{"id":"W7092316688","doi":"","title":"Reinforcement Learning for Unsupervised Domain Adaptation in Spatio-Temporal Echocardiography Segmentation","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Data Analysis and Archiving","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Mitacs; Agence Nationale de la Recherche","keywords":"Segmentation; Consistency (knowledge bases); Adaptation (eye); Reinforcement learning; Noise (video); Reliability (semiconductor); Domain (mathematical analysis); Landmark; Key (lock)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00194482,0.000251636,0.0004088235,0.0006900416,0.001020004,0.0002040455,0.0003291694,0.0001206616,0.0001279863],"category_scores_gemma":[0.0002199327,0.0002804104,0.000385365,0.002011411,0.0001615593,0.000748973,0.0001020439,0.0002521613,0.00002293371],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055706,"about_ca_system_score_gemma":0.0002433566,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002802895,"about_ca_topic_score_gemma":0.003584863,"domain_scores_codex":[0.9970549,0.0005423398,0.0008332937,0.0005798911,0.000439143,0.0005504681],"domain_scores_gemma":[0.9988961,0.0003065367,0.0003205657,0.0002554404,0.0001214712,0.00009984973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008901086,0.00006825936,0.9378157,0.00007804429,0.0001834252,0.00000178239,0.01476546,0.03072381,0.0003973205,0.002065009,0.0001412229,0.01367094],"study_design_scores_gemma":[0.003521051,0.0003039838,0.7506469,0.0006638644,0.0004093342,9.236858e-8,0.09783149,0.1121172,0.0005076747,0.003130219,0.03009378,0.0007744661],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8693368,0.0002029058,0.1238565,0.001007048,0.0004122928,0.0009913042,0.000009557718,0.00004233132,0.004141196],"genre_scores_gemma":[0.995545,0.0005908391,0.00164308,0.0002554741,0.0001589664,0.0001564203,0.0006248226,0.00001598607,0.001009377],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1871689,"threshold_uncertainty_score":0.9999648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03370322623975175,"score_gpt":0.3049587498582225,"score_spread":0.2712555236184707,"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."}}