{"id":"W2953387605","doi":"10.1016/j.measurement.2019.06.019","title":"Assessing a binary measurement system: A new plan using targeted verification with conditional sampling and baseline information","year":2019,"lang":"en","type":"article","venue":"Measurement","topic":"Advanced Statistical Process Monitoring","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Binary number; Measure (data warehouse); Plan (archaeology); Phase (matter); Computer science; Baseline (sea); Protocol (science); Word error rate; Sample (material); System of measurement; Data mining; Sampling (signal processing); Statistics; Artificial intelligence; Mathematics; Telecommunications; Detector","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":[0.004846996,0.0001862604,0.0002623935,0.0002324915,0.0002526272,0.0005242844,0.0001832304,0.00005112748,0.00003748853],"category_scores_gemma":[0.001651301,0.0001434878,0.00002602481,0.0004017141,0.00003733952,0.001919337,0.00004601935,0.0001409495,0.00006890006],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007056759,"about_ca_system_score_gemma":0.0004010807,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005753556,"about_ca_topic_score_gemma":0.000007261797,"domain_scores_codex":[0.9943085,0.0001570572,0.0007038835,0.0003815828,0.004191615,0.000257302],"domain_scores_gemma":[0.9973876,0.0001981032,0.0004196105,0.0003062345,0.001511761,0.0001766615],"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":[0.001533607,0.0003546694,0.09537372,0.00147118,0.0003691858,0.00002959742,0.003367325,0.3793754,0.293885,0.01308046,0.0008095051,0.2103503],"study_design_scores_gemma":[0.008152041,0.0007669098,0.3314414,0.00353381,0.0002954229,0.0001695223,0.01764832,0.5974578,0.01267818,0.01196783,0.01384248,0.002046346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06609074,0.0001982865,0.9325585,0.0001113658,0.0002827126,0.0004365729,0.00001373478,0.0000649683,0.0002431709],"genre_scores_gemma":[0.9393026,9.732993e-7,0.0605091,0.00004528832,0.00008967658,0.00001366653,0.00002027662,0.00001142869,0.000006978272],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8732119,"threshold_uncertainty_score":0.5851262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3298990793424701,"score_gpt":0.3921707955939006,"score_spread":0.06227171625143046,"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."}}