{"id":"W3155600250","doi":"10.18653/v1/2021.naacl-main.138","title":"Modeling Event Plausibility with Consistent Conceptual Abstraction","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McGill University","funders":"Canadian Institute for Advanced Research; Compute Canada; Microsoft Research","keywords":"Computer science; Natural language processing; Transformer; Hierarchy; Artificial intelligence; Cognitive psychology; Psychology","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":[0.007529818,0.00121432,0.001284129,0.003535824,0.00137975,0.005806987,0.003306743,0.002047771,0.007753827],"category_scores_gemma":[0.05481754,0.00168478,0.002916619,0.002604797,0.002638543,0.01256653,0.005829871,0.00407013,0.001119304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002285414,"about_ca_system_score_gemma":0.001698305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008233208,"about_ca_topic_score_gemma":0.009403946,"domain_scores_codex":[0.9947096,0.002439496,0.0003372625,0.001183058,0.0009817898,0.0003487777],"domain_scores_gemma":[0.9700544,0.02230334,0.001668164,0.003928647,0.001514217,0.0005311344],"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":[0.0005142561,0.00009186016,0.004505082,0.0002710583,0.0003306515,0.0006437202,0.001061028,0.1891875,0.001037575,0.7439887,0.004831033,0.05353748],"study_design_scores_gemma":[0.00005100119,0.00001967802,0.0002894815,0.00003439798,0.00009279123,0.0001041099,0.00009022843,0.3966459,0.0005227687,0.5988352,0.003290006,0.00002451191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03434055,0.0008022438,0.9514375,0.002054719,0.0001040716,0.0001081007,0.001079177,0.001217684,0.008855935],"genre_scores_gemma":[0.7548789,0.0005713403,0.2385063,0.0002989856,0.0001794531,0.0001847362,0.001858662,0.0002897035,0.003231976],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008233208,"threshold_uncertainty_score":0.03982192,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06236140920146336,"score_gpt":0.2777404454129202,"score_spread":0.2153790362114568,"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."}}