{"id":"W4389524278","doi":"10.18653/v1/2023.findings-emnlp.180","title":"CASE: Commonsense-Augmented Score with an Expanded Answer Space","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Commonsense knowledge; Space (punctuation); Commonsense reasoning; Weighting; Artificial intelligence; Question answering; Measure (data warehouse); Natural language processing; Machine learning; Data mining; Domain knowledge","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003475305,0.001668226,0.001448693,0.002523202,0.0007047498,0.001663152,0.002279785,0.002168862,0.016045],"category_scores_gemma":[0.01678602,0.0002911779,0.001039562,0.001381909,0.001091555,0.004447197,0.004834319,0.002540553,0.005284428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006916905,"about_ca_system_score_gemma":0.00136507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001544737,"about_ca_topic_score_gemma":0.004203944,"domain_scores_codex":[0.9950919,0.002016989,0.0002712591,0.001000952,0.001339328,0.0002795065],"domain_scores_gemma":[0.9940348,0.002772784,0.0002391472,0.001466257,0.001142267,0.0003447141],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009399846,0.0006746372,0.003462868,0.0005153983,0.0001705135,0.0003666795,0.0005219898,0.03698588,0.02593834,0.0258038,0.04212775,0.8624921],"study_design_scores_gemma":[0.000394574,0.000806477,0.00311961,0.00011166,0.0001224461,0.0006699559,0.0002826393,0.8530237,0.02181286,0.08274154,0.03674431,0.0001701753],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07335749,0.001061766,0.8744979,0.001146455,0.0003857957,0.0005082097,0.001747273,0.03118716,0.01610787],"genre_scores_gemma":[0.5880972,0.0001974832,0.382264,0.0007180008,0.0004157325,0.0006968992,0.006148965,0.001403598,0.02005822],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.016045,"threshold_uncertainty_score":0.05367589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06141825289089449,"score_gpt":0.2746300107929852,"score_spread":0.2132117579020907,"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."}}