{"id":"W7111355838","doi":"10.1080/02626667.2025.2596274","title":"A benchmark test problem for reservoir simulation models and comparison of their results","year":2025,"lang":"en","type":"article","venue":"Hydrological Sciences Journal","topic":"Reservoir Engineering and Simulation Methods","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"WSP (Canada)","funders":"","keywords":"Reservoir simulation; Simulation modeling; Benchmark (surveying); Reservoir modeling; Mathematical model","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":[],"consensus_categories":[],"category_scores_codex":[0.004003106,0.001101638,0.0009545338,0.001374772,0.0007149418,0.001320782,0.001343371,0.001502719,0.002281661],"category_scores_gemma":[0.02344919,0.0004272835,0.0008229645,0.001735655,0.0007513769,0.001527975,0.001002205,0.00113507,0.0002168128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001485954,"about_ca_system_score_gemma":0.001019506,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01117645,"about_ca_topic_score_gemma":0.007933306,"domain_scores_codex":[0.9973683,0.001681234,0.0001806131,0.0001887006,0.0003626413,0.0002186003],"domain_scores_gemma":[0.9826545,0.01347243,0.0006423882,0.001336229,0.001645871,0.0002486444],"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":[0.0002814693,0.0004412063,0.005360374,0.0002120106,0.00007983517,0.0001041189,0.00006922764,0.9666159,0.0009467976,0.008504889,0.001866097,0.015518],"study_design_scores_gemma":[0.00004662677,0.0001939838,0.0007519727,0.00001829216,0.0000125096,0.00002503348,0.00007175335,0.9943574,0.00188265,0.002051008,0.0005776367,0.00001105397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8394471,0.001079532,0.1305576,0.001151143,0.0002342885,0.0003837227,0.003207116,0.001742652,0.02219687],"genre_scores_gemma":[0.937631,0.0002248931,0.05916508,0.00007703948,0.00001726867,0.000208262,0.001565389,0.0001771367,0.0009341289],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01117645,"threshold_uncertainty_score":0.02222276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07694352462050204,"score_gpt":0.3585060137635075,"score_spread":0.2815624891430055,"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."}}