{"id":"W4416987049","doi":"10.1101/2025.11.21.689756","title":"Selector: A General Python Library for Diverse Subset Selection","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Computational Physics and Python Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University; Queen's University","funders":"National Institute of General Medical Sciences; Social Sciences and Humanities Research Council of Canada; National Institutes of Health; Canadian Institutes of Health Research; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; McMaster University; Queen's University; Canada Research Chairs","keywords":"Python (programming language); Upload; Interoperability; Software; Extensibility; User interface","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":[0.003604372,0.002259021,0.002070137,0.002551655,0.001434844,0.002945972,0.003798923,0.000784473,0.05844517],"category_scores_gemma":[0.007836023,0.001562183,0.002487143,0.002783723,0.0009074377,0.003385614,0.004006239,0.002886384,0.04728405],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006911215,"about_ca_system_score_gemma":0.003350979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002363187,"about_ca_topic_score_gemma":0.004034637,"domain_scores_codex":[0.9976094,0.0004857299,0.0002493199,0.0005022788,0.0009025089,0.0002508156],"domain_scores_gemma":[0.9979608,0.000751329,0.0001612034,0.0005271484,0.0004091833,0.0001903643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007310279,0.0001414696,0.004033365,0.002108179,0.0004149559,0.000359973,0.0004315118,0.009183584,0.01296318,0.01351242,0.8133967,0.1427236],"study_design_scores_gemma":[0.0005432834,0.0001776668,0.006560527,0.0003924022,0.0001519594,0.000827278,0.0002062953,0.1096976,0.03344345,0.06104681,0.7865452,0.0004075394],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.003839456,0.0004156687,0.5017608,0.0003588808,0.0002693524,0.0006354811,0.09908764,0.3822618,0.01137096],"genre_scores_gemma":[0.03009691,0.0008925367,0.5488457,0.001711021,0.0002577976,0.005057816,0.2402649,0.1591765,0.01369673],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.05844517,"threshold_uncertainty_score":0.1955186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01493201655033337,"score_gpt":0.2334349480658977,"score_spread":0.2185029315155643,"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."}}