{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6136017,0.001781213,0.003273997,0.01096256,0.01281303,0.02474861,0.009169281,0.005932034,0.008165064],"category_scores_gemma":[0.8245074,0.002514798,0.003699622,0.01689539,0.0319167,0.0309354,0.03136292,0.01429951,0.003042398],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008998806,"about_ca_system_score_gemma":0.03322365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003496067,"about_ca_topic_score_gemma":0.002851013,"domain_scores_codex":[0.1901652,0.6991874,0.04312016,0.01641452,0.04823031,0.002882418],"domain_scores_gemma":[0.07625436,0.6893801,0.03775667,0.1586414,0.03501413,0.002953338],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0006517494,0.000234672,0.01402511,0.006569583,0.0007381627,0.0005767375,0.08511855,0.001682509,0.001603258,0.4118535,0.02683337,0.4501129],"study_design_scores_gemma":[0.0002578154,0.0002645628,0.005460276,0.01299879,0.0003628393,0.001521971,0.032299,0.006756328,0.004721781,0.7153331,0.2195723,0.0004513147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01638436,0.008975896,0.8341309,0.1085288,0.003850566,0.005265143,0.0009036844,0.0009960423,0.0209647],"genre_scores_gemma":[0.217477,0.005412315,0.7376012,0.01499823,0.003048864,0.01599152,0.0007123672,0.0009288929,0.003829663],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9908307,"threshold_uncertainty_score":0.4764979,"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."}}