{"id":"W6888525715","doi":"10.21227/2me6-nm77","title":"Our World in Data 2023_Marco Vlajnic_Accuracy and Performance of Machine Learning Methodologies","year":2023,"lang":"en","type":"dataset","venue":"IEEE DataPort","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Data center; Real world data; Center (category theory); Feature engineering; Coronavirus disease 2019 (COVID-19)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002468439,0.002320696,0.001357917,0.004365015,0.001015094,0.002828285,0.002775847,0.002069386,0.0330278],"category_scores_gemma":[0.0105871,0.000587478,0.001512239,0.006777123,0.0005360591,0.001897613,0.002046969,0.002104529,0.05266704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002055038,"about_ca_system_score_gemma":0.002337212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03088547,"about_ca_topic_score_gemma":0.05361492,"domain_scores_codex":[0.9970247,0.0006088734,0.0003821526,0.0005835479,0.001061073,0.0003397811],"domain_scores_gemma":[0.993932,0.001503485,0.0004203251,0.001510452,0.002185937,0.0004479011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004498671,0.00003062822,0.001011763,0.000185468,0.00002343573,0.00001090769,0.0000134533,0.0004649076,0.00004979618,0.0003157647,0.9942644,0.003584436],"study_design_scores_gemma":[0.0002190814,0.00005361694,0.009999201,0.0003029667,0.00003915403,0.0001122447,0.0001512901,0.003909394,0.0008069554,0.0017458,0.9826067,0.00005345376],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0009824053,0.0002168633,0.0003065198,0.0002374396,0.0001685591,0.00003113475,0.9950655,0.0008592667,0.002132355],"genre_scores_gemma":[0.001280941,0.00006025221,0.0005904222,0.00005211774,0.00002130847,0.00005398296,0.9970862,0.00008819097,0.0007665749],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0330278,"threshold_uncertainty_score":0.110489,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2555066975682351,"score_gpt":0.4267242016799915,"score_spread":0.1712175041117564,"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."}}