{"id":"W4295135780","doi":"10.1007/978-3-031-15471-3_32","title":"Assessment of Creditworthiness Models Privacy-Preserving Training with Synthetic Data","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Synthetic data; Scarcity; Quality (philosophy); Training set; Work (physics); Data quality; Credit risk; Data mining; Artificial intelligence; Finance; Business; Metric (unit)","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":[0.002037722,0.0004779259,0.0006679896,0.000819928,0.000271986,0.0003843819,0.01673664,0.0001614846,0.00005847755],"category_scores_gemma":[0.0001429657,0.000422477,0.00005752635,0.0009010111,0.0006490183,0.002688916,0.01144863,0.001005167,0.000001039196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000307395,"about_ca_system_score_gemma":0.001555266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003415396,"about_ca_topic_score_gemma":0.00002858064,"domain_scores_codex":[0.9946107,0.00007212,0.000690994,0.002208999,0.001865844,0.0005513236],"domain_scores_gemma":[0.9911161,0.0005961807,0.0007069174,0.007158237,0.0003039795,0.0001185852],"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":[0.000009628536,0.0001029004,0.00009981136,0.000198104,0.00004701722,0.0001171658,0.001804475,0.1770276,0.0003523724,0.2438695,0.0001177571,0.5762537],"study_design_scores_gemma":[0.000136731,0.0001253494,0.0001284286,0.0003934779,0.00001030456,0.00005716181,5.050352e-7,0.9040406,0.0002309864,0.09328539,0.001137144,0.0004538866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001824769,0.0001175124,0.9909019,0.0006290593,0.0005363579,0.0004994776,0.00008287255,0.0002832319,0.006931311],"genre_scores_gemma":[0.21276,0.00004227532,0.7866608,0.0002365876,0.000103558,0.00002626745,0.00007791744,0.00003772319,0.00005490228],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.727013,"threshold_uncertainty_score":0.9998227,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07513686561004515,"score_gpt":0.3056106964338318,"score_spread":0.2304738308237866,"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."}}