{"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-final","entry":"extract_final","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":4,"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":2,"n_samples_fingerprinted":2,"n_places":5,"n_places_pointer_only":1,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"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":"2605.30345","paper":"/paper/arxiv-2605-30345","title":"SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"microsoft/SchGen","path":"modules/dataset_filter.py","file_url":"https://github.com/microsoft/SchGen/blob/HEAD/modules/dataset_filter.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7ff743eec8809c0c","mcp_get_code":{"code_sha256":"7ff743eec8809c0c"}},{"arxiv_id":"2604.11048","paper":"/paper/arxiv-2604-11048","title":"A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"cjia7/DPR","path":"src/npti/eval/eval_mmlu.py","file_url":"https://github.com/cjia7/DPR/blob/HEAD/src/npti/eval/eval_mmlu.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"55653ca966a845f6","mcp_get_code":{"code_sha256":"55653ca966a845f6"}},{"arxiv_id":"2601.22139","paper":"/paper/arxiv-2601-22139","title":"Reasoning While Asking: Transforming Reasoning Large Language Models from Passive Solvers to Proactive Inquirers","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"SUAT-AIRI/Proactive-Interactive-R1","path":"generalization_eval/factual_knowledge/run_mmlu_interactive_generation.py","file_url":"https://github.com/SUAT-AIRI/Proactive-Interactive-R1/blob/HEAD/generalization_eval/factual_knowledge/run_mmlu_interactive_generation.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":"bfcfbf7614a49849","mcp_get_code":{"code_sha256":"bfcfbf7614a49849"}},{"arxiv_id":"2601.11866","paper":"/paper/arxiv-2601-11866","title":"Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"bernardolab/mARC-Reasoning","path":"compute_accuracy.py","file_url":"https://github.com/bernardolab/mARC-Reasoning/blob/HEAD/compute_accuracy.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":"bfcfbf7614a49849","mcp_get_code":{"code_sha256":"bfcfbf7614a49849"}},{"arxiv_id":"2406.01574","paper":"/paper/mmlu-pro-a-more-robust-and-challenging-multi","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark","date":"2024-06-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tiger-ai-lab/mmlu-pro","path":"compute_accuracy.py","file_url":"https://github.com/tiger-ai-lab/mmlu-pro/blob/HEAD/compute_accuracy.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":"bfcfbf7614a49849","mcp_get_code":{"code_sha256":"bfcfbf7614a49849"}}]}