{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09328672,0.002587328,0.004727828,0.008454557,0.002215079,0.005121782,0.006208984,0.003843637,0.007568873],"category_scores_gemma":[0.4159961,0.00149619,0.003600134,0.009951093,0.008431978,0.01463933,0.007587335,0.007534698,0.001491592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001984488,"about_ca_system_score_gemma":0.004002061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002385688,"about_ca_topic_score_gemma":0.002072698,"domain_scores_codex":[0.8966683,0.08125072,0.004246017,0.006092516,0.01050147,0.001241034],"domain_scores_gemma":[0.3647835,0.5905966,0.007460124,0.02562383,0.01006402,0.001471984],"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":[0.0008168364,0.0002231393,0.01080782,0.001020519,0.001028579,0.0006395135,0.001137739,0.0710713,0.001506689,0.6168037,0.003936152,0.2910081],"study_design_scores_gemma":[0.0001088592,0.0003456021,0.001415815,0.0001307648,0.0001330944,0.0003910751,0.0001811832,0.2353841,0.0009696811,0.7580333,0.002792524,0.0001138873],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004161882,0.0004257991,0.9942445,0.0002039345,0.0001274197,0.00004951697,0.00007321344,0.000192808,0.0005208374],"genre_scores_gemma":[0.3235976,0.001185654,0.6705168,0.0006790513,0.0008676857,0.0007569154,0.0004798609,0.0006236929,0.001292887],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.09328672,"threshold_uncertainty_score":0.4933532,"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."}}