{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009285277,0.00131824,0.0004847842,0.0003482171,0.000393238,0.0005965923,0.001392688,0.0009077766,0.006300306],"category_scores_gemma":[0.002886438,0.0003639121,0.0007210624,0.0002417018,0.0008664564,0.001498268,0.002674133,0.001595814,0.001625521],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004859287,"about_ca_system_score_gemma":0.0009622767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002635502,"about_ca_topic_score_gemma":0.00610399,"domain_scores_codex":[0.9993774,0.0001965978,0.00002157625,0.0002319608,0.00009871399,0.00007366571],"domain_scores_gemma":[0.9994624,0.0002200408,0.00005344096,0.0001625167,0.00005658007,0.00004497413],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006921693,0.0004749048,0.002878624,0.0006426102,0.0001537942,0.0002942791,0.0005764101,0.2294854,0.0526762,0.01602372,0.02291822,0.6731837],"study_design_scores_gemma":[0.00005575215,0.0004084323,0.001733307,0.00006914475,0.00003646419,0.0002210196,0.0001886803,0.9279881,0.02983087,0.0255567,0.01384034,0.00007124772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05025954,0.0007685532,0.9213092,0.0004254089,0.0001203766,0.0002289597,0.001005074,0.01521216,0.0106707],"genre_scores_gemma":[0.6527994,0.0003951395,0.3259453,0.0006415307,0.00006820776,0.0007519074,0.003682617,0.001237229,0.01447873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006300306,"threshold_uncertainty_score":0.02107662,"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."}}