{"id":"W3196789716","doi":"10.1145/3485820","title":"Anonymizing Sensor Data on the Edge: A Representation Learning and Transformation Approach","year":2021,"lang":"en","type":"preprint","venue":"ACM Transactions on Internet of Things","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University; University of Alberta","funders":"","keywords":"Autoencoder; Computer science; Probabilistic logic; Representation (politics); Enhanced Data Rates for GSM Evolution; Transformation (genetics); Data transformation; Data mining; External Data Representation; Artificial intelligence; Feature learning; Machine learning; Deep learning; Data warehouse","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.000967135,0.0003027044,0.0003500962,0.0003004608,0.0001953876,0.0005395876,0.02273218,0.0003245529,0.00002274279],"category_scores_gemma":[0.005349572,0.0002550097,0.0001142013,0.0003535371,0.0001688639,0.00133601,0.01269244,0.002040049,0.000004795183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008025984,"about_ca_system_score_gemma":0.00006764611,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003451683,"about_ca_topic_score_gemma":0.000006065388,"domain_scores_codex":[0.9973547,0.0002636561,0.0005305083,0.001074689,0.0005337952,0.0002425791],"domain_scores_gemma":[0.9876287,0.0007645599,0.0003674764,0.01108073,0.0001164881,0.00004204031],"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":[0.0003152654,0.001292941,0.0001998588,0.002302536,0.001859156,0.00004289918,0.05082276,0.01009001,0.005038921,0.005714542,0.01773016,0.904591],"study_design_scores_gemma":[0.0003144149,0.0001267153,0.00006017308,0.0008529418,0.00008382954,0.00004934025,0.002293114,0.9493788,0.02929513,0.01657601,0.0005759282,0.0003936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02047867,0.0001063351,0.9581774,0.01891104,0.0004503577,0.0004372217,0.00003373445,0.0004452147,0.0009600452],"genre_scores_gemma":[0.6324966,0.0003745001,0.366558,0.0002020237,0.00001813577,0.00004381103,0.000183641,0.00002384218,0.00009949133],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9392888,"threshold_uncertainty_score":0.9999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07664836839314856,"score_gpt":0.311884658218367,"score_spread":0.2352362898252185,"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."}}