{"id":"W203732173","doi":"10.1007/978-3-319-09584-4_6","title":"Evaluating Instance Generators by Configuration","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; University of British Columbia","funders":"","keywords":"Benchmark (surveying); Generator (circuit theory); Metric (unit); Computer science; Solver; Satisfiability; Set (abstract data type); Development (topology); Boolean satisfiability problem; Theoretical computer science; Artificial intelligence; Algorithm; Programming language; Mathematics; Power (physics); Engineering","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":[0.004255171,0.002673097,0.002297587,0.003450282,0.0005610989,0.003025922,0.004198576,0.003087553,0.01085392],"category_scores_gemma":[0.02189623,0.001155815,0.001985924,0.002249178,0.001094353,0.005007031,0.001821134,0.003070621,0.003898195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001490207,"about_ca_system_score_gemma":0.001537648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001841275,"about_ca_topic_score_gemma":0.002961011,"domain_scores_codex":[0.9953749,0.001743163,0.0002484731,0.00124595,0.001132819,0.0002547602],"domain_scores_gemma":[0.9790075,0.0162497,0.0005118243,0.00292736,0.0007230085,0.0005805897],"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":[0.002121467,0.0008119576,0.01123292,0.0005392968,0.0006114689,0.0005317684,0.00007958916,0.2551242,0.006903066,0.009770966,0.04531065,0.6669626],"study_design_scores_gemma":[0.0001528267,0.0002626162,0.0009849143,0.00005738421,0.0001449652,0.0002732131,0.00004100525,0.964895,0.007739707,0.02291224,0.002509397,0.00002671129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3399439,0.008676419,0.5652923,0.003324472,0.001553969,0.0008782977,0.005837674,0.05560832,0.01888463],"genre_scores_gemma":[0.731356,0.001012092,0.2433639,0.0006772833,0.0004886922,0.0003096134,0.01288083,0.002879334,0.007032361],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01085392,"threshold_uncertainty_score":0.03630996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02930185925289589,"score_gpt":0.2975607159534128,"score_spread":0.2682588567005169,"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."}}