{"id":"W2913189977","doi":"10.48550/arxiv.1902.05454","title":"Procrastinating with Confidence: Near-Optimal, Anytime, Adaptive Algorithm Configuration","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Procrastination; Computer science; Parameterized complexity; Property (philosophy); Heuristic; Algorithm; Work (physics); Running time; Mathematical optimization; Mathematics; Artificial intelligence","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001740151,0.0006238859,0.0008761582,0.0006215397,0.0005312487,0.000790311,0.002301399,0.0004852154,0.0008298462],"category_scores_gemma":[0.001115761,0.0005471336,0.0002410861,0.001859221,0.0008423601,0.001147789,0.001480051,0.001678027,0.001419287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004690244,"about_ca_system_score_gemma":0.001508928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001871061,"about_ca_topic_score_gemma":0.00003956457,"domain_scores_codex":[0.9941435,0.0005153564,0.0006531869,0.002563238,0.001306402,0.0008183318],"domain_scores_gemma":[0.9923722,0.00167753,0.001063425,0.001745021,0.002790934,0.0003508621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002761978,0.0000905011,0.0008705803,0.0000234263,0.0001133547,0.0004875021,0.0003761482,0.9845583,0.000023265,0.002021723,0.0006881717,0.01047084],"study_design_scores_gemma":[0.001033034,0.000428937,0.001192584,0.0001950867,0.00006139182,0.0000215475,0.002104493,0.9771705,0.0004047457,0.01580684,0.0008606454,0.0007201998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04708124,0.00006985963,0.9464799,0.00008209798,0.0003929113,0.001402494,0.0001307477,0.0001700059,0.004190708],"genre_scores_gemma":[0.9614579,0.00004449406,0.02021924,0.00004560483,0.0001519395,0.000007415335,0.00005206568,0.00006079471,0.01796057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9262607,"threshold_uncertainty_score":0.999698,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1731089549398051,"score_gpt":0.2948445957333864,"score_spread":0.1217356407935813,"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."}}