{"id":"W4403152041","doi":"10.1101/2024.10.04.615514","title":"Defining a tandem repeat catalog and variation clusters for genome-wide analyses","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Forensic and Genetic Research","field":"Biochemistry, Genetics and Molecular Biology","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Variation (astronomy); Genome; Population; Computer science; Database; Computational biology; Information retrieval; Biology; Genetics; Medicine","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":[0.000612341,0.0003816863,0.0003629581,0.0001782518,0.0001415186,0.0002201138,0.0002836679,0.0005364791,0.000005584872],"category_scores_gemma":[0.0004243833,0.0003832225,0.0001683242,0.0001807236,0.0001424634,0.000004318384,0.0008809944,0.0003383451,0.00001418269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007138307,"about_ca_system_score_gemma":0.000512746,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000516862,"about_ca_topic_score_gemma":0.000010632,"domain_scores_codex":[0.9977556,0.0000784129,0.0003810535,0.001110119,0.0002255935,0.0004492479],"domain_scores_gemma":[0.9984489,0.00005185794,0.0001657791,0.0008254523,0.0003177197,0.0001902691],"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":[0.00008092366,0.00003547111,0.00412482,0.0006741906,0.0005835363,0.00001763226,0.00002249338,0.0002886556,0.9922965,0.0002908296,0.00157416,0.00001077809],"study_design_scores_gemma":[0.001911443,0.0007237737,0.1964531,0.0005904063,0.0009862046,2.689503e-7,0.00002690263,0.004353372,0.759093,0.000134931,0.03335371,0.00237286],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9747252,0.01266658,0.01042123,0.0003004186,0.0005633391,0.000844862,0.0003788953,0.00007436277,0.00002507075],"genre_scores_gemma":[0.9908947,0.0008189518,0.007268495,0.0002010884,0.0004158442,0.0002412826,0.00001162854,0.0001028715,0.00004508415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2332035,"threshold_uncertainty_score":0.999862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01920968624667846,"score_gpt":0.2772954510363662,"score_spread":0.2580857647896877,"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."}}