{"id":"W4393343556","doi":"10.36227/techrxiv.171177556.62647395/v1","title":"MediCaption: Integrating YOLO-Driven Computer Vision and NLP for Advanced Pharmaceutical Package Recognition and Annotation","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Annotation; Computer science; Artificial intelligence; Natural language processing; Information retrieval","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":[0.0002892801,0.0002312969,0.0002297126,0.0002148696,0.0001098561,0.0005515365,0.0003047913,0.0002591714,0.00001281998],"category_scores_gemma":[0.00007254264,0.000184943,0.00005624058,0.0001377925,0.0001240647,0.0003341081,0.001328019,0.0004508846,0.00002025356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004537336,"about_ca_system_score_gemma":0.00004027479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003231951,"about_ca_topic_score_gemma":0.000004611208,"domain_scores_codex":[0.9984494,0.0000447259,0.0003441267,0.0007885824,0.0001941155,0.0001790618],"domain_scores_gemma":[0.9991254,0.0002285252,0.0001396345,0.000303411,0.0001276428,0.00007537512],"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":[0.00001075224,0.00002143133,0.00001171087,0.0002410849,0.00002091807,0.00000236748,0.0003632533,0.000006176347,0.001666339,0.02833377,0.0009926095,0.9683296],"study_design_scores_gemma":[0.0006543658,0.0002950623,0.0002522884,0.0005464634,0.00004873353,0.00002229557,0.0002539606,0.718548,0.004515831,0.2700837,0.004344739,0.0004345448],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02964916,0.0007007342,0.9570067,0.009766141,0.0007905836,0.0007302446,0.00002570475,0.001018028,0.0003127245],"genre_scores_gemma":[0.5110531,0.0006973783,0.4871759,0.0003377826,0.0001491255,0.0002484713,0.0001643167,0.00001727801,0.000156607],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.967895,"threshold_uncertainty_score":0.7541755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05480120033226021,"score_gpt":0.3483446999975729,"score_spread":0.2935434996653127,"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."}}