{"id":"W4393178192","doi":"10.1051/0004-6361/202348239","title":"Galaxy merger challenge: A comparison study between machine learning-based detection methods","year":2024,"lang":"en","type":"preprint","venue":"Astronomy and Astrophysics","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":15,"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":"Galaxy; Computer science; Artificial intelligence; Astrophysics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001271112,0.0004391508,0.0008021814,0.0002821762,0.0003458997,0.0005692893,0.000988638,0.0002548567,0.00004308378],"category_scores_gemma":[0.0001357307,0.0003555199,0.0002261253,0.0005171518,0.0001651727,0.00008985098,0.002623073,0.002190407,0.0001288018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004994296,"about_ca_system_score_gemma":0.00008470885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671202,"about_ca_topic_score_gemma":0.00004559072,"domain_scores_codex":[0.9966037,0.0003990003,0.0008036332,0.001282655,0.0005665183,0.0003445501],"domain_scores_gemma":[0.9975045,0.0005228099,0.0005116266,0.001198744,0.0001405443,0.0001217646],"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":[0.00001058229,0.000156621,0.0042052,0.00001415085,0.0001107219,8.0998e-7,0.0001237626,0.002929729,0.00009058184,0.000141333,0.0001004925,0.992116],"study_design_scores_gemma":[0.001575869,0.00281488,0.04178834,0.0001920153,0.001369573,0.00000159392,0.009727584,0.1051839,0.005864589,0.07395529,0.7553632,0.002163121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1672622,0.0005090558,0.8297631,0.0009223086,0.0002864285,0.0006576372,0.0002335756,0.0002786696,0.00008702768],"genre_scores_gemma":[0.8908188,0.000008874489,0.1084663,0.000004732396,0.0002656969,0.0002011148,0.0001279,0.00003289905,0.00007372964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9899529,"threshold_uncertainty_score":0.9998897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1774949725398429,"score_gpt":0.4213214920683637,"score_spread":0.2438265195285208,"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."}}