{"id":"W3048504327","doi":"10.1002/aic.17021","title":"Using prior parameter knowledge in <scp>model‐based</scp> design of experiments for pharmaceutical production","year":2020,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Optimal Experimental Design Methods","field":"Decision Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Eli Lilly and Company","keywords":"Fisher information; Computation; Computer science; Bayesian probability; Selection (genetic algorithm); Bayesian information criterion; Invertible matrix; Prior information; Sequential analysis; Design of experiments; Algorithm; Process (computing); Mathematical optimization; Model selection; Matrix (chemical analysis); Mathematics; Machine learning; Artificial intelligence; Statistics","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"],"consensus_categories":[],"category_scores_codex":[0.005473673,0.0002051249,0.0004487169,0.0002851388,0.0001336735,0.0001483931,0.0005716475,0.0001123886,0.00005642097],"category_scores_gemma":[0.009402196,0.0001634309,0.0001935991,0.000731855,0.0001239818,0.0005525965,0.00009765608,0.0003622307,0.00002128299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001439867,"about_ca_system_score_gemma":0.0003524847,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":8.708992e-7,"about_ca_topic_score_gemma":1.248335e-7,"domain_scores_codex":[0.9962264,0.000988248,0.001051201,0.0004768522,0.0008587127,0.0003985549],"domain_scores_gemma":[0.9961745,0.002481442,0.0004288529,0.0002331213,0.0003729542,0.0003090955],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002770661,0.0002868451,0.000449994,0.00001477955,0.00002590963,0.000006423843,0.003262616,0.1429141,0.8391071,0.00004115005,0.003195659,0.01041833],"study_design_scores_gemma":[0.0007529481,0.0002123292,0.00003459704,0.00002308864,0.00001740107,0.00001784533,0.0007228044,0.5435487,0.4530412,0.001102321,0.0004753531,0.00005138831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2198454,0.0007135333,0.7781219,0.0002625374,0.0004117595,0.0005139324,0.000002712934,0.00001256623,0.0001156042],"genre_scores_gemma":[0.4216004,0.000006884689,0.5778939,0.0002396861,0.00016593,0.00001560012,2.492278e-7,0.00002036522,0.00005700999],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4006346,"threshold_uncertainty_score":0.998942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6399688166531778,"score_gpt":0.5589323547005753,"score_spread":0.0810364619526025,"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."}}