{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0270087,0.003165847,0.002190009,0.006257552,0.001577457,0.008258489,0.003660685,0.001824471,0.01920052],"category_scores_gemma":[0.05806659,0.001293497,0.00210701,0.006802089,0.001496938,0.008768754,0.004682876,0.006034166,0.007381381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004481051,"about_ca_system_score_gemma":0.006188413,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006527297,"about_ca_topic_score_gemma":0.007308567,"domain_scores_codex":[0.9667131,0.01231264,0.001919923,0.002526267,0.0141615,0.002366471],"domain_scores_gemma":[0.9734476,0.01009717,0.0007597798,0.003404443,0.01080509,0.001485985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002298959,0.001140771,0.003521606,0.003472674,0.0003616443,0.000212982,0.0003529053,0.02607729,0.005467865,0.0637282,0.4056265,0.4877386],"study_design_scores_gemma":[0.0007251049,0.001426428,0.00607145,0.003932602,0.0004410751,0.0005376498,0.000509538,0.1003149,0.02462181,0.05963809,0.8014976,0.0002838607],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1170402,0.1705127,0.2847382,0.03100869,0.01644008,0.002744081,0.04138402,0.03763797,0.2984941],"genre_scores_gemma":[0.3020131,0.04967615,0.3736862,0.008381559,0.004644119,0.002661964,0.1819914,0.02970488,0.04724078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0270087,"threshold_uncertainty_score":0.1428373,"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."}}