{"id":"W4413274834","doi":"10.1016/j.bspc.2025.108347","title":"Supervised sequential contrastive regression: Improving performance on imbalanced rehabilitation exercises","year":2025,"lang":"en","type":"article","venue":"Biomedical Signal Processing and Control","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Manitoba; Toronto Rehabilitation Institute; University Health Network","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Regression; Rehabilitation; Artificial intelligence; Machine learning; Regression analysis; Linear regression; Pattern recognition (psychology); Physical medicine and rehabilitation; Statistics; Mathematics; Physical therapy; Medicine","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":[0.0004873874,0.0001912124,0.0002742845,0.0001904912,0.0003412189,0.0002291614,0.0004535979,0.0001390374,0.000008682357],"category_scores_gemma":[0.0001887325,0.0001452558,0.00004228928,0.0004342051,0.0002983291,0.0005122659,0.00008471981,0.000217157,0.000004685861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007413139,"about_ca_system_score_gemma":0.0002338342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007551925,"about_ca_topic_score_gemma":2.608502e-7,"domain_scores_codex":[0.9983144,0.0001020868,0.0003598783,0.0005483172,0.0003772578,0.000298034],"domain_scores_gemma":[0.9989862,0.0003131329,0.0001422808,0.0002636179,0.0001735944,0.0001211695],"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":[0.0001845839,0.0001052226,0.0004458182,0.0001609109,0.00001021656,0.000002943304,0.0001269951,0.000001741038,0.04202682,0.00208937,0.0005057689,0.9543396],"study_design_scores_gemma":[0.006327725,0.001408952,0.02287694,0.001967092,0.00006550519,0.00001159644,0.0001688831,0.9274005,0.02987099,0.004690171,0.004534569,0.000677073],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01562204,0.0003960168,0.9789089,0.003773514,0.0001394859,0.0003486561,0.00001161281,0.000415321,0.0003844818],"genre_scores_gemma":[0.9881287,0.00001991961,0.01065536,0.0008771631,0.00007543841,0.0001255054,0.000013825,0.000006806075,0.00009734243],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9725066,"threshold_uncertainty_score":0.592336,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008597259272130895,"score_gpt":0.2546839958405389,"score_spread":0.246086736568408,"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."}}