{"id":"W2995736486","doi":"10.3233/sat190119","title":"MaxSAT Evaluation 2018: New Developments and Detailed Results","year":2019,"lang":"en","type":"article","venue":"Journal on Satisfiability Boolean Modeling and Computation","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"Carnegie Mellon Portugal; National Science Foundation","keywords":"Maximum satisfiability problem; Satisfiability; Boolean satisfiability problem; Series (stratigraphy); Computer science; Radiomics; Theoretical computer science; Artificial intelligence; Algorithm; Boolean function","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":[],"consensus_categories":[],"category_scores_codex":[0.003729757,0.0001601767,0.0001928197,0.0001662472,0.000209437,0.0003575929,0.000190507,0.00008344475,0.000003836594],"category_scores_gemma":[0.0003335642,0.0001461521,0.00003542812,0.0001732448,0.00002080092,0.0008421093,0.00008235444,0.0002726061,0.00002442483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001698435,"about_ca_system_score_gemma":0.0001873414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001287532,"about_ca_topic_score_gemma":0.000002786564,"domain_scores_codex":[0.9977236,0.0003936272,0.0006040182,0.0004475312,0.0006389829,0.0001922781],"domain_scores_gemma":[0.9988642,0.0001448876,0.0002814228,0.0002693886,0.0002696762,0.0001703707],"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":[0.000100316,0.00002849246,0.002396428,0.00001786865,0.00001456233,6.273966e-7,0.001064411,0.2112058,0.0001258856,0.002734965,0.00006339881,0.7822472],"study_design_scores_gemma":[0.001172027,0.0001796403,0.02420705,0.00007515655,0.00001097584,0.00003846203,0.00005013958,0.9368488,0.00006048382,0.03714147,0.00005715583,0.0001586219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4662171,0.00005653847,0.5326582,0.0002420467,0.0002977064,0.0002531503,5.539139e-7,0.00003303947,0.0002416837],"genre_scores_gemma":[0.6526798,0.00003006202,0.3470825,0.0001172442,0.00004305145,0.000003602767,0.000003514288,0.000006119572,0.00003416058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7820886,"threshold_uncertainty_score":0.595991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06352342221819057,"score_gpt":0.3266440326746796,"score_spread":0.263120610456489,"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."}}