{"id":"W4317612585","doi":"10.1088/0026-1394/60/1a/09001","title":"Final report on the key comparison CCAUV.A-K6","year":2023,"lang":"en","type":"article","venue":"Metrologia","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Mutual recognition; Library science; Calibration; Mathematics; Statistics; Computer science; Business","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03544364,0.002009675,0.001776156,0.006615478,0.003243931,0.009396625,0.004721716,0.003689246,0.3044528],"category_scores_gemma":[0.09724509,0.0009848324,0.002221003,0.005663266,0.001055873,0.005387418,0.006128215,0.003345006,0.232649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006277427,"about_ca_system_score_gemma":0.0202528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01305378,"about_ca_topic_score_gemma":0.008286569,"domain_scores_codex":[0.9653696,0.006800989,0.003024272,0.002540865,0.01981218,0.002452062],"domain_scores_gemma":[0.8745992,0.009344866,0.003945489,0.009692417,0.09841795,0.004000082],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0007953879,0.0001033524,0.0007533145,0.001237382,0.00004384298,0.0001011109,0.0001460558,0.0003965148,0.001349086,0.007239769,0.9310116,0.05682258],"study_design_scores_gemma":[0.00009539301,0.0001770578,0.003358837,0.0007026585,0.00003461987,0.00007742464,0.0002999009,0.0001665878,0.001998482,0.002427197,0.9906052,0.00005668047],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.008220887,0.003494665,0.03803555,0.01471485,0.03514442,0.01911686,0.4409316,0.008168792,0.4321724],"genre_scores_gemma":[0.04319349,0.004011071,0.07826055,0.008393546,0.004687012,0.03731659,0.3732824,0.01141413,0.4394412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3044528,"threshold_uncertainty_score":0.9921137,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6341346036138763,"score_gpt":0.478842459702077,"score_spread":0.1552921439117993,"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."}}