{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001688484,0.000403506,0.0003631933,0.0004109836,0.0003367311,0.0007186673,0.002403392,0.0002553298,0.00002449822],"category_scores_gemma":[0.0002801534,0.0003791172,0.00006483372,0.0004308331,0.0003157593,0.0004954924,0.0004514234,0.0007269916,0.00009478995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002280941,"about_ca_system_score_gemma":0.0003915366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001996169,"about_ca_topic_score_gemma":0.00002705653,"domain_scores_codex":[0.9963933,0.00009563969,0.0005155412,0.001491238,0.001063018,0.0004412798],"domain_scores_gemma":[0.9973508,0.0003547898,0.0004499721,0.001454636,0.000253956,0.0001358915],"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":[0.000001846156,0.00000745145,0.00002929817,0.00001708415,0.000003277053,0.000002947711,0.0001781473,0.01295735,0.001447167,0.04602215,0.0001495172,0.9391838],"study_design_scores_gemma":[0.00020795,0.0001554909,0.00007095592,0.0001566125,0.000004908538,0.00001380104,5.530328e-8,0.9576136,0.00251044,0.0257348,0.01300947,0.0005219212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001062465,0.0003811768,0.9921875,0.001079412,0.001112276,0.0002467908,0.000005652065,0.0001970226,0.004683896],"genre_scores_gemma":[0.3031137,0.00006698651,0.6910706,0.003223275,0.0008177691,0.0000223111,0.0001176496,0.00005523446,0.001512507],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9446563,"threshold_uncertainty_score":0.9998661,"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."}}