{"id":"W4392557862","doi":"10.46471/gigabyte.113","title":"Julearn: an easy-to-use library for leakage-free evaluation and inspection of ML models","year":2024,"lang":"en","type":"article","venue":"Gigabyte","topic":"Functional Brain Connectivity Studies","field":"Neuroscience","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deutsche Forschungsgemeinschaft; National Institute on Aging; DoD Alzheimer's Disease Neuroimaging Initiative; Canadian Institutes of Health Research; Northern California Institute for Research and Education; Foundation for the National Institutes of Health","keywords":"Python (programming language); Generalizability theory; Computer science; Documentation; Pipeline (software); Artificial intelligence; Open source; Software engineering; Machine learning; Data science; Software; Programming language; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003188126,0.0001079005,0.0001234062,0.0001784205,0.0001490081,0.0001241481,0.0001208139,0.00004408431,0.00001767197],"category_scores_gemma":[0.003418883,0.000104105,0.00004487257,0.0003283189,0.00007446273,0.001680107,0.0001322291,0.0000866394,0.00001166473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003149596,"about_ca_system_score_gemma":0.00006326297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001668539,"about_ca_topic_score_gemma":0.00001890848,"domain_scores_codex":[0.9988093,0.0001047477,0.0001488478,0.0004851522,0.0003088292,0.0001430792],"domain_scores_gemma":[0.9980004,0.001573579,0.00003327462,0.0002751511,0.00005976723,0.00005777603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000991683,0.0003484288,0.001001739,0.0006208386,0.0001093367,0.0000146018,0.005274603,0.02012407,0.5448735,0.2036345,0.1360376,0.08696906],"study_design_scores_gemma":[0.001027416,0.00115236,0.009328189,0.0001454829,0.00009600009,0.00002495491,0.0001965388,0.6122923,0.1477377,0.1906083,0.03697623,0.0004144731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9688192,0.0004160629,0.01393106,0.009630556,0.001348871,0.001406147,0.0002319656,0.0008781292,0.003337995],"genre_scores_gemma":[0.9962262,0.00004109572,0.001445384,0.0011134,0.0001570227,0.0001179938,0.000006744035,0.00004003987,0.0008521102],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5921683,"threshold_uncertainty_score":0.4245278,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1050477757235592,"score_gpt":0.3104633408325803,"score_spread":0.2054155651090211,"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."}}