{"id":"W4396927620","doi":"10.1515/cclm-2024-0527","title":"The final part of the CRESS trilogy – how to evaluate the quality of stability studies","year":2024,"lang":"en","type":"article","venue":"Clinical Chemistry and Laboratory Medicine (CCLM)","topic":"Clinical Laboratory Practices and Quality Control","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Hôpital Maisonneuve-Rosemont","funders":"","keywords":"Checklist; Quality (philosophy); Computer science; Sample (material); Stability (learning theory); Resource (disambiguation); Risk analysis (engineering); Plan (archaeology); Reliability engineering; Data mining; Engineering; Machine learning; Medicine; Psychology; Chemistry","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.01942694,0.0002481442,0.001126946,0.00001035413,0.000229881,0.00002452569,0.0003865983,0.0002238057,0.000149308],"category_scores_gemma":[0.06780543,0.0001012342,0.0002570143,0.0006217407,0.003221036,0.00006636589,0.0002229573,0.001082069,0.000002769674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003252592,"about_ca_system_score_gemma":0.000645312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001324429,"about_ca_topic_score_gemma":0.00002774119,"domain_scores_codex":[0.9948064,0.001713636,0.001906143,0.0005478272,0.0007409875,0.0002849817],"domain_scores_gemma":[0.9704629,0.02595089,0.0005328549,0.001386362,0.001367053,0.0002999304],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.03153555,0.00414798,0.2469992,0.02495175,0.01181742,0.0001453401,0.01064863,0.00001601263,0.1786355,0.02352509,0.3723931,0.09518439],"study_design_scores_gemma":[0.006123968,0.00165474,0.06358217,0.001948582,0.002381061,0.00001144799,0.0115134,0.0001756105,0.01577702,0.001652234,0.8947896,0.0003901376],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8425476,0.01782693,0.00001091076,0.1375495,0.0009883582,0.0005240851,0.000118677,0.00002719261,0.0004067713],"genre_scores_gemma":[0.992438,0.002056481,0.00001802698,0.003181064,0.001451695,0.00004175702,0.000004480225,0.00001657863,0.0007919593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5223965,"threshold_uncertainty_score":0.9994916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3497082966979214,"score_gpt":0.5294942181390766,"score_spread":0.1797859214411552,"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."}}