{"id":"W4394822575","doi":"10.1051/0004-6361/202348239/pdf","title":"Galaxy merger challenge: A comparison study between machine learning-based detection methods","year":2024,"lang":"en","type":"article","venue":"Springer Link (Chiba Institute of Technology)","topic":"Galaxies: Formation, Evolution, Phenomena","field":"Physics and Astronomy","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Victoria","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Science and Technology Facilities Council; European Commission; Rijksuniversiteit Groningen; Comunidad de Madrid","keywords":"Benchmark (surveying); Galaxy; Task (project management); Binary classification; Artificial intelligence; Computer science; Binary number; Recall; Redshift; Machine learning; Astrophysics; Physics; Support vector machine; Mathematics; Engineering; Psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006974081,0.0003565178,0.0005621373,0.000943584,0.0002871391,0.00005593558,0.0004324145,0.0002038249,0.0001214118],"category_scores_gemma":[0.00005166917,0.0003484554,0.0001884332,0.001086983,0.000244727,0.0003609136,0.0001950651,0.001039203,0.00009587174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001231846,"about_ca_system_score_gemma":0.0001221741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003331211,"about_ca_topic_score_gemma":0.00008477006,"domain_scores_codex":[0.9979463,0.00009349449,0.0007706651,0.00052227,0.000269242,0.0003979939],"domain_scores_gemma":[0.9988798,0.00004812357,0.0002837642,0.0005703542,0.0001413395,0.00007662438],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000111891,0.0002303626,0.9609711,0.00009062266,0.0003605015,1.131074e-7,0.0004192095,0.0008429307,0.0009860278,0.004251781,0.0000130595,0.03182308],"study_design_scores_gemma":[0.001321979,0.0008507272,0.8834971,0.0001743487,0.0003991662,0.000001168189,0.0005886946,0.04130057,0.02213153,0.004135067,0.04486063,0.0007390094],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9417792,0.0005767737,0.05409436,0.0007334818,0.0009484648,0.0006050066,0.00001289198,0.0008669486,0.00038286],"genre_scores_gemma":[0.9875286,0.000006489534,0.01179023,7.134323e-7,0.0003551589,0.0001293648,0.00003875626,0.00005016923,0.0001005204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07747402,"threshold_uncertainty_score":0.9998968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01981327055624217,"score_gpt":0.2908476663048913,"score_spread":0.2710343957486491,"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."}}