{"id":"W4412819361","doi":"10.1017/s1743921323001394","title":"How do we design data sets for Machine Learning astronomy?","year":2023,"lang":"en","type":"article","venue":"Proceedings of the International Astronomical Union","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Institute for Theoretical Astrophysics","funders":"","keywords":"Computer science; Astronomy; Artificial intelligence; Physics","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":[0.08787493,0.001713734,0.004239562,0.008315079,0.003449981,0.01837217,0.006716108,0.004951682,0.006522984],"category_scores_gemma":[0.3377853,0.002291787,0.003348548,0.007190155,0.01320836,0.03289534,0.01077918,0.01143868,0.003427273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004159373,"about_ca_system_score_gemma":0.005112829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003091583,"about_ca_topic_score_gemma":0.002218604,"domain_scores_codex":[0.9088526,0.06512269,0.00648815,0.006420075,0.01191611,0.001200398],"domain_scores_gemma":[0.6592241,0.2348081,0.01685514,0.05452658,0.02978607,0.004800088],"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":[0.0004400536,0.0004389115,0.02272778,0.001903993,0.0007924062,0.0001472215,0.002034235,0.0361916,0.001773826,0.7623613,0.0344123,0.1367764],"study_design_scores_gemma":[0.00008687654,0.0000695554,0.002217665,0.0005657676,0.0000504495,0.00006568163,0.00107005,0.05412783,0.001129871,0.9154526,0.02508367,0.00007992786],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02774614,0.003119569,0.8909162,0.06054178,0.001523235,0.0009867229,0.003675231,0.001365045,0.01012604],"genre_scores_gemma":[0.1915025,0.001224135,0.7925106,0.006432017,0.0009342469,0.002467512,0.003111333,0.0006414644,0.001176098],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08787493,"threshold_uncertainty_score":0.4647326,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2644297115902468,"score_gpt":0.3662506250858025,"score_spread":0.1018209134955557,"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."}}