{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208061,0.001592969,0.0009018239,0.0007571425,0.0006802343,0.001787467,0.003628282,0.001667258,0.01460319],"category_scores_gemma":[0.004752511,0.001051484,0.002220927,0.0005087286,0.0009794603,0.003066624,0.003746346,0.003367029,0.004717906],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009342418,"about_ca_system_score_gemma":0.001964764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006100857,"about_ca_topic_score_gemma":0.01370184,"domain_scores_codex":[0.9994057,0.0001685896,0.00003664551,0.0001978317,0.0001374155,0.00005382613],"domain_scores_gemma":[0.9990965,0.0004800641,0.00006076109,0.0001872118,0.000116255,0.0000591945],"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":[0.0005022025,0.0003363847,0.003019532,0.0007089843,0.0003118346,0.0007450165,0.0005770976,0.3714185,0.01169462,0.0822639,0.03764369,0.4907782],"study_design_scores_gemma":[0.00003094393,0.00004587732,0.0001702049,0.00003457471,0.00001984879,0.00007638412,0.00003875335,0.9531094,0.001766631,0.03444844,0.01024322,0.00001563718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003030714,0.0001953448,0.9780751,0.0002300868,0.00007543532,0.0001289504,0.0007398746,0.01580996,0.001714496],"genre_scores_gemma":[0.1301056,0.0003752936,0.8509617,0.0005137491,0.00009824734,0.0008021648,0.00507294,0.003341502,0.00872881],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01460319,"threshold_uncertainty_score":0.04885256,"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."}}