{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001843855,0.0003394797,0.0002803911,0.00009042708,0.0005222497,0.0006722731,0.003917865,0.000317596,0.00006046448],"category_scores_gemma":[0.0005714842,0.0002234198,0.0001797625,0.0002171433,0.0003720122,0.0003742844,0.001534342,0.000668329,0.001928484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001338187,"about_ca_system_score_gemma":0.000221185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005245222,"about_ca_topic_score_gemma":0.00005050739,"domain_scores_codex":[0.9969116,0.0003109743,0.0007456567,0.0008866445,0.0005361286,0.0006090162],"domain_scores_gemma":[0.9961141,0.0005929897,0.0004066399,0.002434554,0.0003237457,0.0001279576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000791613,0.00002499851,0.000002012304,0.0000130881,0.00001464358,0.00000286061,0.0004092039,0.00008854568,0.0003062198,0.6627294,0.0002712581,0.3361298],"study_design_scores_gemma":[0.000009520721,0.00005554186,0.00002716256,0.0001068884,0.000008330531,0.000004110394,0.00007742041,0.06197793,0.07335153,0.8402766,0.02372332,0.0003816425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003258523,0.0008730126,0.969776,0.005012633,0.005545693,0.0004921553,0.000008937476,0.0002920933,0.01767363],"genre_scores_gemma":[0.8233229,0.002238571,0.1705026,0.0004685709,0.001196282,0.0004036368,0.000009214188,0.00006692309,0.001791251],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8229971,"threshold_uncertainty_score":0.9988486,"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."}}