{"id":"W4394780685","doi":"10.48550/arxiv.2404.07282","title":"Validating the Galaxy and Quasar Catalog-Level Blinding Scheme for the DESI 2024 analysis","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Astronomy and Astrophysical Research","field":"Physics and Astronomy","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Regional Municipality of Waterloo; Perimeter Institute; University of Waterloo","funders":"Commissariat à l'Énergie Atomique et aux Énergies Alternatives; Division of Astronomical Sciences; Science and Technology Facilities Council; European Commission; U.S. Department of Energy; Gordon and Betty Moore Foundation; Office of Science; University of Michigan; National Science Foundation","keywords":"Blinding; Dark energy; Redshift; Galaxy; Computer science; Quasar; Astrophysics; Physics; Data science; Cosmology; Bioinformatics; Biology","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":[],"consensus_categories":[],"category_scores_codex":[0.0004210628,0.0003061601,0.000339326,0.0001703819,0.0005694675,0.0003065206,0.0007323672,0.00008773905,0.0001392173],"category_scores_gemma":[0.00001960407,0.0002118658,0.0005519607,0.0007556991,0.0002548346,0.00008483775,0.001658521,0.001034775,0.00004660604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006941715,"about_ca_system_score_gemma":0.0001809603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005290356,"about_ca_topic_score_gemma":0.00002449539,"domain_scores_codex":[0.9983985,0.00008995939,0.0001898501,0.0007691109,0.0001054793,0.0004470292],"domain_scores_gemma":[0.9982305,0.0007648228,0.0001471466,0.0006344224,0.0001029295,0.000120214],"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":[0.0002089188,0.0002395841,0.2004898,0.0002692746,0.01662021,0.00003115999,0.00117033,0.1496925,0.0002531402,0.5895982,0.002083664,0.03934325],"study_design_scores_gemma":[0.0007887596,0.00008405567,0.008065913,0.0001905591,0.005852304,4.11629e-7,0.005209457,0.8859966,0.001254836,0.09002963,0.001596917,0.0009306092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3706852,0.0001187093,0.6264114,0.0003204204,0.0001927611,0.0006438266,0.0004382191,0.00003317342,0.001156356],"genre_scores_gemma":[0.9942118,0.00001030892,0.0006225732,0.000009525076,0.0004584813,0.00001432719,0.0001185854,0.00002575558,0.004528633],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.736304,"threshold_uncertainty_score":0.8639636,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1320414058918728,"score_gpt":0.2524732072644576,"score_spread":0.1204318013725848,"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."}}