{"id":"W4385570795","doi":"10.18653/v1/2023.findings-acl.526","title":"Open-WikiTable : Dataset for Open Domain Question Answering with Complex Reasoning over Table","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Samsung; Korea Health Industry Development Institute; National Research Foundation of Korea; Ministry of Science and ICT, South Korea; National Research Foundation","keywords":"Open domain; Computer science; Question answering; Parsing; Table (database); Domain (mathematical analysis); Open research; Task (project management); SQL; Range (aeronautics); Information retrieval; Sorting; Artificial intelligence; Data mining; World Wide Web; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001047402,0.0001220148,0.0001838089,0.00006411383,0.0002911398,0.001463534,0.002672278,0.00003203057,0.00006855281],"category_scores_gemma":[0.00002667829,0.0001027706,0.00001216476,0.0004767243,0.0000141753,0.002409193,0.002817185,0.00006490926,0.00003747511],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004959025,"about_ca_system_score_gemma":0.00009916004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002865422,"about_ca_topic_score_gemma":0.0005930111,"domain_scores_codex":[0.9986497,0.00003840296,0.0001825315,0.0005601347,0.0001784319,0.0003908635],"domain_scores_gemma":[0.9989107,0.00008479116,0.00006523,0.0008118851,0.00004297533,0.00008446719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007113004,0.00006937497,0.001834791,0.00006677464,0.00004857582,0.00003266263,0.000464889,0.02117398,0.002045372,0.6633163,0.2939563,0.01691989],"study_design_scores_gemma":[0.001059423,0.00008621825,0.0007341649,0.00008197888,0.000004436352,0.00001036011,0.00009238897,0.7963014,0.0002867626,0.007189373,0.1938983,0.0002551764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002877484,0.000008449288,0.9877815,0.0007887051,0.00010842,0.0008153553,0.0001584106,0.0001876855,0.007274032],"genre_scores_gemma":[0.03365498,0.00000296546,0.9614533,0.0007532147,0.00005488884,0.0001791403,0.0009206958,0.00002132606,0.0029595],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7751274,"threshold_uncertainty_score":0.9995731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06894793121732369,"score_gpt":0.3401330571122272,"score_spread":0.2711851258949036,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}