{"id":"W6891699754","doi":"10.4230/lipics.sat.2024.27","title":"Revisiting SATZilla Features in 2024","year":2024,"lang":"en","type":"article","venue":"DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Satisfiability; Preprocessor; Feature selection; Benchmark (surveying); Feature (linguistics); Boolean satisfiability problem; Ranging; Software","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":[0.002112524,0.001921372,0.001025565,0.003250774,0.0006550274,0.002670295,0.002415265,0.001192649,0.00923115],"category_scores_gemma":[0.02435082,0.001228607,0.002129145,0.002575329,0.0007644544,0.003625356,0.001856586,0.002569191,0.003790159],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001585262,"about_ca_system_score_gemma":0.002361937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004591553,"about_ca_topic_score_gemma":0.009366498,"domain_scores_codex":[0.9964758,0.0005314364,0.0003620114,0.0007486172,0.00159247,0.0002896826],"domain_scores_gemma":[0.9874622,0.007511262,0.001130845,0.002176193,0.001554208,0.0001652091],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001814129,0.0006061014,0.03699745,0.001689508,0.0003732601,0.0007509965,0.0004521822,0.1593702,0.03753245,0.02366691,0.09903133,0.6377155],"study_design_scores_gemma":[0.0002299995,0.0003736299,0.008921187,0.0002312287,0.0001310748,0.0004892302,0.00008207285,0.8578078,0.05742762,0.02522364,0.04896281,0.0001197593],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1259784,0.001508207,0.6632838,0.002228304,0.0006304937,0.0004219803,0.01944365,0.177849,0.008656054],"genre_scores_gemma":[0.4527899,0.0003682068,0.4930996,0.0006692968,0.0002005147,0.0006496225,0.0337433,0.01282319,0.005656312],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00923115,"threshold_uncertainty_score":0.03088129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01815246545251966,"score_gpt":0.3067046303418024,"score_spread":0.2885521648892828,"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."}}