{"id":"W4416177895","doi":"10.26599/cvm.2025.9450408","title":"GRIG: Data-Efficient Generative Residual Image Inpainting","year":2025,"lang":"en","type":"article","venue":"Computational Visual Media","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"Natural Science Foundation of Zhejiang Province","keywords":"Inpainting; Generative grammar; Residual; Pattern recognition (psychology); Image (mathematics); Computer graphics; Convolutional neural network; Feature (linguistics)","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":[0.0006418781,0.0001966168,0.0002274043,0.0001912723,0.0003235362,0.0003230671,0.001121157,0.00005777971,0.00002998469],"category_scores_gemma":[0.0006546337,0.0001822248,0.00004768542,0.0006675096,0.0001309854,0.0004576921,0.001068256,0.000173464,0.00007558609],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005603298,"about_ca_system_score_gemma":0.0002642129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001454949,"about_ca_topic_score_gemma":0.000008717029,"domain_scores_codex":[0.9979354,0.0002550125,0.0003701787,0.0006868806,0.0004421581,0.0003103992],"domain_scores_gemma":[0.9979684,0.001036582,0.0001129179,0.0004588585,0.0003277827,0.00009546252],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002989619,0.0004416675,0.0002774286,0.00003345558,0.0002060393,0.00005779005,0.00195457,0.6718311,0.00240374,0.1395352,0.06161054,0.1216185],"study_design_scores_gemma":[0.0003275891,0.00002421674,0.004273662,0.00003158478,0.00001284321,0.000002442784,0.00006962358,0.9864004,0.001281929,0.006062368,0.001327735,0.0001856257],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005988532,0.0001969758,0.9887702,0.002182345,0.001169726,0.0001706039,0.00002381365,0.0001227975,0.001375016],"genre_scores_gemma":[0.6144181,0.000004108325,0.3837645,0.0009965757,0.0005186994,0.00001214432,0.0001783969,0.0000090038,0.00009839528],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6084296,"threshold_uncertainty_score":0.7430912,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02920426856878057,"score_gpt":0.3178622097112278,"score_spread":0.2886579411424472,"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."}}