{"id":"W3043243165","doi":"10.2196/18055","title":"Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study","year":2020,"lang":"en","type":"article","venue":"Journal of Medical Internet Research","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Health and Long-Term Care","keywords":"Computer science; Word (group theory); Natural language processing; Code (set theory); Word embedding; Artificial intelligence; Representation (politics); Embedding; Information retrieval; Source code; Linguistics","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":[0.01093819,0.0001010204,0.0002802603,0.0002285046,0.00009599318,0.0002192787,0.005546066,0.00005369083,0.0001134584],"category_scores_gemma":[0.01367398,0.00005825358,0.00008593598,0.0007519983,0.0001306453,0.0006479058,0.002692499,0.002398115,0.00001458737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008124035,"about_ca_system_score_gemma":0.0003884512,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004235492,"about_ca_topic_score_gemma":0.000008545147,"domain_scores_codex":[0.9921465,0.001793536,0.0008219146,0.0002354416,0.004656821,0.0003458089],"domain_scores_gemma":[0.9972541,0.0007315768,0.0003019061,0.0004447839,0.0008917371,0.0003758455],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005366607,0.001113362,0.0433907,0.001394071,0.000502631,0.000985058,0.3241994,0.0009194478,0.003067103,0.002347216,0.01651381,0.6050305],"study_design_scores_gemma":[0.001955449,0.005289957,0.01683738,0.003165863,0.00002296444,0.0002727036,0.01769408,0.9278209,0.01664051,0.0006160041,0.009371393,0.0003128376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9191997,0.0003099048,0.01686874,0.06290284,0.0003443037,0.0002821647,1.216532e-7,0.0000211927,0.0000710481],"genre_scores_gemma":[0.9977288,0.00009036972,0.001363948,0.0001540452,0.0005772479,0.00001567303,9.634047e-8,0.00001123957,0.00005857263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9269014,"threshold_uncertainty_score":0.9999034,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3527306694668679,"score_gpt":0.4402682928113027,"score_spread":0.08753762334443477,"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."}}