{"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/parse-scores","entry":"parse_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":6,"n_papers_ran":4,"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":6,"n_samples_ran":4,"n_samples_fingerprinted":2,"n_places":7,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":4,"unverified":2},"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":"2608.26119","paper":"/paper/arxiv-2608-26119","title":"DeflectBench: A Benchmark for Evaluating Rhetorical Fallacy Generation in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-08","title_source":"syntology","repo":"ArtKanke/DeflectBench","path":"evaluation/core.py","file_url":"https://github.com/ArtKanke/DeflectBench/blob/HEAD/evaluation/core.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"c2a77303ec2c2d90","mcp_get_code":{"code_sha256":"c2a77303ec2c2d90"}},{"arxiv_id":"2607.16721","paper":"/paper/arxiv-2607-16721","title":"Half the Experts, All the Code: One-Shot Domain Pruning of Mixture-of-Experts LLMs for Coding *","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"anik-jha/moep","path":"src/moep/codeval.py","file_url":"https://github.com/anik-jha/moep/blob/HEAD/src/moep/codeval.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b9e6f7bbe3b43270","mcp_get_code":{"code_sha256":"b9e6f7bbe3b43270"}},{"arxiv_id":"2410.22587","paper":"/paper/toxicity-of-the-commons-curating-open-source","title":"Toxicity of the Commons: Curating Open-Source Pre-Training Data","date":"2024-10-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Pleias/toxic-commons","path":"src/2.1_create_annotations.py","file_url":"https://github.com/Pleias/toxic-commons/blob/HEAD/src/2.1_create_annotations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e33db98fe5baada8","mcp_get_code":{"code_sha256":"e33db98fe5baada8"}},{"arxiv_id":"2402.15527","paper":"/paper/pca-bench-evaluating-multimodal-large","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkunlp-icler/pca-eval","path":"pca-eval/evaluation/pca_auto_scoring.py","file_url":"https://github.com/pkunlp-icler/pca-eval/blob/HEAD/pca-eval/evaluation/pca_auto_scoring.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"9505dff883276ceb","mcp_get_code":{"code_sha256":"9505dff883276ceb"}},{"arxiv_id":"2402.15527","paper":"/paper/pca-bench-evaluating-multimodal-large","title":"PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain","date":"2024-02-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkunlp-icler/pca-eval","path":"pca-eval/evaluation/pca_auto_scoring_action.py","file_url":"https://github.com/pkunlp-icler/pca-eval/blob/HEAD/pca-eval/evaluation/pca_auto_scoring_action.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4d55e3ac6c2f1ffe","mcp_get_code":{"code_sha256":"4d55e3ac6c2f1ffe"}},{"arxiv_id":"2312.02896","paper":"/paper/benchlmm-benchmarking-cross-style-visual","title":"BenchLMM: Benchmarking Cross-style Visual Capability of Large Multimodal Models","date":"2023-12-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"aifeg/benchgpt","path":"evaluate/gpt_evaluation_script_Robots_Games.py","file_url":"https://github.com/aifeg/benchgpt/blob/HEAD/evaluate/gpt_evaluation_script_Robots_Games.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"4d55e3ac6c2f1ffe","mcp_get_code":{"code_sha256":"4d55e3ac6c2f1ffe"}},{"arxiv_id":"2305.13829","paper":"/paper/learn-from-mistakes-through-cooperative","title":"Learning from Mistakes via Cooperative Study Assistant for Large Language Models","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"madaan/self-refine","path":"src/acronym/run_mcts.py","file_url":"https://github.com/madaan/self-refine/blob/HEAD/src/acronym/run_mcts.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":"024bf912c9a8a3df","mcp_get_code":{"code_sha256":"024bf912c9a8a3df"}}]}