{"id":"W7117851814","doi":"","title":"Galaxy Zoo Evo: 1 million human-annotated images of galaxies","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Toronto; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Galaxy; Space (punctuation); Benchmark (surveying); Image (mathematics); Domain (mathematical analysis); Spiral galaxy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008649856,0.0004200743,0.0005503956,0.0005252574,0.0005489536,0.0002263489,0.00157077,0.0002236016,0.0002256452],"category_scores_gemma":[0.0005372527,0.0004219829,0.0002045271,0.001776425,0.0003826414,0.0007553276,0.0006710716,0.0005986797,0.0003464943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008593637,"about_ca_system_score_gemma":0.0002445617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000524641,"about_ca_topic_score_gemma":0.00002735897,"domain_scores_codex":[0.9964343,0.0004541207,0.001015982,0.001064563,0.0004686682,0.000562423],"domain_scores_gemma":[0.9966696,0.0002445632,0.0006056142,0.00185761,0.0004937904,0.0001288043],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003031637,0.0002346127,0.9363952,0.0002645295,0.00009812695,0.000007532723,0.0006469656,0.00007087152,0.0327538,0.007268164,0.00636449,0.01586543],"study_design_scores_gemma":[0.0006304445,0.0001910775,0.9613909,0.000355425,0.00007597114,0.000003619533,0.0000862419,0.009359885,0.01940596,0.0005238265,0.007622293,0.0003543872],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9353198,0.002827365,0.04350795,0.005600125,0.001493594,0.0004417195,0.00003363305,0.0003098033,0.010466],"genre_scores_gemma":[0.9823861,0.000411387,0.001433451,0.0001264774,0.0001116673,0.00002034647,0.00009717682,0.00002233027,0.0153911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04706626,"threshold_uncertainty_score":0.9998232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03054621689064294,"score_gpt":0.3079074448161753,"score_spread":0.2773612279255323,"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."}}