{"id":"W4403679217","doi":"10.1063/5.0234204","title":"Applying different analysis methods to the CCT-K7.2021 key comparison","year":2024,"lang":"en","type":"article","venue":"AIP conference proceedings","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Key (lock); Computer science; Computer security","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":[0.01041276,0.001213384,0.0009461833,0.004333728,0.001576879,0.003908781,0.001966326,0.001630816,0.02559775],"category_scores_gemma":[0.03727413,0.0003619351,0.002366602,0.004934968,0.0007307464,0.002298771,0.00230703,0.001995153,0.005244663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004246667,"about_ca_system_score_gemma":0.005425973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03284872,"about_ca_topic_score_gemma":0.02727779,"domain_scores_codex":[0.9901501,0.003970489,0.0004877394,0.0007302373,0.0040563,0.0006052207],"domain_scores_gemma":[0.9813028,0.007024497,0.0005635722,0.002036647,0.008775096,0.0002973653],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004047422,0.0006407443,0.0185422,0.0021595,0.001621536,0.0002643334,0.0006031498,0.1608568,0.01230157,0.1890972,0.09157937,0.5182863],"study_design_scores_gemma":[0.0005953481,0.001025068,0.03077408,0.0007415522,0.001054377,0.0002232929,0.001408768,0.6626583,0.03663292,0.1536272,0.1106366,0.0006226246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1291817,0.003077166,0.7019749,0.003070774,0.001973121,0.001723204,0.02073241,0.004204619,0.1340621],"genre_scores_gemma":[0.6171189,0.001129551,0.3381582,0.0009017139,0.0002797952,0.001740147,0.01828629,0.002777236,0.01960814],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03284872,"threshold_uncertainty_score":0.08563298,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3225083629447883,"score_gpt":0.4797785808671653,"score_spread":0.1572702179223771,"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."}}