{"id":"W2011855045","doi":"10.1109/iccchina.2014.7008276","title":"Natural image splicing detection based on defocus blur at edges","year":2014,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Consistency (knowledge bases); Gaussian blur; Edge detection; Image (mathematics); Feature (linguistics); RNA splicing; Pattern recognition (psychology); Enhanced Data Rates for GSM Evolution; Image restoration; Image processing; Mathematics","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":[0.0001929566,0.0001343139,0.0001063645,0.0001459149,0.000112189,0.0001838685,0.0002905643,0.00004667875,0.00001078633],"category_scores_gemma":[0.0001871314,0.000109938,0.00006484359,0.000278076,0.00003850998,0.0005415533,0.0001157843,0.0001166706,0.0005079737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000132265,"about_ca_system_score_gemma":0.00001151971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003100308,"about_ca_topic_score_gemma":0.0001508812,"domain_scores_codex":[0.9989158,0.00003949599,0.000137078,0.000361404,0.0002995641,0.0002466727],"domain_scores_gemma":[0.9991741,0.0001609632,0.00005532198,0.0004651152,0.00006003884,0.00008442748],"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":[0.00002200349,0.00003063653,0.0000503425,0.00001053327,0.000004204456,0.000004353331,0.00004575308,0.0002075,0.04505317,0.002258631,0.0004941827,0.9518187],"study_design_scores_gemma":[0.000290411,0.0002401402,0.001895697,0.00001516177,0.000002569263,0.00001334699,0.000003529112,0.4796354,0.5146897,0.0009852013,0.002063873,0.0001650462],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1732624,0.000004559839,0.7776169,0.0004194526,0.002510498,0.00012988,2.611944e-7,0.000608522,0.04544758],"genre_scores_gemma":[0.987803,1.913528e-7,0.01066079,0.0005342058,0.0001362575,0.0000095515,8.652328e-7,0.00001069388,0.0008444511],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9516537,"threshold_uncertainty_score":0.6529143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.004558079946051603,"score_gpt":0.1902789347291812,"score_spread":0.1857208547831296,"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."}}