{"id":"W4382203029","doi":"10.1609/aaai.v37i8.26196","title":"A Fair Generative Model Using LeCam Divergence","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology; National Research Foundation of Korea; Institute for Information and Communications Technology Promotion; Korea Customs Service; National Research Foundation","keywords":"Benchmark (surveying); Divergence (linguistics); Measure (data warehouse); Computer science; Set (abstract data type); Range (aeronautics); Generative grammar; Sample size determination; Generative model; Statistical power; Sample (material); Machine learning; Data mining; Artificial intelligence; Statistics; Mathematics","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":[0.001125193,0.0001496639,0.000217873,0.000173602,0.0007726476,0.0001365781,0.000807852,0.00007743382,0.0001630357],"category_scores_gemma":[0.0008231809,0.0001180514,0.0001634512,0.001687787,0.0005155458,0.0002397565,0.000211476,0.0001787253,0.000100999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007177266,"about_ca_system_score_gemma":0.0002628359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003964153,"about_ca_topic_score_gemma":0.0001345668,"domain_scores_codex":[0.9981629,0.0000544182,0.0003836207,0.0003463661,0.0007139133,0.0003388266],"domain_scores_gemma":[0.9985619,0.0001559611,0.0002626695,0.0001050462,0.0008209539,0.00009350523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002644076,0.00005370744,0.0004188238,0.00001007642,0.00002417319,3.114295e-7,0.009423736,0.02941113,0.02469091,0.9118006,0.000217206,0.02392291],"study_design_scores_gemma":[0.000007855198,0.00001872899,0.00008057714,0.00004277322,0.00001940086,1.729794e-7,0.003153414,0.5367202,0.03710248,0.4226566,0.00007660098,0.0001212195],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9214576,0.00001803029,0.04619532,0.005366202,0.0004928393,0.0004325563,0.00001279279,0.0001761015,0.02584858],"genre_scores_gemma":[0.9932734,0.00006015751,0.004746261,0.0001173344,0.0001339654,0.00001325707,7.183887e-7,0.000009394063,0.00164554],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.507309,"threshold_uncertainty_score":0.5942659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2930600442660267,"score_gpt":0.4240172083587,"score_spread":0.1309571640926733,"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."}}