{"id":"W7024823896","doi":"","title":"Stability testing and quantitation of certified reference materials","year":2008,"lang":"en","type":"article","venue":"NPARC","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certified reference materials; Calibration; Certification; Quality assurance; Matrix (chemical analysis); Reference data; Quality (philosophy); Stability (learning theory)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009939201,0.001096346,0.0008677362,0.002839347,0.0007839605,0.001350114,0.002284253,0.001808195,0.002668185],"category_scores_gemma":[0.02229326,0.0004471147,0.0007766529,0.001992989,0.001639092,0.001239611,0.001532037,0.001627071,0.001928422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001642692,"about_ca_system_score_gemma":0.001073707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00127243,"about_ca_topic_score_gemma":0.001298727,"domain_scores_codex":[0.9835585,0.003826309,0.0008693056,0.002106413,0.009237495,0.0004020431],"domain_scores_gemma":[0.9921901,0.001776602,0.001061006,0.001284933,0.003585778,0.0001016927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000456553,0.0005713301,0.004027807,0.001391116,0.0001837723,0.00045553,0.0005810378,0.0298056,0.7369807,0.02769843,0.008214794,0.1896332],"study_design_scores_gemma":[0.00004697673,0.0009641413,0.00283188,0.0002162336,0.00007148206,0.0005220043,0.0001508454,0.04932598,0.8932081,0.009023382,0.04352227,0.0001167047],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06725136,0.004782355,0.899761,0.0008848981,0.0007046961,0.001689332,0.001361342,0.001768613,0.0217963],"genre_scores_gemma":[0.4290647,0.006981766,0.5360616,0.001284009,0.0003822497,0.003393539,0.00406765,0.0005240453,0.01824043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009939201,"threshold_uncertainty_score":0.0525642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1164427979215902,"score_gpt":0.2853128511212935,"score_spread":0.1688700531997033,"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."}}