{"id":"W2009759057","doi":"10.1016/j.measurement.2010.03.004","title":"A recommended method for evaluation of international comparison results","year":2010,"lang":"en","type":"article","venue":"Measurement","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Calibration; Gauge (firearms); Block (permutation group theory); Simple (philosophy); Key (lock); Computer science; Mathematics; Engineering drawing; Reliability engineering; Engineering; Algorithm; Statistics; Geography; Computer security; Geometry; Epistemology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.1456819,0.003551043,0.0045688,0.01418114,0.003569237,0.007052841,0.00610394,0.005069783,0.02359322],"category_scores_gemma":[0.4356486,0.001450181,0.006123611,0.014639,0.002681255,0.005567471,0.00380123,0.005924331,0.0082632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004598803,"about_ca_system_score_gemma":0.01024809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005864332,"about_ca_topic_score_gemma":0.006571539,"domain_scores_codex":[0.7599252,0.1767224,0.01784769,0.007928058,0.03580664,0.001770065],"domain_scores_gemma":[0.65232,0.2031683,0.01577616,0.03104609,0.09587275,0.001816778],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001303244,0.0004072742,0.008573916,0.007690221,0.002206509,0.0002943771,0.001341623,0.005900729,0.002714893,0.09983225,0.1770026,0.6927324],"study_design_scores_gemma":[0.00287447,0.00332709,0.05738794,0.02239568,0.005475122,0.003907411,0.004192192,0.08461081,0.02925694,0.2809291,0.5040745,0.00156875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003552287,0.002748508,0.9504009,0.003119936,0.002610076,0.005992936,0.004870011,0.002492251,0.02421298],"genre_scores_gemma":[0.01843406,0.0004436104,0.9668192,0.0005760115,0.000166602,0.00988466,0.001314511,0.000338294,0.002023141],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8543181,"threshold_uncertainty_score":0.7704488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6507330414326267,"score_gpt":0.5528794407505461,"score_spread":0.0978536006820806,"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."}}