{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000211564,0.0004034643,0.0003573567,0.0003005108,0.0003137889,0.0005873546,0.00119816,0.000277144,0.00001216805],"category_scores_gemma":[0.00003286887,0.0004768446,0.0002223799,0.001082471,0.00003510218,0.000436353,0.0009359654,0.0004251877,0.00003032018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001510024,"about_ca_system_score_gemma":0.001241165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002493246,"about_ca_topic_score_gemma":0.000001491986,"domain_scores_codex":[0.9977217,0.00008511723,0.0003852566,0.001108824,0.000285675,0.0004134596],"domain_scores_gemma":[0.9979926,0.0001469491,0.0002902741,0.0009569298,0.0004338502,0.0001793804],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005485347,0.0006247082,0.004031088,0.0008340072,0.0004888123,0.000009188139,0.0000478895,0.006510553,0.1341045,0.771212,0.0819611,0.0001212165],"study_design_scores_gemma":[0.001345231,0.0001496606,0.05585505,0.0003492419,0.0002118834,3.566418e-8,9.120941e-7,0.5375237,0.1769221,0.002705642,0.2224719,0.002464629],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05814683,0.0002955178,0.9337014,0.001489055,0.00169802,0.001673084,0.001083114,0.001857121,0.00005585041],"genre_scores_gemma":[0.71416,0.00008162917,0.2819969,0.001118035,0.001271092,0.00115968,0.00000730558,0.00009392725,0.0001114125],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7685064,"threshold_uncertainty_score":0.9997683,"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."}}