{"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/llmresponse","entry":"LLMResponse","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":5,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":3,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"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":"2607.24717","paper":"/paper/arxiv-2607-24717","title":"DataOrchestra: Learning to Orchestrate Per-Example Curation of Pretraining Data","date":null,"month_inferred_from_arxiv_id":"2026-07","title_source":"syntology","repo":"GAIR-NLP/DataOrchestra","path":"inference/student/pipeline.py","file_url":"https://github.com/GAIR-NLP/DataOrchestra/blob/HEAD/inference/student/pipeline.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"5f8aadad34284911","mcp_get_code":{"code_sha256":"5f8aadad34284911"}},{"arxiv_id":"2604.22239","paper":"/paper/arxiv-2604-22239","title":"Navigating Large-Scale Document Collections: MuDABench for Multi-Document Analytical QA","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"Zhanli-Li/MuDABench","path":"agent/agent_runner.py","file_url":"https://github.com/Zhanli-Li/MuDABench/blob/HEAD/agent/agent_runner.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":"814a75b8ec1ca439","mcp_get_code":{"code_sha256":"814a75b8ec1ca439"}},{"arxiv_id":"2604.13552","paper":"/paper/arxiv-2604-13552","title":"Training-Free Test-Time Contrastive Learning for Large Language Models","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"KevinSCUTer/TF-TTCL","path":"core/source/compare/selection_kernel.py","file_url":"https://github.com/KevinSCUTer/TF-TTCL/blob/HEAD/core/source/compare/selection_kernel.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"096987a022c9dd64","mcp_get_code":{"code_sha256":"096987a022c9dd64"}},{"arxiv_id":"2409.19753","paper":"/paper/cotkr-chain-of-thought-enhanced-knowledge","title":"CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering","date":"2024-09-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wuyike2000/CoTKR","path":"inference/closed/rewrite/infer_chain.py","file_url":"https://github.com/wuyike2000/CoTKR/blob/HEAD/inference/closed/rewrite/infer_chain.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":"2278fb78c9421228","mcp_get_code":{"code_sha256":"2278fb78c9421228"}},{"arxiv_id":"2402.17753","paper":"/paper/evaluating-very-long-term-conversational","title":"Evaluating Very Long-Term Conversational Memory of LLM Agents","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"danny911kr/REALTALK","path":"eval_memory/qa_tool.py","file_url":"https://github.com/danny911kr/REALTALK/blob/HEAD/eval_memory/qa_tool.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6ee6284bd946785c","mcp_get_code":{"code_sha256":"6ee6284bd946785c"}}]}