{"id":"W4412862136","doi":"10.36227/techrxiv.175416075.52956738/v1","title":"OPEN: A Benchmark Dataset and Baseline for Older Adult Patient Engagement Recognition in Virtual Rehabilitation Learning Environments","year":2025,"lang":"en","type":"article","venue":"","topic":"Telemedicine and Telehealth Implementation","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"J.P. Bickell Foundation","keywords":"Benchmark (surveying); Baseline (sea); Rehabilitation; Physical medicine and rehabilitation; Computer science; Psychology; Artificial intelligence; Machine learning; Human–computer interaction; Medicine; Physical therapy; Geography; Political science; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001316768,0.001717309,0.0009751776,0.001896766,0.00076525,0.001085081,0.001761532,0.001912877,0.003661172],"category_scores_gemma":[0.004620465,0.0002150757,0.001270865,0.001462288,0.0005418626,0.001074678,0.002093409,0.001469009,0.004320557],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001146561,"about_ca_system_score_gemma":0.001030736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01208424,"about_ca_topic_score_gemma":0.02316592,"domain_scores_codex":[0.9984592,0.000326028,0.0002271567,0.0004768404,0.0003037861,0.0002071015],"domain_scores_gemma":[0.9985296,0.0003306803,0.0001871484,0.0003295051,0.0004031518,0.0002199327],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002805015,0.003756635,0.08634806,0.003039326,0.0005963157,0.001641013,0.001009087,0.01487803,0.007442976,0.002236029,0.6025524,0.2736951],"study_design_scores_gemma":[0.001047388,0.003291213,0.3107153,0.001559718,0.0004480115,0.004166568,0.004546878,0.1192046,0.01492103,0.006634104,0.5330399,0.0004252839],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2879415,0.004356911,0.01945918,0.001741395,0.00139077,0.002175383,0.6641045,0.007250214,0.01158011],"genre_scores_gemma":[0.1382029,0.0006606969,0.01864686,0.0004416678,0.0002133095,0.001949312,0.835044,0.0001769356,0.004664251],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01208424,"threshold_uncertainty_score":0.02402782,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02594242508532365,"score_gpt":0.3513047999988734,"score_spread":0.3253623749135498,"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."}}