{"id":"W2896201656","doi":"10.1101/448795","title":"Model Selection for Biological Crystallography","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Enzyme Structure and Function","field":"Materials Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Lawrence Berkeley National Laboratory; National Institutes of Health; Western Canada Research Grid; Los Alamos National Laboratory; Compute Canada","keywords":"Overfitting; Model selection; Computer science; Selection (genetic algorithm); Noise (video); Inference; Algorithm; Experimental data; Information Criteria; Data mining; Artificial intelligence; Biological system; Statistical physics; Mathematics; Statistics; Biology; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006358409,0.0004707238,0.0004615038,0.000233374,0.0002961957,0.0002233714,0.0004484113,0.0008278356,0.0001133806],"category_scores_gemma":[0.0001695042,0.000428273,0.0002352766,0.0003037662,0.0002007628,0.0001520941,0.0002539011,0.0003646026,0.00004543759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001348385,"about_ca_system_score_gemma":0.0003318986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000149432,"about_ca_topic_score_gemma":0.000002985867,"domain_scores_codex":[0.9975343,0.00008696233,0.0004374423,0.001126295,0.0002480734,0.000566977],"domain_scores_gemma":[0.9981342,0.00005106109,0.000348148,0.0006593246,0.0006348541,0.0001724117],"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":[0.0000789999,0.0000452409,0.001433984,0.0001265128,0.00003358093,8.344788e-7,0.000003818916,0.0004297505,0.9943976,0.0008209241,0.002628357,4.200245e-7],"study_design_scores_gemma":[0.0004879282,0.0002671628,0.006205707,0.0001134528,0.0001222806,1.753647e-8,0.000001144958,0.01373579,0.9721881,0.0002207313,0.005728179,0.0009295399],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8926265,0.0002028588,0.1028388,0.00005758962,0.002400846,0.0008076499,0.0003453992,0.0006988849,0.00002144423],"genre_scores_gemma":[0.9502644,0.00004565675,0.04766961,0.0002194071,0.001352105,0.0003663987,7.841663e-7,0.00007549158,0.000006159387],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0576379,"threshold_uncertainty_score":0.9998169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02593963778374599,"score_gpt":0.2331828774433912,"score_spread":0.2072432396596452,"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."}}