{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01505542,0.0008004756,0.0005997262,0.001378875,0.001916542,0.002915499,0.004568505,0.001751478,0.002002401],"category_scores_gemma":[0.05278422,0.0007002518,0.0009552644,0.002638525,0.003746551,0.002952112,0.004099984,0.00287271,0.001096632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002309327,"about_ca_system_score_gemma":0.002733187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0150148,"about_ca_topic_score_gemma":0.008511814,"domain_scores_codex":[0.9858449,0.005982573,0.0009570018,0.001008252,0.005519432,0.0006879102],"domain_scores_gemma":[0.9400955,0.03083673,0.001908543,0.01732944,0.008555413,0.001274349],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.005054662,0.002642793,0.1833803,0.002802614,0.0008780628,0.008055892,0.01523787,0.3329779,0.02587532,0.1148752,0.08779189,0.2204276],"study_design_scores_gemma":[0.001254222,0.001895436,0.03435406,0.0005269552,0.0003978987,0.001683575,0.003021281,0.673615,0.08811569,0.03423119,0.1604091,0.0004956623],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8919304,0.001010668,0.05038576,0.003635821,0.0004368862,0.0005110439,0.002028077,0.02343428,0.0266271],"genre_scores_gemma":[0.9231311,0.0003588359,0.06434731,0.0004997781,0.00009146395,0.000336721,0.002516071,0.004925899,0.003792787],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9849446,"threshold_uncertainty_score":0.07962161,"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."}}