{"id":"W4366122282","doi":"10.1177/20539517231163174","title":"Recording the ethical provenance of data and automating data stewardship","year":2023,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Ethics in Clinical Research","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; European Commission","keywords":"Stewardship (theology); Interoperability; Data governance; Compromise; Normative; Data science; Data exchange; Computer science; Scale (ratio); Knowledge management; Business; Political science; Data quality; Law; World Wide Web","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":["metaresearch","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02872857,0.0001180225,0.0003119026,0.00001645269,0.0002301497,0.00006576233,0.004130909,0.0004737036,0.00001511717],"category_scores_gemma":[0.06257855,0.00007863441,0.00003926969,0.0005627018,0.0007298228,0.0003061519,0.01893143,0.003391073,0.00002404981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002442842,"about_ca_system_score_gemma":0.0007715325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002323317,"about_ca_topic_score_gemma":0.0001683998,"domain_scores_codex":[0.996647,0.0002183706,0.0005380385,0.00100276,0.001219539,0.0003743111],"domain_scores_gemma":[0.968792,0.01977455,0.0002064541,0.0108597,0.0002067624,0.0001605132],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008879543,0.0001542264,0.01459292,0.003786496,0.0004406323,0.00004795609,0.002195464,7.426586e-7,0.002583247,0.002497203,0.6460282,0.3275841],"study_design_scores_gemma":[0.003410675,0.0003881865,0.07337917,0.004658012,0.0005233822,0.00006557764,0.01173249,0.6258346,0.0003209924,0.01983183,0.259214,0.0006410427],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3772171,0.004983645,0.006176251,0.5641377,0.002152364,0.00402255,0.03664768,0.001154756,0.003508005],"genre_scores_gemma":[0.9168863,0.01538874,0.0460658,0.004825197,0.0016982,0.00001868727,0.01395967,0.00008516086,0.001072209],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6258339,"threshold_uncertainty_score":0.9989082,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8288543813695006,"score_gpt":0.606879055657871,"score_spread":0.2219753257116296,"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."}}