{"id":"W4414527039","doi":"10.1007/978-3-031-96684-2_12","title":"Can ChatGPT Make Explanatory Inferences? Benchmarks for Abductive Reasoning","year":2025,"lang":"en","type":"book-chapter","venue":"Synthese Library/Synthese library","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Abductive reasoning; Generative grammar; Set (abstract data type); Inference; Verbal reasoning; Generative model; Non-monotonic logic; Visual reasoning","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0003705379,0.001684559,0.001790111,0.001452892,0.0004902965,0.001369522,0.005715123,0.001428436,0.002371229],"category_scores_gemma":[0.000453297,0.001664885,0.0009094501,0.0003738245,0.0003422139,0.005826918,0.003167441,0.001542088,0.00008291128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001024521,"about_ca_system_score_gemma":0.002466327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002068427,"about_ca_topic_score_gemma":0.000007242699,"domain_scores_codex":[0.992974,0.0002334335,0.001477026,0.002934991,0.0009371482,0.001443341],"domain_scores_gemma":[0.9920549,0.002524585,0.0009517458,0.003581237,0.00007919934,0.0008083484],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007650472,0.0000528471,0.0001228351,0.0004144548,0.0003708823,0.0001419439,0.000845641,0.00002721201,0.0000123993,0.9001854,0.03297867,0.06477119],"study_design_scores_gemma":[0.0003451994,0.0001212792,0.00001746298,0.003570731,0.0001200463,0.000034423,0.00008279616,0.008630859,0.002013608,0.4175403,0.5655807,0.001942628],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0000713871,0.003941362,0.02739855,0.01582134,0.002575607,0.002204887,0.001216144,0.002232235,0.9445385],"genre_scores_gemma":[0.01076857,0.001648465,0.1779249,0.00625407,0.002710192,0.0008336852,0.001068765,0.0006519241,0.7981394],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.532602,"threshold_uncertainty_score":0.9998679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01453471825925627,"score_gpt":0.214162609239223,"score_spread":0.1996278909799667,"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."}}