{"id":"W1966985101","doi":"10.1016/j.ejpb.2013.12.013","title":"Development of a multivariate light-induced fluorescence (LIF) PAT tool for in-line quantitative analysis of pharmaceutical granules in a V-blender","year":2013,"lang":"en","type":"article","venue":"European Journal of Pharmaceutics and Biopharmaceutics","topic":"Spectroscopy and Chemometric Analyses","field":"Chemistry","cited_by":27,"is_retracted":false,"has_abstract":false,"ca_institutions":"Pfizer (Canada); Université de Sherbrooke","funders":"Université de Sherbrooke; Pfizer","keywords":"Process analytical technology; Multivariate statistics; Fluorescence; Process engineering; Critical quality attributes; Biological system; Process (computing); Fluorescence spectroscopy; Spectrum analyzer; Process control; Materials science; Particle size; Computer science; Analytical Chemistry (journal); Chemistry; Chromatography; Optics; Chemical engineering; Engineering; Machine learning; Physics; Bioprocess","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001484529,0.0003570996,0.0009996393,0.001229027,0.00006238889,0.00003887909,0.0004375852,0.00008274394,0.0002319751],"category_scores_gemma":[0.0002228734,0.0003033426,0.0002971595,0.00166206,0.0001379768,0.0002029122,0.0001372348,0.0005780049,0.000002390488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009695086,"about_ca_system_score_gemma":0.0001362914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009588462,"about_ca_topic_score_gemma":0.000005934819,"domain_scores_codex":[0.99655,0.0001764042,0.002027802,0.0003255811,0.0004452798,0.0004748942],"domain_scores_gemma":[0.9976028,0.0004044246,0.001058622,0.0001756277,0.0005201917,0.0002383737],"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":[0.0005788998,0.0007983421,0.00891036,0.0004635032,0.001673208,0.00004527207,0.001969563,0.0001933589,0.9672071,0.0001217687,0.00001099767,0.01802759],"study_design_scores_gemma":[0.005175284,0.0001220995,0.004346048,0.0001575686,0.002204629,0.00001119672,0.001003993,0.04579539,0.9390103,0.00002676988,0.001785922,0.0003608226],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962391,0.001673243,0.001302412,0.0001887198,0.00009661748,0.0002180692,0.00004078909,0.000009264061,0.0002318082],"genre_scores_gemma":[0.9775681,0.001319342,0.02088762,0.00009423571,0.00005166009,0.000006350367,0.000009693971,0.00003700761,0.00002595517],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04560203,"threshold_uncertainty_score":0.9999419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09651017128817813,"score_gpt":0.3826847537102118,"score_spread":0.2861745824220337,"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."}}