{"id":"W4283741227","doi":"10.1109/i2mtc48687.2022.9806449","title":"A Novel Method to Estimate Measurement Error in AI-Assisted Measurements","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Observational error; Artificial intelligence; Algorithm; Statistics; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003323694,0.0003362941,0.0003417303,0.00141625,0.0004199148,0.0001990807,0.001581143,0.0001073261,0.0001986214],"category_scores_gemma":[0.0003484166,0.0003872537,0.00006612316,0.001189726,0.00006952742,0.0005518085,0.000869517,0.000736314,0.00001703364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001808098,"about_ca_system_score_gemma":0.0003768625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002032073,"about_ca_topic_score_gemma":0.0004970416,"domain_scores_codex":[0.9947479,0.0002936835,0.0007168491,0.000963037,0.002806311,0.0004722306],"domain_scores_gemma":[0.9983112,0.00002875037,0.0003318285,0.0004560346,0.0007363325,0.0001358664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002017593,0.0008801147,0.02209517,0.00003510266,0.0003583201,0.0000401335,0.001734133,0.02648627,0.5560995,0.06814652,0.0007488528,0.3231741],"study_design_scores_gemma":[0.02082928,0.001908043,0.08453997,0.0006578644,0.0002001416,0.0008609457,0.00564403,0.7359623,0.09043428,0.02078468,0.03455362,0.003624889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0192013,0.00003789801,0.9555601,0.02116298,0.001878593,0.0007899633,0.00001182585,0.0003317996,0.001025512],"genre_scores_gemma":[0.8741906,0.000003300151,0.1238295,0.001178249,0.00002745648,0.0006500632,0.00001184912,0.00002123456,0.00008777619],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8549893,"threshold_uncertainty_score":0.999858,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.13028622222323,"score_gpt":0.3819306952879926,"score_spread":0.2516444730647627,"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."}}