{"id":"W4389599675","doi":"10.48550/arxiv.2312.04968","title":"NEural Engine for Discovering Luminous Events (NEEDLE): identifying rare transient candidates in real time from host galaxy images","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Gamma-ray bursts and supernovae","field":"Physics and Astronomy","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; European Commission; Science and Technology Facilities Council; UK Research and Innovation","keywords":"Galaxy; Supernova; Computer science; False positive paradox; Sky; Photometry (optics); Virtual observatory; Host (biology); Classifier (UML); Observatory; Astrophysics; Physics; Artificial intelligence; Astronomy; Machine learning; Stars","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001085365,0.0008451718,0.0008775783,0.001336341,0.0004644853,0.001076265,0.002180512,0.001153204,0.001727504],"category_scores_gemma":[0.003044635,0.0003646031,0.0005540163,0.0007860733,0.000374874,0.001482389,0.001158539,0.00102765,0.001095829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007039838,"about_ca_system_score_gemma":0.0006889675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007625867,"about_ca_topic_score_gemma":0.009096837,"domain_scores_codex":[0.9996054,0.0000395037,0.00002696334,0.0001580785,0.00009621464,0.00007394916],"domain_scores_gemma":[0.9991865,0.0003171044,0.0001163794,0.00008781166,0.0002269249,0.00006535885],"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":[0.0005432742,0.0006777571,0.03000434,0.0003286212,0.0002762918,0.0003644613,0.0001740867,0.1455227,0.01564842,0.004086747,0.01949369,0.7828796],"study_design_scores_gemma":[0.00001441515,0.00009377367,0.00246531,0.00002583014,0.00005121075,0.0001228669,0.00004265357,0.9849072,0.006223863,0.003383691,0.002649582,0.00001954984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2729769,0.00268732,0.6972011,0.001779651,0.0003365377,0.0005842382,0.003454969,0.01363516,0.007344118],"genre_scores_gemma":[0.7662138,0.001030771,0.2134415,0.0009954796,0.0001931506,0.0003898923,0.006440013,0.0001834741,0.01111181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007625867,"threshold_uncertainty_score":0.015163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04340179875411623,"score_gpt":0.2056263375360882,"score_spread":0.162224538781972,"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."}}