{"id":"W4307022160","doi":"10.48550/arxiv.2009.05283","title":"Fair and accurate age prediction using distribution aware data curation and augmentation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Face recognition and analysis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nanyang Technological University; National Research Foundation Singapore; National Satellite of Excellence in Trustworthy Software Systems, National University of Singapore; University of Alberta; National Research Foundation; European Commission; Nvidia","keywords":"Computer science; IBM; Cloud computing; Feature (linguistics); Artificial intelligence; Artificial neural network; Machine learning; Diversity (politics); Task (project management); Deep learning; Raw data","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001268842,0.0001567687,0.0001634886,0.00009384861,0.000187542,0.0002687515,0.000392446,0.000123298,0.000005754879],"category_scores_gemma":[0.00002740689,0.0001861878,0.0000369386,0.0003507773,0.00005437092,0.001483086,0.001347611,0.0002030011,0.000005383814],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000956704,"about_ca_system_score_gemma":0.00006135188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001053556,"about_ca_topic_score_gemma":0.00003637134,"domain_scores_codex":[0.9987162,0.0001050564,0.0001455668,0.0008452283,0.00007136336,0.000116555],"domain_scores_gemma":[0.9991428,0.0000286324,0.0001860167,0.0004565156,0.00007703977,0.000109055],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003801835,0.0007102851,0.03952369,0.002751381,0.002340307,0.001796043,0.004692598,0.6726604,0.009326991,0.1704045,0.004673361,0.09074024],"study_design_scores_gemma":[0.0002701958,0.0000164038,0.002234851,0.00005689881,0.0001413465,0.000003782904,0.0001286538,0.9915785,0.00006833654,0.005248312,0.00008576504,0.0001669777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1536625,0.00002574861,0.8453592,0.0002011245,0.0001230273,0.0001426037,0.0003470176,0.0001134207,0.00002536395],"genre_scores_gemma":[0.996306,0.0004351687,0.0008853376,0.00004052246,0.00004178835,3.275166e-7,0.002251261,0.000005403788,0.00003418466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8444738,"threshold_uncertainty_score":0.7592518,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2295866761936491,"score_gpt":0.2362417920041554,"score_spread":0.00665511581050629,"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."}}