{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001812188,0.002544454,0.001113184,0.004754243,0.001300419,0.002561446,0.003311236,0.002597298,0.01576212],"category_scores_gemma":[0.01452973,0.0006422242,0.001941681,0.006120942,0.0007729079,0.00447203,0.003925839,0.002425272,0.01839682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002294914,"about_ca_system_score_gemma":0.003375648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02813121,"about_ca_topic_score_gemma":0.05594509,"domain_scores_codex":[0.9967825,0.0007500748,0.0005502997,0.0008915139,0.0007583609,0.0002672187],"domain_scores_gemma":[0.9932715,0.002690417,0.000619911,0.001605658,0.00118199,0.0006305791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002233977,0.0001907628,0.005079104,0.002199373,0.00008915413,0.0001931282,0.0004357035,0.00221304,0.001132983,0.00555026,0.9637538,0.01893936],"study_design_scores_gemma":[0.0003080643,0.00008369308,0.01021254,0.0005638822,0.00006465012,0.0004693,0.001245466,0.0126501,0.003123192,0.01413295,0.9570311,0.000115125],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.004809733,0.0005473452,0.004143809,0.000556428,0.0001245581,0.0001693457,0.9790758,0.006233704,0.004339121],"genre_scores_gemma":[0.004956405,0.0001167303,0.005858715,0.0001219505,0.00001947836,0.0001821277,0.9875907,0.0002356025,0.000918227],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02813121,"threshold_uncertainty_score":0.05593497,"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."}}