{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02137738,0.003573262,0.002137512,0.01148722,0.001354569,0.004167995,0.004148367,0.00446369,0.001275809],"category_scores_gemma":[0.03433517,0.0006112253,0.002069892,0.004455961,0.001185012,0.004443681,0.004107803,0.002108147,0.001896308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002289239,"about_ca_system_score_gemma":0.001213457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007245478,"about_ca_topic_score_gemma":0.006664987,"domain_scores_codex":[0.982811,0.005798355,0.001530547,0.003397117,0.005734246,0.0007287054],"domain_scores_gemma":[0.9714847,0.01801906,0.002185429,0.003203694,0.003904959,0.001202158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003877817,0.001525246,0.2846356,0.005260183,0.006422693,0.0006362757,0.001015569,0.06136433,0.005376291,0.004752947,0.09756172,0.5275713],"study_design_scores_gemma":[0.0009992991,0.00413541,0.2468556,0.001363188,0.001835833,0.003420123,0.002143247,0.6193652,0.02137315,0.01232428,0.08552742,0.0006572111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7035581,0.1710651,0.05910265,0.007058012,0.002650855,0.001290552,0.01744891,0.01215212,0.02567393],"genre_scores_gemma":[0.833504,0.009059652,0.0902914,0.002749537,0.001915149,0.0004051524,0.05604153,0.0009041736,0.005129439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02137738,"threshold_uncertainty_score":0.1130558,"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."}}