{"id":"W2132033701","doi":"10.1016/j.ijrmms.2005.03.004","title":"The FEBEX benchmark test: case definition and comparison of modelling approaches","year":2005,"lang":"en","type":"article","venue":"International Journal of Rock Mechanics and Mining Sciences","topic":"Soil and Unsaturated Flow","field":"Engineering","cited_by":146,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Canadian Nuclear Safety Commission","funders":"","keywords":"Inflow; Benchmark (surveying); Geotechnical engineering; Field (mathematics); Scale (ratio); Test data; Geology; Engineering; Mathematics","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":[0.002318618,0.001471157,0.000928802,0.001892544,0.0006894703,0.001608411,0.002364671,0.00239414,0.004529664],"category_scores_gemma":[0.009208448,0.0003699894,0.0008059251,0.001071026,0.0007344087,0.001538801,0.001111598,0.0006268262,0.001192668],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009891617,"about_ca_system_score_gemma":0.000618487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008535957,"about_ca_topic_score_gemma":0.009455108,"domain_scores_codex":[0.9983815,0.0006514835,0.0001375945,0.0001769092,0.0004914251,0.0001611569],"domain_scores_gemma":[0.9956856,0.002115497,0.0002618353,0.000832414,0.0009722861,0.000132443],"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":[0.01067483,0.006635151,0.02971498,0.001387444,0.0003398649,0.002896678,0.0008017148,0.6874341,0.02525772,0.01777927,0.03891515,0.1781631],"study_design_scores_gemma":[0.001376915,0.005828054,0.02698253,0.0002341685,0.0002316621,0.001229213,0.001419836,0.8868316,0.04831626,0.006950416,0.02044857,0.0001506612],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9295357,0.0003740857,0.03678562,0.0005288258,0.0001478088,0.0005239479,0.007170003,0.001342718,0.02359128],"genre_scores_gemma":[0.9575761,0.0001557402,0.02905659,0.0001237348,0.00002911565,0.000445701,0.006846304,0.0003308125,0.005435954],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008535957,"threshold_uncertainty_score":0.01697254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06195118569088796,"score_gpt":0.2585457285016359,"score_spread":0.196594542810748,"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."}}