{"id":"W7124309595","doi":"10.65109/yyrj6883","title":"OPEx: A Large Language Model-Powered Framework for Embodied Instruction Following","year":2024,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada); Université de Montréal","funders":"","keywords":"Embodied cognition; Bridge (graph theory); Natural language; Language model; Language assessment; Higher education","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008144792,0.000419041,0.0003908959,0.0003080164,0.0006268403,0.001397253,0.001141209,0.0003589077,0.0001626496],"category_scores_gemma":[0.0003556773,0.000417603,0.0005263601,0.001108249,0.00003975321,0.0008313212,0.0005161471,0.0008399312,0.0003771847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001730133,"about_ca_system_score_gemma":0.0002943891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002403334,"about_ca_topic_score_gemma":0.00002899606,"domain_scores_codex":[0.9966832,0.00009488984,0.0005957672,0.001362407,0.0004464071,0.0008173521],"domain_scores_gemma":[0.9978454,0.0004716914,0.0001091621,0.001250451,0.00008806955,0.000235293],"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":[0.00001209811,0.00009473706,0.00006605477,0.0001532175,0.0001291417,0.000009308929,0.007260625,0.004388347,0.0005623308,0.8865938,0.0003061296,0.1004242],"study_design_scores_gemma":[0.000522856,0.00006919447,0.0001080722,0.0002635177,0.00007736144,0.000008752744,0.0002275424,0.9012272,0.0002400263,0.09467531,0.002140751,0.0004393576],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02871681,0.00124629,0.9548893,0.003897634,0.002359708,0.001234045,0.00006040763,0.001203811,0.006392016],"genre_scores_gemma":[0.5968322,0.00001164506,0.401118,0.0003284115,0.0002613259,0.0002279098,0.00001903939,0.00004987116,0.001151599],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8968389,"threshold_uncertainty_score":0.9998276,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01866547196441454,"score_gpt":0.3408533074043221,"score_spread":0.3221878354399075,"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."}}