{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009675449,0.001411042,0.000693388,0.001985953,0.0004190708,0.001211387,0.001945846,0.001229973,0.006530708],"category_scores_gemma":[0.001664942,0.0004200575,0.0009273461,0.0008315928,0.0004165632,0.001454048,0.001324025,0.0008867064,0.00778097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001293842,"about_ca_system_score_gemma":0.0009211172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009899194,"about_ca_topic_score_gemma":0.01650242,"domain_scores_codex":[0.9992512,0.000117056,0.0000444026,0.0003491438,0.0001761434,0.00006196318],"domain_scores_gemma":[0.9993099,0.0002270637,0.00007431028,0.0001853293,0.0001706362,0.00003283616],"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":[0.0007317622,0.000461626,0.003224666,0.0007814256,0.0001493613,0.0002707502,0.0002739075,0.01513846,0.08141819,0.001627036,0.06856915,0.8273537],"study_design_scores_gemma":[0.0001411922,0.001041289,0.009968902,0.0001930799,0.0001539769,0.0006504792,0.0002276469,0.7320593,0.1360215,0.004516325,0.1148739,0.0001524097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05963124,0.002194207,0.779206,0.0006673236,0.00041281,0.0009927236,0.02269544,0.1253369,0.008863294],"genre_scores_gemma":[0.1179224,0.0007909723,0.8125359,0.0006384223,0.000139138,0.0008529981,0.05365077,0.002114153,0.01135523],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009899194,"threshold_uncertainty_score":0.02184737,"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."}}