{"id":"W2060998495","doi":"10.1002/cjs.10103","title":"Planning and analysis of measurement reliability studies","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Reliability (semiconductor); Plan (archaeology); Measure (data warehouse); Mathematics; Statistics; Humanities; Computer science; Geography; Philosophy; Data mining; Physics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3831679,0.004359182,0.005399141,0.01366401,0.002351389,0.006678092,0.007765201,0.003094756,0.01130387],"category_scores_gemma":[0.5811241,0.00340689,0.007690948,0.0103115,0.003549092,0.005768789,0.005687749,0.009379835,0.003526148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008568103,"about_ca_system_score_gemma":0.02673974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005903218,"about_ca_topic_score_gemma":0.004135235,"domain_scores_codex":[0.6048892,0.3181456,0.02347908,0.01404158,0.03612816,0.003316286],"domain_scores_gemma":[0.3113241,0.5189097,0.0236549,0.06344192,0.08033998,0.002329328],"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":[0.003645563,0.0008823213,0.009514437,0.01243379,0.002414347,0.0007838702,0.007127904,0.06524113,0.005305127,0.1413011,0.03369051,0.71766],"study_design_scores_gemma":[0.004191454,0.01027034,0.03160004,0.008015593,0.004380006,0.0007643271,0.008269992,0.2996606,0.02965283,0.3620344,0.2399277,0.001232665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004654511,0.0007704886,0.9338197,0.0009706016,0.0003132311,0.05276384,0.001403383,0.001107178,0.004197026],"genre_scores_gemma":[0.02250169,0.0003369918,0.8897849,0.0002062279,0.0001275304,0.08548353,0.0007767293,0.0001662379,0.0006161898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6168321,"threshold_uncertainty_score":0.7606639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4922490454234743,"score_gpt":0.3848306343614787,"score_spread":0.1074184110619956,"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."}}