{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2674653,0.001001593,0.001684286,0.006923207,0.008271136,0.02391726,0.004589269,0.005438813,0.00495157],"category_scores_gemma":[0.4156949,0.001628726,0.001579221,0.008439196,0.01873624,0.02564692,0.02201013,0.01006311,0.00724993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007388806,"about_ca_system_score_gemma":0.07034394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007694867,"about_ca_topic_score_gemma":0.006580155,"domain_scores_codex":[0.5891103,0.3020054,0.03326748,0.01663312,0.05370091,0.005282895],"domain_scores_gemma":[0.3727506,0.3076355,0.04934881,0.1803592,0.07998396,0.009922008],"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":[0.0002873417,0.0002052332,0.01957143,0.002788953,0.0001599358,0.0007335085,0.04245264,0.002425582,0.005689092,0.4037846,0.08508065,0.436821],"study_design_scores_gemma":[0.00006014149,0.00009039412,0.005632531,0.003774822,0.00008433673,0.0007733474,0.01057391,0.003627832,0.00769236,0.3282647,0.6392097,0.0002158651],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01853462,0.006150626,0.7579026,0.1284834,0.003498808,0.004799468,0.001956463,0.003050495,0.07562348],"genre_scores_gemma":[0.1936488,0.007178456,0.7603718,0.01207292,0.002307315,0.00392321,0.003996514,0.001971159,0.01452981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9954107,"threshold_uncertainty_score":0.9033457,"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."}}