{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001860314,0.0004383408,0.0005382239,0.0005882759,0.0002646328,0.0004472413,0.04418556,0.0002738247,0.000004659313],"category_scores_gemma":[0.0154583,0.0003782787,0.00008901401,0.0006208145,0.000989723,0.0008924631,0.1129381,0.001154508,0.000007444479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002042995,"about_ca_system_score_gemma":0.0006191499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002225976,"about_ca_topic_score_gemma":0.00002622635,"domain_scores_codex":[0.9959602,0.00002084819,0.0006261087,0.001920402,0.0008387557,0.000633635],"domain_scores_gemma":[0.9910014,0.0008375266,0.0003377692,0.007521436,0.0002298138,0.00007210689],"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":[0.00001381901,0.00003572158,0.0001228192,0.0007209348,0.00006895104,0.00006307149,0.0004546129,0.008505874,0.002149794,0.04130878,0.0007394626,0.9458162],"study_design_scores_gemma":[0.00008564407,0.00007055366,0.000004513605,0.0009808105,0.000008934002,0.00004164935,2.414191e-7,0.6763101,0.001364296,0.3192702,0.001572902,0.0002901109],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000534303,0.002319596,0.9897317,0.005342481,0.001019136,0.0003850921,0.0002875667,0.0005387727,0.0003222738],"genre_scores_gemma":[0.1456127,0.00003524652,0.8536339,0.000116605,0.0002552939,0.00001452884,0.0001764747,0.00003954581,0.0001156584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9455261,"threshold_uncertainty_score":0.9998669,"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."}}