{"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/select-field","entry":"select_field","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":12,"n_papers_ran":0,"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":0,"n_samples_fingerprinted":0,"n_places":12,"n_places_pointer_only":5,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":0,"ran_fixture":0,"ran":0,"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":"2505.11683","paper":"/paper/evaluating-design-decisions-for-dual-encoder","title":"Evaluating Design Decisions for Dual Encoder-based Entity Disambiguation","date":"2025-05-16","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"facebookresearch/BLINK","path":"blink/biencoder/data_process.py","file_url":"https://github.com/facebookresearch/BLINK/blob/HEAD/blink/biencoder/data_process.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"code_sha256_prefix":"bff0f2e6d48007b2","mcp_get_code":{"code_sha256":"bff0f2e6d48007b2"}},{"arxiv_id":"2402.02636","paper":"/paper/can-large-language-models-learn-independent","title":"Can Large Language Models Learn Independent Causal Mechanisms?","date":"2024-02-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Strong-AI-Lab/Logical-and-abstract-reasoning","path":"models/run_multiple_choice.py","file_url":"https://github.com/Strong-AI-Lab/Logical-and-abstract-reasoning/blob/HEAD/models/run_multiple_choice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2310.13316","paper":"/paper/coarse-to-fine-dual-encoders-are-better-frame","title":"Coarse-to-Fine Dual Encoders are Better Frame Identification Learners","date":"2023-10-20","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"pkunlp-icler/cofftea","path":"code/dataset.py","file_url":"https://github.com/pkunlp-icler/cofftea/blob/HEAD/code/dataset.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2310.09430","paper":"/paper/a-systematic-evaluation-of-large-language-1","title":"Assessing and Enhancing the Robustness of Large Language Models with Task Structure Variations for Logical Reasoning","date":"2023-10-13","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"strong-ai-lab/logical-and-abstract-reasoning","path":"models/run_multiple_choice.py","file_url":"https://github.com/strong-ai-lab/logical-and-abstract-reasoning/blob/HEAD/models/run_multiple_choice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2108.00648","paper":"/paper/from-lsat-the-progress-and-challenges-of","title":"From LSAT: The Progress and Challenges of Complex Reasoning","date":"2021-08-02","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"zhongwanjun/AR-LSAT","path":"LSTM/main_large.py","file_url":"https://github.com/zhongwanjun/AR-LSAT/blob/HEAD/LSTM/main_large.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2011.03080","paper":"/paper/exams-a-multi-subject-high-school","title":"EXAMS: A Multi-Subject High School Examinations Dataset for Cross-Lingual and Multilingual Question Answering","date":"2020-11-05","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":null,"path":"","file_url":null,"status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2009.06504","paper":"/paper/filling-the-gap-of-utterance-aware-and","title":"Filling the Gap of Utterance-aware and Speaker-aware Representation for Multi-turn Dialogue","date":"2020-09-14","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"comprehensiveMap/MDFN","path":"run_MDFN.py","file_url":"https://github.com/comprehensiveMap/MDFN/blob/HEAD/run_MDFN.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2004.11546","paper":"/paper/g-daug-generative-data-augmentation-for","title":"Generative Data Augmentation for Commonsense Reasoning","date":"2020-04-24","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning","path":"finetune_gd_swag.py","file_url":"https://github.com/yangyiben/G-DAUG-c-Generative-Data-Augmentation-for-Commonsense-Reasoning/blob/HEAD/finetune_gd_swag.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"56c5c1024fb026bd","mcp_get_code":{"code_sha256":"56c5c1024fb026bd"}},{"arxiv_id":"2004.04494","paper":"/paper/mutual-a-dataset-for-multi-turn-dialogue","title":"MuTual: A Dataset for Multi-Turn Dialogue Reasoning","date":"2020-04-09","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"Nealcly/MuTual","path":"baseline/multi-choice/run_multiple_choice.py","file_url":"https://github.com/Nealcly/MuTual/blob/HEAD/baseline/multi-choice/run_multiple_choice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"2002.04326","paper":"/paper/reclor-a-reading-comprehension-dataset-1","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","date":"2020-02-11","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"yuweihao/reclor","path":"run_multiple_choice.py","file_url":"https://github.com/yuweihao/reclor/blob/HEAD/run_multiple_choice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"1908.05739","paper":"/paper/abductive-commonsense-reasoning","title":"Abductive Commonsense Reasoning","date":"2019-08-15","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"allenai/abductive-commonsense-reasoning","path":"anli/data_processors.py","file_url":"https://github.com/allenai/abductive-commonsense-reasoning/blob/HEAD/anli/data_processors.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":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}},{"arxiv_id":"aaai_29850","paper":null,"title":"arXiv:aaai_29850","date":null,"month_inferred_from_arxiv_id":null,"title_source":null,"repo":"ozyyshr/FocalReasoner","path":"run_multiple_choice.py","file_url":"https://github.com/ozyyshr/FocalReasoner/blob/HEAD/run_multiple_choice.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"0a546b305d274996","mcp_get_code":{"code_sha256":"0a546b305d274996"}}]}