{"id":"W4372260367","doi":"10.1109/icassp49357.2023.10097150","title":"Evaluation of Categorical Generative Models - Bridging the Gap Between Real and Synthetic Data","year":2023,"lang":"en","type":"article","venue":"","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bridging (networking); Categorical variable; Generative grammar; Computer science; Data modeling; Generative model; Artificial intelligence; Machine learning; Database","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":[],"consensus_categories":[],"category_scores_codex":[0.002533993,0.00005508945,0.0001094536,0.00004642167,0.0001262889,0.00008793435,0.0005198115,0.00001754793,0.00001019333],"category_scores_gemma":[0.00007247888,0.00003393783,0.00001901433,0.0004147125,0.00003960065,0.0004232069,0.0006548427,0.00004289941,0.000004600445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001255469,"about_ca_system_score_gemma":0.00004608293,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003487766,"about_ca_topic_score_gemma":0.00003551864,"domain_scores_codex":[0.9988749,0.0001386921,0.000162632,0.0002598743,0.000447359,0.0001165306],"domain_scores_gemma":[0.99907,0.0001263437,0.00006298644,0.0005785897,0.0001351342,0.00002697808],"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":[0.000001609084,0.00001456092,0.0004571016,0.000009561472,0.0001693385,0.000001910118,0.002738445,0.04535359,0.0004885523,0.1343166,0.002412523,0.8140362],"study_design_scores_gemma":[0.00004815225,0.00001090493,0.001154797,0.00000268601,0.00006603032,0.000001329087,0.00009609637,0.9837648,0.0001569121,0.0146388,0.00001589338,0.00004356499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08635036,0.00009755404,0.9053645,0.001627813,0.00004298403,0.0001340537,0.00001072566,0.0000729064,0.006299122],"genre_scores_gemma":[0.9969676,0.00002801579,0.002832463,0.00001090139,0.00005658347,0.000002869385,0.00001717932,0.000003009462,0.00008134749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9384112,"threshold_uncertainty_score":0.1383944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.279198974995376,"score_gpt":0.3430289548141723,"score_spread":0.06382997981879635,"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."}}