{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003489678,0.002099876,0.001526969,0.001796015,0.0007245996,0.001878249,0.003250456,0.001938471,0.001593711],"category_scores_gemma":[0.02201975,0.0006244268,0.001185208,0.001762813,0.001387964,0.002707336,0.003708068,0.004175481,0.001091727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001064298,"about_ca_system_score_gemma":0.001519912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002865106,"about_ca_topic_score_gemma":0.002621087,"domain_scores_codex":[0.9951367,0.001059138,0.0003277838,0.001593206,0.001656812,0.0002264748],"domain_scores_gemma":[0.9897763,0.004143748,0.001602752,0.002380014,0.001897127,0.0002000207],"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":[0.0003646996,0.000319454,0.01020131,0.0004243115,0.000360172,0.0002563695,0.0003457411,0.5266031,0.02339815,0.03088192,0.009621447,0.3972233],"study_design_scores_gemma":[0.00001535352,0.00007742822,0.001703614,0.00003315743,0.00002474085,0.0001322869,0.00002510825,0.9749976,0.00869302,0.0107801,0.003480258,0.00003740144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004803067,0.0001732266,0.9930273,0.0001512782,0.00009112807,0.00004746052,0.0001898913,0.0009006794,0.0006159613],"genre_scores_gemma":[0.3682795,0.000425892,0.6242748,0.0004711613,0.0004170602,0.000454581,0.001930859,0.0004684995,0.00327759],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003489678,"threshold_uncertainty_score":0.01845539,"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."}}