reason": "Exact same title and likely the same body; these are duplicate reports of the scraping-service request." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "Summary is grounded in the packet, and the duplicate/ non-duplicate pair judgments are conservative. The two exact-title pairs (45870/45871 and 45872/45873) are supported by identical titles and body lengths, while the cross-topic pairs are reasonably rejected based on the titles. The cluster-level summary correctly notes the heterogeneous mix of topics." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 1, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-39895-15", + "nodes": [ + "pull_request:39895", + "pull_request:41855", + "pull_request:42668", + "pull_request:43251", + "pull_request:43254", + "pull_request:43424", + "pull_request:43823", + "pull_request:43995", + "pull_request:44827", + "pull_request:45170", + "pull_request:45213", + "pull_request:45655", + "pull_request:46048", + "pull_request:46267", + "pull_request:46268" + ], + "soft_pairs": [ + "pull_request:39895|pull_request:43424", + "pull_request:41855|pull_request:43424", + "pull_request:41855|pull_request:43823", + "pull_request:42668|pull_request:43823", + "pull_request:43251|pull_request:43823", + "pull_request:43251|pull_request:44827", + "pull_request:43424|pull_request:44827", + "pull_request:43424|pull_request:43823", + "pull_request:43823|pull_request:45655", + "pull_request:43823|pull_request:43995", + "pull_request:43995|pull_request:45213", + "pull_request:43995|pull_request:44827", + "pull_request:44827|pull_request:45170", + "pull_request:44827|pull_request:46267", + "pull_request:44827|pull_request:46048", + "pull_request:44827|pull_request:45655", + "pull_request:44827|pull_request:45213", + "pull_request:43823|pull_request:45213", + "pull_request:46048|pull_request:46268", + "pull_request:43251|pull_request:43254" + ], + "prepared_review_unit_hash": "597bbbe0dbb0e70ed4f90ee90f7070279d45bba491ba99ec3609ef55def200f1", + "component_budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 20, + "serialized_chars": 40304, + "estimated_input_tokens": 10076, + "estimated_eval_tokens": 20408 + }, + "budget": { + "node_count": 15, + "item_count": 15, + "soft_pair_count": 20, + "serialized_chars": 40304, + "estimated_input_tokens": 10076, + "estimated_eval_tokens": 20408 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "This cluster is mostly heterogeneous: unrelated model additions, tokenizer/API tweaks, export tests, docs, and kernel-routing changes. Only one soft edge looks like a true duplicate/subsumable change: the two fixed_cross_entropy kwargs patches (43251 and 43254).", + "confidence": 0.9, + "canonical_issue_reason": null, + "canonical_pr_reason": "No cluster-wide canonical PR: the items are mostly unrelated. The only near-duplicate pair is 43251/43254, and 43251 is the better representative because it is explicitly tied to issue #43240 and presents the more direct fix.", + "best_issue_reason": null, + "best_pr_reason": "43251 is the best PR to keep for the loss-kwargs bug because it directly targets the tracked issue and is the stronger representative of the 43251/43254 duplicate pair.", + "soft_edge_verdicts": [ + { + "left": "pull_request:39895", + "right": "pull_request:43424", + "accept": false, + "reason": "VideoPrism model onboarding is unrelated to an executorch dynamic-shape export test." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43424", + "accept": false, + "reason": "Mistral tokenizer method additions and executorch export testing address different code paths and bugs." + }, + { + "left": "pull_request:41855", + "right": "pull_request:43823", + "accept": false, + "reason": "Tokenizer API fixes are unrelated to adding the MobileLLM model." + }, + { + "left": "pull_request:42668", + "right": "pull_request:43823", + "accept": false, + "reason": "Processor/pretrained auto-loading robustness is unrelated to the MobileLLM model implementation." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43823", + "accept": false, + "reason": "A cross-entropy kwargs fix is unrelated to adding MobileLLM." + }, + { + "left": "pull_request:43251", + "right": "pull_request:44827", + "accept": false, + "reason": "Loss utility kwargs handling is unrelated to Mistral4 test fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:44827", + "accept": false, + "reason": "Executorch dynamic-shape export testing is unrelated to Mistral4 test fixes." + }, + { + "left": "pull_request:43424", + "right": "pull_request:43823", + "accept": false, + "reason": "Executorch export tests and MobileLLM model addition are different changes." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45655", + "accept": false, + "reason": "Adding MobileLLM is unrelated to the config-resolution ordering fix." + }, + { + "left": "pull_request:43823", + "right": "pull_request:43995", + "accept": false, + "reason": "MobileLLM model addition and Falcon output-interface refactoring do not fix the same problem." + }, + { + "left": "pull_request:43995", + "right": "pull_request:45213", + "accept": false, + "reason": "Falcon refactoring and the model-creation skill are unrelated changes." + }, + { + "left": "pull_request:43995", + "right": "pull_request:44827", + "accept": false, + "reason": "Falcon output-capturing refactor and Mistral4 test fixes are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45170", + "accept": false, + "reason": "Mistral4 test fixes are unrelated to the layrnorm-to-layernorm typo/renaming pass." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46267", + "accept": false, + "reason": "Mistral4 test fixes and serve chat parsing updates are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:46048", + "accept": false, + "reason": "Mistral4 test fixes are unrelated to adding the TDT loss kernel." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45655", + "accept": false, + "reason": "Mistral4 test fixes and config-resolution ordering changes are unrelated." + }, + { + "left": "pull_request:44827", + "right": "pull_request:45213", + "accept": false, + "reason": "Mistral4 test fixes are unrelated to the model-creation skill PR." + }, + { + "left": "pull_request:43823", + "right": "pull_request:45213", + "accept": false, + "reason": "MobileLLM model addition is unrelated to the model-creation skill." + }, + { + "left": "pull_request:46048", + "right": "pull_request:46268", + "accept": false, + "reason": "Both touch hub-kernel plumbing, but one adds TDT loss kernel support while the other adds ROCm AITER routing; they are different kernels and different fixes." + }, + { + "left": "pull_request:43251", + "right": "pull_request:43254", + "accept": true, + "reason": "Both PRs patch fixed_cross_entropy to forward supported nn.functional.cross_entropy kwargs for the same underlying issue #43240; one is a narrower variant of the same fix and could plausibly be merged into one PR." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet and stays conservative. The only true near-duplicate is 43251/43254, and the mergeability claim is supported by the shared file, shared issue target, and overlapping cross-entropy kwargs fix. The other soft-edge rejections are appropriately cautious and not overstated." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 2, + "component_count": 30, + "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": "e96dc70583d4c3bcf638e9beac0db2e47198196eca70291a44361bcd14486aaf", + "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 items are related VibeVoice model integrations, but they are not the same PR: one is the base VibeVoice implementation, the other adds VibeVoice Realtime and an acoustic tokenizer path. The overlap is expected from shared model scaffolding, not a duplicate change.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 40546 is the broader foundational VibeVoice implementation with substantial review activity; it looks like the main integration rather than the specialized realtime follow-up.", + "best_issue_reason": null, + "best_pr_reason": "PR 40546 is the best representative of the cluster because it is the primary VibeVoice model bring-up and covers the core code paths shared by later VibeVoice work.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40546", + "right": "pull_request:42781", + "accept": false, + "reason": "Shared filenames reflect common VibeVoice scaffolding, but 40546 implements the base model while 42781 adds Realtime/acoustic-tokenizer functionality; these are different concrete changes and should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 3, + "component_count": 30, + "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": "d12e8776c103ae2f6f70c96c4360f50cde16416ee4b8fd3620436ad6542762b0", + "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": "The two pull requests are unrelated model-feature additions: one adds covariate forecasting to TimesFM, the other adds image classification support for DINOv3ViT. They do not appear to fix the same bug or implement the same change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: these PRs target different models, different code paths, and different user-facing capabilities, so they are not duplicates of one another.", + "best_issue_reason": null, + "best_pr_reason": "Neither PR is a good global canonical representative for this cluster because the cluster is not a duplicate set; the changes are unrelated.", + "soft_edge_verdicts": [ + { + "left": "pull_request:40755", + "right": "pull_request:41224", + "accept": false, + "reason": "Different features in different model families (TimesFM covariates vs. DINOv3 image classification); no shared bug or mergeable single 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": 4, + "component_count": 30, + "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": 30, + "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": "c4d970101d2c9d8215176a3dd84f6829411405a359372a39bef79fc285918a36", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10435, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10435, + "estimated_input_tokens": 2609, + "estimated_eval_tokens": 5474 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are three separate model-addition PRs for different models (DeepSeek OCR, Isaac, and Kimi2-6). They share the same scaffolding pattern, but they do not fix the same code-path problem and should not be merged as duplicates.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": "No duplicate canonical PR exists here; if a representative were needed, Kimi2-6 is the most mature/active PR, but it is still unrelated to the other model additions.", + "soft_edge_verdicts": [ + { + "left": "pull_request:41797", + "right": "pull_request:45186", + "accept": false, + "reason": "Different model integrations (DeepSeek OCR vs Isaac) with different model files, tests, and implementation details; shared auto-registration/docs changes are just template overlap." + }, + { + "left": "pull_request:45186", + "right": "pull_request:45630", + "accept": false, + "reason": "Different model integrations (Isaac vs Kimi2-6). They touch the same infrastructure because all new models need registration, but they are not the same bug/change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 6, + "component_count": 30, + "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": "d1cd92a0c8e528983adfbd6d9246f8f0c7aa329e8232a9eefc2274cf7663c869", + "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 touch GitHub Actions workflow maintenance, but they address different upgrades: one updates many official actions for Node 24 compatibility, while the other specifically bumps docker/build-push-action from v5 to v6. They overlap in some workflow files, but the underlying change is not the same.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 42975 is the better canonical PR because it is the broader, more directly stated maintenance change: upgrading multiple GitHub Actions to Node 24-compatible versions across many workflows.", + "best_issue_reason": null, + "best_pr_reason": "PR 42975 is the best representative of the cluster since its title and diff align with the shared workflow-action upgrade theme and it spans the larger, primary compatibility update.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42975", + "right": "pull_request:42976", + "accept": false, + "reason": "Reject: these are different changes. 42975 updates several GitHub Actions versions for Node 24 compatibility, while 42976 specifically bumps docker/build-push-action versions in docker image workflows. Shared workflow filenames are not enough to treat them as the same underlying fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 7, + "component_count": 30, + "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": "4d937dd526e546603ee776f5b0606dd0349e55b5edde2cab03ee9a736739c6e3", + "component_budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14184, + "estimated_input_tokens": 3546, + "estimated_eval_tokens": 7348 + }, + "budget": { + "node_count": 4, + "item_count": 4, + "soft_pair_count": 6, + "serialized_chars": 14184, + "estimated_input_tokens": 3546, + "estimated_eval_tokens": 7348 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All four PRs are separate model-addition feature branches (ViT NEPA, Molmo, Molmo2, CTSM). They share generic Hugging Face boilerplate files like docs/toctree and auto registries, but they do not fix the same code-path problem or represent one mergeable duplicate change set.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the PRs target different models and different implementation paths, so there is no single duplicate representative.", + "best_issue_reason": null, + "best_pr_reason": "PR 43451 is the broadest/most complete feature addition, but it is still unrelated to the others; it is not a duplicate canonical choice.", + "soft_edge_verdicts": [ + { + "left": "pull_request:42978", + "right": "pull_request:43448", + "accept": false, + "reason": "Different model additions (ViT NEPA vs Molmo). Shared auto/docs files are generic scaffolding, not the same underlying change." + }, + { + "left": "pull_request:42978", + "right": "pull_request:43451", + "accept": false, + "reason": "Different model additions (ViT NEPA vs Molmo2). Similar repository touchpoints do not indicate the same bug or feature." + }, + { + "left": "pull_request:42978", + "right": "pull_request:45490", + "accept": false, + "reason": "Different model additions (ViT NEPA vs CTSM) with distinct modeling code; only boilerplate overlaps." + }, + { + "left": "pull_request:43448", + "right": "pull_request:43451", + "accept": false, + "reason": "Molmo and Molmo2 are related by naming but are distinct model implementations with separate configs, processors, and tests." + }, + { + "left": "pull_request:43448", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo and CTSM are unrelated model integrations; shared docs/auto registry edits are incidental." + }, + { + "left": "pull_request:43451", + "right": "pull_request:45490", + "accept": false, + "reason": "Molmo2 and CTSM are separate model additions touching different concrete code paths, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 8, + "component_count": 30, + "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": "cd838f89756a8732579eda3cbfd04b526b32b7f5cf46d5f1a2ce5fb1cac7c248", + "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": "No true duplicates here. The three PRs only share vague 'fix' language and some test-file overlap; their concrete code paths are unrelated (Whisper decoding, CLIP/ViT test placeholders, and FP8/Mistral dequantization).", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": "pull_request:44815 is the most substantive and self-contained fix, with real code-path changes across loading/FP8 quantization rather than test-only noise.", + "best_issue_reason": null, + "best_pr_reason": "pull_request:44815 is the best representative of the cluster because it contains the clearest functional bug fix and the broadest meaningful implementation changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43291", + "right": "pull_request:43665", + "accept": false, + "reason": "Both are test-related, but they target different models and different failure modes; 43291 is Whisper tokenizer decoding, while 43665 is placeholder assertions in CLIP/ViT tests." + }, + { + "left": "pull_request:43291", + "right": "pull_request:44815", + "accept": false, + "reason": "Different subsystems and different bugs: Whisper decoding/test cleanup versus FP8 dequantization and model-loading changes for Mistral4." + }, + { + "left": "pull_request:43665", + "right": "pull_request:44815", + "accept": false, + "reason": "Shared test-file presence is not enough; 43665 is clearly unrelated test noise, while 44815 fixes a concrete quantization/dequant 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": 9, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43488-5", + "nodes": [ + "pull_request:43488", + "pull_request:43532", + "pull_request:45932", + "pull_request:46100", + "pull_request:46114" + ], + "soft_pairs": [ + "pull_request:43488|pull_request:46114", + "pull_request:43488|pull_request:43532", + "pull_request:43532|pull_request:46114", + "pull_request:45932|pull_request:46100", + "pull_request:46100|pull_request:46114" + ], + "prepared_review_unit_hash": "78bf2c97e96a779794363b9a269d31bb13fa34311ab51f6c5c851bd8958b0344", + "component_budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 12262, + "estimated_input_tokens": 3066, + "estimated_eval_tokens": 6388 + }, + "budget": { + "node_count": 5, + "item_count": 5, + "soft_pair_count": 5, + "serialized_chars": 12262, + "estimated_input_tokens": 3066, + "estimated_eval_tokens": 6388 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are mostly unrelated dummy/test or CI changes. The only seemingly close pair (45932 and 46100) still targets different code paths and test areas, so this cluster does not form a true duplicate set.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: the items span unrelated placeholder workflow, model, and test edits rather than one shared change.", + "best_issue_reason": null, + "best_pr_reason": "No single PR is a good global representative because the cluster is not one duplicate change set; the edits are heterogeneous and mostly artificial.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43488", + "right": "pull_request:43532", + "accept": false, + "reason": "Both touch vit tests, but one is a repo-bot/version check PR and the other is CI/workflow plumbing plus model files; not the same underlying bug or fix." + }, + { + "left": "pull_request:43488", + "right": "pull_request:46114", + "accept": false, + "reason": "Shared vit test filename is too broad; 43488 is a format/check PR while 46114 is a migration/OTEL test PR with many unrelated edits." + }, + { + "left": "pull_request:43532", + "right": "pull_request:46114", + "accept": false, + "reason": "Both are workflow-heavy test PRs, but they target different automation changes and test edits, not one concrete code-path problem." + }, + { + "left": "pull_request:45932", + "right": "pull_request:46100", + "accept": false, + "reason": "Despite similar test-migration flavor, 45932 changes model/config/workflow code while 46100 only injects failing Vit test assertions; not mergeable as one fix." + }, + { + "left": "pull_request:46100", + "right": "pull_request:46114", + "accept": false, + "reason": "They share vit test files, but 46114 also changes CI, download, tensor-parallel, and hub/modeling utils; this is not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 10, + "component_count": 30, + "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": "3401f7c792da6c9be101261c88e8e486ab67cb708db66a359926012da5a6669a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6082, + "estimated_input_tokens": 1521, + "estimated_eval_tokens": 3298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are related in theme but not duplicates: one adds a Promptable Concept Segmentation pipeline, the other adds a Promptable Visual Segmentation pipeline. They share some docs/registry scaffolding, but they target different pipelines, model integrations, and test suites.", + "confidence": 0.96, + "canonical_issue_reason": null, + "canonical_pr_reason": null, + "best_issue_reason": null, + "best_pr_reason": null, + "soft_edge_verdicts": [ + { + "left": "pull_request:43612", + "right": "pull_request:43613", + "accept": false, + "reason": "Different concrete features and code paths: concept segmentation vs visual segmentation. Shared documentation and pipeline-registration changes are generic setup, not evidence of 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": "pull_request", + "component_index": 11, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43649-2", + "nodes": [ + "pull_request:43649", + "pull_request:46301" + ], + "soft_pairs": [ + "pull_request:43649|pull_request:46301" + ], + "prepared_review_unit_hash": "44ca84e5cd37c4b3128aabff85acc44b31031ed113e983abd2a46bb74a474baf", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4492, + "estimated_input_tokens": 1123, + "estimated_eval_tokens": 2502 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4492, + "estimated_input_tokens": 1123, + "estimated_eval_tokens": 2502 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These two open PRs are not duplicates: one is a workflow/test infrastructure change around new-failures reporting, while the other is a test/debugging change for tensor-parallel thread/process exit diagnostics. They touch different code paths and should not be merged together.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43649 is the better canonical PR because it has a concrete, descriptive title and a focused workflow/test infrastructure change, whereas #46301 is generic and appears to be a narrower debugging-oriented update.", + "best_issue_reason": null, + "best_pr_reason": "PR #43649 is the strongest representative of the cluster because it is more substantively described and more likely to be the intended change, while #46301 is too vague to serve as a good anchor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43649", + "right": "pull_request:46301", + "accept": false, + "reason": "Different problems and code paths: #43649 edits CI/workflow scripts and test reporting utilities, while #46301 adds tensor-parallel test diagnostics and process-exit handling. They are not plausibly one merged 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": 30, + "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": "1693a39d3589f776ccde23e52a47910e758be83eac8448d202d1fc099ed5d131", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4293, + "estimated_input_tokens": 1074, + "estimated_eval_tokens": 2404 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are two distinct trainer extensibility PRs in the same file, but they address different code paths: gradient-accumulation loss scaling vs. signature-column filtering. Similar pattern, not a duplicate change.", + "confidence": 0.95, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR for a duplicate cluster: PR 43651 changes loss scaling in training_step, while PR 43663 changes column filtering/signature inspection.", + "best_issue_reason": null, + "best_pr_reason": "No best PR as a duplicate representative; the PRs solve different problems and should be triaged separately.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43651", + "right": "pull_request:43663", + "accept": false, + "reason": "Different underlying trainer behaviors: one controls gradient accumulation loss normalization, the other controls input column filtering for custom/PEFT trainers. Shared file and similar refactor pattern are not enough to treat them as the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 13, + "component_count": 30, + "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": "17d3ea9804249ac40065f63b84bef3f8103ac7232f331fa57ab611abc1f69503", + "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": "The two PRs touch the same file and both relate to annotation/type-related `NameError` risk, but they do not appear to fix the same concrete bug or code path. PR #43656 is a broader `from __future__ import annotations` cleanup with multiple type-hint adjustments, while PR #43842 specifically fixes the `TypeAdapter` import/annotation issue in `_validate_request`.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43842 is the more direct and narrowly scoped fix for the reported `TypeAdapter` NameError in `src/transformers/cli/serve.py`, matching the explicit target without the broader annotation cleanup in PR #43656.", + "best_issue_reason": null, + "best_pr_reason": "PR #43842 best fits the concrete runtime failure because it addresses the specific `TypeAdapter` annotation/import problem in the affected function, rather than making a broader module-wide typing change.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43656", + "right": "pull_request:43842", + "accept": false, + "reason": "Related by file and general annotation safety, but not the same underlying bugfix. #43656 is a broad deferred-annotations/type-hint cleanup, whereas #43842 targets a specific `TypeAdapter` NameError in a different code path, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": { + "accept": false, + "feedback": "The packet supports that both PRs touch `src/transformers/cli/serve.py` and address annotation-related runtime `NameError` risk, but the summary overstates the relationship. PR #43656 adds `from __future__ import annotations` and cleans up several unrelated type hints; PR #43842 specifically handles `TypeAdapter` in a different function. That is related, but not clearly the same bugfix or the same affected code path. The soft-edge accept is too strong given the evidence, so this should be rejected as an overreach." + }, + "evaluator_used": true, + "retried": true, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 14, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "cache", + "cache_hit": true, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43779-2", + "nodes": [ + "pull_request:43779", + "pull_request:43816" + ], + "soft_pairs": [ + "pull_request:43779|pull_request:43816" + ], + "prepared_review_unit_hash": "e7c674adcc031aa8883109a5dfc678b4407fb20b10764302092e384d031ba83a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4362, + "estimated_input_tokens": 1091, + "estimated_eval_tokens": 2438 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both pull requests appear to implement the same SwanLab integration change: adding run id/resume support in `integration_utils.py` for issue #43698, with one variant also expanding the docs. They are strong duplicate PR candidates.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #43816 is the cleaner representative: it carries the same SwanLab id/resume support plus the accompanying documentation updates, making it the more complete version of the shared change.", + "best_issue_reason": null, + "best_pr_reason": "PR #43816 is the best global representative because it appears to include the full feature change and docs for SwanLab run id/resume support, while #43779 is the narrower implementation-focused variant.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43779", + "right": "pull_request:43816", + "accept": true, + "reason": "Same underlying SwanLab callback enhancement for id/resume support in the same file and same issue target; the doc differences do not change the core code-path change, so these are duplicate PRs." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: both PRs target issue #43698, touch the same file, and the previews indicate the same SwanLab id/resume support with #43816 adding docs. The duplicate/mergeable verdict is conservative enough given the shared target and overlapping code change." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43996", + "pull_request:43997", + "pull_request:44007", + "pull_request:44010", + "pull_request:44013", + "pull_request:44017", + "pull_request:44018", + "pull_request:44019", + "pull_request:44044", + "pull_request:44056", + "pull_request:44059", + "pull_request:44066", + "pull_request:44068", + "pull_request:44071", + "pull_request:44072", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44085", + "pull_request:44086", + "pull_request:44098", + "pull_request:44101", + "pull_request:44116", + "pull_request:44129", + "pull_request:44154", + "pull_request:44161", + "pull_request:44722" + ], + "soft_pairs": [ + "pull_request:43996|pull_request:44085", + "pull_request:43996|pull_request:44044", + "pull_request:44066|pull_request:44085", + "pull_request:44007|pull_request:44072", + "pull_request:44072|pull_request:44722", + "pull_request:44066|pull_request:44072", + "pull_request:44013|pull_request:44044", + "pull_request:44066|pull_request:44086", + "pull_request:44066|pull_request:44071", + "pull_request:44018|pull_request:44068", + "pull_request:44018|pull_request:44066", + "pull_request:44066|pull_request:44068", + "pull_request:44019|pull_request:44722", + "pull_request:44086|pull_request:44722", + "pull_request:44019|pull_request:44085", + "pull_request:44018|pull_request:44019", + "pull_request:44019|pull_request:44071", + "pull_request:44068|pull_request:44116", + "pull_request:44018|pull_request:44116", + "pull_request:44068|pull_request:44722", + "pull_request:44071|pull_request:44722", + "pull_request:44018|pull_request:44085", + "pull_request:44018|pull_request:44086", + "pull_request:44068|pull_request:44086", + "pull_request:44071|pull_request:44085", + "pull_request:44059|pull_request:44086", + "pull_request:44085|pull_request:44086", + "pull_request:44098|pull_request:44101", + "pull_request:44059|pull_request:44722", + "pull_request:44018|pull_request:44071", + "pull_request:44017|pull_request:44722", + "pull_request:44017|pull_request:44161", + "pull_request:44017|pull_request:44073", + "pull_request:44068|pull_request:44071", + "pull_request:43997|pull_request:44073", + "pull_request:44071|pull_request:44086", + "pull_request:44017|pull_request:44071", + "pull_request:44073|pull_request:44101", + "pull_request:44059|pull_request:44071", + "pull_request:44018|pull_request:44059", + "pull_request:44073|pull_request:44161", + "pull_request:44056|pull_request:44101", + "pull_request:44059|pull_request:44068", + "pull_request:44101|pull_request:44161", + "pull_request:44017|pull_request:44018", + "pull_request:43997|pull_request:44056", + "pull_request:44071|pull_request:44076", + "pull_request:44074|pull_request:44101", + "pull_request:43997|pull_request:44018", + "pull_request:44056|pull_request:44161", + "pull_request:43997|pull_request:44161", + "pull_request:44074|pull_request:44161", + "pull_request:44018|pull_request:44161", + "pull_request:43997|pull_request:44071", + "pull_request:44010|pull_request:44071", + "pull_request:44018|pull_request:44129", + "pull_request:44010|pull_request:44073", + "pull_request:43997|pull_request:44074", + "pull_request:44071|pull_request:44129", + "pull_request:44010|pull_request:44018", + "pull_request:43997|pull_request:44129", + "pull_request:43996|pull_request:44161", + "pull_request:43996|pull_request:44017", + "pull_request:44010|pull_request:44044", + "pull_request:44044|pull_request:44074", + "pull_request:44066|pull_request:44722", + "pull_request:44085|pull_request:44722", + "pull_request:44085|pull_request:44129", + "pull_request:43996|pull_request:44007", + "pull_request:43996|pull_request:44129", + "pull_request:44044|pull_request:44129", + "pull_request:44044|pull_request:44154" + ], + "prepared_review_unit_hash": "0230e55b264c40d59ffc9140f036c1905ad0b40f56c3249c6612375bee23bb1f", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84897, + "estimated_input_tokens": 21225, + "estimated_eval_tokens": 42706 + }, + "budget": { + "node_count": 27, + "item_count": 27, + "soft_pair_count": 72, + "serialized_chars": 75094, + "estimated_input_tokens": 18774, + "estimated_eval_tokens": 37804 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "This cluster is mostly a wave of model-specific refactors to standardized output tracing around issue #43979, not true duplicates across different architectures. The only clear duplicate-like overlaps are within the GPT-Neo and GPT-J refactor series.", + "confidence": 0.84, + "canonical_issue_reason": "Issue #43979 is the shared tracking issue repeatedly referenced by the refactor PRs and captures the common output-tracing migration.", + "canonical_pr_reason": "PR #44722 is the strongest representative of the GPT-J/CodeGen subset: explicit issue-linked, broadest same-code-path coverage, and it subsumes the smaller GPT-J-only variants.", + "best_issue_reason": "#43979 is the best issue anchor because it unifies the common standardized output tracing change across the model-specific PRs.", + "best_pr_reason": "PR #44722 is the best single PR representative because it is the most complete GPT-J/CodeGen implementation of the shared tracing refactor.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43996", + "right": "pull_request:44085", + "accept": false, + "reason": "Different model families; same broad refactor theme but not the same concrete code path." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44044", + "accept": false, + "reason": "Different architectures and files; only share the issue theme, not a duplicate change." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44085", + "accept": true, + "reason": "Both target GPT-J output-tracing refactoring in the same file; these are close enough to merge into one PR." + }, + { + "left": "pull_request:44007", + "right": "pull_request:44072", + "accept": false, + "reason": "RegNet/ResNet vs EfficientNet are separate model implementations, so this is not the same change." + }, + { + "left": "pull_request:44072", + "right": "pull_request:44722", + "accept": false, + "reason": "EfficientNet and GPT-J/CodeGen are unrelated code paths despite similar decorator migration." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44072", + "accept": false, + "reason": "Different model code paths; same output-tracing framework, not the same bug or change." + }, + { + "left": "pull_request:44013", + "right": "pull_request:44044", + "accept": false, + "reason": "MobileNetV2 and DeBERTa V2 are unrelated implementations." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J/CodeGen vs MGP-STR; same pattern, different model-specific code." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-J/CodeGen and MPT are separate refactors in different code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44068", + "accept": true, + "reason": "Both are GPT-Neo output-tracing refactors on the same model and file; they look like overlapping implementations of the same change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44066", + "accept": false, + "reason": "GPT-Neo vs GPT-J/CodeGen are different model families and code paths." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44068", + "accept": false, + "reason": "GPT-J/CodeGen and GPT-Neo are different underlying implementations." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44722", + "accept": false, + "reason": "ResNet and GPT-J/CodeGen are unrelated code paths." + }, + { + "left": "pull_request:44086", + "right": "pull_request:44722", + "accept": false, + "reason": "MGP-STR and GPT-J/CodeGen are separate model-specific refactors." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are different model implementations." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44019", + "accept": false, + "reason": "GPT-Neo and ResNet are unrelated code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44071", + "accept": false, + "reason": "ResNet and MPT are unrelated model refactors." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo vs Flaubert; different models and code paths." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44116", + "accept": false, + "reason": "GPT-Neo and Flaubert are unrelated model changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-Neo and GPT-J/CodeGen are different model families." + }, + { + "left": "pull_request:44071", + "right": "pull_request:44722", + "accept": false, + "reason": "MPT and GPT-J/CodeGen are separate model-specific changes." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44085", + "accept": false, + "reason": "GPT-Neo and GPT-J are not the same concrete code-path change." + }, + { + "left": "pull_request:44018", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are unrelated model implementations." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-Neo and MGP-STR are different code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-2 and MGP-STR share only the high-level tracing theme." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44086", + "accept": false, + "reason": "GPT-J and MGP-STR are unrelated model refactors." + }, + { + "left": "pull_request:44098", + "right": "pull_request:44101", + "accept": false, + "reason": "ViLT and Flaubert/XLM are different model code paths." + }, + { + "left": "pull_request:44059", + "right": "pull_request:44722", + "accept": false, + "reason": "GPT-2 and GPT-J/CodeGen are separate implementations." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44722", + "accept": false, + "reason": "SegFormer and GPT-J/CodeGen are unrelated models." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44161", + "accept": false, + "reason": "SegFormer and LongT5 are different code paths." + }, + { + "left": "pull_request:44017", + "right": "pull_request:44073", + "accept": false, + "reason": "SegFormer and VisualBert are separate model changes." + }, + { + "left": "pull_request:44068", + "right": "pull_request:44071", + "accept": false, + "reason": "GPT-Neo and MPT are different model implementations." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44073", + "accept": false, + "reason": "RegNet and VisualBert are unrelated." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44161", + "accept": false, + "reason": "MPNet and LongT5 are separate model code paths." + }, + { + "left": "pull_request:44019", + "right": "pull_request:44085", + "accept": false, + "reason": "ResNet and GPT-J are unrelated implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa V2 and SpeechT5 are different model code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa V2 and ViTS are unrelated changes." + }, + { + "left": "pull_request:44066", + "right": "pull_request:44722", + "accept": true, + "reason": "Same GPT-J output-tracing refactor; 44722 is a broader version of the same change and could absorb 44066." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44722", + "accept": true, + "reason": "Both are GPT-J tracing refactors on the same file; one is a narrower subset of the other." + }, + { + "left": "pull_request:44085", + "right": "pull_request:44129", + "accept": false, + "reason": "GPT-J and SpeechT5 are unrelated model changes." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44007", + "accept": false, + "reason": "CVT/FNet and RegNet/ResNet are different model families." + }, + { + "left": "pull_request:43996", + "right": "pull_request:44129", + "accept": false, + "reason": "CVT/FNet and SpeechT5 are separate code paths." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44129", + "accept": false, + "reason": "DeBERTa V2 and SpeechT5 are unrelated implementations." + }, + { + "left": "pull_request:44044", + "right": "pull_request:44154", + "accept": false, + "reason": "DeBERTa V2 and ViTS are different model-specific changes." + } + ] + }, + "evaluator_result": { + "accept": true, + "feedback": "The summary is grounded in the packet: #43979 is the shared issue anchor, and #44722 is a reasonable representative of the GPT-J/CodeGen subset. The accepted soft-edge pairs are conservative because they stay within the same model family and concrete file path, while the rejected pairs correctly avoid cross-architecture merges. I don\u2019t see evidence of overstated duplication." + }, + "evaluator_used": true, + "retried": false, + "accepted_nontrivial_soft_edge": true, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 15, + "component_count": 30, + "review_unit_index": 2, + "review_unit_count": 2, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43996-28", + "nodes": [ + "pull_request:43997", + "pull_request:44010", + "pull_request:44024", + "pull_request:44056", + "pull_request:44073", + "pull_request:44074", + "pull_request:44076", + "pull_request:44129" + ], + "soft_pairs": [ + "pull_request:44024|pull_request:44076", + "pull_request:44073|pull_request:44074", + "pull_request:44056|pull_request:44073", + "pull_request:44056|pull_request:44074", + "pull_request:43997|pull_request:44010", + "pull_request:44010|pull_request:44129" + ], + "prepared_review_unit_hash": "ff9895bccaac4a2a27dc1ca0e84108f6aa887f4fab9e4b840c08120915c89bc6", + "component_budget": { + "node_count": 28, + "item_count": 28, + "soft_pair_count": 78, + "serialized_chars": 84897, + "estimated_input_tokens": 21225, + "estimated_eval_tokens": 42706 + }, + "budget": { + "node_count": 8, + "item_count": 8, + "soft_pair_count": 6, + "serialized_chars": 17124, + "estimated_input_tokens": 4281, + "estimated_eval_tokens": 8818 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": true, + "analyst_result": { + "summary": "All items are model-specific refactors to standardized output tracing/capture APIs, but they target different architectures and code paths, so they do not look like duplicates of the same change.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single PR spans the whole cluster; this one is a clear, representative standardized-output refactor with an explicit capture_outputs/can_return_tuple migration in a single model family.", + "best_issue_reason": null, + "best_pr_reason": "PR 44073 is the clearest representative of the cluster theme: its title and diff directly describe the standardized output tracing refactor, and it is self-contained and readable as the cluster exemplar.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44024", + "right": "pull_request:44076", + "accept": false, + "reason": "Both are standardized-output refactors, but for different models (FocalNet vs ImageGPT) with different internals; they are related in pattern, not the same underlying bug/change." + }, + { + "left": "pull_request:44073", + "right": "pull_request:44074", + "accept": false, + "reason": "VisualBert and TextNet are separate model implementations; these are parallel refactors to output tracing, not one concrete shared fix." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44073", + "accept": false, + "reason": "MPNet vs VisualBert touches different forward/output plumbing in different architectures, so they should not be merged as duplicates." + }, + { + "left": "pull_request:44056", + "right": "pull_request:44074", + "accept": false, + "reason": "These are distinct model-specific refactors in different code paths; similarity is only at the abstraction level of output capture." + }, + { + "left": "pull_request:43997", + "right": "pull_request:44010", + "accept": false, + "reason": "RegNet and SqueezeBert are unrelated model implementations; the PRs share a migration pattern but not the same bug or change." + }, + { + "left": "pull_request:44010", + "right": "pull_request:44129", + "accept": false, + "reason": "SqueezeBert and SpeechT5 address different model-specific output handling changes, so they are 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": 16, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-43998-13", + "nodes": [ + "pull_request:43998", + "pull_request:43999", + "pull_request:44000", + "pull_request:44001", + "pull_request:44002", + "pull_request:44003", + "pull_request:44004", + "pull_request:44025", + "pull_request:44026", + "pull_request:44027", + "pull_request:44028", + "pull_request:44029", + "pull_request:44030" + ], + "soft_pairs": [ + "pull_request:43998|pull_request:44002", + "pull_request:43998|pull_request:44000", + "pull_request:43998|pull_request:44001", + "pull_request:43998|pull_request:44003", + "pull_request:43998|pull_request:44029", + "pull_request:43999|pull_request:44001", + "pull_request:43999|pull_request:44002", + "pull_request:43999|pull_request:44025", + "pull_request:43999|pull_request:44026", + "pull_request:43999|pull_request:44027", + "pull_request:44000|pull_request:44001", + "pull_request:44000|pull_request:44002", + "pull_request:44000|pull_request:44003", + "pull_request:44000|pull_request:44025", + "pull_request:44001|pull_request:44002", + "pull_request:44001|pull_request:44003", + "pull_request:44001|pull_request:44025", + "pull_request:44002|pull_request:44029", + "pull_request:44002|pull_request:44003", + "pull_request:44003|pull_request:44004", + "pull_request:43998|pull_request:44004", + "pull_request:44001|pull_request:44004", + "pull_request:44002|pull_request:44004", + "pull_request:44000|pull_request:44004", + "pull_request:44025|pull_request:44026", + "pull_request:44025|pull_request:44027", + "pull_request:44025|pull_request:44028", + "pull_request:44025|pull_request:44029", + "pull_request:44025|pull_request:44030", + "pull_request:44026|pull_request:44029", + "pull_request:44026|pull_request:44027", + "pull_request:44026|pull_request:44028", + "pull_request:44026|pull_request:44030", + "pull_request:44027|pull_request:44028", + "pull_request:44027|pull_request:44029", + "pull_request:44027|pull_request:44030", + "pull_request:44028|pull_request:44029", + "pull_request:44028|pull_request:44030", + "pull_request:44029|pull_request:44030" + ], + "prepared_review_unit_hash": "71d50e1d275f0aef8ae214efe6ebcb1dff9a1c825aea96da70d332bed8b2b029", + "component_budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 + }, + "budget": { + "node_count": 13, + "item_count": 13, + "soft_pair_count": 39, + "serialized_chars": 39780, + "estimated_input_tokens": 9945, + "estimated_eval_tokens": 20146 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "A set of model-specific output-tracing refactors in different Transformers architectures; they share a theme but not the same underlying code-path change, so they should not be deduplicated together.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 44025 is the broadest representative of the cluster (depth_anything plus prompt_depth_anything), but the PRs are still separate model-specific refactors rather than duplicates.", + "best_issue_reason": null, + "best_pr_reason": "PR 44025 is the closest exemplar of the shared theme because it spans a core model and its prompt variant, yet it is still not a mergeable duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:43998", + "right": "pull_request:44002", + "accept": false, + "reason": "Different model families (timm_backbone vs upernet); same refactor theme only, not the same code-path bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44000", + "accept": false, + "reason": "Different architectures (timm_backbone vs vision_text_dual_encoder); no shared concrete fix beyond output-tracing cleanup." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44001", + "accept": false, + "reason": "Different models (timm_backbone vs univnet); these are separate per-model refactors." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44003", + "accept": false, + "reason": "Different subsystems and code paths (timm_backbone vs mamba/falcon_mamba); not the same bug/change." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44029", + "accept": false, + "reason": "Different models (timm_backbone vs rwkv); shared wording only, not a duplicate fix." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44001", + "accept": false, + "reason": "MobileNetV1 and UnivNet are unrelated implementations; same tracing refactor pattern, but not the same change." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44002", + "accept": false, + "reason": "MobileNetV1 vs UperNet are different model code paths; no single underlying bug." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families (MobileNetV1 vs DepthAnything); not mergeable as one PR." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44026", + "accept": false, + "reason": "Different architectures (MobileNetV1 vs VisionEncoderDecoder); only generic output-tracing similarity." + }, + { + "left": "pull_request:43999", + "right": "pull_request:44027", + "accept": false, + "reason": "Different model code paths (MobileNetV1 vs SpeechEncoderDecoder); not the same concrete fix." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44001", + "accept": false, + "reason": "VisionTextDualEncoder and UnivNet are unrelated; they just share the refactor motif." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44002", + "accept": false, + "reason": "Different models and runtime paths (vision-text dual encoder vs upernet); not duplicates." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44003", + "accept": false, + "reason": "VisionTextDualEncoder vs Mamba/FalconMamba are different code bases and problems." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44025", + "accept": false, + "reason": "Different model families (vision-text dual encoder vs depth-anything); no shared concrete bug." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44002", + "accept": false, + "reason": "UnivNet and UperNet are distinct model implementations; same cleanup pattern only." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44003", + "accept": false, + "reason": "UnivNet vs Mamba/FalconMamba are different code paths; not a duplicate pair." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44025", + "accept": false, + "reason": "UnivNet and DepthAnything are unrelated models; no common underlying change." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen differ completely; the PRs are not mergeable into one fix." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44029", + "accept": false, + "reason": "UperNet and RWKV are unrelated architectures; only the same output-tracing theme overlaps." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44003", + "accept": false, + "reason": "UperNet vs Mamba/FalconMamba are different model code paths; not the same bug/change." + }, + { + "left": "pull_request:44003", + "right": "pull_request:44004", + "accept": false, + "reason": "Mamba/FalconMamba and CodeGen are different models with different implementation details; no shared concrete fix." + }, + { + "left": "pull_request:43998", + "right": "pull_request:44004", + "accept": false, + "reason": "TimmBackbone and CodeGen are unrelated; only the refactor theme matches." + }, + { + "left": "pull_request:44001", + "right": "pull_request:44004", + "accept": false, + "reason": "UnivNet and CodeGen are different subsystems; not a duplicate PR." + }, + { + "left": "pull_request:44002", + "right": "pull_request:44004", + "accept": false, + "reason": "UperNet and CodeGen are separate model implementations; same theme, different change." + }, + { + "left": "pull_request:44000", + "right": "pull_request:44004", + "accept": false, + "reason": "VisionTextDualEncoder and CodeGen are unrelated code paths; no same underlying bug." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44026", + "accept": false, + "reason": "DepthAnything and VisionEncoderDecoder are different model families; the output-tracing refactor is separate in each." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44027", + "accept": false, + "reason": "DepthAnything vs SpeechEncoderDecoder are unrelated models; not the same concrete change." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44028", + "accept": false, + "reason": "DepthAnything and SuperPoint are different model paths; no mergeable duplicate." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44029", + "accept": false, + "reason": "DepthAnything vs RWKV are different model implementations; same refactor motif only." + }, + { + "left": "pull_request:44025", + "right": "pull_request:44030", + "accept": false, + "reason": "DepthAnything and DPR are distinct code paths; not the same bug/change." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44027", + "accept": false, + "reason": "VisionEncoderDecoder and SpeechEncoderDecoder are sibling wrappers but still separate code paths; not the same concrete fix." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44028", + "accept": false, + "reason": "VisionEncoderDecoder vs SuperPoint are unrelated models; only generic tracing refactor similarity." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44029", + "accept": false, + "reason": "VisionEncoderDecoder and RWKV are different architectures; not duplicates." + }, + { + "left": "pull_request:44026", + "right": "pull_request:44030", + "accept": false, + "reason": "VisionEncoderDecoder and DPR are different model paths; no shared underlying bug." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44028", + "accept": false, + "reason": "SpeechEncoderDecoder and SuperPoint are unrelated model implementations; not the same change." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44029", + "accept": false, + "reason": "SpeechEncoderDecoder and RWKV are separate code paths; same cleanup theme only." + }, + { + "left": "pull_request:44027", + "right": "pull_request:44030", + "accept": false, + "reason": "SpeechEncoderDecoder vs DPR are different model families; not mergeable as one fix." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44029", + "accept": false, + "reason": "SuperPoint and RWKV are unrelated models; no same concrete bug or change." + }, + { + "left": "pull_request:44028", + "right": "pull_request:44030", + "accept": false, + "reason": "SuperPoint and DPR are different implementations; only the refactor motif overlaps." + }, + { + "left": "pull_request:44029", + "right": "pull_request:44030", + "accept": false, + "reason": "RWKV and DPR are distinct model code paths; not a duplicate pair." + } + ] + }, + "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": 30, + "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": "4f176dfcee5d238fae6cd2309ba621c0a55075e74a9bd9f02f67cbd30bc8b6f0", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Three separate model-addition PRs for different architectures (PenguinVL, DeepSeek-OCR-2, Voxtral TTS); they overlap on scaffolding files but do not look like the same change.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "No canonical PR: each PR adds a different model family and different implementation/code paths, so they are not duplicates.", + "best_issue_reason": null, + "best_pr_reason": "PR #45401 is the most self-contained/referenced (it targets an explicit issue), but it is still just a Voxtral TTS model addition and not a duplicate of the others.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44662", + "right": "pull_request:45401", + "accept": false, + "reason": "PenguinVL vs Voxtral TTS are different model families with different tasks/code paths; shared auto-registration and docs scaffolding are not enough to treat them as the same change." + }, + { + "left": "pull_request:44662", + "right": "pull_request:45075", + "accept": false, + "reason": "PenguinVL and DeepSeek-OCR-2 are unrelated model implementations; overlapping repo setup files do not indicate the same underlying bug or feature." + }, + { + "left": "pull_request:45075", + "right": "pull_request:45401", + "accept": false, + "reason": "DeepSeek-OCR-2 (OCR/vision-language) and Voxtral TTS (speech generation) fix/add different concrete capabilities, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 18, + "component_count": 30, + "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": "bbb10481086ac862e35ef5db23838a2f7458671687e6fe339f98a3b74f4d457a", + "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 related by the general theme of module/kernel fusion, but they are not duplicates: one introduces a generic module fusion API, while the other implements a specific n-to-1 kernel-fusion path via `KernelConfig` and integration changes.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: #44979 is generic module-fusion infrastructure, while #45363 is a concrete `KernelConfig`-driven kernel-fusion implementation with different scope and code paths.", + "best_issue_reason": null, + "best_pr_reason": "#45363 is the more concrete and directly user-facing feature implementation; it targets specific integration points (`modeling_utils`, `integrations`, `kernel_config`) rather than just API scaffolding.", + "soft_edge_verdicts": [ + { + "left": "pull_request:44979", + "right": "pull_request:45363", + "accept": false, + "reason": "Related fusion work, but not the same underlying change: #44979 adds a generic module-fusion API, while #45363 implements a specific kernel-fusion mechanism and example. They 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": 19, + "component_count": 30, + "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": "a40971f848bea24dcd1d5999eb9317972bd75b0daaf3b92d7c47bdb18fce6e7a", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4414, + "estimated_input_tokens": 1104, + "estimated_eval_tokens": 2464 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same concrete bug in `_patch_mistral_regex`: an `AttributeError` from accessing `tokenizer.backend_tokenizer.pre_tokenizer` instead of `tokenizer.pre_tokenizer`. They touch the same code path and target the same issue; the second PR is the more complete fix because it adds tests.", + "confidence": 0.98, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45317 is the better canonical PR because it implements the same fix as 45086 but also includes test coverage, making it the more complete change set for the same bug.", + "best_issue_reason": null, + "best_pr_reason": "PR 45317 is the best representative because it fixes the same underlying AttributeError and adds validation tests, while remaining focused on the same code path.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45086", + "right": "pull_request:45317", + "accept": true, + "reason": "Same underlying bug and same fix in the same function; 45317 is a superset with tests, so these are duplicate PRs for triage purposes." + } + ] + }, + "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": 30, + "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": "916ae0b5f1abc23e16258a4afd9df30fbe086597b8edf555446e4f5301bb36b5", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 6065, + "estimated_input_tokens": 1517, + "estimated_eval_tokens": 3290 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs overlap on NemotronH internals, but they are not the same change: #45115 is a targeted inheritance/refactor for NemotronH conversion and model wiring, while #45569 is a broader architectural split that introduces dedicated NemotronHDense/NemotronHSparse docs, configs, modeling, and tests. The shared files reflect the common base model area, not a duplicate fix.", + "confidence": 0.91, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45569 is the more complete and representative PR in this cluster because it encompasses the larger NemotronH family restructuring and the new dense/sparse model split, whereas #45115 is a narrower prerequisite-style refactor.", + "best_issue_reason": null, + "best_pr_reason": "#45569 is the best PR to represent the cluster overall because it carries the main user-facing architectural change; #45115 is a smaller internal refactor and does not appear to fix the same concrete code-path problem.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45115", + "right": "pull_request:45569", + "accept": false, + "reason": "Shared NemotronH files are not enough here: #45115 only adjusts conversion mapping and inheritance/refactoring, while #45569 introduces separate NemotronHDense/NemotronHSparse implementations, docs, and tests. They are related but not the same underlying change and would not plausibly merge as one duplicate PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 21, + "component_count": 30, + "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": "6f62d14a7f04022feb8d9910f64e5d515a5b2fb217bcd7537b73768d90cbbab5", + "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 PRs are closely related, but they are not the same change: one adds heterogeneous config support, while the other adds broader heterogeneous model/runtime support on top of that. The overlap in configuration files/tests reflects dependency, not duplicate scope.", + "confidence": 0.88, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #45332 is the broader superset: it includes heterogeneous per-layer config handling plus modeling/cache changes, so it better represents the main combined feature work.", + "best_issue_reason": null, + "best_pr_reason": "PR #45332 is the best standalone representative because it covers the larger end-to-end heterogeneous support effort rather than only the config layer.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45332", + "right": "pull_request:45333", + "accept": false, + "reason": "Related but distinct scope: #45333 is config-only, while #45332 adds broader modeling/cache support and cannot be merged as the same concrete 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": 22, + "component_count": 30, + "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": "511e3f8c507e7ec32c9f340a13916df3b43bc1e0e81fde56e8c2a0279d05709e", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5514, + "estimated_input_tokens": 1379, + "estimated_eval_tokens": 3014 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These are both typing-related PRs, but they address different changes: #45415 is a broad type-checking sweep across many files plus pyproject typing-ignore config, while #45425 adds specific typing protocols and model-integration helpers in a narrower area. They are similar in theme, not the same underlying change.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "#45425 is the more focused, concrete typing change; #45415 is a broad repo-wide type-checking cleanup with different scope and intent.", + "best_issue_reason": null, + "best_pr_reason": "#45425 is the better representative of a single code-change topic because it introduces specific typing abstractions and targeted integrations, whereas #45415 is a sweeping lint/type cleanup across many files.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45415", + "right": "pull_request:45425", + "accept": false, + "reason": "Shared typing theme only. #45415 is a broad type-checking/config sweep across many modules; #45425 adds specific protocols and model-related typing support. They are not the same concrete fix and would not merge cleanly as one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 23, + "component_count": 30, + "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": "5bcf75ac29f6f8c917aa310484afae783d9d502c4ca19b6223e5f247f92a143d", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4859, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4859, + "estimated_input_tokens": 1215, + "estimated_eval_tokens": 2686 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two open PRs with a similar cache-aware decoding theme, but they fix different model families and different code paths: Qwen3.5/Qwen3-next/Olmo hybrid vs. Mamba2. They are not duplicates.", + "confidence": 0.97, + "canonical_issue_reason": null, + "canonical_pr_reason": "No single canonical PR: these changes target different bugs in different model implementations rather than one shared fix.", + "best_issue_reason": null, + "best_pr_reason": "PR 46084 is the cleaner representative of its bug class: it has an explicit issue target (#46032) and a narrowly scoped fix/test for Mamba2 cache handling with seq_len > 1.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45513", + "right": "pull_request:46084", + "accept": false, + "reason": "Both involve cached forward logic, but they act on different architectures and different concrete paths; this is a theme match, not the same underlying change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 24, + "component_count": 30, + "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": "c6a0c4f60ad0a9a7d9d66f03287bb9cb114a0937cc6695b7c2d98d3b8eb95227", + "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": "These two PRs share an expert-parallelism theme, but they fix different loading bugs in different distributed paths: DeepSpeed ZeRO-3/accelerate launch vs FSDP2 rank-0 broadcast overwriting experts.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45662 is the better representative of the cluster because it targets a concrete, multi-file loading bug in the expert-parallel/FSDP2 path with direct code-path fixes.", + "best_issue_reason": null, + "best_pr_reason": "PR 45662 is the stronger standalone PR: it addresses a specific failure mode, changes the relevant loader/integration code, and has the broader technical scope.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45548", + "right": "pull_request:45662", + "accept": false, + "reason": "Both concern EP loading, but they fix different underlying problems and code paths. 45548 adds distributed_config serialization and a has_ep property for DeepSpeed ZeRO-3/accelerate launch; 45662 prevents expert parameters from being overwritten after FSDP2 sharding. They are related but not the same change." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 25, + "component_count": 30, + "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": "54a222fd9d42d89a0b3adfffb13c6197699d0a7326e7671ec31f9bc19c0ad063", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4590, + "estimated_input_tokens": 1148, + "estimated_eval_tokens": 2552 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs address the same xdist/captured_info collision in testing debug artifacts; PR 45645 is the broader, more complete fix, while 45639 is a narrower subset.", + "confidence": 0.89, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 45645 is the better canonical PR because it contains the core xdist-safe captured_info fix plus the CI/workflow adjustments needed to consume the new per-worker artifact layout.", + "best_issue_reason": null, + "best_pr_reason": "PR 45645 is the best overall PR here since it covers the same underlying bug and includes the downstream handling changes, making it the most complete representative of the fix.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45639", + "right": "pull_request:45645", + "accept": true, + "reason": "Same underlying xdist collision bug for captured_info artifacts; 45645 is a superset that adds the workflow-side log collection changes, so these are plausibly merged into one PR." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 26, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-45720-3", + "nodes": [ + "pull_request:45720", + "pull_request:46023", + "pull_request:46259" + ], + "soft_pairs": [ + "pull_request:45720|pull_request:46259", + "pull_request:46023|pull_request:46259" + ], + "prepared_review_unit_hash": "ec48c4c91aa9b458922469d94ef2c2269a42e310411e32afbb2d17229c2455bd", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 2, + "serialized_chars": 10912, + "estimated_input_tokens": 2728, + "estimated_eval_tokens": 5712 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "These PRs are all linter/rule-related, but they target different underlying checks: TRF003 tuple-return behavior, TRF016 dead do_* flags in image/video processors, and TRF018-related modeling-rule additions. The only close pair (46023 vs 46259) shares infra/docs files but not the same bug/change.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46259 is the best representative of the linter-rule cluster: it is the latest and broadest rule addition, with the clearest shared rule-doc/config footprint.", + "best_issue_reason": null, + "best_pr_reason": "PR 46259 is the strongest standalone candidate because it adds the most complete rule implementation and touches the widest set of affected model files.", + "soft_edge_verdicts": [ + { + "left": "pull_request:45720", + "right": "pull_request:46259", + "accept": false, + "reason": "Different rule families and code paths: 45720 is about can_return_tuple / forward return handling, while 46259 is about dead do_* preprocessing flags. Same repo area, not the same change." + }, + { + "left": "pull_request:46023", + "right": "pull_request:46259", + "accept": false, + "reason": "Both are linter-rule updates, but TRF016 and TRF018 target different dead-flag patterns and different model families. Shared docs/config files are not enough to treat them as the same fix." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 27, + "component_count": 30, + "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": 28, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-46073-3", + "nodes": [ + "pull_request:46073", + "pull_request:46154", + "pull_request:46196" + ], + "soft_pairs": [ + "pull_request:46073|pull_request:46154", + "pull_request:46073|pull_request:46196", + "pull_request:46154|pull_request:46196" + ], + "prepared_review_unit_hash": "07510306d928c2f5e834f787a267a7144ccc17e37e2c20d3bd41e922a3df4957", + "component_budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 8083, + "estimated_input_tokens": 2021, + "estimated_eval_tokens": 4298 + }, + "budget": { + "node_count": 3, + "item_count": 3, + "soft_pair_count": 3, + "serialized_chars": 8083, + "estimated_input_tokens": 2021, + "estimated_eval_tokens": 4298 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "All three pull requests are about enabling SDPA dispatch, but they target different model families and code paths, so they are not duplicates. The broadest and most complete PR is the wav2vec2_conformer/SeamlessM4T one, but the others remain separate changes.", + "confidence": 0.93, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46196 is the broadest and most developed change, covering multiple related speech/text models and including corresponding tests, so it is the best representative PR in this cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR 46196 has the widest scope and the most supporting test coverage, making it the strongest single PR candidate for the cluster.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46073", + "right": "pull_request:46154", + "accept": false, + "reason": "Both are SDPA-dispatch work, but one is for CTRL and the other for T5; they touch different model implementations and are not the same fix." + }, + { + "left": "pull_request:46073", + "right": "pull_request:46196", + "accept": false, + "reason": "These target different model families and code paths (CTRL vs wav2vec2/SeamlessM4T), so they are related by theme only, not by duplicate bug or mergeable change." + }, + { + "left": "pull_request:46154", + "right": "pull_request:46196", + "accept": false, + "reason": "T5 SDPA dispatch is a separate model-specific implementation from wav2vec2/SeamlessM4T SDPA dispatch; they 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": 29, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-46126-2", + "nodes": [ + "pull_request:46126", + "pull_request:46269" + ], + "soft_pairs": [ + "pull_request:46126|pull_request:46269" + ], + "prepared_review_unit_hash": "fbc28c5a4e709e299c8619d729d978b7544290cce05b9f6131fd619f63a20d60", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5570, + "estimated_input_tokens": 1393, + "estimated_eval_tokens": 3042 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 5570, + "estimated_input_tokens": 1393, + "estimated_eval_tokens": 3042 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Two pull requests only weakly overlap on distributed files, but they are not the same change: one is a focused EP/trainer integration PR, the other is a broad distributed branch-base PR with many unrelated edits.", + "confidence": 0.94, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR #46126 is the focused, concrete EP + trainer integration change; it has a narrow implementation footprint and a clear purpose, unlike the broad branch-base PR.", + "best_issue_reason": null, + "best_pr_reason": "PR #46126 is the best representative of the cluster because it targets a specific distributed feature path, whereas #46269 is an umbrella branch-base carrying many unrelated distributed changes.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46126", + "right": "pull_request:46269", + "accept": false, + "reason": "Shared distributed filenames do not indicate the same underlying bug or mergeable change. #46126 is a focused EP/trainer integration patch; #46269 is a broad distributed base branch spanning FSDP, CI, integrations, and model files, so they should not be merged as duplicates." + } + ] + }, + "evaluator_result": null, + "evaluator_used": false, + "retried": false, + "accepted_nontrivial_soft_edge": false, + "error_kind": null, + "error_message": null + }, + { + "label": "pull_request", + "component_index": 30, + "component_count": 30, + "review_unit_index": 1, + "review_unit_count": 1, + "status": "reviewed", + "reason": null, + "source": "llm", + "cache_hit": false, + "model": "gpt-5.4-mini?service_tier=flex", + "cluster_id": "cluster-46152-2", + "nodes": [ + "pull_request:46152", + "pull_request:46207" + ], + "soft_pairs": [ + "pull_request:46152|pull_request:46207" + ], + "prepared_review_unit_hash": "2f9fc36c5298bb9fd52f0c9e7d4510960a64880b00bd4ba1b98fe63048508fd3", + "component_budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4275, + "estimated_input_tokens": 1069, + "estimated_eval_tokens": 2394 + }, + "budget": { + "node_count": 2, + "item_count": 2, + "soft_pair_count": 1, + "serialized_chars": 4275, + "estimated_input_tokens": 1069, + "estimated_eval_tokens": 2394 + }, + "overflow_policy": "truncate_then_skip", + "trimmed": false, + "aggressively_trimmed": false, + "split": false, + "analyst_result": { + "summary": "Both PRs replace direct source-file opening with safer source/resource inspection, but they target different code paths and different behaviors, so they are related in theme rather than duplicates.", + "confidence": 0.92, + "canonical_issue_reason": null, + "canonical_pr_reason": "PR 46207 is the stronger representative: it has a clearer, narrower concrete behavior change in _can_set_attn_implementation and includes tests, making it the better canonical PR for this cluster.", + "best_issue_reason": null, + "best_pr_reason": "PR 46207 is the best standalone example of the cluster\u2019s theme because it cleanly addresses one source-reading heuristic with test coverage; PR 46152 is a separate implementation in a different module.", + "soft_edge_verdicts": [ + { + "left": "pull_request:46152", + "right": "pull_request:46207", + "accept": false, + "reason": "Same general pattern (avoid open() on source), but they fix different functions in different files with different semantics: import_utils resource resolution vs modeling_utils attention-implementation detection. They are not the same underlying bug 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 + } + ] +} diff --git a/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/manifest.json b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/manifest.json new file mode 100644 index 0000000000000000000000000000000000000000..08c8b20b9887052b0f200158ce823ddeac225cc0 --- /dev/null +++ b/snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/manifest.json @@ -0,0 +1,14 @@ +{ + "analysis_id": "hybrid-model-20260531t000035z", + "artifacts": { + "hybrid": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "model": null, + "published_at": "2026-05-31T00:04:31Z", + "repo": "huggingface/transformers", + "schema_version": 1, + "snapshot_id": "20260531T000035Z", + "variant": "hybrid" +} diff --git a/snapshots/20260531T000035Z/manifest.json b/snapshots/20260531T000035Z/manifest.json index 6b45e5e4061b62d9fb0970aed8dbabb7fccbcb26..63db221c7cebaabad5f3f0a723fa38d22996270d 100644 --- a/snapshots/20260531T000035Z/manifest.json +++ b/snapshots/20260531T000035Z/manifest.json @@ -32,6 +32,24 @@ "timeline_events": 347 }, "extracted_at": "2026-05-31T00:00:35Z", + "published_analysis": { + "canonical_analysis_id": "hybrid-model-20260531t000035z", + "runs": { + "hybrid-model-20260531t000035z": { + "analysis_id": "hybrid-model-20260531t000035z", + "artifacts": { + "hybrid": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.json", + "hybrid_reviews": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/analysis-report-hybrid.llm-reviews.json" + }, + "channel": "canonical", + "manifest_path": "snapshots/20260531T000035Z/analysis-runs/hybrid-model-20260531t000035z/manifest.json", + "model": null, + "published_at": "2026-05-31T00:04:31Z", + "variant": "hybrid" + } + }, + "schema_version": 1 + }, "repo": "huggingface/transformers", "snapshot_id": "20260531T000035Z", "watermark": {