{"id":"W2153904215","doi":"10.1609/aaai.v26i1.8142","title":"Predicting Satisfiability at the Phase Transition","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Western Canada Research Grid; Compute Canada","keywords":"Satisfiability; Conjecture; Computer science; Range (aeronautics); Decision tree; Classifier (UML); Simple (philosophy); Binary number; Binary classification; Algorithm; Mathematics; Artificial intelligence; Machine learning; Discrete 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":[0.0004772849,0.0001389077,0.0001460362,0.00004076856,0.000394043,0.0002109636,0.0006645474,0.000061353,0.0003595705],"category_scores_gemma":[0.0004318535,0.00009419542,0.0001115088,0.000595856,0.0002546426,0.0003548908,0.0002154349,0.0002179726,0.00003686102],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006742001,"about_ca_system_score_gemma":0.0001252341,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002172165,"about_ca_topic_score_gemma":0.00006360988,"domain_scores_codex":[0.9985318,0.00003910876,0.0004252938,0.0003949866,0.0004056623,0.0002032124],"domain_scores_gemma":[0.9986279,0.0001302233,0.0002372899,0.0003040769,0.0006434586,0.0000570489],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000572778,0.0002231625,0.001182795,0.00003663532,0.00002060952,9.002125e-7,0.004085722,0.0007577728,0.07654446,0.610899,0.0001550878,0.3060365],"study_design_scores_gemma":[0.00006404535,0.00008322908,0.0007092538,0.00008836992,0.00001508725,0.00001995449,0.0008345357,0.2552325,0.6987714,0.04392315,0.0001120236,0.0001464829],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.69651,0.00003241423,0.2604063,0.02821842,0.0008023824,0.0005635525,0.00001811583,0.0001698099,0.01327902],"genre_scores_gemma":[0.997414,0.00002617052,0.001961883,0.0003690119,0.00004168897,0.00001649164,0.000001343814,0.000005544953,0.0001638786],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6222269,"threshold_uncertainty_score":0.3937045,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0556724554641079,"score_gpt":0.2974611224413914,"score_spread":0.2417886669772835,"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."}}