{"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-llm","entry":"query_llm","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":7,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"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":"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":"utils/llm_api.py","file_url":"https://github.com/JHU-CLSP/citation-granularity/blob/HEAD/utils/llm_api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5f1bd4130fb0e230","mcp_get_code":{"code_sha256":"5f1bd4130fb0e230"}},{"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":"debaef85ade9e3d0","mcp_get_code":{"code_sha256":"debaef85ade9e3d0"}},{"arxiv_id":"2505.13237","paper":"/paper/sakura-on-the-multi-hop-reasoning-of-large","title":"SAKURA: On the Multi-hop Reasoning of Large Audio-Language Models Based on Speech and Audio Information","date":"2025-05-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ckyang1124/sakura","path":"evaluation/llm_judge.py","file_url":"https://github.com/ckyang1124/sakura/blob/HEAD/evaluation/llm_judge.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4c6c9926d43d2ecf","mcp_get_code":{"code_sha256":"4c6c9926d43d2ecf"}},{"arxiv_id":"2407.18525","paper":"/paper/is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yhzhu99/ehr-llm-benchmark","path":"src/structured_ehr/query_llm.py","file_url":"https://github.com/yhzhu99/ehr-llm-benchmark/blob/HEAD/src/structured_ehr/query_llm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f67c74bf273cfe78","mcp_get_code":{"code_sha256":"f67c74bf273cfe78"}},{"arxiv_id":"2407.18525","paper":"/paper/is-larger-always-better-evaluating-and","title":"ClinicRealm: Re-evaluating Large Language Models with Conventional Machine Learning for Non-Generative Clinical Prediction Tasks","date":"2024-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yhzhu99/ehr-llm-benchmark","path":"src/multimodal/query_llm.py","file_url":"https://github.com/yhzhu99/ehr-llm-benchmark/blob/HEAD/src/multimodal/query_llm.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b1cd5549432dbd63","mcp_get_code":{"code_sha256":"b1cd5549432dbd63"}},{"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":"72f354ebceb04921","mcp_get_code":{"code_sha256":"72f354ebceb04921"}},{"arxiv_id":"2307.13883","paper":"/paper/exedec-execution-decomposition-for","title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","date":"2023-07-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"google-deepmind/exedec","path":"spec_decomposition/cached_llm_access.py","file_url":"https://github.com/google-deepmind/exedec/blob/HEAD/spec_decomposition/cached_llm_access.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":"d204dbbda2b2669f","mcp_get_code":{"code_sha256":"d204dbbda2b2669f"}}]}