{"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/load-csv-data","entry":"load_csv_data","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":8,"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":8,"n_samples_ran":5,"n_samples_fingerprinted":1,"n_places":9,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":4,"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":"2606.29424","paper":"/paper/arxiv-2606-29424","title":"ENTROROUTER: Learning Efficient Model Routing via Entropy Regulation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"huggingface/Math-Verify","path":"evaluate_model_outputs.py","file_url":"https://github.com/huggingface/Math-Verify/blob/HEAD/evaluate_model_outputs.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e22a383e9fd48c5","mcp_get_code":{"code_sha256":"7e22a383e9fd48c5"}},{"arxiv_id":"2606.29424","paper":"/paper/arxiv-2606-29424","title":"ENTROROUTER: Learning Efficient Model Routing via Entropy Regulation","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"huggingface/Math-Verify","path":"extract_answers.py","file_url":"https://github.com/huggingface/Math-Verify/blob/HEAD/extract_answers.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":"c518cad720d81620","mcp_get_code":{"code_sha256":"c518cad720d81620"}},{"arxiv_id":"2606.16617","paper":"/paper/arxiv-2606-16617","title":"Sycophancy as Material Failure under Pushback Loading A Multi-Axis Characterization Across Three Loading Cases and up to Seventeen Material Charges","date":null,"month_inferred_from_arxiv_id":"2026-06","title_source":"syntology","repo":"JiseungHong/SYCON-Bench","path":"debate_setting/evaluate_ToF.py","file_url":"https://github.com/JiseungHong/SYCON-Bench/blob/HEAD/debate_setting/evaluate_ToF.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"d54c1c90f68abb2b","mcp_get_code":{"code_sha256":"d54c1c90f68abb2b"}},{"arxiv_id":"2604.18566","paper":"/paper/arxiv-2604-18566","title":"Benchmarking System Dynamics AI Assistants: Cloud Versus Local Large Language Models on CLD Extraction and Discussion","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"UB-IAD/sd-ai","path":"third-party/time-series-behavior-analysis/classify_behavior.py","file_url":"https://github.com/UB-IAD/sd-ai/blob/HEAD/third-party/time-series-behavior-analysis/classify_behavior.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"4add2d583e034913","mcp_get_code":{"code_sha256":"4add2d583e034913"}},{"arxiv_id":"2604.05818","paper":"/paper/arxiv-2604-05818","title":"WikiSeeker: Rethinking the Role of Vision-Language Models in Knowledge-Based Visual Question Answering","date":null,"month_inferred_from_arxiv_id":"2026-04","title_source":"syntology","repo":"zhuyjan/WikiSeeker","path":"utils/utils.py","file_url":"https://github.com/zhuyjan/WikiSeeker/blob/HEAD/utils/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":"5d45d4d98e2da070","mcp_get_code":{"code_sha256":"5d45d4d98e2da070"}},{"arxiv_id":"2505.20347","paper":"/paper/serl-self-play-reinforcement-learning-for","title":"SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data","date":"2025-05-25","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"wantbook-book/serl","path":"evaluation/Math-Benchmarks/evaluate_outputs.py","file_url":"https://github.com/wantbook-book/serl/blob/HEAD/evaluation/Math-Benchmarks/evaluate_outputs.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"code_sha256_prefix":"7e22a383e9fd48c5","mcp_get_code":{"code_sha256":"7e22a383e9fd48c5"}},{"arxiv_id":"2402.17302","paper":"/paper/can-llm-generate-culturally-relevant","title":"Can LLM Generate Culturally Relevant Commonsense QA Data? Case Study in Indonesian and Sundanese","date":"2024-02-27","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"rifkiaputri/id-csqa","path":"utils/helpers.py","file_url":"https://github.com/rifkiaputri/id-csqa/blob/HEAD/utils/helpers.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"4087fe280199d65b","mcp_get_code":{"code_sha256":"4087fe280199d65b"}},{"arxiv_id":"2310.10467","paper":"/paper/stance-detection-with-collaborative-role","title":"Stance Detection with Collaborative Role-Infused LLM-Based Agents","date":"2023-10-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"tsinghua-fib-lab/cola","path":"cola.py","file_url":"https://github.com/tsinghua-fib-lab/cola/blob/HEAD/cola.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6b07bf5f6ee06db0","mcp_get_code":{"code_sha256":"6b07bf5f6ee06db0"}},{"arxiv_id":"2306.12330","paper":"/paper/protogate-prototype-based-neural-networks","title":"ProtoGate: Prototype-based Neural Networks with Global-to-local Feature Selection for Tabular Biomedical Data","date":"2023-06-21","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"SilenceX12138/ProtoGate","path":"src/dataset.py","file_url":"https://github.com/SilenceX12138/ProtoGate/blob/HEAD/src/dataset.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":"6e369ec9defcbdf3","mcp_get_code":{"code_sha256":"6e369ec9defcbdf3"}}]}