{"id":"W4403536217","doi":"10.1145/3691620.3695522","title":"Diagnosis via Proofs of Unsatisfiability for First-Order Logic with Relational Objects","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Logic, programming, and type systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematical proof; Computer science; First-order logic; Order (exchange); Theoretical computer science; Programming language; Calculus (dental); Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006130073,0.0002850518,0.0004228266,0.0001158411,0.00008783105,0.0001461055,0.0006845911,0.0002842224,0.00004538735],"category_scores_gemma":[0.0001222639,0.0001901974,0.0001714823,0.0003300279,0.00009818993,0.00009973923,0.000972477,0.0003170412,0.00003001821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000882839,"about_ca_system_score_gemma":0.0003668206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003502696,"about_ca_topic_score_gemma":0.0006550765,"domain_scores_codex":[0.9978824,0.00006452996,0.0004622485,0.0009048639,0.0004102651,0.0002756428],"domain_scores_gemma":[0.997964,0.0004141513,0.0002571408,0.0008588685,0.0004311643,0.00007473081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001582504,0.0002221429,0.0156335,0.002820639,0.0001924019,0.000007138764,0.001208265,0.00191823,0.000001998702,0.962312,0.001358257,0.01430954],"study_design_scores_gemma":[0.0003178831,0.000355742,0.003013112,0.00008910859,0.00006033207,0.00001069587,0.0000197319,0.04400295,0.0002508307,0.94736,0.00407748,0.0004421265],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009429189,0.0006111842,0.9875803,0.001232122,0.001006656,0.002196181,0.000009668781,0.0003136084,0.006107355],"genre_scores_gemma":[0.8792399,0.000009766672,0.1184407,0.00005655644,0.0001178929,0.001318143,0.00002497499,0.00001768713,0.0007744564],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8782969,"threshold_uncertainty_score":0.7756025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268418901927705,"score_gpt":0.2616805887919561,"score_spread":0.228996399772679,"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."}}