{"id":"W7131181425","doi":"10.1109/iccvw69036.2025.00780","title":"PRISM: Pruning for Rank-adaptive Interpretable Segmentation Model with Application to Historical Document Multiband Images","year":2025,"lang":"","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interpretability; Autoencoder; Pruning; Non-negative matrix factorization; Pattern recognition (psychology); Multispectral image; Rank (graph theory); Matrix decomposition; Segmentation; Feature (linguistics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007745239,0.0004422836,0.0004649009,0.0004081706,0.0005985718,0.0005969099,0.0009947632,0.0001404397,0.00001562726],"category_scores_gemma":[0.0001011939,0.0004133836,0.0001178668,0.001194314,0.00007868176,0.0016693,0.0004125088,0.000222088,0.0000500139],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002637537,"about_ca_system_score_gemma":0.0004823221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009904682,"about_ca_topic_score_gemma":0.0001897987,"domain_scores_codex":[0.9964233,0.0001000794,0.0008416223,0.001383583,0.0004909381,0.0007604584],"domain_scores_gemma":[0.9976975,0.0003148667,0.0002704905,0.0008573998,0.0006239696,0.0002357206],"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":[0.001482521,0.000580543,0.0001116925,0.0001943626,0.0001985948,0.000003962464,0.01463637,0.3848191,0.04326747,0.1248275,0.009259231,0.4206187],"study_design_scores_gemma":[0.0004482467,0.0005874485,0.00000953398,0.0001583576,0.00007174892,0.000001327134,0.0008151762,0.8253198,0.1619141,0.008339192,0.001941299,0.0003938474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001061741,0.0002247056,0.9844047,0.005508392,0.0004220033,0.004412444,0.000004009836,0.0001644355,0.003797546],"genre_scores_gemma":[0.4847351,0.00002274148,0.493241,0.0008839399,0.00004012005,0.001280371,0.00000490162,0.00002299038,0.01976875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4911637,"threshold_uncertainty_score":0.9998318,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01828642338290286,"score_gpt":0.2942341274000022,"score_spread":0.2759477040170993,"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."}}