{"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/query-openai","entry":"query_openai","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":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":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":2,"unverified":4},"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":"2603.02176","paper":"/paper/arxiv-2603-02176","title":"Organizing, Orchestrating, and Benchmarking Agent Skills at Ecosystem Scale","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"ynulihao/AgentSkillOS","path":"benchmark/AgentSkillOS_bench/utils/llm_clients.py","file_url":"https://github.com/ynulihao/AgentSkillOS/blob/HEAD/benchmark/AgentSkillOS_bench/utils/llm_clients.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"d0aaa277c641b9ac","mcp_get_code":{"code_sha256":"d0aaa277c641b9ac"}},{"arxiv_id":"2510.17947","paper":"/paper/arxiv-2510-17947","title":"PLAGUE: PLUG-AND-PLAY FRAMEWORK FOR LIFE-LONG ADAPTIVE GENERATION OF MULTI-TURN JAIL-BREAKS","date":null,"month_inferred_from_arxiv_id":"2025-10","title_source":"syntology","repo":"madhavaggar/PLAGUE","path":"src/plague/infer.py","file_url":"https://github.com/madhavaggar/PLAGUE/blob/HEAD/src/plague/infer.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7ff98c4bf3d1b7eb","mcp_get_code":{"code_sha256":"7ff98c4bf3d1b7eb"}},{"arxiv_id":"2410.01171","paper":"/paper/bordirlines-a-dataset-for-evaluating-cross","title":"BordIRlines: A Dataset for Evaluating Cross-lingual Retrieval-Augmented Generation","date":"2024-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"manestay/bordirlines","path":"generation/generation.py","file_url":"https://github.com/manestay/bordirlines/blob/HEAD/generation/generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"b2d772cb7fde06e6","mcp_get_code":{"code_sha256":"b2d772cb7fde06e6"}},{"arxiv_id":"2402.07876","paper":"/paper/policy-improvement-using-language-feedback","title":"Policy Improvement using Language Feedback Models","date":"2024-02-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vzhong/language_feedback_models","path":"experiments/get_llm_feedback.py","file_url":"https://github.com/vzhong/language_feedback_models/blob/HEAD/experiments/get_llm_feedback.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"99f9e3f30575cb13","mcp_get_code":{"code_sha256":"99f9e3f30575cb13"}},{"arxiv_id":"2402.03620","paper":"/paper/self-discover-large-language-models-self","title":"Self-Discover: Large Language Models Self-Compose Reasoning Structures","date":"2024-02-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"catid/self-discover","path":"langs/kor.py","file_url":"https://github.com/catid/self-discover/blob/HEAD/langs/kor.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":"35424214c3a86ca4","mcp_get_code":{"code_sha256":"35424214c3a86ca4"}},{"arxiv_id":"2307.02477","paper":"/paper/reasoning-or-reciting-exploring-the","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","date":"2023-07-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhaofengwu/counterfactual-evaluation","path":"query_utils.py","file_url":"https://github.com/zhaofengwu/counterfactual-evaluation/blob/HEAD/query_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"36f593974514e07c","mcp_get_code":{"code_sha256":"36f593974514e07c"}}]}