{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.03056512,0.0001144438,0.0002196002,0.0003673535,0.0003684602,0.0003075039,0.0008706667,0.00006688544,0.002288889],"category_scores_gemma":[0.02319312,0.00005731907,0.0001217756,0.002332143,0.0001318455,0.00008855251,0.0001045997,0.0001807347,0.008137373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005014591,"about_ca_system_score_gemma":0.00006415034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000170962,"about_ca_topic_score_gemma":0.00004786015,"domain_scores_codex":[0.9947078,0.000562384,0.0006429767,0.0005437786,0.003234808,0.0003082355],"domain_scores_gemma":[0.9958915,0.00238036,0.0003158675,0.0009845647,0.000369385,0.0000583984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00006331573,0.00005174368,0.1033964,6.651229e-7,0.00001695939,0.00003034661,0.0003377408,0.001828123,0.001384865,0.004670854,0.872332,0.01588697],"study_design_scores_gemma":[0.0005464793,0.0003069946,0.6005475,0.000008941241,0.00003063792,0.000010718,0.00139533,0.07030374,0.003032071,0.04775801,0.2758135,0.0002460694],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9499675,0.00002510933,0.001365563,0.01291107,0.002194835,0.0002480762,0.000003594696,0.0001395602,0.03314469],"genre_scores_gemma":[0.9798476,9.423672e-7,0.0001217935,0.0005198463,0.0001202156,0.00002568836,0.00001468649,0.00000482669,0.01934442],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5965186,"threshold_uncertainty_score":0.9986231,"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."}}