{"id":"W2757536903","doi":"10.1038/nmeth.4457","title":"The inconvenience of data of convenience: computational research beyond post-mortem analyses","year":2017,"lang":"en","type":"letter","venue":"Nature Methods","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; University of Toronto","funders":"","keywords":"Computer science; Data science; Computational biology; Biology","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":["metaresearch","open_science","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.01861753,0.0003416085,0.0008247156,0.0005559954,0.000838579,0.0002386242,0.01693178,0.001449333,0.00001719469],"category_scores_gemma":[0.01126606,0.0002375737,0.0001794868,0.001017898,0.001417939,0.0005760213,0.004453454,0.01075689,0.000005934488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008561509,"about_ca_system_score_gemma":0.001844446,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006406156,"about_ca_topic_score_gemma":0.00002443318,"domain_scores_codex":[0.9871143,0.007108137,0.0009670443,0.001326359,0.002784193,0.0006999826],"domain_scores_gemma":[0.9717197,0.01676521,0.001563539,0.006712103,0.003140232,0.00009923273],"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":[0.00004031158,0.00005687545,0.001373264,0.00158723,0.0003233919,0.0002493818,0.001272477,0.0003460797,0.0003968434,0.02258267,0.7086737,0.2630978],"study_design_scores_gemma":[0.0003112423,0.0003232881,0.008020917,0.0004180604,0.00006272885,0.0001260141,0.0000622174,0.1166282,0.0007926239,0.0312267,0.8414956,0.0005324642],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.0001852313,0.009455694,0.3208223,0.6626823,0.00303223,0.0008367712,0.000385688,0.00008584493,0.00251399],"genre_scores_gemma":[0.006126866,0.00008331834,0.9540092,0.03738661,0.001168987,0.00002133845,0.0003487633,0.000039595,0.0008153638],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6331869,"threshold_uncertainty_score":0.999847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3262454615031201,"score_gpt":0.6153864163255818,"score_spread":0.2891409548224617,"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."}}