{"id":"W4313562939","doi":"10.1109/humanoids53995.2022.10000141","title":"A Standardized Benchmark for Humanoid Whole-Body Manipulation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids)","topic":"Robotic Locomotion and Control","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Benchmarking; Humanoid robot; Computer science; Set (abstract data type); Key (lock); Human–computer interaction; Focus (optics); Artificial intelligence; Robot; Simulation; 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":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006304689,0.0006600674,0.0006438312,0.0007028782,0.001074543,0.0003939747,0.001263338,0.0001647376,0.01225025],"category_scores_gemma":[0.00005268652,0.0007548233,0.0004366193,0.0003035745,0.0001042575,0.0004311086,0.0001939271,0.0008350042,0.0002462165],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001023759,"about_ca_system_score_gemma":0.0001676778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002250129,"about_ca_topic_score_gemma":0.00003084915,"domain_scores_codex":[0.9957556,0.0001876232,0.001006129,0.0008850608,0.001422602,0.000742968],"domain_scores_gemma":[0.9982758,0.0001412714,0.0002872386,0.0006961181,0.0003832394,0.0002163645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005671796,0.0005998745,0.0002244625,0.0001251222,0.0007243878,0.0000382731,0.001115986,0.5189575,0.07095065,0.3460996,0.0569965,0.003600502],"study_design_scores_gemma":[0.0121074,0.001409232,0.002351329,0.0001609281,0.0002378719,0.00005864968,0.001566594,0.849798,0.005461808,0.02140784,0.1028186,0.002621809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2150071,0.0008447893,0.3436441,0.006406837,0.03686078,0.009943377,0.003579858,0.004637855,0.3790754],"genre_scores_gemma":[0.9788251,0.00006696452,0.000634152,0.0006449115,0.0008499313,0.001688323,0.001377869,0.0001621372,0.01575061],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.763818,"threshold_uncertainty_score":0.9994903,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03545382935288508,"score_gpt":0.2791332350138127,"score_spread":0.2436794056609276,"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."}}