{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108238,0.0009551484,0.001063297,0.003499368,0.002392616,0.01069806,0.003768305,0.002533977,0.006571941],"category_scores_gemma":[0.02042694,0.0008742764,0.001386358,0.00408256,0.01908518,0.01532885,0.007075816,0.00859076,0.002710153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003725505,"about_ca_system_score_gemma":0.006582365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0047608,"about_ca_topic_score_gemma":0.004010417,"domain_scores_codex":[0.9917548,0.003130665,0.0007021301,0.001613902,0.002361729,0.0004368003],"domain_scores_gemma":[0.9781148,0.01074009,0.0007251545,0.006801172,0.002742471,0.0008763094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008846389,0.000009665869,0.0001095618,0.00007914467,0.00001142413,0.00001719334,0.0002658375,0.0007836336,0.0001197148,0.9856941,0.002061233,0.01083963],"study_design_scores_gemma":[0.00001001236,0.00001135842,0.00005156895,0.00008241818,0.00000886351,0.0000541195,0.00009920363,0.00358275,0.0003643818,0.9545491,0.04117417,0.00001198397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002150154,0.00442108,0.8924848,0.01543002,0.0006648221,0.0001823769,0.0003053536,0.0005433722,0.08381796],"genre_scores_gemma":[0.278686,0.007210135,0.6804308,0.007092627,0.001696615,0.001061223,0.0007585994,0.0004829476,0.02258112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0108238,"threshold_uncertainty_score":0.05724239,"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."}}