{"id":"W4386080688","doi":"10.48550/arxiv.2308.09740","title":"Machine-learning recovery of foreground wedge-removed 21-cm light cones for high-$z$ galaxy mapping","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Jet Propulsion Laboratory; McGill University; Canadian Institute for Advanced Research; National Aeronautics and Space Administration; California Institute of Technology; Oak Ridge Associated Universities","keywords":"Wedge (geometry); Galaxy; Artificial intelligence; Computer science; Physics; Geology; Astrophysics; Optics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0003913031,0.0003899994,0.0005849068,0.0005557254,0.0002723662,0.0001333141,0.00167019,0.0002240153,0.00001575456],"category_scores_gemma":[0.0001956026,0.0004443676,0.0003575125,0.0007181444,0.00008964652,0.0006524539,0.002235842,0.0006086745,0.00005329851],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001798212,"about_ca_system_score_gemma":0.0001523715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000133921,"about_ca_topic_score_gemma":0.00001455107,"domain_scores_codex":[0.9976585,0.0001205816,0.0003921172,0.001216324,0.0001320538,0.0004804322],"domain_scores_gemma":[0.9975414,0.000416328,0.0006102872,0.001001948,0.0002831647,0.0001468185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004825178,0.0002919903,0.008568805,0.001680593,0.0009070755,0.000569467,0.001713733,0.4135583,0.005554982,0.5344706,0.00388974,0.02831223],"study_design_scores_gemma":[0.001230909,0.00009769947,0.001615891,0.0004139266,0.00005668932,0.00000477827,0.0002101614,0.8317103,0.0007200755,0.1578281,0.005421356,0.0006900964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01617559,0.000188405,0.9799703,0.0003452725,0.001370603,0.0004681266,0.00002901213,0.0004675941,0.0009851141],"genre_scores_gemma":[0.9432855,0.0006183021,0.04287715,0.0001022491,0.0001211578,0.00000367977,0.00006229984,0.00006314398,0.01286654],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9370931,"threshold_uncertainty_score":0.9998008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07325271661990534,"score_gpt":0.2113524320701591,"score_spread":0.1380997154502538,"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."}}