{"id":"W3168854329","doi":"10.14778/3467861.3467872","title":"Data acquisition for improving machine learning models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Data acquisition; Process (computing); Data modeling; Online machine learning; Knowledge acquisition; Training set; Annotation; Data integration; Supervised learning","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":[0.003924377,0.0001105722,0.0002081797,0.00007268613,0.0002344033,0.0002969926,0.001821279,0.0000323962,0.00006977861],"category_scores_gemma":[0.002043221,0.000072175,0.00009857395,0.0003692503,0.00004576832,0.0009666055,0.00273927,0.0001047081,0.0000106327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003737287,"about_ca_system_score_gemma":0.00003440355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004646267,"about_ca_topic_score_gemma":0.00001721971,"domain_scores_codex":[0.997707,0.00002416758,0.0005174584,0.0005506269,0.0009839372,0.0002167936],"domain_scores_gemma":[0.9982992,0.0002339583,0.0004221108,0.0005367546,0.0004596683,0.00004828629],"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":[0.0002727789,0.0006811334,0.001876251,0.0006955244,0.0002340544,0.000002107047,0.002417813,0.002590723,0.1232382,0.5196707,0.08047108,0.2678497],"study_design_scores_gemma":[0.001653374,0.0001589616,0.00046786,0.0001174401,0.0001860013,0.00001267462,0.006433871,0.3492173,0.09174051,0.3349099,0.2147164,0.0003857961],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3409065,0.00576634,0.4242298,0.08517427,0.005716568,0.008959401,0.006814382,0.0006522082,0.1217805],"genre_scores_gemma":[0.9832612,0.00004495927,0.01113982,0.0006037925,0.00009906612,0.00004473323,0.00009258271,0.00001359773,0.004700242],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6423547,"threshold_uncertainty_score":0.3414305,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2848510771576441,"score_gpt":0.3865902747486838,"score_spread":0.1017391975910397,"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."}}