{"id":"W4403520169","doi":"10.1145/3691620.3695281","title":"In-Simulation Testing of Deep Learning Vision Models in Autonomous Robotic Manipulators","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Robot manipulator; Computer science; Artificial intelligence; Deep learning; Robot vision; Control engineering; Robot; Mobile robot; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002306422,0.0002045635,0.0002967177,0.0004213025,0.00003229766,0.00007183808,0.0006179549,0.0001612494,0.000003125353],"category_scores_gemma":[0.00005264446,0.0002125772,0.00005442639,0.0009753035,0.00002010409,0.0003165591,0.002065797,0.0008779028,0.00001609129],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002050054,"about_ca_system_score_gemma":0.00005524878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009313859,"about_ca_topic_score_gemma":0.00007236045,"domain_scores_codex":[0.9981723,0.00006299365,0.0006017485,0.0007175429,0.0002050857,0.0002403248],"domain_scores_gemma":[0.9987586,0.0003911762,0.0002120949,0.0005348207,0.00006180364,0.00004146928],"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":[7.832951e-7,0.00002100354,0.0003169943,0.00006417502,0.000002029553,0.000007101235,0.000214322,0.9447681,0.00007586296,0.02598605,0.000001003949,0.02854262],"study_design_scores_gemma":[0.00005184977,0.00001411345,0.001026024,0.0001715312,0.000002893831,0.000001721205,0.000005108707,0.7758152,0.00005424632,0.2227087,0.000004977315,0.0001437128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03227173,0.000232354,0.9644195,0.0001733763,0.0002128952,0.0004247645,1.531587e-7,0.0002454543,0.002019716],"genre_scores_gemma":[0.8192853,0.00000743688,0.1805104,0.00002337899,0.00002726545,0.00003689433,0.000002806237,0.00001889364,0.00008767397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7870135,"threshold_uncertainty_score":0.8668646,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04952000702817206,"score_gpt":0.3169745183179272,"score_spread":0.2674545112897551,"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."}}