{"id":"W7162449046","doi":"10.1109/urtc68753.2025.11533141","title":"Machine Learning Pipeline for Fast Radio Burst Host Galaxy Identification Using Multi-Survey Data Integration","year":2025,"lang":"","type":"article","venue":"","topic":"Radio Astronomy Observations and Technology","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pipeline (software); Identification (biology); Data integration; Host (biology); Pattern recognition (psychology); Noisy data","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002937114,0.001018329,0.0009807163,0.002421052,0.00081254,0.001072469,0.002290694,0.0009631536,0.00370733],"category_scores_gemma":[0.006559693,0.0006825913,0.001480727,0.001352077,0.0003502223,0.001396528,0.001991798,0.001891318,0.004502625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009878286,"about_ca_system_score_gemma":0.001883435,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00796975,"about_ca_topic_score_gemma":0.008285903,"domain_scores_codex":[0.9988164,0.0002016233,0.00009373342,0.0003240809,0.0004286698,0.0001356511],"domain_scores_gemma":[0.9976709,0.0006440467,0.0002364286,0.0005499375,0.0007694216,0.0001292671],"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":[0.0003973864,0.0005252955,0.02962967,0.0001717423,0.0002941792,0.0003733211,0.0002822927,0.1201201,0.04738417,0.004828771,0.02012233,0.7758707],"study_design_scores_gemma":[0.00002992123,0.00006538751,0.006995816,0.00000779713,0.00002661666,0.00008284814,0.00004207643,0.9691504,0.01478626,0.004391415,0.004386179,0.00003535191],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02419575,0.00006777066,0.943325,0.0001976682,0.00002351568,0.0001977214,0.001169123,0.03024326,0.0005801104],"genre_scores_gemma":[0.1936575,0.00007466185,0.795614,0.0001923823,0.0000388447,0.000558878,0.007382067,0.000888308,0.001593351],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00796975,"threshold_uncertainty_score":0.01584667,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07569585276001384,"score_gpt":0.3284742354224435,"score_spread":0.2527783826624296,"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."}}