{"id":"W2044846198","doi":"10.1016/j.cam.2005.04.041","title":"Extending chi-squared statistics for key comparisons in metrology","year":2005,"lang":"en","type":"article","venue":"Journal of Computational and Applied Mathematics","topic":"Scientific Measurement and Uncertainty Evaluation","field":"Decision Sciences","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Metrology; Mathematics; Statistics; Statistic; Monte Carlo method; Statistical hypothesis testing; Test statistic; Key (lock); Null hypothesis; Computer science","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":[],"consensus_categories":[],"category_scores_codex":[0.005094339,0.00008517872,0.0003235624,0.0003692779,0.00009353839,0.0001258843,0.0002015002,0.00003528485,0.00007678873],"category_scores_gemma":[0.0009404219,0.0000613243,0.00005073981,0.000246665,0.00005446906,0.0001139993,0.00002271933,0.00009148833,0.00001163085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004041292,"about_ca_system_score_gemma":0.00008487375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":2.482043e-7,"about_ca_topic_score_gemma":0.000009939396,"domain_scores_codex":[0.9975412,0.00003710289,0.001059877,0.0001300424,0.001101506,0.0001302006],"domain_scores_gemma":[0.9964337,0.002178649,0.0007228179,0.0000744603,0.0005239314,0.00006649318],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001534438,0.0004173034,0.0005849467,0.00003438198,0.0000489959,0.000001216913,0.003001471,0.3624165,0.000680031,0.5253522,0.02611045,0.08119903],"study_design_scores_gemma":[0.001265039,0.00006863161,0.003394014,0.00001767305,0.00002608481,0.00001822646,0.0008497568,0.4658765,0.00009028323,0.5223694,0.005941529,0.00008278758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1066622,0.0000668135,0.8916517,0.0007142258,0.0001479288,0.0001705701,0.00001392744,0.000003305042,0.0005692224],"genre_scores_gemma":[0.4812365,0.000001967714,0.5185283,0.0000694987,0.000083065,0.000003236758,0.000004131159,0.000003408043,0.00006988762],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3745742,"threshold_uncertainty_score":0.2500733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2122891661237735,"score_gpt":0.4189385513864782,"score_spread":0.2066493852627047,"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."}}