{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/code/extract-scores","entry":"extract_scores","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":16,"n_papers_ran":5,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":17,"n_samples_ran":5,"n_samples_fingerprinted":2,"n_places":21,"n_places_pointer_only":6,"by_status":{"ran_honours":1,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":12},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2606.05183","paper":"/paper/arxiv-2606-05183","title":"The Granularity Gap: A Multi-Dimensional Cross-Generational Audit of Sycophancy in Gemini Models","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"pskeough/The-Granularity-Gap","path":"pipeline/01_run_panel.py","file_url":"https://github.com/pskeough/The-Granularity-Gap/blob/HEAD/pipeline/01_run_panel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"cba861db7a9c5864","mcp_get_code":{"code_sha256":"cba861db7a9c5864"}},{"arxiv_id":"2605.16234","paper":"/paper/arxiv-2605-16234","title":"No Free Swap: Protocol-Dependent Layer Redundancy in Transformers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"Gpgabriel25/ProtocolGapDiagnostic","path":"downstream_benchmark.py","file_url":"https://github.com/Gpgabriel25/ProtocolGapDiagnostic/blob/HEAD/downstream_benchmark.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"7f3fe518c40f3bd4","mcp_get_code":{"code_sha256":"7f3fe518c40f3bd4"}},{"arxiv_id":"2603.28488","paper":"/paper/arxiv-2603-28488","title":"Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"mnc13/PROClaim","path":"sycophancy_analysis.py","file_url":"https://github.com/mnc13/PROClaim/blob/HEAD/sycophancy_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"703660e8ca176031","mcp_get_code":{"code_sha256":"703660e8ca176031"}},{"arxiv_id":"2601.22156","paper":"/paper/arxiv-2601-22156","title":"Hybrid Linear Attention Done Right: Efficient Distillation and Effective Architectures for Extremely Long Contexts","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"THUNLP/hybrid-linear-attention","path":"attn-layer-selection/layer_analysis.py","file_url":"https://github.com/THUNLP/hybrid-linear-attention/blob/HEAD/attn-layer-selection/layer_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"217db10d5f6c7d5a","mcp_get_code":{"code_sha256":"217db10d5f6c7d5a"}},{"arxiv_id":"2509.25050","paper":"/paper/arxiv-2509-25050","title":"Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models","date":"2025-09-29","month_inferred_from_arxiv_id":null,"title_source":"syntology","repo":"scxue/advantage_weighted_matching","path":"advantage_weighted_matching/flow_grpo/qwenvl.py","file_url":"https://github.com/scxue/advantage_weighted_matching/blob/HEAD/advantage_weighted_matching/flow_grpo/qwenvl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"aaf3538ea48a524d","mcp_get_code":{"code_sha256":"aaf3538ea48a524d"}},{"arxiv_id":"2507.03167","paper":"/paper/adversarial-manipulation-of-reasoning-models","title":"Adversarial Manipulation of Reasoning Models using Internal Representations","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ky295/reasoning-manipulation","path":"evals/plot_eval_results.py","file_url":"https://github.com/ky295/reasoning-manipulation/blob/HEAD/evals/plot_eval_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"03321a7b056bd1b5","mcp_get_code":{"code_sha256":"03321a7b056bd1b5"}},{"arxiv_id":"2505.17908","paper":"/paper/comfymind-toward-general-purpose-generation","title":"ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback","date":"2025-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"EnVision-Research/ComfyMind","path":"script/evaluation_wise.py","file_url":"https://github.com/EnVision-Research/ComfyMind/blob/HEAD/script/evaluation_wise.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4b8a94cc59053bf8","mcp_get_code":{"code_sha256":"4b8a94cc59053bf8"}},{"arxiv_id":"2505.05470","paper":"/paper/flow-grpo-training-flow-matching-models-via","title":"Flow-GRPO: Training Flow Matching Models via Online RL","date":"2025-05-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yifan123/flow_grpo","path":"flow_grpo/qwenvl.py","file_url":"https://github.com/yifan123/flow_grpo/blob/HEAD/flow_grpo/qwenvl.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"aaf3538ea48a524d","mcp_get_code":{"code_sha256":"aaf3538ea48a524d"}},{"arxiv_id":"2412.05631","paper":"/paper/characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paitesanshi/characterbox","path":"evaluate.py","file_url":"https://github.com/paitesanshi/characterbox/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd6ba1a21f12998e","mcp_get_code":{"code_sha256":"fd6ba1a21f12998e"}},{"arxiv_id":"2412.05631","paper":"/paper/characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paitesanshi/characterbox","path":"evaluate_narrator.py","file_url":"https://github.com/paitesanshi/characterbox/blob/HEAD/evaluate_narrator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4ceb5e434c0e21e","mcp_get_code":{"code_sha256":"a4ceb5e434c0e21e"}},{"arxiv_id":"2412.05631","paper":"/paper/characterbox-evaluating-the-role-playing","title":"CharacterBox: Evaluating the Role-Playing Capabilities of LLMs in Text-Based Virtual Worlds","date":"2024-12-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"paitesanshi/characterbox","path":"evaluate_scene.py","file_url":"https://github.com/paitesanshi/characterbox/blob/HEAD/evaluate_scene.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3798794817974d8f","mcp_get_code":{"code_sha256":"3798794817974d8f"}},{"arxiv_id":"2410.12851","paper":"/paper/vibecheck-discover-and-quantify-qualitative","title":"VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models","date":"2024-10-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"lisadunlap/vibecheck","path":"get_preference_labels.py","file_url":"https://github.com/lisadunlap/vibecheck/blob/HEAD/get_preference_labels.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9fe570fe6dee5c7d","mcp_get_code":{"code_sha256":"9fe570fe6dee5c7d"}},{"arxiv_id":"2409.02813","paper":"/paper/mmmu-pro-a-more-robust-multi-discipline","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","date":"2024-09-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"opendatalab/pm4bench","path":"src/pm4bench/miqa.py","file_url":"https://github.com/opendatalab/pm4bench/blob/HEAD/src/pm4bench/miqa.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"6ec5c1760b10f4d4","mcp_get_code":{"code_sha256":"6ec5c1760b10f4d4"}},{"arxiv_id":"2406.04264","paper":"/paper/mlvu-a-comprehensive-benchmark-for-multi-task","title":"MLVU: Benchmarking Multi-task Long Video Understanding","date":"2024-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"junjie99/mlvu","path":"evaluation/generation_evaluation/calculate.py","file_url":"https://github.com/junjie99/mlvu/blob/HEAD/evaluation/generation_evaluation/calculate.py","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"00ae2b911e74b6c4","mcp_get_code":{"code_sha256":"00ae2b911e74b6c4"}},{"arxiv_id":"2402.11683","paper":"/paper/one-prompt-to-rule-them-all-llms-for-opinion","title":"One Prompt To Rule Them All: LLMs for Opinion Summary Evaluation","date":"2024-02-18","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tjsiledar/SummEval-OP","path":"code/efficient-evaluator-v2.py","file_url":"https://github.com/tjsiledar/SummEval-OP/blob/HEAD/code/efficient-evaluator-v2.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"462312c0339acd23","mcp_get_code":{"code_sha256":"462312c0339acd23"}},{"arxiv_id":"2005.00160","paper":"/paper/pipelineprofiler-a-visual-analytics-tool-for","title":"PipelineProfiler: A Visual Analytics Tool for the Exploration of AutoML Pipelines","date":null,"month_inferred_from_arxiv_id":"2020-05","title_source":"archive","repo":"VIDA-NYU/PipelineVis","path":"PipelineProfiler/_powerset_analysis.py","file_url":"https://github.com/VIDA-NYU/PipelineVis/blob/HEAD/PipelineProfiler/_powerset_analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"code_sha256_prefix":"2bdd440663e3b6c7","mcp_get_code":{"code_sha256":"2bdd440663e3b6c7"}},{"arxiv_id":"openreview_9DfcvXahRb","paper":null,"title":"arXiv:openreview_9DfcvXahRb","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xuwang0117/EIG-LLM-Eval","path":"calculate_human_consistency.py","file_url":"https://github.com/xuwang0117/EIG-LLM-Eval/blob/HEAD/calculate_human_consistency.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3805b372e46a6a2e","mcp_get_code":{"code_sha256":"3805b372e46a6a2e"}},{"arxiv_id":"openreview_9DfcvXahRb","paper":null,"title":"arXiv:openreview_9DfcvXahRb","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"xuwang0117/EIG-LLM-Eval","path":"calculate_self_consistency.py","file_url":"https://github.com/xuwang0117/EIG-LLM-Eval/blob/HEAD/calculate_self_consistency.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b924b43d271c8d20","mcp_get_code":{"code_sha256":"b924b43d271c8d20"}},{"arxiv_id":"2025.naacl-long.323","paper":null,"title":"arXiv:2025.naacl-long.323","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Paitesanshi/CharacterBox","path":"evaluate.py","file_url":"https://github.com/Paitesanshi/CharacterBox/blob/HEAD/evaluate.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"fd6ba1a21f12998e","mcp_get_code":{"code_sha256":"fd6ba1a21f12998e"}},{"arxiv_id":"2025.naacl-long.323","paper":null,"title":"arXiv:2025.naacl-long.323","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Paitesanshi/CharacterBox","path":"evaluate_narrator.py","file_url":"https://github.com/Paitesanshi/CharacterBox/blob/HEAD/evaluate_narrator.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a4ceb5e434c0e21e","mcp_get_code":{"code_sha256":"a4ceb5e434c0e21e"}},{"arxiv_id":"2025.naacl-long.323","paper":null,"title":"arXiv:2025.naacl-long.323","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Paitesanshi/CharacterBox","path":"evaluate_scene.py","file_url":"https://github.com/Paitesanshi/CharacterBox/blob/HEAD/evaluate_scene.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3798794817974d8f","mcp_get_code":{"code_sha256":"3798794817974d8f"}}]}