{"id":"W4412017881","doi":"10.1177/23328584251352814","title":"Data Deidentification for Data Sharing in Education and Psychological Research: Importance, Barriers, and Techniques","year":2025,"lang":"en","type":"article","venue":"AERA Open","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Canada Excellence Research Chairs, Government of Canada; Eunice Kennedy Shriver National Institute of Child Health and Human Development; Office of Special Education Programs, Office of Special Education and Rehabilitative Services","keywords":"Psychology; Data sharing; Applied psychology; Medicine","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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01977534,0.00005080527,0.0001207679,0.0002185845,0.000190183,0.00152661,0.004984203,0.0000401433,0.00004803386],"category_scores_gemma":[0.006261542,0.00004132068,0.000004089683,0.0005244267,0.0001015652,0.001941274,0.00859369,0.00009227095,0.000005451955],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001627654,"about_ca_system_score_gemma":0.00007242298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003503008,"about_ca_topic_score_gemma":0.001957001,"domain_scores_codex":[0.9980321,0.0001605426,0.0003707371,0.001035203,0.000270792,0.000130661],"domain_scores_gemma":[0.9963911,0.000484645,0.00007072206,0.002908897,0.00009512007,0.00004953515],"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":[0.00003055605,0.00006543661,0.01624172,0.00001218319,0.000004175882,4.118736e-7,0.00007054937,2.307445e-8,0.00005207895,0.05538665,0.4960843,0.4320519],"study_design_scores_gemma":[0.0001712495,0.00002076565,0.0387345,0.00004726521,0.000004867319,7.288809e-7,0.00174294,0.0005910123,0.00003766527,0.2331511,0.7254343,0.00006360279],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6336772,0.00626227,0.06367683,0.1265866,0.001884542,0.01966873,0.004743806,0.0001947793,0.1433052],"genre_scores_gemma":[0.8806764,0.001875285,0.09223961,0.004244672,0.0001123965,0.000810119,0.005015427,0.00001596451,0.01501012],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4319883,"threshold_uncertainty_score":0.9995099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8329394390274139,"score_gpt":0.6719423566313527,"score_spread":0.1609970823960611,"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."}}