{"id":"W4399156410","doi":"10.1145/3654934","title":"Data Acquisition for Improving Model Confidence","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Data acquisition; Machine learning; Context (archaeology); Knowledge acquisition; Range (aeronautics); Process (computing); Artificial intelligence; Data mining; Data quality; Data science; Engineering","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":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001149031,0.00009036245,0.00009823619,0.00007872344,0.00006875848,0.0001993884,0.01460913,0.00002355131,0.000001692036],"category_scores_gemma":[0.0002313609,0.00006692661,0.00002418117,0.000263363,0.00003464207,0.001913748,0.0117803,0.00008588455,0.000004472566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001268386,"about_ca_system_score_gemma":0.00001840373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007010779,"about_ca_topic_score_gemma":3.367759e-7,"domain_scores_codex":[0.9986843,0.000004231973,0.0002316189,0.0006214407,0.0003340466,0.0001243129],"domain_scores_gemma":[0.9960983,0.00007027651,0.0001817926,0.003559578,0.00007014562,0.00001987056],"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":[0.00002101077,0.00005815615,0.0000452954,0.002318568,0.00006015063,2.007479e-7,0.00007290684,0.0001060741,0.00430352,0.7822855,0.04631901,0.1644096],"study_design_scores_gemma":[0.0001098178,0.00003467237,0.0002208569,0.0002929323,0.00005664574,9.412082e-7,0.00004675375,0.967835,0.0008870623,0.02610713,0.00433099,0.00007721037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002718276,0.0003063394,0.974722,0.01593141,0.0003309291,0.0008520631,0.001275029,0.0002307827,0.003633127],"genre_scores_gemma":[0.6256407,0.00008017886,0.373152,0.0001203863,0.00005025498,0.00001835934,0.0003722272,0.00001295139,0.000552868],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9677289,"threshold_uncertainty_score":0.9962122,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1126036958320424,"score_gpt":0.3468254042837654,"score_spread":0.234221708451723,"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."}}