{"id":"W4402216230","doi":"10.1007/978-3-031-70879-4_1","title":"Attesting Distributional Properties of Training Data for Machine Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Training (meteorology); Artificial intelligence; Training set; Machine learning","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":[0.0108579,0.0006589266,0.001267412,0.001321617,0.001306478,0.003510084,0.002173498,0.002234329,0.002618775],"category_scores_gemma":[0.06029499,0.0009262308,0.001298556,0.001844676,0.005184612,0.008627868,0.006009833,0.007632528,0.001554909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217814,"about_ca_system_score_gemma":0.001524518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002888589,"about_ca_topic_score_gemma":0.0003414915,"domain_scores_codex":[0.9889853,0.004927426,0.0008250732,0.001459684,0.003319871,0.0004826672],"domain_scores_gemma":[0.9177992,0.0479623,0.002444742,0.02881945,0.002409826,0.0005643215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004565901,0.0001620553,0.004320431,0.0003108104,0.0001226268,0.0002820245,0.0009608418,0.03716264,0.01053389,0.6902404,0.01271462,0.2427332],"study_design_scores_gemma":[0.00001514795,0.00006913903,0.0005059243,0.00005240383,0.00002070043,0.0003435664,0.00008533281,0.1409564,0.008808151,0.8437101,0.005412953,0.00002014748],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0153937,0.0005467495,0.9766922,0.002049797,0.0001809907,0.0000451845,0.000225226,0.0007376731,0.004128501],"genre_scores_gemma":[0.6928844,0.001687471,0.2901066,0.001636991,0.001003833,0.0003231004,0.00170728,0.0008851933,0.009765086],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0108579,"threshold_uncertainty_score":0.05742282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.105038459810962,"score_gpt":0.2912313150925623,"score_spread":0.1861928552816004,"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."}}