{"id":"W4411801769","doi":"10.1029/2025jf008661","title":"Continental-Scale Machine-Learning Classification of Arctic Glacial Landscapes using Simple Morphometrics","year":2025,"lang":"en","type":"preprint","venue":"Journal of Geophysical Research Earth Surface","topic":"Climate change and permafrost","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Environment Research Council","keywords":"Morphometrics; Arctic; Scale (ratio); Glacial period; Geology; Artificial intelligence; Physical geography; Geography; Computer science; Paleontology; Cartography; Oceanography; Ecology; Biology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002172334,0.0002426261,0.0007479604,0.0006064602,0.0002324214,0.000170725,0.0005969735,0.000243543,0.0013038],"category_scores_gemma":[0.0008356141,0.0002019136,0.0003459614,0.001139407,0.0001839853,0.0001986411,0.0002165953,0.002434544,0.00003927686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002775593,"about_ca_system_score_gemma":0.0004731543,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01172294,"about_ca_topic_score_gemma":0.004519881,"domain_scores_codex":[0.9959983,0.0007140584,0.0007774401,0.0003254817,0.001636705,0.0005479867],"domain_scores_gemma":[0.9958621,0.001727844,0.0006829264,0.0002777369,0.00117304,0.0002763725],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004811599,0.00016103,0.9670238,0.000633047,0.0001070464,0.00003807064,0.0004183837,0.01944971,0.007378071,0.000009923651,0.0002533497,0.004046357],"study_design_scores_gemma":[0.0006755986,0.0005221227,0.7699581,0.0005807899,0.00008626818,0.00001803112,0.000610381,0.2217961,0.001110201,0.0006640633,0.003689935,0.0002884181],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953119,0.001553275,0.0001136945,0.0002031161,0.0004311229,0.0002463484,0.001443691,0.000008657515,0.0006881956],"genre_scores_gemma":[0.9967299,0.001302239,0.0005536478,0.00001491175,0.0004956881,3.406849e-7,0.0005745821,0.000008414098,0.0003202508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2023464,"threshold_uncertainty_score":0.9998669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.111599469978614,"score_gpt":0.3551376928273618,"score_spread":0.2435382228487478,"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."}}