{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003645146,0.00006100688,0.000121516,0.0000332687,0.0000973171,0.00001993249,0.0002194482,0.0000319256,0.00004357546],"category_scores_gemma":[0.001058346,0.00005750339,0.000007858029,0.0001635785,0.00007742651,0.0002602691,0.0001502127,0.00006739572,0.000004041686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001181247,"about_ca_system_score_gemma":0.00003782365,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006513477,"about_ca_topic_score_gemma":0.00000195059,"domain_scores_codex":[0.999242,0.0001121997,0.0001913912,0.0001993348,0.0001478477,0.0001072124],"domain_scores_gemma":[0.9991776,0.0003463202,0.0001144071,0.0002375926,0.00009595529,0.00002812174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00001734106,0.00003010911,0.02125625,0.0000614748,0.000005480973,0.000006575968,0.001832315,0.0002370045,0.9159174,0.05033377,0.0000262849,0.01027597],"study_design_scores_gemma":[0.0008488614,0.0002932627,0.4304548,0.00009815766,0.0000126188,0.00006972001,0.0001403645,0.1278504,0.3660685,0.07360569,0.00007705166,0.0004806328],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8420885,0.000005614987,0.1549721,0.0001045423,0.00008065495,0.00005849319,0.000001090895,0.0000583394,0.002630661],"genre_scores_gemma":[0.7505515,0.000002206611,0.2494103,0.00001087025,0.00001160517,0.000001272689,5.890399e-7,0.000002668892,0.000008958467],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.549849,"threshold_uncertainty_score":0.234492,"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."}}