{"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":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.014073,0.0002636632,0.0005207555,0.0009316492,0.0004373467,0.004158786,0.001478339,0.00008694264,0.002922252],"category_scores_gemma":[0.003706766,0.0001457176,0.0003046943,0.005545963,0.00009671363,0.0004443701,0.0002822187,0.0002964976,0.001013487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001175344,"about_ca_system_score_gemma":0.0001323952,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004759505,"about_ca_topic_score_gemma":0.0001495203,"domain_scores_codex":[0.994248,0.0001865349,0.0009105392,0.001128047,0.0030792,0.0004477296],"domain_scores_gemma":[0.9966055,0.001016123,0.0002129014,0.0004686607,0.001471688,0.0002251637],"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":[0.00004316483,0.00008126485,0.07849118,0.0000232409,0.0004411363,0.00000113229,0.0244825,0.0001946595,0.04311859,0.02081785,0.07583912,0.7564662],"study_design_scores_gemma":[0.0001193415,0.0000704651,0.01597024,0.00006494424,0.0005304924,0.000001331469,0.009196452,0.7608566,0.004066763,0.01758867,0.1912079,0.0003268285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1306361,0.0004989158,0.8361162,0.01160971,0.001981173,0.001263624,0.000009313067,0.0001520377,0.0177329],"genre_scores_gemma":[0.9892573,0.000007530334,0.004817886,0.0003146422,0.0002068341,0.0003584431,0.000007994867,0.00001132719,0.005018043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8586212,"threshold_uncertainty_score":0.9997643,"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."}}