{"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/gpt-2","entry":"gpt","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":7,"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":7,"n_samples_ran":3,"n_samples_fingerprinted":0,"n_places":7,"n_places_pointer_only":2,"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":"2412.08972","paper":"/paper/rulearena-a-benchmark-for-rule-guided","title":"RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"skyriver-2000/rulearena","path":"nba/micro_evaluation.py","file_url":"https://github.com/skyriver-2000/rulearena/blob/HEAD/nba/micro_evaluation.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"dde255079fb4a398","mcp_get_code":{"code_sha256":"dde255079fb4a398"}},{"arxiv_id":"2407.12784","paper":"/paper/agentpoison-red-teaming-llm-agents-via","title":"AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases","date":"2024-07-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"BillChan226/AgentPoison","path":"ReAct/run_strategyqa_gpt3.5.py","file_url":"https://github.com/BillChan226/AgentPoison/blob/HEAD/ReAct/run_strategyqa_gpt3.5.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4ee2e20b4f838311","mcp_get_code":{"code_sha256":"4ee2e20b4f838311"}},{"arxiv_id":"2401.08190","paper":"/paper/mario-math-reasoning-with-code-interpreter","title":"MARIO: MAth Reasoning with code Interpreter Output -- A Reproducible Pipeline","date":"2024-01-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mario-math-reasoning/mario","path":"gpt_react.py","file_url":"https://github.com/mario-math-reasoning/mario/blob/HEAD/gpt_react.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"3103e261ed5433cb","mcp_get_code":{"code_sha256":"3103e261ed5433cb"}},{"arxiv_id":"2312.12343","paper":"/paper/avoiding-data-contamination-in-language-model","title":"LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction","date":"2023-12-19","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"liyucheng09/latesteval","path":"eval/contamination.py","file_url":"https://github.com/liyucheng09/latesteval/blob/HEAD/eval/contamination.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"7072fd7e0b193209","mcp_get_code":{"code_sha256":"7072fd7e0b193209"}},{"arxiv_id":"2309.06490","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":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"2c3c80cf9b4ef1fd","mcp_get_code":{"code_sha256":"2c3c80cf9b4ef1fd"}},{"arxiv_id":"2025.findings-acl.979","paper":null,"title":"arXiv:2025.findings-acl.979","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"Mrshenshen/FRUIT","path":"models/gpt/get_ll_doc.py","file_url":"https://github.com/Mrshenshen/FRUIT/blob/HEAD/models/gpt/get_ll_doc.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":"9ed3cd8714bdfcd9","mcp_get_code":{"code_sha256":"9ed3cd8714bdfcd9"}},{"arxiv_id":"2025.emnlp-main.105","paper":null,"title":"arXiv:2025.emnlp-main.105","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"VelikayaScarlet/F2Bench","path":"eval-api.py","file_url":"https://github.com/VelikayaScarlet/F2Bench/blob/HEAD/eval-api.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":"b86a1daa874249be","mcp_get_code":{"code_sha256":"b86a1daa874249be"}}]}