{"id":"W4408135470","doi":"10.1007/978-3-031-82153-0_26","title":"BA-GAN: A Boundary-Aware Generative Adversarial Network for Document Restoration","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Image Processing and 3D Reconstruction","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Generative grammar; Generative adversarial network; Boundary (topology); Adversarial system; Computer science; Information retrieval; Artificial intelligence; Mathematics; Deep learning","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":[0.0006526324,0.001023234,0.001080048,0.0005651125,0.0002931662,0.0009990676,0.002000757,0.001373443,0.006058443],"category_scores_gemma":[0.001358091,0.0006112817,0.001005061,0.0006768596,0.0006233559,0.001266969,0.001634837,0.002914885,0.004265044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005658827,"about_ca_system_score_gemma":0.0005737443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003060907,"about_ca_topic_score_gemma":0.005018523,"domain_scores_codex":[0.999649,0.00008335334,0.00001108505,0.00009432065,0.0001227532,0.00003945813],"domain_scores_gemma":[0.999632,0.0001551775,0.00002179387,0.00008451222,0.00008433106,0.0000220802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001982332,0.00009742718,0.0002440429,0.0001665952,0.00009844738,0.0001141552,0.00006304088,0.4024891,0.0215598,0.02173391,0.03014105,0.5230941],"study_design_scores_gemma":[0.000004341493,0.00001502156,0.0000456975,0.00001004871,0.000006863113,0.00005077396,0.000003807589,0.9870663,0.003306363,0.006065856,0.003417315,0.00000755804],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001559976,0.0004013904,0.9930876,0.0001152896,0.00007794698,0.00002919087,0.0001623577,0.002359354,0.002206968],"genre_scores_gemma":[0.1221975,0.00121486,0.8483958,0.0006241265,0.0001637151,0.0001716611,0.001778755,0.00181857,0.023635],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006058443,"threshold_uncertainty_score":0.02026755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02240356776309566,"score_gpt":0.2882971187412098,"score_spread":0.2658935509781142,"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."}}