{"id":"W4413925758","doi":"10.1109/icra55743.2025.11127531","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Task (project management); Artificial intelligence; Human–computer interaction; Computer vision; Engineering; Systems engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002699109,0.0001359416,0.0001699357,0.0001876902,0.0001552664,0.0001871763,0.0006608624,0.00008294719,0.0000299612],"category_scores_gemma":[0.00008210076,0.0001238924,0.00006800028,0.0006225291,0.00002917079,0.0003386482,0.0001718501,0.0001663052,0.0008425643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007887051,"about_ca_system_score_gemma":0.00007689768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002863247,"about_ca_topic_score_gemma":0.00002975324,"domain_scores_codex":[0.9986898,0.0001095548,0.0002651709,0.0004238348,0.0002084105,0.0003031708],"domain_scores_gemma":[0.99913,0.0001165145,0.00006875908,0.0005091268,0.00008750927,0.00008815934],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005974141,0.0004079579,0.02124312,0.0001294571,0.0001387093,0.00005786659,0.001594635,0.06050925,0.04651473,0.6205435,0.01457101,0.23423],"study_design_scores_gemma":[0.0007438406,0.00007502431,0.0237187,0.0000390312,0.00000953085,0.00001941727,0.0001050741,0.956239,0.005124051,0.004267901,0.009319794,0.0003386525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001931055,0.0000836496,0.9378223,0.0009479917,0.001024125,0.0001832671,2.493832e-7,0.0004510494,0.05755624],"genre_scores_gemma":[0.961231,0.00000377525,0.031185,0.0002266408,0.0001114447,0.00001377925,0.00001024406,0.00000686164,0.007211254],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9592999,"threshold_uncertainty_score":0.9999354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00956508267107371,"score_gpt":0.2367220622426354,"score_spread":0.2271569795715617,"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."}}