{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4716808,0.001493727,0.003763652,0.009951431,0.004885046,0.02345999,0.007209255,0.006502254,0.01262449],"category_scores_gemma":[0.8196675,0.001680194,0.004194365,0.01129075,0.02017683,0.01841384,0.01437092,0.008581602,0.005872608],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.005438542,"about_ca_system_score_gemma":0.01765725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002080776,"about_ca_topic_score_gemma":0.001411568,"domain_scores_codex":[0.4601951,0.3704855,0.04473064,0.03460053,0.08714934,0.002838897],"domain_scores_gemma":[0.07443631,0.6773295,0.02692142,0.1747163,0.04433597,0.002260432],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001858452,0.000372141,0.05496072,0.01622811,0.004669312,0.0006395125,0.008862902,0.008793873,0.002628224,0.2792491,0.07410432,0.5476333],"study_design_scores_gemma":[0.0006551771,0.0009915752,0.02510001,0.009681862,0.001578368,0.001174026,0.001976793,0.01667238,0.01245345,0.6637135,0.2655615,0.0004415484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04064262,0.09516395,0.6213042,0.1292033,0.01917387,0.003347571,0.009023819,0.006527454,0.07561321],"genre_scores_gemma":[0.5869431,0.01821156,0.319281,0.02800192,0.0146158,0.00740254,0.008655816,0.004857499,0.01203076],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5283191,"threshold_uncertainty_score":0.6515115,"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."}}