{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000319347,0.00005227043,0.00008039847,0.00007427546,0.0001203661,0.00007616678,0.0001194767,0.00002537371,0.000001439952],"category_scores_gemma":[0.00004117038,0.00003502706,0.00002047797,0.00005973689,0.00001467723,0.0001642257,0.00001926635,0.00008219959,1.277983e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001050748,"about_ca_system_score_gemma":0.00001517243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000324587,"about_ca_topic_score_gemma":0.00001109233,"domain_scores_codex":[0.9994437,0.000005847118,0.0002262482,0.00005213843,0.0002013943,0.00007066596],"domain_scores_gemma":[0.9995479,0.000205126,0.0001096421,0.00002176733,0.00008454033,0.00003100677],"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":[0.000008504447,0.0000186976,0.0003376956,0.00000555511,0.00003688489,0.00001311079,0.001277562,0.9416988,0.0002294228,0.006343749,0.00008365873,0.04994632],"study_design_scores_gemma":[0.0001170014,0.00006591573,0.00001164291,0.00004661191,0.000009958255,0.0006882466,0.001982995,0.9940166,0.0006163424,0.002150471,0.0002517398,0.00004250544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9690105,0.002936837,0.02689828,0.0002917217,0.0003468969,0.00001928827,0.000003151828,0.00000610477,0.0004871759],"genre_scores_gemma":[0.9933292,0.0004604011,0.006106685,0.000008704439,0.0000861124,4.465073e-7,3.025239e-7,0.000002715655,0.000005472681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05231773,"threshold_uncertainty_score":0.1428362,"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."}}