{"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/extract-info","entry":"extract_info","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":8,"n_papers_ran":7,"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":6,"n_samples_fingerprinted":3,"n_places":8,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":4,"unverified":1},"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":"2506.18841","paper":"/paper/longwriter-zero-mastering-ultra-long-text","title":"LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning","date":"2025-06-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"thudm/longwriter","path":"evaluation/eval_quality.py","file_url":"https://github.com/thudm/longwriter/blob/HEAD/evaluation/eval_quality.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"05ae45b3b7e836be","mcp_get_code":{"code_sha256":"05ae45b3b7e836be"}},{"arxiv_id":"2506.04180","paper":"/paper/superwriter-reflection-driven-long-form","title":"SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models","date":"2025-06-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"mozhu621/superwriter","path":"Agent/Super_write_agent.py","file_url":"https://github.com/mozhu621/superwriter/blob/HEAD/Agent/Super_write_agent.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"05ae45b3b7e836be","mcp_get_code":{"code_sha256":"05ae45b3b7e836be"}},{"arxiv_id":"2406.05720","paper":"/paper/villageragent-a-graph-based-multi-agent","title":"VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft","date":"2024-06-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"cnsdqd-dyb/villageragent","path":"model/utils.py","file_url":"https://github.com/cnsdqd-dyb/villageragent/blob/HEAD/model/utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"798386af5ebc3fb6","mcp_get_code":{"code_sha256":"798386af5ebc3fb6"}},{"arxiv_id":"2402.17786","paper":"/paper/stepwise-self-consistent-mathematical","title":"Stepwise Self-Consistent Mathematical Reasoning with Large Language Models","date":"2024-02-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhao-zilong/ssc-cot","path":"KG.py","file_url":"https://github.com/zhao-zilong/ssc-cot/blob/HEAD/KG.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f718a056b37ca750","mcp_get_code":{"code_sha256":"f718a056b37ca750"}},{"arxiv_id":"2402.02309","paper":"/paper/jailbreaking-attack-against-multimodal-large","title":"Jailbreaking Attack against Multimodal Large Language Model","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"naver-ai/jood","path":"evaluate_metrics.py","file_url":"https://github.com/naver-ai/jood/blob/HEAD/evaluate_metrics.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"82dfbc3db8906d82","mcp_get_code":{"code_sha256":"82dfbc3db8906d82"}},{"arxiv_id":"2310.08367","paper":"/paper/mcu-a-task-centric-framework-for-open-ended","title":"Towards Evaluating Generalist Agents: An Automated Benchmark in Open World","date":"2023-10-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"craftjarvis/mcu","path":"MCU_benchmark/run_task.py","file_url":"https://github.com/craftjarvis/mcu/blob/HEAD/MCU_benchmark/run_task.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"f4d591306a89b6a5","mcp_get_code":{"code_sha256":"f4d591306a89b6a5"}},{"arxiv_id":"2309.04077","paper":"/paper/saynav-grounding-large-language-models-for","title":"SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments","date":"2023-09-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"arajv/SayNav","path":"src/python/pointnav_utils.py","file_url":"https://github.com/arajv/SayNav/blob/HEAD/src/python/pointnav_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"fab4fadbda28248c","mcp_get_code":{"code_sha256":"fab4fadbda28248c"}},{"arxiv_id":"2025.emnlp-main.965","paper":null,"title":"arXiv:2025.emnlp-main.965","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"salmakh1/ACING","path":"Induction/logger.py","file_url":"https://github.com/salmakh1/ACING/blob/HEAD/Induction/logger.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"9add3b16b441ab03","mcp_get_code":{"code_sha256":"9add3b16b441ab03"}}]}