{"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/calculate-f1","entry":"calculate_f1","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":8,"n_papers_ran":2,"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":7,"n_samples_ran":2,"n_samples_fingerprinted":1,"n_places":8,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":5},"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":"2604.01432","paper":"/paper/arxiv-2604-01432","title":"Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"JHU-CLSP/citation-granularity","path":"evaluate_stratification.py","file_url":"https://github.com/JHU-CLSP/citation-granularity/blob/HEAD/evaluate_stratification.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"96f69f1680124fd8","mcp_get_code":{"code_sha256":"96f69f1680124fd8"}},{"arxiv_id":"2603.07487","paper":"/paper/arxiv-2603-07487","title":"A Joint Neural Baseline for Concept, Assertion, and Relation Extraction from Clinical Text","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"racerandom/JaMIE","path":"clinical_eval.py","file_url":"https://github.com/racerandom/JaMIE/blob/HEAD/clinical_eval.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"12d328b2a64b0209","mcp_get_code":{"code_sha256":"12d328b2a64b0209"}},{"arxiv_id":"2411.17465","paper":"/paper/showui-one-vision-language-action-model-for","title":"ShowUI: One Vision-Language-Action Model for GUI Visual Agent","date":"2024-11-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"showlab/showui","path":"main/eval_mind2web.py","file_url":"https://github.com/showlab/showui/blob/HEAD/main/eval_mind2web.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":"c3c22ae25acb9f88","mcp_get_code":{"code_sha256":"c3c22ae25acb9f88"}},{"arxiv_id":"2411.16495","paper":"/paper/atomr-atomic-operator-empowered-large","title":"AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge Reasoning","date":"2024-11-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"THU-KEG/AtomR","path":"src/calculate_metrics.py","file_url":"https://github.com/THU-KEG/AtomR/blob/HEAD/src/calculate_metrics.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"06bd0fab42352980","mcp_get_code":{"code_sha256":"06bd0fab42352980"}},{"arxiv_id":"2312.13772","paper":"/paper/on-task-performance-and-model-calibration","title":"On Task Performance and Model Calibration with Supervised and Self-Ensembled In-Context Learning","date":"2023-12-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cambridgeltl/ensembled-sicl","path":"utils/evaluator.py","file_url":"https://github.com/cambridgeltl/ensembled-sicl/blob/HEAD/utils/evaluator.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bdb225300bc83baa","mcp_get_code":{"code_sha256":"bdb225300bc83baa"}},{"arxiv_id":"2312.07000","paper":"/paper/alignment-for-honesty","title":"Alignment for Honesty","date":"2023-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"GAIR-NLP/alignment-for-honesty","path":"evaluation/utils.py","file_url":"https://github.com/GAIR-NLP/alignment-for-honesty/blob/HEAD/evaluation/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"647d5f0831f57b1c","mcp_get_code":{"code_sha256":"647d5f0831f57b1c"}},{"arxiv_id":"Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper","paper":null,"title":"arXiv:Lin_ShowUI_One_Vision-Language-Action_Model_for_GUI_Visual_Agent_CVPR_2025_paper","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"showlab/ShowUI","path":"main/eval_mind2web.py","file_url":"https://github.com/showlab/ShowUI/blob/HEAD/main/eval_mind2web.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":"c3c22ae25acb9f88","mcp_get_code":{"code_sha256":"c3c22ae25acb9f88"}},{"arxiv_id":"2025.acl-long.179","paper":null,"title":"arXiv:2025.acl-long.179","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"RUC-NLPIR/RAG-Critic","path":"rag_error_bench/caculate_acc.py","file_url":"https://github.com/RUC-NLPIR/RAG-Critic/blob/HEAD/rag_error_bench/caculate_acc.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4f35f7112f7c5044","mcp_get_code":{"code_sha256":"4f35f7112f7c5044"}}]}