{"id":"W2774512527","doi":"","title":"MaxSAT Evaluation 2017: Solver and Benchmark Descriptions","year":2017,"lang":"en","type":"article","venue":"","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Maximum satisfiability problem; Solver; Artificial intelligence; Programming language; Algorithm; Geography; Cartography","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":[0.005541108,0.003915476,0.001293106,0.00389847,0.001149077,0.003359352,0.004754819,0.002856796,0.03848152],"category_scores_gemma":[0.02601074,0.001441386,0.001883902,0.007000375,0.0008448453,0.003799113,0.001954806,0.003386888,0.01384226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003044014,"about_ca_system_score_gemma":0.005211662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01330914,"about_ca_topic_score_gemma":0.02477744,"domain_scores_codex":[0.9933756,0.002383038,0.0006657663,0.0007401229,0.002137366,0.0006980859],"domain_scores_gemma":[0.9890583,0.004934408,0.0004137345,0.001926378,0.003249444,0.0004176998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009897418,0.0008246771,0.00105821,0.002640121,0.00022017,0.0001439834,0.00007281335,0.06487906,0.001518326,0.01005903,0.8283129,0.08928095],"study_design_scores_gemma":[0.003769342,0.001006913,0.003387958,0.001557177,0.0004209549,0.0006133187,0.0004156021,0.4400514,0.02473586,0.03925009,0.4845724,0.000218983],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.09873224,0.01667428,0.14893,0.009447478,0.004256544,0.002557447,0.3667576,0.1171783,0.2354662],"genre_scores_gemma":[0.1184455,0.005023957,0.2646935,0.002851783,0.0003843008,0.002120455,0.5598631,0.0205858,0.02603165],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03848152,"threshold_uncertainty_score":0.1287335,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05351257202851611,"score_gpt":0.3038087786782595,"score_spread":0.2502962066497433,"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."}}