{"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/analyze-results","entry":"analyze_results","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":5,"n_papers_ran":3,"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":4,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"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":"2406.02919","paper":"/paper/multifaceteval-multifaceted-evaluation-to","title":"MultifacetEval: Multifaceted Evaluation to Probe LLMs in Mastering Medical Knowledge","date":"2024-06-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thumlp/multifaceteval","path":"analysis.py","file_url":"https://github.com/thumlp/multifaceteval/blob/HEAD/analysis.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f1992607d65dde76","mcp_get_code":{"code_sha256":"f1992607d65dde76"}},{"arxiv_id":"2311.17918","paper":"/paper/driving-into-the-future-multiview-visual","title":"Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Driving","date":"2023-11-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"bravegroup/drive-wm","path":"utils/check_inits.py","file_url":"https://github.com/bravegroup/drive-wm/blob/HEAD/utils/check_inits.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":"169c706af1000176","mcp_get_code":{"code_sha256":"169c706af1000176"}},{"arxiv_id":"2310.20708","paper":"/paper/unexpected-improvements-to-expected","title":"Unexpected Improvements to Expected Improvement for Bayesian Optimization","date":"2023-10-31","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"omerronen/scales","path":"les/analysis/opt_results.py","file_url":"https://github.com/omerronen/scales/blob/HEAD/les/analysis/opt_results.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a71685e684ff7417","mcp_get_code":{"code_sha256":"a71685e684ff7417"}},{"arxiv_id":"2310.16579","paper":"/paper/wsdms-debunk-fake-news-via-weakly-supervised","title":"WSDMS: Debunk Fake News via Weakly Supervised Detection of Misinforming Sentences with Contextualized Social Wisdom","date":"2023-10-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"HKBUNLP/WSDMS-EMNLP2023","path":"analysis_results.py","file_url":"https://github.com/HKBUNLP/WSDMS-EMNLP2023/blob/HEAD/analysis_results.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"bb6c5267f8535bd5","mcp_get_code":{"code_sha256":"bb6c5267f8535bd5"}},{"arxiv_id":"2110.15064","paper":"/paper/towards-fine-grained-reasoning-for-fake-news","title":"Towards Fine-Grained Reasoning for Fake News Detection","date":"2021-09-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Ahren09/FinerFact","path":"kgat/analysis.py","file_url":"https://github.com/Ahren09/FinerFact/blob/HEAD/kgat/analysis.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"bb6c5267f8535bd5","mcp_get_code":{"code_sha256":"bb6c5267f8535bd5"}}]}