{"id":"W6910477341","doi":"10.48448/2zwc-6969","title":"A New Benchmark and Model for Challenging Image Manipulation Detection","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Benchmark (surveying); Image (mathematics); Image manipulation; Face (sociological concept); Image compression; Pattern recognition (psychology); Data compression; Image editing","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":[0.001376447,0.003108731,0.00131691,0.003000433,0.0008121709,0.002046011,0.004486572,0.002692037,0.004055771],"category_scores_gemma":[0.00537435,0.0004973514,0.001240202,0.001958994,0.0007635112,0.002499731,0.001450892,0.001977703,0.002214775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003220814,"about_ca_system_score_gemma":0.001465032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03530564,"about_ca_topic_score_gemma":0.03486728,"domain_scores_codex":[0.9988751,0.0002104912,0.00005612957,0.0004516127,0.0002456441,0.0001610179],"domain_scores_gemma":[0.9984414,0.0005116433,0.0001564345,0.0002579545,0.000520214,0.0001124221],"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":[0.001057222,0.0007870169,0.008304323,0.001035247,0.0002770617,0.0004976693,0.00008481166,0.6248829,0.005328254,0.008999565,0.1503881,0.1983578],"study_design_scores_gemma":[0.00003624986,0.00008404242,0.00120765,0.00004618515,0.00002912922,0.0001258464,0.00003483021,0.9831949,0.001873177,0.004676118,0.00866864,0.00002335087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2665503,0.01932516,0.496835,0.006600738,0.002610223,0.001618766,0.1309842,0.03164033,0.04383528],"genre_scores_gemma":[0.5158157,0.003657211,0.2365889,0.001533307,0.0007694706,0.001448048,0.2198123,0.001204061,0.01917095],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03530564,"threshold_uncertainty_score":0.07020032,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0357763259560234,"score_gpt":0.314082109441217,"score_spread":0.2783057834851935,"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."}}