{"id":"W4388135783","doi":"10.1002/aic.18279","title":"Deep‐learning based <i>in situ</i> image monitoring crystal polymorph and size distribution: Modeling and validation","year":2023,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Crystallization and Solubility Studies","field":"Materials Science","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Key Technology Research and Development Program of Shandong; National Natural Science Foundation of China","keywords":"Critical quality attributes; In situ; Process analytical technology; Biological system; Crystallization; Process (computing); Particle-size distribution; Process control; Materials science; Algorithm; Artificial intelligence; Particle size; Computer science; Chemistry; Work in process; Engineering; Chemical engineering","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":[],"consensus_categories":[],"category_scores_codex":[0.0009562985,0.00008968977,0.0001289414,0.00003123073,0.000399708,0.0002538097,0.000050511,0.00003871737,0.00004679383],"category_scores_gemma":[0.0005141754,0.00008516302,0.00002281745,0.0001859181,0.00004552966,0.0003045875,0.00006578358,0.0001647124,0.000005662661],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005008201,"about_ca_system_score_gemma":0.00002314358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001390401,"about_ca_topic_score_gemma":0.00000819605,"domain_scores_codex":[0.9990708,0.0001206132,0.0002405413,0.0001601827,0.0001991688,0.0002086471],"domain_scores_gemma":[0.9995461,0.0001652564,0.00007216317,0.00005719161,0.00008047959,0.00007880889],"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":[0.00005184795,0.00002908435,0.0478428,0.0000502474,0.000007850247,0.00003853495,0.001788087,0.04142247,0.9078847,0.00002705623,0.00006545321,0.0007919319],"study_design_scores_gemma":[0.003236141,0.0001642439,0.1701625,0.0003156552,0.0000666678,0.0001775107,0.01118288,0.7555358,0.05645907,0.001358255,0.0006507279,0.000690573],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.960193,0.0002194813,0.03874392,0.0005284508,0.0001567985,0.00005235847,0.000003428866,0.00005517296,0.0000474038],"genre_scores_gemma":[0.9987839,0.0002277286,0.0007731041,0.00001920443,0.0001236282,0.000002921662,0.000006709886,0.000008068876,0.00005468011],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8514256,"threshold_uncertainty_score":0.3472847,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02048166268725026,"score_gpt":0.2715465675191257,"score_spread":0.2510649048318754,"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."}}