{"id":"W2114600785","doi":"10.1007/978-3-540-74970-7_49","title":"Hierarchical Hardness Models for SAT","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Classifier (UML); Computer science; Boolean satisfiability problem; Solver; Class (philosophy); Artificial intelligence; Machine learning; Algorithm","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"],"consensus_categories":[],"category_scores_codex":[0.002792445,0.0005251133,0.0005467559,0.001010246,0.0003071983,0.0004789129,0.00459212,0.0005050905,0.000006978848],"category_scores_gemma":[0.0002105483,0.0004929572,0.0001938185,0.0006091795,0.0008378753,0.001072188,0.001128861,0.0008844698,0.00002848537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003948134,"about_ca_system_score_gemma":0.0005391894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000619196,"about_ca_topic_score_gemma":0.0000161033,"domain_scores_codex":[0.9955624,0.00004209573,0.0006663135,0.001740132,0.001111814,0.0008771867],"domain_scores_gemma":[0.9966123,0.0006559726,0.0003001522,0.001810769,0.0003878685,0.0002329736],"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":[0.00001079168,0.00001577738,0.000002293505,0.00003717174,0.000004827538,0.00001072179,0.0003409415,0.02202569,0.00003802951,0.3649412,0.00001526214,0.6125573],"study_design_scores_gemma":[0.0001454777,0.00009822566,0.00001554185,0.0001068237,0.000003670342,0.00003014404,3.643119e-8,0.5816592,0.0008397974,0.4146864,0.002049994,0.0003647543],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000102862,0.0002319716,0.9896185,0.0003625629,0.003810707,0.000753553,0.000009392782,0.0002228318,0.004980177],"genre_scores_gemma":[0.005012947,0.00001916058,0.9925345,0.001358867,0.0005630999,0.00002656805,0.000008502393,0.00004131045,0.0004350538],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6121925,"threshold_uncertainty_score":0.9997522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06872056972064919,"score_gpt":0.320588590816526,"score_spread":0.2518680210958768,"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."}}