{"id":"W4385248297","doi":"10.1145/3571724","title":"The Principles of Data-Centric AI","year":2023,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; TRACE (psycholinguistics); Data science; Philosophy","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":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0009645508,0.0000385003,0.00005909386,0.00004238415,0.0003589779,0.00003888305,0.07968687,0.00001668948,8.974995e-7],"category_scores_gemma":[0.008738233,0.00002222017,0.00002804703,0.0008319112,0.0001711389,0.0001959937,0.05622783,0.000135407,0.00003075276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006995846,"about_ca_system_score_gemma":0.00006127952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004424748,"about_ca_topic_score_gemma":0.00003313091,"domain_scores_codex":[0.9992136,0.0002373265,0.0002064021,0.000110578,0.0001518835,0.00008021826],"domain_scores_gemma":[0.9348066,0.0009126774,0.0001961891,0.06399283,0.00007850934,0.0000131919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002598057,0.00009285302,0.01049728,0.00001996107,0.000034042,4.341228e-8,0.0005613671,0.0002863798,0.0006900791,0.8259072,0.07525229,0.08665591],"study_design_scores_gemma":[0.0001067329,0.000009358263,0.1236864,0.00002726251,0.00001189451,0.000001347099,0.00007431437,0.2279606,0.0003151842,0.03329159,0.6144552,0.00006008918],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.00847356,0.00301724,0.01365436,0.9624579,0.0003945488,0.000518128,0.0001100692,0.0003507428,0.01102344],"genre_scores_gemma":[0.913794,0.00175798,0.08327096,0.0001320921,0.00001408613,0.00001581369,0.0001149951,0.000006562826,0.000893549],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9623258,"threshold_uncertainty_score":0.9996116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1798954497282311,"score_gpt":0.3795690690161228,"score_spread":0.1996736192878917,"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."}}