{"id":"W6966782472","doi":"10.48448/bnyy-ne17","title":"Logical Fallacy Detection","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Fallacy; Logical consequence; Logical conjunction; Truth table; Task (project management); Logical reasoning; Set (abstract data type); Language model","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":[0.006451194,0.002436752,0.001013286,0.009599246,0.002223736,0.006003326,0.003165081,0.004055936,0.01348309],"category_scores_gemma":[0.06923396,0.0005800577,0.001922832,0.004828244,0.001724383,0.01304102,0.004988961,0.00454174,0.007672922],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001996965,"about_ca_system_score_gemma":0.003578281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00416107,"about_ca_topic_score_gemma":0.00734926,"domain_scores_codex":[0.9897816,0.002145942,0.001599594,0.002083813,0.003919258,0.000469672],"domain_scores_gemma":[0.9578212,0.02826355,0.004235128,0.004115624,0.004766258,0.0007982006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008648779,0.0006458407,0.08228383,0.003720579,0.0003605392,0.003630824,0.001939142,0.009270838,0.009153747,0.06092734,0.3530665,0.4741358],"study_design_scores_gemma":[0.0002715749,0.000249335,0.02446773,0.001667303,0.0003368911,0.005850997,0.003219115,0.2197364,0.03022281,0.2835614,0.4301717,0.0002448683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3059926,0.01485967,0.3187436,0.02394407,0.002841238,0.002021936,0.2085251,0.04053177,0.08253998],"genre_scores_gemma":[0.5741215,0.002355779,0.1958065,0.003115568,0.0006734582,0.0008478704,0.2099226,0.001566883,0.01158983],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01348309,"threshold_uncertainty_score":0.0451054,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0282615285090122,"score_gpt":0.298867070414143,"score_spread":0.2706055419051308,"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."}}