{"id":"W4407638996","doi":"10.1109/tgrs.2025.3542803","title":"A Weakly Supervised Learning Approach for Sea Ice Stage of Development Classification From AI4Arctic Sea Ice Challenge Dataset","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Geoscience and Remote Sensing","topic":"Arctic and Antarctic ice dynamics","field":"Earth and Planetary Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary; University of Waterloo","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; Environment and Climate Change Canada","keywords":"Sea ice; Stage (stratigraphy); Geology; Remote sensing; Computer science; Artificial intelligence; Climatology; Paleontology","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":[0.0004080018,0.0001645952,0.0002039501,0.0001597082,0.0007860754,0.00005864968,0.0001478586,0.00009193354,0.00002470773],"category_scores_gemma":[0.00001928813,0.0001452518,0.00004826182,0.0003468418,0.0002158771,0.0002397651,0.000002211258,0.0002475093,0.000004595063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001777242,"about_ca_system_score_gemma":0.0001928632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004191094,"about_ca_topic_score_gemma":0.001056296,"domain_scores_codex":[0.9986244,0.00007833205,0.0002865299,0.0004609388,0.0002492394,0.0003005193],"domain_scores_gemma":[0.9992383,0.000300614,0.00009692206,0.0002020932,0.00007002732,0.00009200897],"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":[0.0001261087,0.00005575406,0.0003536227,0.0001977837,0.00004516408,0.000002258389,0.00128153,0.008137533,0.0007333655,0.000009453946,0.00001312571,0.9890443],"study_design_scores_gemma":[0.0003361099,0.0000839701,0.005999986,0.0001008586,0.00004969273,0.000004643818,0.0029551,0.9875851,0.0007009421,0.00005636356,0.001947354,0.0001799172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1709089,0.00004206322,0.8273618,0.0002788779,0.0002207688,0.0002507036,0.0004942986,0.00002946469,0.000413099],"genre_scores_gemma":[0.8633695,0.0001877288,0.1352939,0.0001617809,0.00001864303,2.271973e-7,0.0004560085,0.000004549299,0.0005076485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9888644,"threshold_uncertainty_score":0.6335708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0291244200041646,"score_gpt":0.2443328289850515,"score_spread":0.2152084089808869,"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."}}