{"id":"W2979222759","doi":"10.1109/iros40897.2019.8967920","title":"Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGB-D video","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Benchmark (surveying); Clutter; Machine learning; Variety (cybernetics); Artificial intelligence; Generalization; Exploit; Code (set theory); RGB color model; Object (grammar); Source code; Data mining; Radar","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":[0.0006812977,0.002218308,0.001142782,0.00153881,0.0007286203,0.0009954101,0.002725093,0.002058063,0.004189783],"category_scores_gemma":[0.003187657,0.0005319759,0.001186676,0.002111351,0.0009442389,0.001495232,0.002120104,0.001930187,0.005326477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006964759,"about_ca_system_score_gemma":0.001085044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262564,"about_ca_topic_score_gemma":0.02890723,"domain_scores_codex":[0.9989927,0.0000867248,0.00007580181,0.0003388559,0.0003821305,0.0001236272],"domain_scores_gemma":[0.9988818,0.0002101995,0.00009255366,0.0004034713,0.000275636,0.0001364394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001649276,0.00179679,0.02561321,0.004165397,0.0004863693,0.000977444,0.0003535715,0.05032901,0.02350364,0.003058136,0.6784639,0.2096032],"study_design_scores_gemma":[0.0007665671,0.001472988,0.1426264,0.001058929,0.0002805093,0.003532803,0.001327478,0.314347,0.06143482,0.01131499,0.4612716,0.0005659623],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.1925538,0.004808667,0.06791897,0.001536082,0.00117175,0.0009711533,0.675091,0.03798813,0.01796045],"genre_scores_gemma":[0.1365797,0.0007898333,0.04328033,0.0003170532,0.00007802157,0.0005374711,0.8146167,0.0006846437,0.003116192],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.01262564,"threshold_uncertainty_score":0.02510428,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03437643651713025,"score_gpt":0.2705937834996467,"score_spread":0.2362173469825165,"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."}}