{"id":"W4415649506","doi":"10.1111/1556-4029.70203","title":"Learning to localize image forgery using boundary‐preserving mask R‐ <scp>CNN</scp>","year":2025,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Preprocessor; Benchmark (surveying); Compositing; Segmentation; Domain (mathematical analysis); Image (mathematics); Digital forensics; Channel (broadcasting)","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":[0.0008066772,0.001483969,0.0008525411,0.000957117,0.0002994633,0.0007366826,0.00186599,0.001147724,0.00197833],"category_scores_gemma":[0.002306694,0.0003883901,0.0007771949,0.0005676486,0.0005889494,0.001448931,0.001201638,0.0008357216,0.001478094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000734638,"about_ca_system_score_gemma":0.0009683809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005219351,"about_ca_topic_score_gemma":0.006976813,"domain_scores_codex":[0.9995696,0.00004153241,0.00001986451,0.0001588815,0.0001349611,0.00007506253],"domain_scores_gemma":[0.9994102,0.000107142,0.0001052206,0.0001837826,0.0001581606,0.00003547508],"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":[0.0003181947,0.0001515516,0.003771969,0.0001724167,0.0001490458,0.0003571058,0.00008985087,0.118547,0.05934362,0.002797128,0.009900303,0.8044018],"study_design_scores_gemma":[0.000009768717,0.0001208227,0.001730803,0.00002833141,0.0000534868,0.0003933842,0.00002924213,0.9471776,0.04513051,0.002401077,0.002905589,0.00001927085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1089914,0.001292376,0.872393,0.0004909951,0.0001857797,0.0002007785,0.0007178112,0.009573885,0.006154019],"genre_scores_gemma":[0.641362,0.0009189525,0.3455881,0.0005843981,0.0001039099,0.0001268155,0.002281474,0.0003957248,0.008638701],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005219351,"threshold_uncertainty_score":0.01037794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01779093602414762,"score_gpt":0.2804418975105068,"score_spread":0.2626509614863592,"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."}}