{"id":"W4248854659","doi":"10.2196/preprints.18055","title":"Exploring the Privacy-Preserving Properties of Word Embeddings: Algorithmic Validation Study (Preprint)","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Michael's Hospital; Institute for Clinical Evaluative Sciences; Vector Institute; University of Toronto","funders":"","keywords":"Word (group theory); Computer science; Preprint; Natural language processing; Word embedding; Code (set theory); Embedding; Information retrieval; Representation (politics); Artificial intelligence; Linguistics; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":[],"consensus_categories":[],"category_scores_codex":[0.01446972,0.001175376,0.0007156753,0.001303766,0.0009424687,0.001893454,0.001442426,0.001922484,0.003111186],"category_scores_gemma":[0.07338292,0.0004402013,0.001386393,0.001329281,0.001867591,0.003483871,0.003207638,0.002711659,0.001465793],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001238242,"about_ca_system_score_gemma":0.001546071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002989909,"about_ca_topic_score_gemma":0.003144892,"domain_scores_codex":[0.9893365,0.006910838,0.0008613605,0.001169296,0.001320454,0.0004016309],"domain_scores_gemma":[0.9251485,0.05626341,0.002272674,0.01080918,0.005086957,0.0004193637],"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":[0.002752419,0.001970073,0.06426179,0.00250965,0.001220471,0.0009378638,0.002719805,0.3696795,0.01237175,0.02898939,0.05059507,0.4619922],"study_design_scores_gemma":[0.0003019241,0.0007596178,0.007944954,0.0002897877,0.0001644569,0.0007582541,0.0009766745,0.9375428,0.01437367,0.02840829,0.008397164,0.000082501],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7291542,0.003635028,0.2482771,0.00273335,0.0008949314,0.0007595387,0.005678657,0.002580922,0.006286277],"genre_scores_gemma":[0.8340975,0.0007230957,0.1445861,0.0006214345,0.0001716285,0.0006740148,0.01593038,0.0003056915,0.002890172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01446972,"threshold_uncertainty_score":0.07652408,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2049936679010446,"score_gpt":0.2940062204409732,"score_spread":0.08901255253992857,"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."}}