{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0253634,0.001880629,0.002409309,0.00303828,0.001191059,0.002757957,0.003423091,0.002074901,0.006169471],"category_scores_gemma":[0.0873878,0.0007423947,0.002468631,0.002557761,0.001839936,0.002244723,0.002968306,0.004728304,0.001853798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808033,"about_ca_system_score_gemma":0.002747644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00315795,"about_ca_topic_score_gemma":0.002717994,"domain_scores_codex":[0.9831275,0.01385606,0.000498175,0.001034524,0.001235877,0.0002478488],"domain_scores_gemma":[0.9460806,0.04605359,0.001732652,0.003062017,0.00242567,0.0006453834],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003472246,0.0001259724,0.006361534,0.0006867863,0.0008201859,0.0004502714,0.0003276562,0.5854136,0.001397091,0.2645948,0.02397639,0.1154985],"study_design_scores_gemma":[0.0000365085,0.00005146364,0.0004203548,0.00008199604,0.00003323563,0.00006769356,0.00003203804,0.8014567,0.0003688719,0.1930154,0.004409085,0.00002653113],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003253617,0.0008246919,0.99264,0.0008629017,0.0001379313,0.0001019071,0.0004471395,0.0006242377,0.001107567],"genre_scores_gemma":[0.2131419,0.00176862,0.7728155,0.001159583,0.0008111825,0.001704291,0.004494117,0.001376153,0.002728569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0253634,"threshold_uncertainty_score":0.1341361,"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."}}