{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001681078,0.0001040548,0.0001452269,0.0001670641,0.0001402874,0.0003659301,0.004328063,0.00005764569,0.00002432984],"category_scores_gemma":[0.002295294,0.00006893679,0.00008173352,0.000368695,0.0001113665,0.0005399777,0.002034015,0.0001768268,0.00003096996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004577107,"about_ca_system_score_gemma":0.000026382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005418665,"about_ca_topic_score_gemma":0.000001501126,"domain_scores_codex":[0.9985746,0.00001014571,0.0003223727,0.0004478576,0.0004640867,0.000180978],"domain_scores_gemma":[0.9985933,0.0005037821,0.0002681744,0.0003347252,0.0002622039,0.00003785112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000141513,0.0001116119,0.04664908,0.000009380571,0.000112172,4.832464e-8,0.0000597147,0.002231011,0.02643654,0.07044915,0.1770068,0.676793],"study_design_scores_gemma":[0.0004453592,0.00007005111,0.00851312,0.00003742756,0.00001578463,0.000001780033,0.000925285,0.1523537,0.01202985,0.04509909,0.7803637,0.0001448616],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5485765,0.00008631722,0.2094746,0.237871,0.0007875299,0.001219961,0.001248894,0.0003332716,0.0004018839],"genre_scores_gemma":[0.9546752,0.00001822162,0.04372976,0.00001390438,0.00009668399,0.00005409813,0.00009605917,0.00001186756,0.001304228],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6766481,"threshold_uncertainty_score":0.804269,"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."}}