{"id":"W3044731091","doi":"10.48550/arxiv.1909.07459","title":"Bridging Visual Perception with Contextual Semantics for Understanding Robot Manipulation Tasks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Bridging (networking); Robot; Human–computer interaction; Semantics (computer science); Perception; Tuple; Artificial intelligence; Ontology; Natural language processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004840085,0.0006244411,0.000261601,0.001367389,0.0004336071,0.001528936,0.0008385917,0.0007588403,0.002750395],"category_scores_gemma":[0.002414199,0.0003254886,0.0008407708,0.0008871399,0.001382633,0.003026822,0.001763222,0.0008967394,0.0005025376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008517377,"about_ca_system_score_gemma":0.0008640622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005667718,"about_ca_topic_score_gemma":0.00677842,"domain_scores_codex":[0.9996653,0.0001057507,0.0000210063,0.0001054285,0.00007481942,0.00002779029],"domain_scores_gemma":[0.999455,0.0002158475,0.00006961646,0.0001388692,0.00008171943,0.00003895407],"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":[0.0002039068,0.000256016,0.003294314,0.0008106935,0.0001275403,0.001133458,0.004623618,0.09718528,0.05161731,0.3938598,0.00687737,0.4400107],"study_design_scores_gemma":[0.00002806391,0.000112833,0.00369706,0.0002458667,0.0001297963,0.0005384705,0.002147481,0.4449302,0.02412178,0.4734939,0.05046297,0.00009152255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0133163,0.0002956304,0.98067,0.0003900448,0.00002397891,0.00008036577,0.0003135831,0.001142307,0.003767782],"genre_scores_gemma":[0.4289432,0.0007373064,0.5672959,0.0001638686,0.00002903048,0.0001652882,0.001082217,0.0002601022,0.001323066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005667718,"threshold_uncertainty_score":0.01126945,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.125483121631795,"score_gpt":0.2426436539427157,"score_spread":0.1171605323109207,"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."}}