{"id":"W4321648896","doi":"10.48550/arxiv.2302.10986","title":"The FluidFlower International Benchmark Study: Process, Modeling Results, and Comparison to Experimental Data","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Deutsche Forschungsgemeinschaft; Energi Simulation; National Science Foundation","keywords":"Benchmarking; Benchmark (surveying); Computer science; Process (computing); Ranking (information retrieval); Software deployment; Scale (ratio); Experimental data; Petrophysics; Data mining; Machine learning; Engineering; Statistics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005417792,0.0002262339,0.0002152016,0.0001377054,0.0001392475,0.0001510477,0.001133414,0.0001109823,0.000005154958],"category_scores_gemma":[0.000127735,0.0002239695,0.00003665185,0.0002232429,0.00002201002,0.0001564321,0.001286312,0.0004067637,0.00001390433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110526,"about_ca_system_score_gemma":0.00002367854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005829945,"about_ca_topic_score_gemma":0.00004158529,"domain_scores_codex":[0.9987255,0.00005453409,0.0002692808,0.0006155444,0.0001266188,0.0002085562],"domain_scores_gemma":[0.9986808,0.0001458427,0.00003853576,0.0009513978,0.00007116045,0.0001122164],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005659129,0.00002859307,0.0007701131,0.0000215584,0.0001224524,0.00001533289,0.0006032901,0.9974267,0.00001272666,0.00007254473,0.0007942758,0.0000758391],"study_design_scores_gemma":[0.0004426928,0.00002046079,0.0002143515,0.00004475418,0.00002563554,3.285336e-7,0.001493743,0.996541,0.00002592398,0.0001862417,0.0007690379,0.000235847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.862472,0.0001620842,0.134839,0.00005195564,0.00120433,0.000363773,0.0000891227,0.0003811671,0.0004365273],"genre_scores_gemma":[0.9981906,0.000119524,0.0009406663,0.000003852601,0.0001217231,0.000003210472,0.0001031704,0.00004077517,0.0004764136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1357187,"threshold_uncertainty_score":0.9133212,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2038416776683454,"score_gpt":0.2954768178291744,"score_spread":0.09163514016082897,"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."}}