{"id":"W4413146879","doi":"10.1109/cvpr52734.2025.02186","title":"Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing","year":2025,"lang":"en","type":"article","venue":"","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation","keywords":"Computer science; Context (archaeology); Image editing; Image (mathematics); Artificial intelligence; History","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":[0.003434799,0.001728389,0.001168211,0.001994422,0.0005412764,0.002126641,0.001661419,0.001283727,0.001892433],"category_scores_gemma":[0.01589993,0.0002489003,0.0006582795,0.0009544293,0.000801057,0.003461324,0.001730862,0.001114609,0.0007655417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001006125,"about_ca_system_score_gemma":0.0007948087,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003192289,"about_ca_topic_score_gemma":0.006297826,"domain_scores_codex":[0.9969261,0.0009212117,0.0002678906,0.0008193325,0.0008672928,0.0001980923],"domain_scores_gemma":[0.9946637,0.002588884,0.0004742379,0.0009215901,0.001053931,0.000297673],"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":[0.002230552,0.0004454876,0.006096174,0.001407847,0.0004206745,0.0002484006,0.0003628286,0.06214979,0.06017529,0.003513686,0.01437519,0.8485741],"study_design_scores_gemma":[0.0002478082,0.001937496,0.009541957,0.0001670239,0.0003592319,0.0009058726,0.0004688081,0.8832556,0.08222536,0.009026539,0.01171715,0.0001471553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3922825,0.01836102,0.5529221,0.0007166177,0.0007047773,0.001138116,0.0025564,0.0192617,0.01205675],"genre_scores_gemma":[0.7421799,0.001087327,0.2490346,0.0004137948,0.0001821144,0.0002298412,0.003024667,0.0009728356,0.002874952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003434799,"threshold_uncertainty_score":0.01816511,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07847100008251207,"score_gpt":0.3666936518639458,"score_spread":0.2882226517814337,"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."}}