{"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/create-test-prompt","entry":"create_test_prompt","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":5,"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":3,"n_samples_ran":3,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":4,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":2,"ran_fixture":0,"ran":1,"unverified":0},"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":"2507.06167","paper":"/paper/skywork-r1v3-technical-report","title":"Skywork-R1V3 Technical Report","date":"2025-07-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"946612831b2fdd2e","mcp_get_code":{"code_sha256":"946612831b2fdd2e"}},{"arxiv_id":"2504.16656","paper":"/paper/skywork-r1v2-multimodal-hybrid-reinforcement","title":"Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning","date":"2025-04-23","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"946612831b2fdd2e","mcp_get_code":{"code_sha256":"946612831b2fdd2e"}},{"arxiv_id":"2504.05599","paper":"/paper/skywork-r1v-pioneering-multimodal-reasoning","title":"Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought","date":"2025-04-08","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SkyworkAI/Skywork-R1V","path":"eval/EMMA/evaluation/evaluate.py","file_url":"https://github.com/SkyworkAI/Skywork-R1V/blob/HEAD/eval/EMMA/evaluation/evaluate.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"946612831b2fdd2e","mcp_get_code":{"code_sha256":"946612831b2fdd2e"}},{"arxiv_id":"2412.09413","paper":"/paper/imitate-explore-and-self-improve-a","title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","date":"2024-12-12","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rucaibox/virgo","path":"evaluation/MathVerse/evaluation/extract_answer_s1.py","file_url":"https://github.com/rucaibox/virgo/blob/HEAD/evaluation/MathVerse/evaluation/extract_answer_s1.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":"60aec79830c634c8","mcp_get_code":{"code_sha256":"60aec79830c634c8"}},{"arxiv_id":"2402.10104","paper":"/paper/geoeval-benchmark-for-evaluating-llms-and","title":"GeoEval: Benchmark for Evaluating LLMs and Multi-Modal Models on Geometry Problem-Solving","date":"2024-02-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"geoeval/geoeval","path":"tool/extract_result.py","file_url":"https://github.com/geoeval/geoeval/blob/HEAD/tool/extract_result.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"a878f818de85fff2","mcp_get_code":{"code_sha256":"a878f818de85fff2"}}]}