{"id":"W4389584819","doi":"10.17118/11143/20883","title":"On deriving test cases for benchmarking methods for simulating transportcharacteristics of triply periodic minimal surfaces","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Theoretical and Applied Studies in Material Sciences and Geometry","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmarking; Computer science; Test (biology); Geology","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":[0.0003541484,0.0001220419,0.0002447481,0.00004690647,0.0001595258,0.0000195905,0.0000888287,0.00004099621,0.00005056534],"category_scores_gemma":[0.0003813919,0.00009666807,0.00007711106,0.0002266274,0.00008000324,0.00003392228,0.000016636,0.0000351087,9.180348e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009735616,"about_ca_system_score_gemma":0.000003970381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001439133,"about_ca_topic_score_gemma":0.000001524845,"domain_scores_codex":[0.9992225,0.000005757092,0.0002695835,0.0001540422,0.00006679014,0.0002813265],"domain_scores_gemma":[0.9966391,0.003185721,0.00003706635,0.00006877664,0.00002931227,0.000040076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002443262,0.00009030613,0.001008977,0.00204542,0.0001060627,0.000006025646,0.001548929,0.3173296,0.218022,0.05373242,0.0002518386,0.4056141],"study_design_scores_gemma":[0.0006387765,0.0007654856,0.001705037,0.0001347478,0.00005176308,0.000001357253,0.001318031,0.9174954,0.03994662,0.0314723,0.005974213,0.0004963032],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5123274,0.00003010827,0.4862966,0.00002069344,0.0003693461,0.0002513527,0.0001034871,0.0001333371,0.000467669],"genre_scores_gemma":[0.8942669,0.00002905232,0.1054893,0.00001333462,0.00008566936,0.00004281249,0.00001496257,0.00001473328,0.00004318832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6001658,"threshold_uncertainty_score":0.394201,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02396647973279546,"score_gpt":0.3319930909516535,"score_spread":0.308026611218858,"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."}}