{"id":"W4398168374","doi":"10.1101/2024.05.16.594622","title":"Enhanced Thompson Sampling by Roulette Wheel Selection for Screening Ultra-Large Combinatorial Libraries","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"AstraZeneca (Canada)","funders":"","keywords":"Roulette; Selection (genetic algorithm); Sampling (signal processing); Fitness proportionate selection; Computer science; Artificial intelligence; Statistics; Machine learning; Mathematics; Computer vision; Genetic algorithm","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00085732,0.0007646593,0.0007098863,0.0003185458,0.0006055308,0.002342335,0.001767647,0.000724457,0.00001172424],"category_scores_gemma":[0.0002362586,0.000801615,0.0002666529,0.0007773138,0.00006416789,0.001005549,0.001804461,0.001307128,0.00002902022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002003098,"about_ca_system_score_gemma":0.0005285488,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000382024,"about_ca_topic_score_gemma":8.630032e-7,"domain_scores_codex":[0.9955804,0.0001381324,0.0007087489,0.001973559,0.0006349683,0.0009641388],"domain_scores_gemma":[0.9971368,0.0002813301,0.000469285,0.001384261,0.0004256465,0.0003026325],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006915164,0.0002207008,0.0001056076,0.0007980652,0.0002440772,0.00000872533,0.00006681177,0.000189462,0.9352064,0.05270607,0.0102995,0.00008543942],"study_design_scores_gemma":[0.00150026,0.0001852939,0.0005750264,0.00149999,0.0001468737,4.549441e-8,0.000003746798,0.09675731,0.8407416,0.0005937305,0.05604218,0.001953984],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01913398,0.001938912,0.9662537,0.0004644647,0.008877663,0.0009688794,0.0007373901,0.001611591,0.00001340225],"genre_scores_gemma":[0.7674927,0.0001097187,0.2295857,0.0002357257,0.001904521,0.0004758147,0.000006826419,0.0001772598,0.00001173317],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7483587,"threshold_uncertainty_score":0.9994435,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01602251742608944,"score_gpt":0.2384339786619829,"score_spread":0.2224114612358934,"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."}}