{"id":"W4410719643","doi":"10.1007/978-3-031-91838-4_14","title":"QSD: Query-Selection Denoising Score for Image Editing in Latent Diffusion Model","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Selection (genetic algorithm); Image denoising; Noise reduction; Artificial intelligence; Image editing; Image (mathematics); Computer vision; Pattern recognition (psychology)","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092215,0.0004853143,0.000529561,0.0009433536,0.0003968221,0.0006530365,0.00157064,0.0002974242,0.000004243444],"category_scores_gemma":[0.0001973854,0.0004585231,0.0001650791,0.0006833411,0.0002441805,0.0008580437,0.0009442798,0.0006186474,0.000003145352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004781367,"about_ca_system_score_gemma":0.0005151926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005308482,"about_ca_topic_score_gemma":0.0003844152,"domain_scores_codex":[0.9966183,0.00004216724,0.0005694628,0.00151032,0.00055391,0.0007057883],"domain_scores_gemma":[0.9982454,0.0004475196,0.0002684777,0.0006090268,0.0003309286,0.00009866583],"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":[0.000009088594,0.00002832984,0.0000869966,0.00005072338,0.000006720372,0.00001457736,0.0003587974,0.5963121,0.001788321,0.004190036,0.0001013684,0.3970529],"study_design_scores_gemma":[0.0002689023,0.00006713792,0.00005600874,0.0007011863,0.000007872953,0.000007844214,1.809288e-7,0.9355928,0.003750601,0.05901114,0.0001361867,0.0004001756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000149648,0.0002052366,0.9960419,0.0006064639,0.001593286,0.0006323064,0.000005592422,0.00008712774,0.0006784255],"genre_scores_gemma":[0.1339373,0.00004553335,0.8636895,0.0008618954,0.0009018282,0.00002847179,0.000008032629,0.00003232682,0.0004951372],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3966528,"threshold_uncertainty_score":0.9997867,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01806262709527675,"score_gpt":0.2431216278014301,"score_spread":0.2250590007061534,"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."}}