{"id":"W4401792540","doi":"10.1002/esp.5961","title":"Stable rivers: A case study in the application of text‐to‐image generative models for Earth sciences","year":2024,"lang":"en","type":"article","venue":"Earth Surface Processes and Landforms","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Generative grammar; Image (mathematics); Geology; Earth (classical element); Earth science; Computer science; Hydrology (agriculture); Artificial intelligence; Mathematics; Geotechnical engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006283335,0.0000963971,0.0001212005,0.00008876484,0.0002434496,0.0004516352,0.000210236,0.00002343558,8.483013e-7],"category_scores_gemma":[0.00001615821,0.0000550019,0.00001732786,0.0008164525,0.00007482267,0.001071879,0.00004782646,0.00007007411,0.000001584125],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002829881,"about_ca_system_score_gemma":0.0001896275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002606561,"about_ca_topic_score_gemma":0.0006462331,"domain_scores_codex":[0.9991633,0.00002288894,0.0001621295,0.0003229129,0.0001601442,0.0001685776],"domain_scores_gemma":[0.9995801,0.0001073096,0.00004542999,0.0001205201,0.0001172026,0.00002941704],"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":[0.0001275867,0.001003556,0.01634158,0.004335238,0.0001276797,0.0002736276,0.2603385,0.08016629,0.002836726,0.02480013,0.0002070059,0.6094421],"study_design_scores_gemma":[0.0004833212,0.0006221501,0.0002157292,0.0001062365,0.00001639014,0.0004046682,0.01193147,0.9704241,0.00524287,0.009516221,0.0008090556,0.0002277903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4675489,0.0006322563,0.5310405,0.000162542,0.00003517465,0.0004100511,0.000005390805,0.00002868868,0.0001364598],"genre_scores_gemma":[0.9337299,0.0000239179,0.06606587,0.00003548371,0.00001853824,0.00004867934,9.337937e-7,0.000003931191,0.00007275061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8902578,"threshold_uncertainty_score":0.4355129,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02500024917661188,"score_gpt":0.2855391223224504,"score_spread":0.2605388731458386,"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."}}