{"id":"W3003035306","doi":"10.1016/j.xphs.2020.01.014","title":"Application of Deep Learning Convolutional Neural Networks for Internal Tablet Defect Detection: High Accuracy, Throughput, and Adaptability","year":2020,"lang":"en","type":"article","venue":"Journal of Pharmaceutical Sciences","topic":"Mineral Processing and Grinding","field":"Engineering","cited_by":90,"is_retracted":false,"has_abstract":false,"ca_institutions":"Object Research Systems (Canada)","funders":"Merck","keywords":"Workflow; Computer science; Deep learning; Artificial intelligence; Convolutional neural network; Adaptability; Throughput; Artificial neural network; Machine learning; Pattern recognition (psychology); Database","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000453741,0.0007291561,0.0004446314,0.0005426945,0.000185432,0.00053819,0.0006718955,0.0005565494,0.001137138],"category_scores_gemma":[0.001065835,0.0003042334,0.0003473134,0.0004570366,0.0001881839,0.0005474926,0.0006283167,0.0006758548,0.0004271694],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005937415,"about_ca_system_score_gemma":0.000711747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007829498,"about_ca_topic_score_gemma":0.01232341,"domain_scores_codex":[0.9997787,0.00002277022,0.00001037192,0.00006100227,0.000084049,0.00004315979],"domain_scores_gemma":[0.9994929,0.0001701576,0.00005560479,0.00005733247,0.0002003047,0.00002368248],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004875625,0.0003269736,0.01040054,0.0002271757,0.000173936,0.0002390785,0.00007122318,0.1126942,0.1046301,0.001930226,0.008185449,0.7606336],"study_design_scores_gemma":[0.000006661741,0.0000482407,0.001797406,0.000007917889,0.00002521744,0.00006125164,0.000009738148,0.9674913,0.02888321,0.0006008039,0.001058227,0.000009968131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2683501,0.002190156,0.7161746,0.000745627,0.0002678463,0.00009311033,0.0009227502,0.005499535,0.005756383],"genre_scores_gemma":[0.8612865,0.000596382,0.1311413,0.0002090003,0.00005570819,0.00004685695,0.0007239273,0.00009017573,0.005849982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007829498,"threshold_uncertainty_score":0.01556784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03925491213168637,"score_gpt":0.3189073438593963,"score_spread":0.27965243172771,"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."}}