{"id":"W4389490903","doi":"10.1088/1361-6382/ad13c5","title":"HPC-driven computational reproducibility in numerical relativity codes: a use case study with IllinoisGRMHD","year":2023,"lang":"en","type":"article","venue":"Classical and Quantum Gravity","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Office of Advanced Cyberinfrastructure; U.S. Department of Energy; High Energy Physics; Office of Science; National Science Foundation","keywords":"Compiler; Code (set theory); Software; Reproducibility; Computer science; Source code; Computational science; Physics; Cornerstone; Einstein; Programming language","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":[0.009747474,0.0001873178,0.0004336616,0.0002875743,0.0003725205,0.0004719734,0.0003465171,0.00005433551,0.00001815948],"category_scores_gemma":[0.005528314,0.0001222761,0.0000649328,0.00253773,0.000393374,0.0003661377,0.000672048,0.0003229417,0.000109964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004397279,"about_ca_system_score_gemma":0.00006466334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007456772,"about_ca_topic_score_gemma":0.001036604,"domain_scores_codex":[0.9944651,0.0008358899,0.0006649047,0.002455209,0.001229655,0.000349289],"domain_scores_gemma":[0.9943673,0.003299803,0.0001619216,0.001766085,0.0001892718,0.0002156345],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001786779,0.001365258,0.9558277,0.00000904425,0.00002345619,0.003295928,0.00190254,0.005956871,0.000005242329,0.005059494,0.006219409,0.02015638],"study_design_scores_gemma":[0.0005659368,0.000270802,0.6333442,0.00001107217,0.00001207783,0.0001064431,0.002228457,0.3433025,6.474763e-7,0.01832309,0.001672814,0.0001619899],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894686,0.000004903795,0.008183906,0.001414892,0.0002522279,0.0004520674,0.00005404152,0.0001222352,0.00004715115],"genre_scores_gemma":[0.9986497,6.99808e-7,0.0006682981,0.00005581338,0.00003529899,0.00001514352,0.00001974521,0.000007332444,0.0005479847],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3373456,"threshold_uncertainty_score":0.6618307,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2006984917841438,"score_gpt":0.3991517077025609,"score_spread":0.1984532159184171,"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."}}