{"id":"W4416252247","doi":"10.1109/ijcnn64981.2025.11228324","title":"GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning","year":2025,"lang":"","type":"article","venue":"","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Pattern recognition (psychology); Cluster analysis; Closed captioning; Feature extraction; Contextual image classification; Graph; Feature vector; Pixel; Artificial neural network","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":[0.001251343,0.002483597,0.001199357,0.001285146,0.0006082489,0.001346034,0.0055697,0.002712069,0.007213113],"category_scores_gemma":[0.003066119,0.0007660055,0.001911597,0.001453544,0.0006250362,0.002087012,0.001995253,0.003324974,0.003536607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001794565,"about_ca_system_score_gemma":0.001358924,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01417738,"about_ca_topic_score_gemma":0.01547397,"domain_scores_codex":[0.9992681,0.0001309988,0.00003410271,0.0003051083,0.000158321,0.0001034358],"domain_scores_gemma":[0.9992493,0.0002359411,0.00005706607,0.0001672207,0.0002272308,0.00006318615],"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":[0.000448286,0.0004029473,0.001150968,0.0003365929,0.0002802898,0.0003138573,0.00007651539,0.2101079,0.01456304,0.003703714,0.0532354,0.7153805],"study_design_scores_gemma":[0.00002272833,0.00005385671,0.0001703892,0.00001136148,0.00002265359,0.00005848606,0.00001229488,0.9895627,0.005209367,0.002221958,0.002639673,0.00001454788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02533602,0.001580104,0.9173266,0.0005151957,0.0006301576,0.0004441937,0.002167627,0.04607853,0.005921541],"genre_scores_gemma":[0.287836,0.0007702652,0.6751651,0.001862537,0.0002583154,0.0008027109,0.0147468,0.001665418,0.01689279],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01417738,"threshold_uncertainty_score":0.02818972,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00910167173983274,"score_gpt":0.2866346593070621,"score_spread":0.2775329875672293,"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."}}