{"id":"W4382752352","doi":"10.3390/geosciences13070200","title":"Comparing Flow-R, Rockyfor3D and RAMMS to Rockfalls from the Mel de la Niva Mountain: A Benchmarking Exercise","year":2023,"lang":"en","type":"article","venue":"Geosciences","topic":"Landslides and related hazards","field":"Environmental Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"","keywords":"Rockfall; Computer science; Benchmark (surveying); Predictability; Geology; Landslide; Geotechnical engineering; Mathematics; Statistics; Geodesy","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":[0.0007596847,0.000109257,0.0001236991,0.00003014246,0.0005750425,0.0002104326,0.0004282815,0.00006048893,0.0002346827],"category_scores_gemma":[0.0000434853,0.00006432759,0.0000324476,0.0005701954,0.0002437893,0.0001598563,0.0005236285,0.0001270975,0.000211445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004763375,"about_ca_system_score_gemma":0.00001553472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005163096,"about_ca_topic_score_gemma":0.0006553276,"domain_scores_codex":[0.9987579,0.00005040957,0.0001270831,0.0003310918,0.0003392049,0.0003943297],"domain_scores_gemma":[0.9994538,0.0001970298,0.00003475888,0.0001685047,0.000003312704,0.000142582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002468972,0.00002710945,0.83756,0.000004852601,0.00001122254,0.00002992852,0.01042647,0.043106,0.002591876,0.00005967874,0.01119471,0.09496348],"study_design_scores_gemma":[0.0002142179,0.00003711529,0.8073049,0.00006895317,0.00002058359,0.000009578359,0.00184293,0.15922,0.000276525,0.001812433,0.02897749,0.000215321],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9951127,0.0001563126,0.0004342651,0.0006165667,0.0001849257,0.0001375858,0.000006414965,0.00006314966,0.00328806],"genre_scores_gemma":[0.9976755,0.0002999402,0.001160454,0.0002956258,0.00006259666,0.00001399246,0.000003734086,0.00000623671,0.0004819374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.116114,"threshold_uncertainty_score":0.7805092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009657637205282194,"score_gpt":0.2288640839359528,"score_spread":0.2192064467306706,"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."}}