{"id":"W4408014605","doi":"10.1016/j.eswa.2025.126965","title":"Referring Expression Comprehension in semi-structured human–robot interaction","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"Dalhousie University","funders":"Young Scientists Fund; National Natural Science Foundation of China","keywords":"Computer science; Expression (computer science); Human–robot interaction; Human–computer interaction; Artificial intelligence; Robot; Comprehension; Natural language processing; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":[0.0001461639,0.0002032979,0.0002391418,0.000351551,0.0003960582,0.0001704891,0.0007500869,0.0001041549,0.000005354304],"category_scores_gemma":[0.000011653,0.0001756132,0.0000355619,0.0009275023,0.0000369816,0.0003095846,0.0002072775,0.0003269672,0.00003531644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002001193,"about_ca_system_score_gemma":0.00005028578,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001390237,"about_ca_topic_score_gemma":0.00008363291,"domain_scores_codex":[0.9983258,0.0001215919,0.0004318127,0.00065269,0.0002237809,0.0002443572],"domain_scores_gemma":[0.9983141,0.0001284683,0.0001867992,0.001187439,0.0001078763,0.00007526482],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003476164,0.0004295099,0.01992868,0.0001858067,0.0000469525,0.000004621338,0.002794595,0.07834681,0.6281351,0.2532812,0.002136252,0.01467568],"study_design_scores_gemma":[0.003253541,0.0001251385,0.1729838,0.002200429,0.00002171377,0.0001000146,0.001341738,0.592723,0.03094971,0.003022995,0.1917879,0.001490171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02657511,0.0003401058,0.9659927,0.0007899862,0.0001620185,0.001389743,0.000001761748,0.0004972421,0.004251309],"genre_scores_gemma":[0.9692498,0.000006468664,0.02727165,0.0001102606,0.00007100459,0.002984495,0.00002712932,0.00001641064,0.0002628182],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9426746,"threshold_uncertainty_score":0.7161299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01705013750644576,"score_gpt":0.3216777303456205,"score_spread":0.3046275928391748,"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."}}