{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001419299,0.0005019252,0.0006061717,0.0004356673,0.0009464659,0.0004827034,0.001112079,0.0002397996,0.0001960068],"category_scores_gemma":[0.0002594088,0.0005317165,0.0001666518,0.0007583892,0.0001817457,0.0008976101,0.0004266562,0.0006230237,0.00003129361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000190261,"about_ca_system_score_gemma":0.000378998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005241734,"about_ca_topic_score_gemma":0.001177521,"domain_scores_codex":[0.9965413,0.0002327055,0.00128153,0.001208601,0.0001545238,0.0005813601],"domain_scores_gemma":[0.9968339,0.0003011671,0.00064918,0.001581032,0.0005462666,0.00008841346],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001903058,0.001152533,0.4733247,0.0001234062,0.0007713629,4.74435e-7,0.000192977,0.005025287,0.01610348,0.06314911,0.00109522,0.4388711],"study_design_scores_gemma":[0.001785924,0.00003867129,0.03821324,0.0001093925,0.000263247,6.336754e-7,0.0007861157,0.9428056,0.002750495,0.0001917736,0.01263955,0.0004153528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01981604,0.0004454781,0.9742492,0.0007773892,0.0009039204,0.00141203,0.002022675,0.0001130735,0.0002601586],"genre_scores_gemma":[0.9286331,0.0000325474,0.04688689,0.00002297936,0.0002626426,0.00008172542,0.01644376,0.00005302327,0.007583307],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9377803,"threshold_uncertainty_score":0.9997134,"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."}}