{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00787729,0.0007691244,0.0015784,0.001639864,0.0001209962,0.00008829944,0.004135968,0.0003508026,0.00008484532],"category_scores_gemma":[0.004703568,0.0007390243,0.00006595316,0.00186327,0.0002185293,0.001267578,0.004980425,0.002476251,0.003583287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000104285,"about_ca_system_score_gemma":0.0003416238,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006742985,"about_ca_topic_score_gemma":0.01754021,"domain_scores_codex":[0.9944307,0.0007091329,0.001436537,0.001700473,0.0009011035,0.000822064],"domain_scores_gemma":[0.9921657,0.00115662,0.001408983,0.005030036,0.0000942714,0.0001443394],"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":[0.0002352172,0.00006006721,0.005417062,0.0009357329,0.0001596299,0.0002478756,0.00001330429,0.0001320225,0.00005663123,5.115123e-7,0.9911242,0.001617765],"study_design_scores_gemma":[0.0006250162,0.00008285021,0.005165759,0.0005703882,0.0002512763,0.00005447188,0.0001097016,0.001877396,0.00004598607,0.00001155875,0.9904804,0.0007251836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.001343976,0.0006588227,0.000009848657,0.00007897552,0.0009163726,0.0005252415,0.9962425,0.0001961177,0.00002816972],"genre_scores_gemma":[0.00016851,0.003651399,0.001848299,0.00004003968,0.0002612626,0.00004716582,0.9923736,0.000177771,0.001431943],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01079723,"threshold_uncertainty_score":0.9998712,"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."}}