{"id":"W2949244450","doi":"10.48550/arxiv.1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Selection (genetic algorithm); Benchmark (surveying); Set (abstract data type); Task (project management); Exploit; Variety (cybernetics); Data mining; Range (aeronautics); Algorithm; Selection algorithm; Interface (matter); Machine learning; Artificial intelligence; 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":[0.0002893436,0.0002261328,0.0002170898,0.0002438491,0.0001550305,0.0002369558,0.001386928,0.0002640366,0.00002231907],"category_scores_gemma":[0.00005459138,0.0002613053,0.0001330213,0.0005218363,0.00003645632,0.0008306199,0.001077457,0.0004625609,0.00005951491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001111968,"about_ca_system_score_gemma":0.0003773803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005510968,"about_ca_topic_score_gemma":0.000006105357,"domain_scores_codex":[0.9983711,0.0001431362,0.0001550567,0.0009923589,0.00007898374,0.0002593407],"domain_scores_gemma":[0.9985182,0.00009713914,0.0002405641,0.0008338107,0.000139928,0.0001703103],"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":[0.0001090587,0.0003826393,0.006466602,0.0003073203,0.0002372755,0.00007307393,0.0005426131,0.1080908,0.00003539366,0.6355134,0.1209048,0.1273371],"study_design_scores_gemma":[0.0003106065,0.00006811928,0.0007015497,0.00002812306,0.00003081326,0.000003399411,0.00001524498,0.8970097,0.00003195865,0.05591364,0.04560389,0.0002829052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003337697,0.00005425198,0.9906346,0.0003727272,0.0005768063,0.0003328251,0.00007032369,0.0007174524,0.003903313],"genre_scores_gemma":[0.8297695,0.0001544161,0.1540441,0.0002531198,0.0005335854,0.000009999713,0.00124949,0.00005897258,0.01392685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8365905,"threshold_uncertainty_score":0.9999839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06976755450058429,"score_gpt":0.200878132000168,"score_spread":0.1311105774995837,"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."}}