{"id":"W1878518276","doi":"10.1016/j.artint.2016.09.006","title":"The Configurable SAT Solver Challenge (CSSC)","year":2016,"lang":"en","type":"preprint","venue":"Artificial Intelligence","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Solver; Boolean satisfiability problem; Benchmark (surveying); Computer science; Competition (biology); Satisfiability; Problem solver; Series (stratigraphy); Theoretical computer science; Programming language; Software engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005603467,0.00134448,0.001760103,0.0008638992,0.001745275,0.005455625,0.004856703,0.004953271,0.02653402],"category_scores_gemma":[0.03761911,0.0009907009,0.001808406,0.002043415,0.003437317,0.006235536,0.00547053,0.0098663,0.006343056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00271847,"about_ca_system_score_gemma":0.006386487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005019538,"about_ca_topic_score_gemma":0.008124997,"domain_scores_codex":[0.9933398,0.002637821,0.0002594445,0.00148175,0.00180765,0.0004735432],"domain_scores_gemma":[0.9685971,0.02301684,0.0005969106,0.004932881,0.001879459,0.0009767985],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005533268,0.000232002,0.001015944,0.0015098,0.0001632088,0.0004416153,0.0002955954,0.05427374,0.002256016,0.4279452,0.3592065,0.152107],"study_design_scores_gemma":[0.0002834943,0.00007276817,0.000476155,0.0002847199,0.00005611148,0.0002947893,0.0001805046,0.139121,0.003639061,0.7649072,0.09062708,0.00005703893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07460313,0.01445996,0.5902364,0.1452973,0.01002817,0.0007821065,0.0153025,0.01564884,0.1336415],"genre_scores_gemma":[0.5331922,0.005184337,0.3872071,0.01630261,0.004246695,0.0007708067,0.02090256,0.004440617,0.02775319],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02653402,"threshold_uncertainty_score":0.08876514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1191412167219816,"score_gpt":0.3493124873586114,"score_spread":0.2301712706366297,"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."}}