{"id":"W4404520551","doi":"10.1109/lra.2024.3502066","title":"GraspAgent 1.0: Adversarial Continual Dexterous Grasp Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Natural Science Foundation of China","keywords":"GRASP; Adversarial system; Computer science; Artificial intelligence; Human–computer interaction","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":[],"consensus_categories":[],"category_scores_codex":[0.0003651455,0.0001954546,0.0001808367,0.0001940607,0.0002520219,0.0006804995,0.0003120353,0.00007481617,0.000008948231],"category_scores_gemma":[0.00006297454,0.0001908635,0.0000733502,0.0003103989,0.00006341414,0.0006983033,0.0001268743,0.0003920241,0.00006138207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006373026,"about_ca_system_score_gemma":0.00003513937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002263795,"about_ca_topic_score_gemma":0.000002123621,"domain_scores_codex":[0.9985119,0.000137054,0.000279127,0.0004472243,0.0003208169,0.0003039063],"domain_scores_gemma":[0.9993865,0.0001963693,0.00008692598,0.0002071638,0.00003192356,0.00009112922],"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":[0.000003740801,0.00001365189,0.0004612602,0.00006126136,0.00005644496,0.0001285476,0.001474758,0.9158947,0.005415304,0.03792998,0.001477454,0.03708292],"study_design_scores_gemma":[0.0002731671,0.00004039767,0.001231189,0.00007408451,0.00002418727,0.00004350814,0.0000262512,0.9944983,0.000185725,0.0004454407,0.00290939,0.0002483968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04065438,0.0001230068,0.9489422,0.006426914,0.002741736,0.0001248685,6.946734e-7,0.0008515324,0.0001346216],"genre_scores_gemma":[0.9426614,0.00001670376,0.05607496,0.0006826975,0.0004023869,0.000006775162,0.000006255766,0.00002398399,0.0001248115],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.902007,"threshold_uncertainty_score":0.7783186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00833948835200547,"score_gpt":0.2396735742048696,"score_spread":0.2313340858528641,"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."}}