{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/code/num-tokens-from-messages","entry":"num_tokens_from_messages","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-10-05T00:36:11+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 = n_papers_ran_no_instrument_failure (papers with a run with no instrument failure) + n_papers_ran_instrument_only (papers where every run was a failure of Syntology's instrument); n_samples_ran = n_samples_ran_checked (honoured, violated, no contract) + n_samples_instrument (failures of Syntology's instrument, not of the code).","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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":14,"n_papers_ran":0,"n_papers_ran_no_instrument_failure":0,"n_papers_ran_instrument_only":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":13,"n_samples_ran":0,"n_samples_constructed":0,"n_samples_ran_checked":0,"n_samples_instrument":0,"n_samples_unverified":13,"n_samples_fingerprinted":0,"n_places":16,"n_places_pointer_only":5,"n_places_pointer_only_link_open":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_places_pointer_only_link_open counts the places where this paper's link allows the text and the stored copy does not","by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"unverified":13},"key_notes":{"n_samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"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":"2408.12787","arxiv_id_is_arxiv":true,"paper":"/paper/llm-pbe-assessing-data-privacy-in-large","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","date":"2024-08-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"QinbinLi/LLM-PBE","path":"models/chatgpt.py","file_url":"https://github.com/QinbinLi/LLM-PBE/blob/HEAD/models/chatgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"0f72adf8ddbb5ec1","code_sha256_prefix":"0f72adf8ddbb5ec1","mcp_get_code":{"code_sha256":"0f72adf8ddbb5ec1"}},{"arxiv_id":"2407.01489","arxiv_id_is_arxiv":true,"paper":"/paper/agentless-demystifying-llm-based-software","title":"Agentless: Demystifying LLM-based Software Engineering Agents","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"OpenAutoCoder/Agentless","path":"agentless/util/api_requests.py","file_url":"https://github.com/OpenAutoCoder/Agentless/blob/HEAD/agentless/util/api_requests.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2df3e1e980b47ac5","code_sha256_prefix":"2df3e1e980b47ac5","mcp_get_code":{"code_sha256":"2df3e1e980b47ac5"}},{"arxiv_id":"2407.01489","arxiv_id_is_arxiv":true,"paper":"/paper/agentless-demystifying-llm-based-software","title":"Agentless: Demystifying LLM-based Software Engineering Agents","date":"2024-07-01","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sorendunn/agentless-lite","path":"agentless_lite/util/repair.py","file_url":"https://github.com/sorendunn/agentless-lite/blob/HEAD/agentless_lite/util/repair.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6475d4ef21dc4237","code_sha256_prefix":"6475d4ef21dc4237","mcp_get_code":{"code_sha256":"6475d4ef21dc4237"}},{"arxiv_id":"2406.14228","arxiv_id_is_arxiv":true,"paper":"/paper/evoagent-towards-automatic-multi-agent","title":"EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithms","date":"2024-06-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"siyuyuan/evoagent","path":"scienceworld/eval_evoagent.py","file_url":"https://github.com/siyuyuan/evoagent/blob/HEAD/scienceworld/eval_evoagent.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, siyuyuan/evoagent when it was checked","code_sha256":"0f72adf8ddbb5ec1","code_sha256_prefix":"0f72adf8ddbb5ec1","mcp_get_code":{"code_sha256":"0f72adf8ddbb5ec1"}},{"arxiv_id":"2403.19114","arxiv_id_is_arxiv":true,"paper":"/paper/top-leaderboard-ranking-top-coding","title":"Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM","date":"2024-03-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"evo-eval/evoeval","path":"evoeval/util/api_request.py","file_url":"https://github.com/evo-eval/evoeval/blob/HEAD/evoeval/util/api_request.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2df3e1e980b47ac5","code_sha256_prefix":"2df3e1e980b47ac5","mcp_get_code":{"code_sha256":"2df3e1e980b47ac5"}},{"arxiv_id":"2403.05297","arxiv_id_is_arxiv":true,"paper":"/paper/peeb-part-based-image-classifiers-with-an","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","date":"2024-03-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"anguyen8/peeb","path":"src/chatgpt.py","file_url":"https://github.com/anguyen8/peeb/blob/HEAD/src/chatgpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"6d1cc911c7acc3cc","code_sha256_prefix":"6d1cc911c7acc3cc","mcp_get_code":{"code_sha256":"6d1cc911c7acc3cc"}},{"arxiv_id":"2402.15809","arxiv_id_is_arxiv":true,"paper":"/paper/empowering-large-language-model-agents","title":"Empowering Large Language Model Agents through Action Learning","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhao-ht/learnact","path":"backbone/gpt.py","file_url":"https://github.com/zhao-ht/learnact/blob/HEAD/backbone/gpt.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, zhao-ht/learnact when it was checked","code_sha256":"f17d8dea2f3b9842","code_sha256_prefix":"f17d8dea2f3b9842","mcp_get_code":{"code_sha256":"f17d8dea2f3b9842"}},{"arxiv_id":"2402.11821","arxiv_id_is_arxiv":true,"paper":"/paper/microstructures-and-accuracy-of-graph-recall","title":"Microstructures and Accuracy of Graph Recall by Large Language Models","date":"2024-02-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"abel0828/llm-graph-recall","path":"api.py","file_url":"https://github.com/abel0828/llm-graph-recall/blob/HEAD/api.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, abel0828/llm-graph-recall when it was checked","code_sha256":"0f72adf8ddbb5ec1","code_sha256_prefix":"0f72adf8ddbb5ec1","mcp_get_code":{"code_sha256":"0f72adf8ddbb5ec1"}},{"arxiv_id":"2311.16714","arxiv_id_is_arxiv":true,"paper":"/paper/embodied-multi-modal-agent-trained-by-an-llm","title":"Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld","date":"2023-11-28","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"stevenyangyj/emma-alfworld","path":"LAVIS/emma_utils.py","file_url":"https://github.com/stevenyangyj/emma-alfworld/blob/HEAD/LAVIS/emma_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, stevenyangyj/emma-alfworld when it was checked","code_sha256":"a7ece9f49be6eb57","code_sha256_prefix":"a7ece9f49be6eb57","mcp_get_code":{"code_sha256":"a7ece9f49be6eb57"}},{"arxiv_id":"2310.02003","arxiv_id_is_arxiv":true,"paper":"/paper/l2mac-large-language-model-automatic-computer","title":"L2MAC: Large Language Model Automatic Computer for Extensive Code Generation","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"samholt/l2mac","path":"l2mac/llm_providers/openai.py","file_url":"https://github.com/samholt/l2mac/blob/HEAD/l2mac/llm_providers/openai.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2c48ff24398fb8a0","code_sha256_prefix":"2c48ff24398fb8a0","mcp_get_code":{"code_sha256":"2c48ff24398fb8a0"}},{"arxiv_id":"2310.02003","arxiv_id_is_arxiv":true,"paper":"/paper/l2mac-large-language-model-automatic-computer","title":"L2MAC: Large Language Model Automatic Computer for Extensive Code Generation","date":"2023-10-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"vanderschaarlab/l2mac","path":"l2mac/llm_providers/openai.py","file_url":"https://github.com/vanderschaarlab/l2mac/blob/HEAD/l2mac/llm_providers/openai.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"b2239c20c6dcebef","code_sha256_prefix":"b2239c20c6dcebef","mcp_get_code":{"code_sha256":"b2239c20c6dcebef"}},{"arxiv_id":"2309.06490","arxiv_id_is_arxiv":true,"paper":"/paper/leveraging-large-language-models-for-1","title":"Leveraging Large Language Models for Automated Dialogue Analysis","date":"2023-09-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"emorynlp/gpt-abceval","path":"gpt_interface/gpt_utils.py","file_url":"https://github.com/emorynlp/gpt-abceval/blob/HEAD/gpt_interface/gpt_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub detected no licence in this paper's repository, emorynlp/gpt-abceval when it was checked","code_sha256":"b5b8238cdd662cba","code_sha256_prefix":"b5b8238cdd662cba","mcp_get_code":{"code_sha256":"b5b8238cdd662cba"}},{"arxiv_id":"2308.03349","arxiv_id_is_arxiv":true,"paper":"/paper/scigraphqa-a-large-scale-synthetic-multi-turn","title":"SciGraphQA: A Large-Scale Synthetic Multi-Turn Question-Answering Dataset for Scientific Graphs","date":"2023-08-07","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"findalexli/SciGraphQA","path":"data_parsing/utilities.py","file_url":"https://github.com/findalexli/SciGraphQA/blob/HEAD/data_parsing/utilities.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"e504b9d94a100457","code_sha256_prefix":"e504b9d94a100457","mcp_get_code":{"code_sha256":"e504b9d94a100457"}},{"arxiv_id":"2212.10560","arxiv_id_is_arxiv":true,"paper":"/paper/self-instruct-aligning-language-model-with","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","date":"2022-12-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"fsoft-ai4code/codecapybara","path":"data_generation/data_generation.py","file_url":"https://github.com/fsoft-ai4code/codecapybara/blob/HEAD/data_generation/data_generation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"da03aab82afbcc6b","code_sha256_prefix":"da03aab82afbcc6b","mcp_get_code":{"code_sha256":"da03aab82afbcc6b"}},{"arxiv_id":"openreview_8ppVmLtA2V","arxiv_id_is_arxiv":false,"paper":null,"title":"OpenReview id openreview_8ppVmLtA2V","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"yanweiyue/Mem-T","path":"llm_stats.py","file_url":"https://github.com/yanweiyue/Mem-T/blob/HEAD/llm_stats.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"2cbec6ae528a3c32","code_sha256_prefix":"2cbec6ae528a3c32","mcp_get_code":{"code_sha256":"2cbec6ae528a3c32"}},{"arxiv_id":"2023.findings-emnlp.446","arxiv_id_is_arxiv":false,"paper":null,"title":"ACL Anthology id 2023.findings-emnlp.446","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"wujunjie1998/BTPGBT","path":"btpg_ner.py","file_url":"https://github.com/wujunjie1998/BTPGBT/blob/HEAD/btpg_ner.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"code_sha256":"79f2a712336fdaf7","code_sha256_prefix":"79f2a712336fdaf7","mcp_get_code":{"code_sha256":"79f2a712336fdaf7"}}],"record_sha256":"618518425b607cbd02d132fd73dd7da24104122062f3f9beed4a2e539eb1c439","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}