{"id":"W4394922976","doi":"10.1145/3627703.3629563","title":"Accelerating Privacy-Preserving Machine Learning With GeniBatch","year":2024,"lang":"en","type":"article","venue":"","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Homomorphic encryption; Encryption; Ciphertext; Bilinear interpolation; Information privacy; Support vector machine; Computation; Artificial intelligence; Algorithm; Computer security","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":["scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005722049,0.0002614191,0.000203709,0.0002449159,0.0002738198,0.001423077,0.03064812,0.0001108251,0.0001818751],"category_scores_gemma":[0.006630484,0.0001948148,0.00005273403,0.001209322,0.0000625358,0.002081136,0.1202097,0.0008111304,0.0001600574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008400435,"about_ca_system_score_gemma":0.00009909111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001610651,"about_ca_topic_score_gemma":0.00003806395,"domain_scores_codex":[0.9977003,0.0000747677,0.0002802938,0.0009075322,0.0004738107,0.000563243],"domain_scores_gemma":[0.9926563,0.0003266717,0.00005750648,0.006811352,0.00006235417,0.00008581525],"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":[0.0000260055,0.0001433364,0.01982932,0.0006648425,0.0004398891,0.00145188,0.001559132,0.001118322,0.01594039,0.0946717,0.4036438,0.4605113],"study_design_scores_gemma":[0.0001244864,0.00009033982,0.000159472,0.0001309798,0.000006725079,0.00009273386,0.00003380282,0.9377241,0.006098042,0.03486073,0.02036288,0.0003156815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02110809,0.001312735,0.9138566,0.03737615,0.0003270123,0.0002237745,0.000003643435,0.008897777,0.0168942],"genre_scores_gemma":[0.3939357,0.00005439809,0.6048759,0.0001338631,0.00005732689,0.00002267449,0.000008668304,0.00003074064,0.0008807998],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9366058,"threshold_uncertainty_score":0.9996135,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03489200890547688,"score_gpt":0.2709649938469287,"score_spread":0.2360729849414518,"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."}}