{"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/parse-question","entry":"parse_question","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":1,"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":1,"n_samples_fingerprinted":0,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"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":"2506.20512","paper":"/paper/octothinker-mid-training-incentivizes","title":"OctoThinker: Mid-training Incentivizes Reinforcement Learning Scaling","date":"2025-06-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"gair-nlp/octothinker","path":"eval/eval/eval_utils.py","file_url":"https://github.com/gair-nlp/octothinker/blob/HEAD/eval/eval/eval_utils.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":"49e328786ffb3f8f","mcp_get_code":{"code_sha256":"49e328786ffb3f8f"}},{"arxiv_id":"2502.12067","paper":"/paper/tokenskip-controllable-chain-of-thought","title":"TokenSkip: Controllable Chain-of-Thought Compression in LLMs","date":"2025-02-17","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"hemingkx/TokenSkip","path":"eval/eval_utils.py","file_url":"https://github.com/hemingkx/TokenSkip/blob/HEAD/eval/eval_utils.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":"49e328786ffb3f8f","mcp_get_code":{"code_sha256":"49e328786ffb3f8f"}},{"arxiv_id":"2406.18629","paper":"/paper/step-dpo-step-wise-preference-optimization","title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","date":"2024-06-26","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"dvlab-research/step-dpo","path":"evaluation/eval/eval_utils.py","file_url":"https://github.com/dvlab-research/step-dpo/blob/HEAD/evaluation/eval/eval_utils.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"49e328786ffb3f8f","mcp_get_code":{"code_sha256":"49e328786ffb3f8f"}},{"arxiv_id":"2402.02823","paper":"/paper/evading-data-contamination-detection-for","title":"Evading Data Contamination Detection for Language Models is (too) Easy","date":"2024-02-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/malicious-contamination","path":"src/contamination/clean_eval.py","file_url":"https://github.com/eth-sri/malicious-contamination/blob/HEAD/src/contamination/clean_eval.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":"260501dfa9ae0d0f","mcp_get_code":{"code_sha256":"260501dfa9ae0d0f"}},{"arxiv_id":"2025.naacl-demo.13","paper":null,"title":"arXiv:2025.naacl-demo.13","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"IBM/InspectorRAGet","path":"converters/acebench/convert.py","file_url":"https://github.com/IBM/InspectorRAGet/blob/HEAD/converters/acebench/convert.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":"9a9782717eb2903a","mcp_get_code":{"code_sha256":"9a9782717eb2903a"}}]}