{"id":"W4412669506","doi":"10.1007/s11249-025-02014-y","title":"The Surface-Topography Challenge: A Multi-Laboratory Benchmark Study to Advance the Characterization of Topography","year":2025,"lang":"en","type":"article","venue":"Tribology Letters","topic":"Surface Roughness and Optical Measurements","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Division of Civil, Mechanical and Manufacturing Innovation; European Research Council; Deutsche Forschungsgemeinschaft; National Science Foundation","keywords":"Scale (ratio); Benchmarking; Standard deviation; Surface (topology); Benchmark (surveying); Length scale; Characterization (materials science); Absolute deviation; Materials science; Computer science; Artificial intelligence; Geodesy; Nanotechnology; Geometry; Mathematics; Geology; Statistics; Cartography; Geography; Physics","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":[0.0004093227,0.0001680992,0.00022215,0.00009474471,0.0001684109,0.00002075206,0.0003360268,0.00004972938,0.000005963062],"category_scores_gemma":[0.00004713306,0.0001117632,0.00007299233,0.0008439494,0.0001198459,0.00006261617,0.00004546471,0.0001950703,0.000004888172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002272435,"about_ca_system_score_gemma":0.00001044915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005136923,"about_ca_topic_score_gemma":0.00002679864,"domain_scores_codex":[0.9988915,0.0001534441,0.0002988044,0.0001989564,0.0001612762,0.0002960371],"domain_scores_gemma":[0.9992347,0.0001819949,0.00004434953,0.0004184647,0.00008062818,0.00003984494],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002316807,0.000807957,0.24446,0.0001367476,0.001116621,0.00001213839,0.003318579,0.008763984,0.7292768,0.001526397,0.001240694,0.009108354],"study_design_scores_gemma":[0.001641338,0.000200039,0.9726709,0.00006293463,0.0001219983,3.344669e-7,0.001131925,0.001099406,0.009998117,0.00007451103,0.01263261,0.0003658526],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889984,0.0006028427,0.004818351,0.003714245,0.0009453883,0.0007181549,0.0000135859,0.00008283097,0.0001062248],"genre_scores_gemma":[0.9988133,0.0001176454,0.000260776,0.0006858951,0.00002305174,0.00007207109,0.000003751625,0.00001529157,0.000008172494],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7282109,"threshold_uncertainty_score":0.4557571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009346569711041352,"score_gpt":0.2442911795586516,"score_spread":0.2349446098476103,"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."}}