{"id":"W4412738914","doi":"10.1016/j.oceaneng.2025.122105","title":"Breaking the ice: Video segmentation for close-range ice-covered waters","year":2025,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada; University of Waterloo","funders":"National Research Council Canada; University of Waterloo; National Research Council","keywords":"Geology; Sea ice; Range (aeronautics); Oceanography; Segmentation; Arctic ice pack; Ice wedge; Remote sensing; Computer science; Artificial intelligence; Engineering; Aerospace engineering; Permafrost","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000454167,0.001144387,0.0003652822,0.001480297,0.0004700139,0.0006778758,0.001026442,0.0007072816,0.001697781],"category_scores_gemma":[0.001290438,0.0002900571,0.0005263552,0.0007443952,0.0003575266,0.00108962,0.0007801121,0.0007938452,0.000912416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001036251,"about_ca_system_score_gemma":0.000949227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02832475,"about_ca_topic_score_gemma":0.04110403,"domain_scores_codex":[0.9997683,0.00002454041,0.000009679514,0.0001047563,0.000041941,0.00005076692],"domain_scores_gemma":[0.9997784,0.00005906849,0.0000330586,0.00003683138,0.0000630853,0.00002958418],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001382536,0.0005763932,0.01637843,0.0004066788,0.0001649621,0.000443362,0.000280116,0.1623634,0.06354302,0.002571048,0.03241187,0.7194781],"study_design_scores_gemma":[0.00002618716,0.0001378994,0.007243887,0.00004725662,0.00002984607,0.0001237835,0.00009068508,0.9488476,0.0350819,0.001955348,0.006393766,0.00002187731],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6310129,0.001852992,0.3041533,0.0006365043,0.0005961003,0.0009720283,0.02312106,0.02707471,0.01058041],"genre_scores_gemma":[0.724527,0.0007089501,0.2156274,0.0002298564,0.0001271041,0.0003431785,0.05256217,0.0005318,0.005342561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02832475,"threshold_uncertainty_score":0.05631977,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.005822520211098467,"score_gpt":0.2003142078074806,"score_spread":0.1944916875963821,"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."}}