{"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/recover-instruct-llama","entry":"recover_instruct_llama","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":0,"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":2,"n_samples_ran":0,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":0,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2406.06357","paper":"/paper/massw-a-new-dataset-and-benchmark-tasks-for","title":"MASSW: A New Dataset and Benchmark Tasks for AI-Assisted Scientific Workflows","date":"2024-06-10","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"xingjian-zhang/massw","path":"factscore/download_data.py","file_url":"https://github.com/xingjian-zhang/massw/blob/HEAD/factscore/download_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"CC0-1.0","inline_ok":true,"code_sha256_prefix":"02c83d89394be1c7","mcp_get_code":{"code_sha256":"02c83d89394be1c7"}},{"arxiv_id":"2403.03823","paper":"/paper/a-modular-approach-for-multimodal","title":"A Modular Approach for Multimodal Summarization of TV Shows","date":"2024-03-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/FActScore","path":"factscore/download_data.py","file_url":"https://github.com/shmsw25/FActScore/blob/HEAD/factscore/download_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02c83d89394be1c7","mcp_get_code":{"code_sha256":"02c83d89394be1c7"}},{"arxiv_id":"2402.18045","paper":"/paper/multi-fact-assessing-multilingual-llms-multi","title":"Multi-FAct: Assessing Factuality of Multilingual LLMs using FActScore","date":"2024-02-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sheikhshafayat/multi-fact","path":"factscore/download_data.py","file_url":"https://github.com/sheikhshafayat/multi-fact/blob/HEAD/factscore/download_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02c83d89394be1c7","mcp_get_code":{"code_sha256":"02c83d89394be1c7"}},{"arxiv_id":"2402.12659","paper":"/paper/the-finben-an-holistic-financial-benchmark","title":"FinBen: A Holistic Financial Benchmark for Large Language Models","date":"2024-02-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"chancefocus/pixiu","path":"src/factscore_package/download_data.py","file_url":"https://github.com/chancefocus/pixiu/blob/HEAD/src/factscore_package/download_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"a643d9a7436e58c2","mcp_get_code":{"code_sha256":"a643d9a7436e58c2"}},{"arxiv_id":"2305.14251","paper":"/paper/factscore-fine-grained-atomic-evaluation-of","title":"FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation","date":"2023-05-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"shmsw25/factscore","path":"factscore/download_data.py","file_url":"https://github.com/shmsw25/factscore/blob/HEAD/factscore/download_data.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"02c83d89394be1c7","mcp_get_code":{"code_sha256":"02c83d89394be1c7"}}]}