{"id":"W4405744884","doi":"10.1016/j.measen.2024.101361","title":"Project on a fully automated evaluation of a virtual comparison of mass using the Digital Calibration Certificate (DCC) schema","year":2024,"lang":"en","type":"article","venue":"Measurement Sensors","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Schema (genetic algorithms); Certificate; Information retrieval; Theoretical computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.02613373,0.000214078,0.0003630137,0.0006232018,0.0001849351,0.0005542775,0.0004561828,0.00008815566,0.0001854155],"category_scores_gemma":[0.006132606,0.0001309555,0.0001995769,0.001882883,0.000173209,0.0004289306,0.00003561708,0.0001432802,0.00005125856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003402057,"about_ca_system_score_gemma":0.0007514214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003476268,"about_ca_topic_score_gemma":0.00002502406,"domain_scores_codex":[0.9835108,0.001174504,0.001462957,0.0006396667,0.01295352,0.0002585927],"domain_scores_gemma":[0.9955475,0.0004583071,0.0005966827,0.000685274,0.002661478,0.00005077058],"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":[0.0003760457,0.0003980884,0.003504346,0.00005943123,0.0002350019,0.000001094528,0.006596855,0.2549443,0.667984,0.001030381,0.01456306,0.05030734],"study_design_scores_gemma":[0.0003631125,0.0001573304,0.0008804587,0.0001693681,0.0001460845,8.754596e-7,0.002643913,0.8835639,0.1107967,0.0006095599,0.00054021,0.0001284226],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9869332,0.0002029179,0.00791706,0.0005034137,0.001179555,0.00138743,0.00003077686,0.0001422352,0.001703411],"genre_scores_gemma":[0.9995502,6.472715e-7,0.0001571648,0.00001092711,0.00006199776,0.00002351032,0.00001817805,0.00001601427,0.0001613185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6286196,"threshold_uncertainty_score":0.9057481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7345176661176916,"score_gpt":0.4978454164453797,"score_spread":0.2366722496723119,"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."}}