{"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-bytes","entry":"sha256_bytes","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":6,"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":4,"n_samples_ran":1,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":1,"unverified":3},"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":"f3f472b0143c5adf","mcp_get_code":{"code_sha256":"f3f472b0143c5adf"}},{"arxiv_id":"2606.00579","paper":"/paper/arxiv-2606-00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"Dongping-Chen/OmniCoding","path":"src/omnicoding/benchmarks/subsets.py","file_url":"https://github.com/Dongping-Chen/OmniCoding/blob/HEAD/src/omnicoding/benchmarks/subsets.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"code_sha256_prefix":"09abe599f437dda7","mcp_get_code":{"code_sha256":"09abe599f437dda7"}},{"arxiv_id":"2603.15020","paper":"/paper/arxiv-2603-15020","title":"MER-Bench: A Comprehensive Benchmark for Multimodal Meme Reappraisal","date":null,"month_inferred_from_arxiv_id":"2026-03","title_source":"syntology","repo":"one-seven17/MER-Bench","path":"judge.py","file_url":"https://github.com/one-seven17/MER-Bench/blob/HEAD/judge.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b3599636629687ea","mcp_get_code":{"code_sha256":"b3599636629687ea"}},{"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":"7f5ffed1f98ca2b1","mcp_get_code":{"code_sha256":"7f5ffed1f98ca2b1"}},{"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":"f3f472b0143c5adf","mcp_get_code":{"code_sha256":"f3f472b0143c5adf"}},{"arxiv_id":"2505.14683","paper":"/paper/emerging-properties-in-unified-multimodal","title":"Emerging Properties in Unified Multimodal Pretraining","date":"2025-05-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"neverbiasu/ComfyUI-BAGEL","path":"modeling/bagel/converted_format.py","file_url":"https://github.com/neverbiasu/ComfyUI-BAGEL/blob/HEAD/modeling/bagel/converted_format.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":"7f5ffed1f98ca2b1","mcp_get_code":{"code_sha256":"7f5ffed1f98ca2b1"}}]}