{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001495271,0.0007569636,0.0006958894,0.0005578726,0.0005539084,0.001366996,0.001099036,0.001148326,0.004175396],"category_scores_gemma":[0.00977778,0.0003879721,0.0003152881,0.0004196339,0.0005442735,0.001336,0.001962411,0.0008413114,0.001876494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004891724,"about_ca_system_score_gemma":0.0007478672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003661196,"about_ca_topic_score_gemma":0.003293372,"domain_scores_codex":[0.9991358,0.0003249225,0.00005456849,0.0002947667,0.0001208586,0.00006911193],"domain_scores_gemma":[0.9976295,0.001443982,0.0001773907,0.0003442299,0.000287546,0.0001172713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00593475,0.001473106,0.0174839,0.0009820055,0.0002966401,0.0007802602,0.005771507,0.01156746,0.1199512,0.002253099,0.009376262,0.8241298],"study_design_scores_gemma":[0.001139574,0.003056262,0.07696798,0.0002431593,0.0007669798,0.001696636,0.00313433,0.7285666,0.1560881,0.009903309,0.01805627,0.0003807686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8887064,0.0006213865,0.09456851,0.0004831326,0.0003527348,0.0006219738,0.0005233639,0.008529261,0.005593207],"genre_scores_gemma":[0.923735,0.0001180242,0.07263333,0.000257997,0.00005355975,0.0003109309,0.0004721079,0.0002719983,0.00214714],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004175396,"threshold_uncertainty_score":0.01396811,"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."}}