{"id":"W4387868960","doi":"10.1145/3627828","title":"Characterizing and Improving Resilience of Accelerators to Memory Errors in Autonomous Robots","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Cyber-Physical Systems","topic":"Radiation Effects in Electronics","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Resilience (materials science); Vulnerability (computing); Robot; Metric (unit); Software deployment; Fault tolerance; Reliability engineering; Soft error; Collision; Fault (geology); Real-time computing; Distributed computing; Artificial intelligence; Electronic 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":[0.0001862087,0.0001721471,0.000296339,0.0003058228,0.00006664813,0.00003402693,0.000213558,0.00007778308,0.000002191726],"category_scores_gemma":[0.00003970428,0.0001840187,0.00005168603,0.0008802106,0.00002673791,0.0002058294,0.000007335038,0.0002563747,0.00004043477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001995021,"about_ca_system_score_gemma":0.00002751251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002120479,"about_ca_topic_score_gemma":0.00005792535,"domain_scores_codex":[0.9988523,0.00005432643,0.0002925439,0.000259348,0.000193439,0.0003481109],"domain_scores_gemma":[0.9991998,0.0002665028,0.00004123714,0.0003685097,0.0000203382,0.000103614],"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":[0.000006608754,0.00002828859,0.00002608201,0.0001146522,0.00001784439,0.000003039638,0.0008883601,0.8892149,0.07809433,0.00005398337,0.00000785349,0.03154409],"study_design_scores_gemma":[0.0003978202,0.0002043475,0.01181108,0.0001848236,0.0000220031,0.000006220566,0.0004067048,0.9359962,0.05035358,0.00004115695,0.0001834947,0.0003926139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904354,0.0000366904,0.008054674,0.00009898279,0.0004787933,0.0004257775,0.00001349744,0.0003358121,0.00012044],"genre_scores_gemma":[0.9995479,0.00001272284,0.0001191302,0.00001376242,0.00006035561,0.0001371849,0.000002355521,0.00004167393,0.0000649205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04678128,"threshold_uncertainty_score":0.7504063,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009961139564098265,"score_gpt":0.2375680408570472,"score_spread":0.2276069012929489,"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."}}