{"id":"W6948037944","doi":"10.48448/wqbv-ak02","title":"Categorical Syllogisms Revisited: A Review of the Logical Reasoning Abilities of LLMs for Analyzing Categorical Syllogisms","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Syllogism; Categorical variable; Inference; Interpretability; Interpretation (philosophy); Interpreter","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":[0.009187285,0.001275869,0.001001515,0.009653025,0.001078099,0.004763966,0.003425136,0.001401181,0.0051175],"category_scores_gemma":[0.05584598,0.0007512083,0.001850234,0.007567176,0.002551038,0.008556441,0.00263319,0.002689703,0.002297406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00365524,"about_ca_system_score_gemma":0.003978156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009078038,"about_ca_topic_score_gemma":0.009156578,"domain_scores_codex":[0.992762,0.002603518,0.0007244961,0.001733999,0.00193107,0.0002448267],"domain_scores_gemma":[0.9566972,0.03397717,0.001301363,0.002980469,0.004568041,0.000475728],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001850583,0.00009665344,0.01135956,0.007052652,0.0002966046,0.0001192261,0.001802136,0.009457172,0.002293799,0.09827018,0.03136443,0.8377026],"study_design_scores_gemma":[0.00003853078,0.0001890969,0.02284534,0.007425508,0.0003450504,0.0007350266,0.003393224,0.1093461,0.00881277,0.4195238,0.4270334,0.0003122599],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.04804447,0.4002422,0.4655343,0.02116072,0.001049138,0.0004473757,0.01096654,0.006832265,0.04572298],"genre_scores_gemma":[0.3812942,0.1618054,0.4125275,0.006276469,0.001732294,0.0009830584,0.02361902,0.002180632,0.009581406],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009653025,"threshold_uncertainty_score":0.04858756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03599498155418739,"score_gpt":0.3369193540830015,"score_spread":0.3009243725288141,"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."}}