{"id":"W4307207473","doi":"10.48550/arxiv.2108.09779","title":"Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Vector Institute","funders":"","keywords":"Computer science; Reinforcement learning; Task (project management); Artificial intelligence; Representation (politics); Object (grammar); Human–computer interaction; Robot; Codebase; Computer vision; Simulation; Source code; 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"],"consensus_categories":[],"category_scores_codex":[0.0001204905,0.0003615033,0.0003878242,0.0004569036,0.0001178511,0.0001464818,0.0002731368,0.0002960473,0.0002770774],"category_scores_gemma":[0.00002597754,0.0005099386,0.0002014781,0.0006093459,0.00001376982,0.0002484827,0.0001383847,0.0006396972,0.00008727176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004445341,"about_ca_system_score_gemma":0.00003480782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001506536,"about_ca_topic_score_gemma":0.001710884,"domain_scores_codex":[0.9984109,0.0001098399,0.0003241883,0.0007358486,0.0001119373,0.0003072892],"domain_scores_gemma":[0.9989381,0.0001184638,0.00007790362,0.0005933403,0.00009596423,0.0001762634],"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":[0.00003347156,0.00001121273,0.002070072,0.00006653106,0.00008632738,0.00009991766,0.0006895867,0.994307,0.000464397,0.0003161463,0.00001660744,0.001838707],"study_design_scores_gemma":[0.0003498424,0.000009396053,0.02725982,0.0002510022,0.0001086203,4.512194e-7,0.00009976051,0.9704564,0.0001479075,0.0005169786,0.000306309,0.0004935028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4947821,0.00002517898,0.5020737,0.00001253356,0.0004115495,0.0002059079,0.000002543153,0.0004077753,0.002078709],"genre_scores_gemma":[0.9967274,0.00007357299,0.001730261,0.00004577895,0.0002088184,6.358206e-7,0.0002169623,0.00008585558,0.0009107346],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5019453,"threshold_uncertainty_score":0.9997352,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025151842495073,"score_gpt":0.2121730388978426,"score_spread":0.1096578546483353,"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."}}