{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001329392,0.0008180852,0.0003462562,0.0003812534,0.000219427,0.0004793378,0.001393507,0.0007810437,0.001627313],"category_scores_gemma":[0.003655554,0.0003753103,0.000542093,0.000191692,0.0007278263,0.0006945494,0.000574186,0.000913237,0.0002114829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154942,"about_ca_system_score_gemma":0.001038288,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008228226,"about_ca_topic_score_gemma":0.008222112,"domain_scores_codex":[0.9995241,0.0001285721,0.00002829943,0.00008986639,0.000158484,0.00007059131],"domain_scores_gemma":[0.9982399,0.001011013,0.000157214,0.0002035966,0.0002914988,0.00009672429],"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":[0.0002199773,0.0001177325,0.00406558,0.00007174549,0.00004034868,0.0001313105,0.00007682463,0.9682776,0.007314499,0.001104141,0.0007140205,0.01786628],"study_design_scores_gemma":[0.00000894416,0.00007324659,0.0003769056,0.000004963857,0.000003827047,0.00001562112,0.00001078927,0.9928807,0.006088459,0.0003210457,0.0002115361,0.00000390892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8380839,0.0002385055,0.1529562,0.0003211786,0.00009207446,0.00009490142,0.0002716559,0.003845713,0.004095806],"genre_scores_gemma":[0.9731407,0.00003856221,0.02584065,0.00005718993,0.000002896991,0.00003377992,0.0001891517,0.00007432763,0.00062267],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008228226,"threshold_uncertainty_score":0.01636064,"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."}}