{"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/sha256-text","entry":"sha256_text","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":2,"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":4,"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":0,"ran_fixture":0,"ran":2,"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":"2609.02548","paper":"/paper/arxiv-2609-02548","title":"Learn from Whoever Is Right: Answer-Verified Multi-Teacher Distillation for Multi-Domain LLMs","date":null,"month_inferred_from_arxiv_id":"2026-09","title_source":"syntology","repo":"hexixiang/MT-SDPO","path":"evaluation/evaluate.py","file_url":"https://github.com/hexixiang/MT-SDPO/blob/HEAD/evaluation/evaluate.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":"ba2d92a5368b72bc","mcp_get_code":{"code_sha256":"ba2d92a5368b72bc"}},{"arxiv_id":"2606.00329","paper":"/paper/arxiv-2606-00329","title":"Benchmarking Recursive-Collapse Warning Claims Under Matched False-Positive Control","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"davidmullett/loopzero-paper-public","path":"src/loopzero_paper/benchmarks/recommender/audit_engine_spec.py","file_url":"https://github.com/davidmullett/loopzero-paper-public/blob/HEAD/src/loopzero_paper/benchmarks/recommender/audit_engine_spec.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"f70dabbe4d3555a0","mcp_get_code":{"code_sha256":"f70dabbe4d3555a0"}},{"arxiv_id":"2605.18374","paper":"/paper/arxiv-2605-18374","title":"Beyond Inference-Time Search: Reinforcement Learning Synthesizes Reusable Solvers","date":null,"month_inferred_from_arxiv_id":"2026-05","title_source":"syntology","repo":"IDEALLab/neural-solver-synthesis","path":"evaluation/sds/adaptive_repair.py","file_url":"https://github.com/IDEALLab/neural-solver-synthesis/blob/HEAD/evaluation/sds/adaptive_repair.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"819df9caf830923b","mcp_get_code":{"code_sha256":"819df9caf830923b"}},{"arxiv_id":"2603.05764","paper":"/paper/arxiv-2603-05764","title":"TML-bench: Benchmark for Data Science Agents on Tabular ML Tasks","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"MykolaPinchuk/TML-bench","path":"orchestrator/provenance.py","file_url":"https://github.com/MykolaPinchuk/TML-bench/blob/HEAD/orchestrator/provenance.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"e2eaf67441c33629","mcp_get_code":{"code_sha256":"e2eaf67441c33629"}},{"arxiv_id":"2505.23281","paper":"/paper/matharena-evaluating-llms-on-uncontaminated","title":"MathArena: Evaluating LLMs on Uncontaminated Math Competitions","date":"2025-05-29","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"eth-sri/matharena","path":"src/matharena/arxivmath_source.py","file_url":"https://github.com/eth-sri/matharena/blob/HEAD/src/matharena/arxivmath_source.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"ba2d92a5368b72bc","mcp_get_code":{"code_sha256":"ba2d92a5368b72bc"}}]}