{"id":"W4415668195","doi":"10.2196/81936","title":"Integrating a Large Language Model Into a Socially Assistive Robot in a Hospital Geriatric Unit: Two-Wave Comparative Study on Performance, Engagement, and User Perceptions","year":2025,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Perception; Quality (philosophy); Robot; Human–robot interaction; Social robot; Social relation; Robotics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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":[0.008612921,0.0006811253,0.0007378598,0.0008099728,0.001159105,0.00148587,0.0007108065,0.0008366578,0.001142098],"category_scores_gemma":[0.01557928,0.0005088096,0.0007079597,0.0003980922,0.001171682,0.00140381,0.00203378,0.0008700138,0.0004037333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001291956,"about_ca_system_score_gemma":0.001076475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003864957,"about_ca_topic_score_gemma":0.007289381,"domain_scores_codex":[0.9960572,0.002414651,0.0002769552,0.0003124022,0.0004626442,0.0004763374],"domain_scores_gemma":[0.9923347,0.003089869,0.001028083,0.0005068724,0.001971639,0.001068793],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.005728159,0.03306104,0.4157673,0.0008691225,0.000321757,0.001516501,0.4408204,0.0007354446,0.01929242,0.0002454593,0.001224935,0.08041747],"study_design_scores_gemma":[0.0004471151,0.06569855,0.6685648,0.0001399952,0.0002315199,0.0005775793,0.2519544,0.002688021,0.005631127,0.0001561663,0.00369379,0.0002169675],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9996599,0.000009724391,0.0001168227,0.000009582653,0.000001740789,0.00006656737,0.00001165875,0.000002520494,0.0001213763],"genre_scores_gemma":[0.9980851,0.00006508086,0.0008383452,0.00005747821,0.00000750992,0.0003609617,0.00006848624,0.000006686637,0.0005102615],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008612921,"threshold_uncertainty_score":0.04554999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07888930352055695,"score_gpt":0.4376293429680049,"score_spread":0.3587400394474479,"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."}}