{"id":"W4408182097","doi":"10.1007/s12369-025-01223-8","title":"Social Referencing Disambiguation with Robot Mental Imagery for Domestic Service Robots: System Implementation and Validation in an Object Selection Task","year":2025,"lang":"en","type":"article","venue":"International Journal of Social Robotics","topic":"Social Robot Interaction and HRI","field":"Psychology","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Canada Research Chairs; Canada Foundation for Innovation","keywords":"Task (project management); Artificial intelligence; Service robot; Selection (genetic algorithm); Robot; Computer science; Object (grammar); Robotics; Service (business); Computer vision; Human–computer interaction; Mental image; Psychology; Natural language processing; Engineering; Cognition","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":[0.0004616541,0.0001554816,0.0002631016,0.0004264778,0.0002534558,0.0001814904,0.000165859,0.0001313054,0.00003596109],"category_scores_gemma":[0.00004162057,0.000158699,0.00007946139,0.0003139092,0.00003572842,0.0005754407,0.00002436553,0.0002362725,0.000002829016],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008872717,"about_ca_system_score_gemma":0.0002001843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002675549,"about_ca_topic_score_gemma":0.000843156,"domain_scores_codex":[0.9983863,0.0001899088,0.0006615742,0.0001993081,0.0003743214,0.0001885624],"domain_scores_gemma":[0.9981115,0.0001519738,0.0006372404,0.00004058567,0.001016666,0.0000419836],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.01491396,0.002833515,0.1128986,0.0005869691,0.004745446,0.0001444113,0.1430485,0.04459636,0.03976605,0.4628869,0.008558369,0.1650209],"study_design_scores_gemma":[0.02512817,0.001612813,0.7516307,0.0008198719,0.001134507,0.0005883829,0.1940043,0.01341667,0.001785483,0.007633818,0.001000306,0.001245011],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7831292,0.00005203025,0.1976127,0.0117226,0.005105601,0.0008940661,0.00004774002,0.00007810797,0.001357973],"genre_scores_gemma":[0.9966028,0.0000048231,0.002052468,0.0002990207,0.0007822757,0.00003065961,0.0001135349,0.0000207815,0.00009366206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6387321,"threshold_uncertainty_score":0.6471556,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04009459867038474,"score_gpt":0.4359820192505962,"score_spread":0.3958874205802115,"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."}}