{"id":"W2953773463","doi":"10.48550/arxiv.1907.01463","title":"Reproducibility in Machine Learning for Health","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Reproducibility; Field (mathematics); Computer science; Machine learning; Scale (ratio); Data science; Artificial intelligence; Human health; Order (exchange); Work (physics); Medicine; Engineering; Business","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":[0.00399318,0.0003510246,0.0006479723,0.000395889,0.0001901739,0.00008399857,0.002042335,0.0002959782,0.000015646],"category_scores_gemma":[0.0009971749,0.0004244682,0.00022728,0.0006579538,0.00004929171,0.0002339563,0.002383369,0.001929242,0.00004577946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007384105,"about_ca_system_score_gemma":0.0007854616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003391568,"about_ca_topic_score_gemma":0.0006985691,"domain_scores_codex":[0.9938064,0.0008299758,0.0004443421,0.004159969,0.0001156075,0.0006437601],"domain_scores_gemma":[0.9940546,0.0003856716,0.0005525702,0.004641614,0.0001696657,0.0001958873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000437926,0.00007075506,0.2272662,0.0008336361,0.00001731441,0.00002776369,0.0005529648,0.7411935,0.000001121248,0.02720053,0.0001353167,0.002657128],"study_design_scores_gemma":[0.0005378316,0.0001786359,0.02359192,0.0001750103,0.000006030628,0.000002774632,0.00002287547,0.9574603,0.000005366706,0.01465112,0.002992684,0.0003754193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1885877,0.0005249666,0.8014356,0.004566647,0.001429838,0.002025022,0.00002430845,0.0005956825,0.0008101235],"genre_scores_gemma":[0.9917451,0.000145925,0.005332304,0.0004024811,0.00008184765,0.000004110472,0.00005549728,0.00003093179,0.002201799],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8031574,"threshold_uncertainty_score":0.9998207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1046919510731376,"score_gpt":0.2557471094962648,"score_spread":0.1510551584231272,"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."}}