{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":175,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":175,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12","author_layer_release":"2026-06-26"},"query_hash":"77b7d61c5f5f","filters":{"topic":"Digital Media Forensic Detection"}},"results":[{"id":"W2407561938","doi":"10.1109/lsp.2015.2438008","title":"Median Filtering Forensics Based on Convolutional Neural Networks","year":2015,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Key Research and Development Program of China; National Science Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pooling; Image (mathematics); Pattern recognition (psychology); Filter (signal processing); Median filter; Residual; Computer vision; Image processing; Algorithm","authors":[{"name":"Jiansheng Chen","is_ca":false},{"name":"Xiangui Kang","is_ca":false},{"name":"Ye Liu","is_ca":false},{"name":"Z. Jane Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02658748460942762,"gpt":0.2257852914226731,"spread":0.1991978068132455,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006215421,0.0007548231,0.0007003896,0.001153946,0.0003174534,0.0006379183,0.001043365,0.0007803113,0.001460836],"category_scores_gemma":[0.0014695,0.0003777245,0.0006912121,0.000714106,0.000501608,0.001133382,0.0006220855,0.0006923903,0.0005189676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000921921,"about_ca_system_score_gemma":0.0007213923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006082251,"about_ca_topic_score_gemma":0.006418267,"domain_scores_codex":[0.9997061,0.00003303598,0.00001337134,0.00007343835,0.0001176919,0.00005628008],"domain_scores_gemma":[0.9995137,0.0001653401,0.00008400509,0.00007205958,0.0001421823,0.00002272655],"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":[0.0003355902,0.00009178843,0.002500992,0.0001056416,0.0001062354,0.0002010628,0.00006303301,0.2245762,0.03588784,0.005126958,0.002637801,0.7283667],"study_design_scores_gemma":[0.00000339687,0.00002338105,0.0005078429,0.000007346959,0.0000130328,0.00007998345,0.000006319338,0.9853476,0.01207172,0.001409605,0.0005211727,0.000008583651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05756595,0.000700035,0.9358151,0.00027058,0.00006181001,0.00004686436,0.0001306393,0.00275324,0.002655699],"genre_scores_gemma":[0.7034728,0.0007738417,0.2903793,0.0001938305,0.00007833142,0.00005671093,0.0004121205,0.0001087571,0.004524301],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006082251,"threshold_uncertainty_score":0.01209366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4297988790","doi":"10.3390/app12199820","title":"A Novel Deep Learning Approach for Deepfake Image Detection","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Convolutional neural network; Face (sociological concept); Transfer of learning; Artificial intelligence; Deep learning; Fake news; Social media; Computer security; Data science; Internet privacy; World Wide Web","authors":[{"name":"Ali Raza","is_ca":false},{"name":"Kashif Munir","is_ca":false},{"name":"Mubarak Almutairi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01717738125733426,"gpt":0.2232634776273456,"spread":0.2060860963700114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004829422,0.00144308,0.0008653546,0.001166346,0.0004714673,0.0009173896,0.001968043,0.001637291,0.003804371],"category_scores_gemma":[0.001138229,0.0005213599,0.001037559,0.0007799901,0.0004241976,0.001412026,0.001218993,0.002062545,0.001700848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009888107,"about_ca_system_score_gemma":0.00121778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00891095,"about_ca_topic_score_gemma":0.01277659,"domain_scores_codex":[0.999611,0.00003448026,0.00002069535,0.0001075408,0.0001149506,0.0001112787],"domain_scores_gemma":[0.9996612,0.00007377389,0.00003910318,0.00004748342,0.0001467299,0.00003177327],"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":[0.0002721731,0.0002658771,0.002286285,0.0001534252,0.0001501153,0.0002871152,0.00006364791,0.1267614,0.0260877,0.004054104,0.01454319,0.825075],"study_design_scores_gemma":[0.000007439952,0.00005664513,0.0004505628,0.00001584206,0.00001681356,0.000103737,0.0000152814,0.986697,0.008118658,0.00200225,0.002504047,0.00001170228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03591277,0.001523527,0.9517304,0.000582927,0.000269868,0.0001401312,0.0007272651,0.004973414,0.004139799],"genre_scores_gemma":[0.5803851,0.001404942,0.3860556,0.0009412232,0.0001909519,0.0002750384,0.003479582,0.0003035849,0.02696389],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00891095,"threshold_uncertainty_score":0.0177182,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145022254","doi":"10.1109/tip.2004.823815","title":"On Missing Data Treatment for Degraded Video and Film Archives: A Survey and a New Bayesian Approach","year":2004,"lang":"en","type":"review","venue":"IEEE Transactions on Image Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Trinity College","funders":"Enterprise Ireland; University of Cambridge","keywords":"Computer science; Image restoration; Context (archaeology); Cultural heritage; Bayesian probability; Missing data; Noise (video); Computer vision; Multimedia; Artificial intelligence; Information retrieval; Image processing; Image (mathematics); Machine learning; Geography; Archaeology","authors":[{"name":"Anil Kokaram","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1179582882245461,"gpt":0.3345613314993465,"spread":0.2166030432748004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00549826,0.001322651,0.002717516,0.003717928,0.0005522378,0.001486983,0.003709228,0.002891101,0.003226676],"category_scores_gemma":[0.009215929,0.001098746,0.001453115,0.005574956,0.001430049,0.003801203,0.001265288,0.001777445,0.001811816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001016136,"about_ca_system_score_gemma":0.001831122,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005295238,"about_ca_topic_score_gemma":0.004421026,"domain_scores_codex":[0.9980283,0.0006704871,0.0001585367,0.0002887014,0.0007953997,0.0000584781],"domain_scores_gemma":[0.9929901,0.004624513,0.0003211463,0.0003508436,0.001628634,0.00008478828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006839616,0.0001211264,0.0007115459,0.003538231,0.0001812469,0.0001367961,0.0001587478,0.01161753,0.0007044455,0.01706373,0.006097189,0.959601],"study_design_scores_gemma":[0.0001969359,0.0007268385,0.007441244,0.008814206,0.001118249,0.005594127,0.0009860203,0.1772621,0.009901265,0.1592623,0.6282588,0.0004379058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001808712,0.5742799,0.4161206,0.001424451,0.0003131348,0.00005484197,0.00007725163,0.0001956739,0.00572534],"genre_scores_gemma":[0.02875414,0.7820476,0.1828406,0.0005410442,0.001244553,0.0001271462,0.0002880235,0.0001134248,0.004043479],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.00549826,"threshold_uncertainty_score":0.02907795,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036651568","doi":"10.1080/13614576.2012.679446","title":"Digital Preservation, Archival Science and Methodological Foundations for Digital Libraries","year":2012,"lang":"en","type":"article","venue":"New Review of Information Networking","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Digital preservation; Digital curation; Computer science; Digital library; Data curation; World Wide Web; Work (physics); Key (lock); Data science; Library science; Engineering ethics; Engineering; Computer security","authors":[{"name":"Seamus Ross","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07153507446322221,"gpt":0.3140304619340112,"spread":0.242495387470789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02422429,0.0006980624,0.0009853195,0.01016419,0.007484423,0.01930499,0.002278763,0.003831837,0.005006331],"category_scores_gemma":[0.02357585,0.0005098432,0.000762417,0.01298003,0.0649271,0.01955299,0.00757982,0.007716693,0.0009607537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01219053,"about_ca_system_score_gemma":0.01105469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00455326,"about_ca_topic_score_gemma":0.003673296,"domain_scores_codex":[0.9813159,0.01441532,0.0008050445,0.001079489,0.001876618,0.0005076466],"domain_scores_gemma":[0.9645584,0.02688324,0.002214884,0.003583247,0.00202056,0.0007398131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000173059,0.000009955068,0.00009751972,0.0000912719,0.00000246087,0.0000168038,0.001364581,0.00007975817,0.00001345842,0.994221,0.0006308265,0.00347065],"study_design_scores_gemma":[0.000003902635,0.00000671943,0.000147568,0.0003246187,0.000003527405,0.00004934469,0.002463033,0.0002930785,0.0000612509,0.9661481,0.03049166,0.000007242323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.02181012,0.174499,0.2753615,0.1677258,0.002346285,0.000555778,0.0003896425,0.0002325477,0.3570794],"genre_scores_gemma":[0.7211038,0.08836311,0.1569755,0.01024767,0.00366008,0.001741316,0.0002843807,0.0001823058,0.01744179],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.02422429,"threshold_uncertainty_score":0.1281118,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2999170936","doi":"10.1007/s11760-020-01636-0","title":"Image splicing detection using mask-RCNN","year":2020,"lang":"en","type":"article","venue":"Signal Image and Video Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Artificial intelligence; Discriminative model; Backbone network; Initialization; Feature (linguistics); Residual neural network; Pattern recognition (psychology); Pyramid (geometry); Convolutional neural network; Set (abstract data type); Feature vector; Computer vision; Network architecture; Mathematics; Telecommunications","authors":[{"name":"Belal Ahmed","is_ca":true},{"name":"T. Aaron Gulliver","is_ca":true},{"name":"Saif alZahir","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01990819478323003,"gpt":0.2486485119037041,"spread":0.2287403171204741,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004779787,0.000866097,0.0006667605,0.001054325,0.0004645543,0.0006414729,0.0008337887,0.0009759161,0.002438619],"category_scores_gemma":[0.0007974948,0.0003679963,0.0006581713,0.0007229807,0.0003048047,0.0007747514,0.0006118428,0.0005110355,0.001227952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003276137,"about_ca_system_score_gemma":0.0006882429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002354862,"about_ca_topic_score_gemma":0.004645343,"domain_scores_codex":[0.9996076,0.00003593973,0.00002225882,0.0001171346,0.000161091,0.00005599423],"domain_scores_gemma":[0.9996537,0.00006644132,0.00003344073,0.00006627179,0.0001574377,0.00002265918],"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":[0.0004491431,0.0001388398,0.003477385,0.0001326672,0.0001025252,0.0002675458,0.00008472975,0.01244889,0.2102966,0.00165557,0.002462186,0.7684839],"study_design_scores_gemma":[0.00002131044,0.0002060194,0.006435706,0.00002389567,0.0001490796,0.0008152314,0.00004501098,0.8039488,0.1828359,0.001362034,0.004117293,0.00003963797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1114788,0.00074177,0.8779909,0.000210896,0.0002002734,0.0001167266,0.000183026,0.003398384,0.005679156],"genre_scores_gemma":[0.4890723,0.0005563105,0.4987665,0.0002200831,0.0001099285,0.00008427041,0.0005994877,0.0002425523,0.01034846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002438619,"threshold_uncertainty_score":0.008157969,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3094138310","doi":"10.1016/j.cose.2020.102092","title":"A survey of machine learning techniques in adversarial image forensics","year":2020,"lang":"en","type":"article","venue":"Computers & Security","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"Università degli Studi di Siena","keywords":"Computer science; Adversarial system; Computer security; Artificial intelligence; Adversarial machine learning; Data science; Computer vision; Machine learning","authors":[{"name":"Ehsan Nowroozi","is_ca":false},{"name":"Ali Dehghantanha","is_ca":true},{"name":"Reza M. Parizi","is_ca":false},{"name":"Kim‐Kwang Raymond Choo","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01554365417211602,"gpt":0.2314940630839041,"spread":0.215950408911788,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003304597,0.001292404,0.001961434,0.003349619,0.0007634342,0.002376076,0.0021149,0.002085497,0.001976564],"category_scores_gemma":[0.005913109,0.0007769009,0.001359339,0.004615038,0.001062459,0.003454479,0.001528494,0.002539422,0.001742434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000666051,"about_ca_system_score_gemma":0.0008341808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001183288,"about_ca_topic_score_gemma":0.0009734055,"domain_scores_codex":[0.9978168,0.0005769847,0.0002168791,0.0003731147,0.0009222423,0.00009403776],"domain_scores_gemma":[0.996128,0.002211086,0.0002202759,0.0005713204,0.0007935149,0.00007584011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009316573,0.0002042171,0.001419541,0.001008124,0.0001593012,0.00006446979,0.0000651303,0.04150212,0.002534802,0.02163558,0.005535148,0.9257783],"study_design_scores_gemma":[0.00002949453,0.0003612213,0.003053439,0.0009591164,0.0001610214,0.001123065,0.0001344578,0.8247606,0.01307712,0.07398204,0.08224771,0.0001107686],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.006833027,0.1466843,0.8374991,0.001233477,0.0004419254,0.0001161145,0.000160733,0.0005559578,0.006475345],"genre_scores_gemma":[0.1874443,0.2307937,0.5654758,0.001126118,0.003043437,0.0002637566,0.0009355221,0.0002715513,0.01064589],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.003349619,"threshold_uncertainty_score":0.01747662,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147386143","doi":"10.1109/tifs.2009.2024715","title":"Digital image source coder forensics via intrinsic fingerprints","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Information Forensics and Security","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Digital watermarking; Encoder; Source code; Watermark; Artificial intelligence; Image processing; Computer vision; Coding (social sciences); Fingerprint recognition; Fingerprint (computing); Image (mathematics); Mathematics","authors":[{"name":"Steven K. Tjoa","is_ca":false},{"name":"Hanqing Zhao","is_ca":true},{"name":"K.J.R. Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.004765004067404885,"gpt":0.1949385777863559,"spread":0.190173573718951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001545147,0.0004026898,0.000551124,0.001677362,0.00032556,0.0009138,0.0005730985,0.0009645518,0.0007687891],"category_scores_gemma":[0.009326929,0.0002311996,0.0003366483,0.0006374175,0.0008325363,0.001643838,0.001219824,0.0005823175,0.0003339266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003782125,"about_ca_system_score_gemma":0.0004932134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004076827,"about_ca_topic_score_gemma":0.000248286,"domain_scores_codex":[0.9989763,0.0002849667,0.00003789126,0.00009455518,0.0005410735,0.00006515538],"domain_scores_gemma":[0.9968125,0.001525041,0.0004432955,0.0006394754,0.0005045097,0.00007500692],"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":[0.0008661067,0.0002613554,0.01823048,0.0003473039,0.0001392514,0.001095276,0.0004742855,0.1283861,0.1357025,0.05262204,0.00224007,0.6596352],"study_design_scores_gemma":[0.00002957784,0.0001699563,0.001699516,0.00005295669,0.00003889788,0.001931448,0.00007395557,0.8217001,0.1612009,0.01105117,0.002009055,0.00004250525],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1407057,0.0004254159,0.8553039,0.0002170927,0.00002855732,0.00006206614,0.00008387799,0.0009481965,0.00222509],"genre_scores_gemma":[0.7869829,0.0003715506,0.2114285,0.00005405197,0.00002574541,0.00003161103,0.00009304973,0.00004177195,0.0009707649],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001677362,"threshold_uncertainty_score":0.008171618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965285802","doi":"10.1007/s10032-008-0076-2","title":"Low quality document image modeling and enhancement","year":2009,"lang":"en","type":"article","venue":"International Journal on Document Analysis and Recognition (IJDAR)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Degradation (telecommunications); Shadow (psychology); Diffusion; Image restoration; Image enhancement; Computer vision; Artificial intelligence; Process (computing); Image (mathematics); Image processing; Physics","authors":[{"name":"Reza Farrahi Moghaddam","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01485540075618043,"gpt":0.2952721653155663,"spread":0.2804167645593859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003668093,0.0005872571,0.0003787785,0.0005705416,0.0001898691,0.001135736,0.0006009028,0.0006403313,0.002975927],"category_scores_gemma":[0.001089489,0.0003180896,0.0005560727,0.0004365229,0.0002754043,0.0009772875,0.0003948972,0.0005982256,0.001623143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003279377,"about_ca_system_score_gemma":0.000328855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00136092,"about_ca_topic_score_gemma":0.001353012,"domain_scores_codex":[0.9997532,0.00002764526,0.00001333553,0.00004787703,0.0001348368,0.00002317449],"domain_scores_gemma":[0.9994838,0.0001041052,0.00005359098,0.0001134465,0.0002261256,0.0000188856],"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":[0.0004274967,0.0001807321,0.001875934,0.0003931216,0.00006433923,0.0002793875,0.0001319659,0.1334947,0.4162803,0.006993312,0.003308667,0.4365701],"study_design_scores_gemma":[0.00001203044,0.0001088448,0.001642806,0.00001958274,0.00005783782,0.0004675003,0.00003078612,0.7721009,0.2170414,0.00134974,0.007145943,0.00002265696],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0322791,0.0005782789,0.9629594,0.0001453236,0.00005846416,0.00005400393,0.0001193765,0.0008704151,0.00293566],"genre_scores_gemma":[0.5282771,0.001992783,0.4463797,0.0001437399,0.00008425137,0.00008697771,0.0006301309,0.0004481114,0.02195717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002975927,"threshold_uncertainty_score":0.009955525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2972799026","doi":"10.3390/info10090286","title":"Copy-Move Forgery Detection and Localization Using a Generative Adversarial Network and Convolutional Neural-Network","year":2019,"lang":"en","type":"article","venue":"Information","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Discriminator; Computer science; Deep learning; Artificial intelligence; Convolutional neural network; Adversarial system; Image (mathematics); Convolution (computer science); Pattern recognition (psychology); Generative adversarial network; Artificial neural network; Computer vision; Detector; Telecommunications","authors":[{"name":"Younis Abdalla","is_ca":true},{"name":"M. Tariq Iqbal","is_ca":true},{"name":"Mohamed Shehata","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007330237573003794,"gpt":0.1956074419454287,"spread":0.1882772043724249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009805298,0.0006652761,0.0005397275,0.0006604925,0.0002339513,0.0005499537,0.0008331524,0.0008351507,0.0005530248],"category_scores_gemma":[0.001585397,0.0003041571,0.0005775564,0.0002968195,0.0007223519,0.0008641597,0.0008736769,0.0008741373,0.0001907657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009081327,"about_ca_system_score_gemma":0.0004584018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003806463,"about_ca_topic_score_gemma":0.00324485,"domain_scores_codex":[0.9996048,0.00009726883,0.00001656913,0.0001101039,0.0001175612,0.0000537601],"domain_scores_gemma":[0.9994393,0.0002386775,0.0001115575,0.0000968297,0.00008999504,0.00002371206],"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":[0.0002338826,0.000109556,0.003246918,0.00005042912,0.00009145479,0.0001789304,0.0000634812,0.8470457,0.02035055,0.003629611,0.0005880202,0.1244115],"study_design_scores_gemma":[0.000001134019,0.0000202314,0.0003972076,0.000002786363,0.00000500027,0.00003320481,0.000003576341,0.9936724,0.005305982,0.0004625793,0.00009210672,0.000003896733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2174467,0.0004467703,0.7789355,0.0003023103,0.00003333377,0.00006630374,0.00006949262,0.0008446877,0.00185492],"genre_scores_gemma":[0.9239423,0.0001576527,0.07420354,0.00006580423,0.00001104081,0.00002202279,0.00009419389,0.000016168,0.001487255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003806463,"threshold_uncertainty_score":0.007568657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160197540","doi":"10.1109/tip.2013.2273672","title":"Automatic Inpainting Scheme for Video Text Detection and Removal","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Inpainting; Artificial intelligence; Computer science; Computer vision; Cluster analysis; Video compression picture types; Frame (networking); Motion compensation; Block-matching algorithm; Pattern recognition (psychology); Video tracking; Video processing; Image (mathematics)","authors":[{"name":"Ali Mosleh","is_ca":true},{"name":"Nizar Bouguila","is_ca":true},{"name":"A. Ben Hamza","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01025403738276653,"gpt":0.232936739287884,"spread":0.2226827019051175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004018488,0.0007080272,0.0006592102,0.0008412343,0.000332918,0.0004408231,0.001220389,0.0007659135,0.00136998],"category_scores_gemma":[0.001002091,0.0002981702,0.0005497157,0.0004106365,0.000388967,0.0006497858,0.0005227863,0.0008669576,0.000756316],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002021751,"about_ca_system_score_gemma":0.0003613116,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003665808,"about_ca_topic_score_gemma":0.0005173499,"domain_scores_codex":[0.9996309,0.00004732642,0.00002215629,0.00008039417,0.0001895067,0.00002972988],"domain_scores_gemma":[0.9994175,0.0001084004,0.0001030708,0.0001857876,0.000154865,0.00003030931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002477871,0.0001817632,0.0004698267,0.0001771152,0.00003639608,0.0002674276,0.0001734776,0.01797507,0.6068239,0.004995256,0.002319528,0.3663324],"study_design_scores_gemma":[0.00007258687,0.0005219448,0.001645673,0.00001991532,0.00005068323,0.001402401,0.00003803115,0.5541078,0.4303728,0.002285249,0.00943114,0.00005168528],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01782389,0.0001339734,0.9807648,0.0000408603,0.00004567438,0.00007490109,0.00003927612,0.0006126249,0.0004639496],"genre_scores_gemma":[0.1216954,0.0002195896,0.8754243,0.00005293456,0.00007685921,0.00009815334,0.0001589803,0.00006901393,0.002204907],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00136998,"threshold_uncertainty_score":0.004583061,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403221680","doi":"10.1145/3699710","title":"Deepfake Detection: A Comprehensive Survey from the Reliability Perspective","year":2024,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"National Key Research and Development Program of China; Natural Science Foundation for Distinguished Young Scholars of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Reliability (semiconductor); Perspective (graphical); Reliability engineering; Data science; Artificial intelligence","authors":[{"name":"Tianyi Wang","is_ca":false},{"name":"Xin Liao","is_ca":false},{"name":"K. P. Chow","is_ca":false},{"name":"Xiaodong Lin","is_ca":true},{"name":"Yinglong Wang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08163808677441459,"gpt":0.3430035862687424,"spread":0.2613654994943279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009055037,0.002481789,0.002201313,0.01064922,0.001007014,0.003605329,0.00377793,0.002819199,0.004024037],"category_scores_gemma":[0.04731679,0.001318315,0.001626427,0.00553081,0.001950825,0.008830711,0.002741362,0.002208778,0.003258817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00146252,"about_ca_system_score_gemma":0.003089297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003177413,"about_ca_topic_score_gemma":0.002700164,"domain_scores_codex":[0.9933285,0.001713873,0.0005780734,0.001316958,0.002734413,0.0003282699],"domain_scores_gemma":[0.9574715,0.03120921,0.001994495,0.002326206,0.006634526,0.0003641081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007333967,0.00007143547,0.008127249,0.007519667,0.0001815108,0.0001508813,0.0003063166,0.006032055,0.0006991279,0.01434555,0.02675476,0.9357379],"study_design_scores_gemma":[0.00004564188,0.0006973318,0.01720686,0.02432584,0.001323633,0.00761892,0.002873474,0.07327046,0.01300288,0.1040465,0.7551632,0.0004251206],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.01110134,0.7923602,0.1646719,0.00596222,0.001300317,0.0003052943,0.001027292,0.001158162,0.02211324],"genre_scores_gemma":[0.1232198,0.802177,0.06119856,0.002458317,0.002251574,0.000262,0.002705172,0.0003966217,0.005330924],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.01064922,"threshold_uncertainty_score":0.04788816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990643530","doi":"10.1016/j.patcog.2008.10.021","title":"RSLDI: Restoration of single-sided low-quality document images","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies; Concordia University","keywords":"Computer science; Artificial intelligence; Classifier (UML); Bayesian probability; Document image processing; Pixel; Pattern recognition (psychology); Image restoration; Machine learning; Data mining; Image (mathematics); Computer vision; Image processing; Image segmentation","authors":[{"name":"Reza Farrahi Moghaddam","is_ca":true},{"name":"Mohamed Cheriet","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05353682242814526,"gpt":0.2622833866411715,"spread":0.2087465642130262,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356598,0.0007653758,0.0005481999,0.001479662,0.0003317483,0.0009631219,0.0009806027,0.0006718503,0.009491441],"category_scores_gemma":[0.0009034568,0.0002637579,0.0004023358,0.0006804026,0.0004714401,0.0008564175,0.0008565562,0.0007942447,0.004330365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003267577,"about_ca_system_score_gemma":0.0005145444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005678112,"about_ca_topic_score_gemma":0.0009608114,"domain_scores_codex":[0.9995903,0.00003525165,0.00001869799,0.00005614684,0.0002601855,0.00003940317],"domain_scores_gemma":[0.9994389,0.00006108794,0.0000674342,0.0002129019,0.0001663051,0.00005327626],"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":[0.0007521756,0.0001851854,0.0006555389,0.0004120383,0.00004794111,0.0003184854,0.0001239939,0.005189932,0.3066319,0.00663519,0.01936663,0.659681],"study_design_scores_gemma":[0.00008801315,0.0003105455,0.002950946,0.00006233269,0.00006022186,0.002596934,0.0000858597,0.2025597,0.7399481,0.002325043,0.04894818,0.00006410443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0458637,0.0009413082,0.9240068,0.0005568008,0.0003784213,0.0001482958,0.0006639886,0.01487309,0.01256763],"genre_scores_gemma":[0.220764,0.0009757041,0.7438985,0.0001691664,0.0001685651,0.0001010416,0.001771422,0.0009970007,0.03115469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009491441,"threshold_uncertainty_score":0.03175205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4377250587","doi":"10.1108/jfc-04-2022-0090","title":"The unethical use of deepfakes","year":2022,"lang":"en","type":"article","venue":"Journal of Financial Crime","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Context (archaeology); Originality; Compromise; Value (mathematics); Perspective (graphical); Commission; Public relations; Business; Psychology; Political science; Computer science; Social psychology; Law","authors":[{"name":"Audrey de Rancourt-Raymond","is_ca":true},{"name":"Nadia Smaïli","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02322430661042927,"gpt":0.2349342952144874,"spread":0.2117099886040582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01187959,0.0007547084,0.0004193966,0.003665839,0.005529157,0.01003864,0.001598506,0.004246407,0.004414564],"category_scores_gemma":[0.07259297,0.0004534283,0.0005524415,0.001375164,0.009773362,0.008217478,0.006154724,0.003449118,0.001015229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002548402,"about_ca_system_score_gemma":0.002031395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001251522,"about_ca_topic_score_gemma":0.001205545,"domain_scores_codex":[0.9717424,0.01498777,0.001439128,0.001588498,0.008189768,0.002052428],"domain_scores_gemma":[0.9016658,0.05149699,0.02471108,0.01340759,0.007249873,0.001468762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003829708,0.0005971349,0.1621868,0.001613169,0.0002236722,0.01054934,0.1661445,0.001521916,0.01347284,0.3107228,0.009619033,0.3229658],"study_design_scores_gemma":[0.00006180424,0.002189197,0.1196079,0.009826961,0.0004001903,0.04159453,0.3059013,0.006770324,0.03455061,0.1092117,0.3694462,0.000439347],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"other","genre_scores_codex":[0.8096921,0.003154467,0.0192232,0.01016695,0.0003255602,0.0002346298,0.00008469879,0.0001332823,0.156985],"genre_scores_gemma":[0.9920318,0.0005002457,0.001854268,0.0009461045,0.00007227749,0.00005649263,0.00001160707,0.0000149937,0.004512194],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01187959,"threshold_uncertainty_score":0.06282604,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979300174","doi":"10.3390/sym11101280","title":"Convolutional Neural Network for Copy-Move Forgery Detection","year":2019,"lang":"en","type":"article","venue":"Symmetry","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Set (abstract data type); Process (computing); Deep learning; Architecture; Limit (mathematics); Scheme (mathematics); Pattern recognition (psychology); Image (mathematics); Digital image; Data set; Machine learning; Computer vision; Image processing","authors":[{"name":"Younis Abdalla","is_ca":true},{"name":"M. Tariq Iqbal","is_ca":true},{"name":"Mohamed Shehata","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00806733060437596,"gpt":0.2148070698731471,"spread":0.2067397392687712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005425861,0.0005195678,0.0003386814,0.0006776853,0.0002445994,0.0003763253,0.0006906343,0.0006378116,0.001663444],"category_scores_gemma":[0.001030563,0.0002272153,0.000336242,0.0004662386,0.000236534,0.0007090532,0.0004093789,0.0006114085,0.0005042982],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007129157,"about_ca_system_score_gemma":0.0006226339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006668518,"about_ca_topic_score_gemma":0.006809812,"domain_scores_codex":[0.999752,0.00003509014,0.00001343679,0.00005173385,0.000107232,0.00004040996],"domain_scores_gemma":[0.9997346,0.00006301975,0.00003616733,0.00004583678,0.00010886,0.00001160477],"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":[0.0004225836,0.0001665425,0.004492523,0.0001644992,0.0001388852,0.000209153,0.00005727606,0.2016288,0.05866185,0.005378167,0.004796261,0.7238835],"study_design_scores_gemma":[0.000004953301,0.00004873855,0.001808396,0.00001311721,0.00002791811,0.0000883737,0.000008694814,0.9704409,0.02505975,0.0009189092,0.001569431,0.00001095923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.165318,0.002818998,0.8211647,0.000474474,0.000195642,0.0001128011,0.0003585205,0.002698371,0.006858607],"genre_scores_gemma":[0.844136,0.001056847,0.1457244,0.0001242427,0.00004192647,0.00004766653,0.0004971973,0.00004775521,0.008323971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006668518,"threshold_uncertainty_score":0.01325941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2921092418","doi":"10.1007/s11554-019-00866-x","title":"A multi-purpose image forensic method using densely connected convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Journal of Real-Time Image Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pooling; Pattern recognition (psychology); JPEG; Robustness (evolution); Image (mathematics); Computer vision","authors":[{"name":"Yifang Chen","is_ca":false},{"name":"Xiangui Kang","is_ca":false},{"name":"Yun Q. Shi","is_ca":false},{"name":"Z. Jane Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0149957316665437,"gpt":0.2802711769003,"spread":0.2652754452337562,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008252682,0.001155106,0.0008138237,0.002067117,0.0006100749,0.0008492258,0.001476796,0.001323047,0.002682504],"category_scores_gemma":[0.001010834,0.0006214536,0.001077731,0.0008948919,0.0003922758,0.001262016,0.00180117,0.001143777,0.00121578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004089935,"about_ca_system_score_gemma":0.001110706,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002347675,"about_ca_topic_score_gemma":0.004565112,"domain_scores_codex":[0.9995756,0.00005783829,0.00002001318,0.00008074754,0.0001892575,0.00007666576],"domain_scores_gemma":[0.9994478,0.0000967599,0.00005860094,0.0001107177,0.0002315476,0.00005462167],"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":[0.0003375562,0.0002457004,0.001671562,0.0001343834,0.0001924495,0.0003364822,0.00006276157,0.04450555,0.07822332,0.004779008,0.004166818,0.8653444],"study_design_scores_gemma":[0.00001263903,0.00006613836,0.0008433425,0.00001386725,0.00005872978,0.0004936776,0.00001918591,0.9609898,0.03353767,0.00183037,0.002110343,0.00002426118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.016381,0.0002886574,0.9800996,0.0001244198,0.00008229983,0.00007928992,0.00006742842,0.001153087,0.001724228],"genre_scores_gemma":[0.2512542,0.000530649,0.7387543,0.0001991181,0.0001316962,0.00008770748,0.0003896692,0.0001812692,0.008471305],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002682504,"threshold_uncertainty_score":0.008973897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4288075323","doi":"10.18280/ts.390330","title":"Deepfakes Classification of Faces Using Convolutional Neural Networks","year":2022,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"King Khalid University","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Benchmark (surveying); Upload; Face (sociological concept); Transfer of learning; Pattern recognition (psychology); Generative model; Deep learning; Machine learning; Generative grammar","authors":[{"name":"Jatin Sharma","is_ca":false},{"name":"Sahil Sharma","is_ca":false},{"name":"Vijay Kumar","is_ca":false},{"name":"Hany S. Hussein","is_ca":false},{"name":"Hammam Alshazly","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03237039336163008,"gpt":0.2338795054782328,"spread":0.2015091121166027,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005739694,0.001053175,0.000564665,0.001152816,0.0003116537,0.0005930699,0.0007549989,0.0006772891,0.001628954],"category_scores_gemma":[0.0009947825,0.0002809257,0.0007629793,0.0003971118,0.0003164957,0.00081894,0.0005692567,0.000948061,0.0006925975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001030252,"about_ca_system_score_gemma":0.0005099032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0102077,"about_ca_topic_score_gemma":0.0101922,"domain_scores_codex":[0.9996412,0.00004124215,0.00001448546,0.00009003047,0.0001172305,0.00009575389],"domain_scores_gemma":[0.9997143,0.00007526566,0.00003924656,0.00005005762,0.0001026346,0.00001848943],"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":[0.0007345424,0.000318875,0.01128959,0.0000996555,0.0001863334,0.0003299037,0.0001084145,0.2462225,0.02904996,0.003654169,0.01039698,0.6976091],"study_design_scores_gemma":[0.000002983499,0.0000279107,0.001583718,0.00000726783,0.00001108145,0.00004761814,0.00001460725,0.9906923,0.006355067,0.0007768656,0.0004725415,0.000007938309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5948172,0.002891154,0.38651,0.0008900368,0.0005365111,0.0001465205,0.001415608,0.004452714,0.008340268],"genre_scores_gemma":[0.9551352,0.000557553,0.03621307,0.0001397904,0.00007679572,0.00003570263,0.001379538,0.00003782468,0.006424627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0102077,"threshold_uncertainty_score":0.02029651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035170697","doi":"","title":"Semi-Supervised StyleGAN for Disentanglement Learning","year":2020,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Generalization; Generator (circuit theory); Controllability; Artificial intelligence; Representation (politics); Machine learning; External Data Representation; Feature learning; Unsupervised learning; Labeled data; Face (sociological concept); Identifiability; Semi-supervised learning; Mathematics; Power (physics)","authors":[{"name":"Weili Nie","is_ca":false},{"name":"Tero Karras","is_ca":false},{"name":"Animesh Garg","is_ca":true},{"name":"Shoubhik Debnath","is_ca":false},{"name":"Anjul Patney","is_ca":false},{"name":"Ankit Patel","is_ca":false},{"name":"Anima Anandkumar","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01959542504845665,"gpt":0.2369606785372796,"spread":0.217365253488823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002029861,0.001858276,0.0009269922,0.000887838,0.0005186934,0.001100219,0.002025211,0.001333833,0.003243912],"category_scores_gemma":[0.007573595,0.0006778137,0.001073667,0.0007341771,0.001488202,0.003115651,0.00275299,0.003281642,0.001221821],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006987589,"about_ca_system_score_gemma":0.0006742433,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001070552,"about_ca_topic_score_gemma":0.002843046,"domain_scores_codex":[0.9987734,0.0003970715,0.00005413111,0.0004352626,0.0002454451,0.00009469994],"domain_scores_gemma":[0.9971023,0.001252445,0.000295817,0.0009230191,0.0003001653,0.0001262069],"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":[0.0003580778,0.0002839242,0.002518588,0.0001915478,0.0001631142,0.0001601051,0.000203559,0.4475402,0.02902433,0.02497139,0.006202355,0.4883828],"study_design_scores_gemma":[0.00001212547,0.00005425425,0.0002303325,0.000009354982,0.000008369723,0.0000527552,0.000009303609,0.9780018,0.006300332,0.01425252,0.001054505,0.00001434097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01697917,0.0002148813,0.9793624,0.000151739,0.00003474603,0.00007338534,0.0001507401,0.001554204,0.001478832],"genre_scores_gemma":[0.5647575,0.0002785074,0.425013,0.0005569009,0.0001013889,0.0003656421,0.001793629,0.0005604365,0.006572966],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003243912,"threshold_uncertainty_score":0.01085198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2922342173","doi":"10.1109/tip.2019.2904267","title":"Shadow Detection in Single RGB Images Using a Context Preserver Convolutional Neural Network Trained by Multiple Adversarial Examples","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Stony Brook University; Simon Fraser University; Government of Canada","keywords":"Artificial intelligence; Convolutional neural network; Computer science; Context (archaeology); Adversarial system; RGB color model; Computer vision; Pattern recognition (psychology); Shadow (psychology); Artificial neural network; Image processing; Contextual image classification; Image (mathematics)","authors":[{"name":"Sorour Mohajerani","is_ca":true},{"name":"Parvaneh Saeedi","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01891916739155991,"gpt":0.2269450545083561,"spread":0.2080258871167962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005688437,0.001015701,0.0006172138,0.0005150018,0.0002470686,0.0004355863,0.001144581,0.0007657821,0.001452249],"category_scores_gemma":[0.0009366357,0.0003950463,0.0006055364,0.0003281107,0.00047121,0.0007223502,0.001008564,0.0009611946,0.000474704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007725279,"about_ca_system_score_gemma":0.0005277374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005173708,"about_ca_topic_score_gemma":0.007397148,"domain_scores_codex":[0.9997372,0.00003850347,0.000009787482,0.00009723349,0.00007092335,0.00004637562],"domain_scores_gemma":[0.9997669,0.00006533454,0.00003341633,0.00006914985,0.00005193789,0.00001330567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005628595,0.0001790782,0.002320095,0.0001301148,0.0001778489,0.0003284784,0.00008216118,0.5566468,0.04110745,0.003364504,0.00394119,0.3911594],"study_design_scores_gemma":[0.000003263903,0.0000255888,0.000262887,0.000004632717,0.000009558497,0.0000347989,0.000003232049,0.9941074,0.00484687,0.0004491115,0.0002493574,0.000003422506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1703718,0.0009465747,0.8192927,0.0003606729,0.0001742776,0.000121156,0.0002646326,0.003731613,0.00473654],"genre_scores_gemma":[0.8618965,0.0004052219,0.1300534,0.0002631629,0.00005243548,0.00006803643,0.0005117749,0.0001073781,0.00664227],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005173708,"threshold_uncertainty_score":0.01028723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963433197","doi":"","title":"A Regularization Approach to Blind Deblurring and Denoising of QR Barcodes","year":2014,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Fields Institute for Research in Mathematical Sciences; University of Toronto","funders":"","keywords":"Deblurring; Regularization (linguistics); Computer science; Noise reduction; Exploit; Artificial intelligence; Pattern recognition (psychology); Image processing; A priori and a posteriori; Source code; Computer vision; Mathematics; Image restoration; Image (mathematics)","authors":[{"name":"Yves van Gennip","is_ca":false},{"name":"Prashant Athavale","is_ca":true},{"name":"Rustum Choksi","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0110242690183514,"gpt":0.2054299133101598,"spread":0.1944056442918084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009266752,0.0009246229,0.0006278513,0.0008392319,0.0004030241,0.0009528125,0.001091484,0.001682701,0.002263929],"category_scores_gemma":[0.003388223,0.0004676482,0.0007650353,0.0005186566,0.001296622,0.0009044106,0.001446118,0.001949541,0.001589815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004813679,"about_ca_system_score_gemma":0.0007301157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001062166,"about_ca_topic_score_gemma":0.00121638,"domain_scores_codex":[0.9994167,0.0001258061,0.00003016355,0.00009717006,0.0002823327,0.00004781061],"domain_scores_gemma":[0.9989091,0.0003980899,0.0001535541,0.0002201078,0.0002611154,0.00005797009],"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":[0.0002864426,0.0001312179,0.0006504794,0.0005353217,0.00008733295,0.0003069749,0.0003213568,0.2581272,0.2865617,0.1524825,0.005206223,0.2953032],"study_design_scores_gemma":[0.00001082214,0.00006352535,0.0002029938,0.00002230926,0.00001088027,0.000243185,0.00001307,0.9354416,0.04530006,0.01356578,0.005078896,0.00004694293],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001767575,0.00005389095,0.9974232,0.00004954328,0.00001703385,0.00001115741,0.00001418602,0.0001882364,0.0004752831],"genre_scores_gemma":[0.05016599,0.0002364807,0.9449117,0.00009570652,0.00005771767,0.00006919288,0.00008937442,0.0002053522,0.004168531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002263929,"threshold_uncertainty_score":0.007573605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888516611","doi":"10.1109/access.2018.2866089","title":"Sparsity-Based Image Inpainting Detection via Canonical Correlation Analysis With Low-Rank Constraints","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Inpainting; Artificial intelligence; Computer science; Pattern recognition (psychology); Image (mathematics); JPEG; Feature (linguistics); Computer vision; Mathematics","authors":[{"name":"Xiao Jin","is_ca":true},{"name":"Yuting Su","is_ca":false},{"name":"Liang Zou","is_ca":false},{"name":"Yongwei Wang","is_ca":true},{"name":"Peiguang Jing","is_ca":false},{"name":"Z. Jane Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009953577584668239,"gpt":0.2505138867084685,"spread":0.2405603091238003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001112042,0.001180172,0.001307992,0.001515697,0.0003947887,0.001035079,0.001091571,0.0006363965,0.001197294],"category_scores_gemma":[0.004548214,0.0003931299,0.001041111,0.001450444,0.0007148968,0.001003352,0.001006354,0.00150201,0.0005747966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004737157,"about_ca_system_score_gemma":0.001535528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00331038,"about_ca_topic_score_gemma":0.005251994,"domain_scores_codex":[0.9989919,0.0002334408,0.00005270625,0.0002207071,0.0003835224,0.0001176967],"domain_scores_gemma":[0.997905,0.0007075037,0.0003420401,0.0002511986,0.0006748814,0.0001194081],"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":[0.0003852643,0.0002777012,0.003961707,0.0004894712,0.000222992,0.000533626,0.0003482831,0.2434218,0.08023504,0.02646101,0.01483218,0.6288309],"study_design_scores_gemma":[0.00001051745,0.00005561056,0.0007530875,0.00001056593,0.00002303323,0.000164363,0.00002571329,0.985213,0.009644867,0.002646181,0.00143218,0.00002092452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01223088,0.0001787552,0.9865007,0.0001049975,0.00002659306,0.00004425421,0.00007073166,0.0003173421,0.0005257857],"genre_scores_gemma":[0.2960841,0.0008405051,0.6987728,0.0002139315,0.0002227261,0.0001957209,0.0008914298,0.0001991799,0.002579624],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00331038,"threshold_uncertainty_score":0.006582201,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285176942","doi":"10.1109/access.2022.3179116","title":"Forensic Analysis of Synthetically Generated Western Blot Images","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Air Force Research Laboratory; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Nvidia","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Computational biology; Biology","authors":[{"name":"Sara Mandelli","is_ca":false},{"name":"Davide Cozzolino","is_ca":false},{"name":"Edoardo Daniele Cannas","is_ca":false},{"name":"João Phillipe Cardenuto","is_ca":true},{"name":"Daniel Moreira","is_ca":false},{"name":"Paolo Bestagini","is_ca":false},{"name":"Walter J. Scheirer","is_ca":false},{"name":"Anderson Rocha","is_ca":true},{"name":"Luisa Verdoliva","is_ca":false},{"name":"Stefano Tubaro","is_ca":false},{"name":"Edward J. Delp","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02164088992676621,"gpt":0.2752600669628085,"spread":0.2536191770360423,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001442198,0.0007646344,0.0004442484,0.001874539,0.0003462115,0.0008795761,0.0007780074,0.0008669986,0.001311956],"category_scores_gemma":[0.004500398,0.0002201796,0.0006065767,0.0006929828,0.0007359816,0.0006400013,0.0006611739,0.0006918774,0.00100664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005403836,"about_ca_system_score_gemma":0.0003807937,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009574833,"about_ca_topic_score_gemma":0.000887934,"domain_scores_codex":[0.9992895,0.0001129502,0.00004573086,0.00019931,0.0002657534,0.00008670465],"domain_scores_gemma":[0.997781,0.0007089401,0.0003084224,0.0006135731,0.0005083121,0.00007970067],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002389551,0.0007706382,0.02641878,0.001730792,0.0003823153,0.003827908,0.0007054381,0.1257371,0.3077367,0.01234542,0.04023143,0.477724],"study_design_scores_gemma":[0.00008171898,0.0004971953,0.03298273,0.0002525555,0.0001497864,0.007564276,0.0005953393,0.5835924,0.3322356,0.008048886,0.03387628,0.0001232751],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.714784,0.002413996,0.2595814,0.001135001,0.0007485796,0.0004302664,0.006540913,0.006828918,0.00753694],"genre_scores_gemma":[0.8267377,0.001134853,0.1553781,0.0003442057,0.0001408085,0.0001764841,0.01190571,0.0005412385,0.003640917],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.999133,"threshold_uncertainty_score":0.00762713,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963502975","doi":"10.1109/cvpr.2019.00439","title":"Deep Blind Video Decaptioning by Temporal Aggregation and Recurrence","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Inpainting; Computer science; Artificial intelligence; Encoder; Pixel; Computer vision; Focus (optics); Residual; Frame (networking); Deep learning; Video decoder; Coherence (philosophical gambling strategy); Pattern recognition (psychology); Image (mathematics); Algorithm; Mathematics","authors":[{"name":"Dahun Kim","is_ca":true},{"name":"Sanghyun Woo","is_ca":true},{"name":"Joon‐Young Lee","is_ca":false},{"name":"In So Kweon","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01602982401692345,"gpt":0.2442405746136241,"spread":0.2282107505967007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005214809,0.000867742,0.0007321681,0.0003362613,0.0002501288,0.0006236212,0.001061831,0.0007701981,0.001321155],"category_scores_gemma":[0.001574816,0.0004354931,0.0006709743,0.0003086751,0.0006003844,0.0009823986,0.001085775,0.001198781,0.0003986763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006323351,"about_ca_system_score_gemma":0.0005313709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004029082,"about_ca_topic_score_gemma":0.004714405,"domain_scores_codex":[0.9997681,0.00003781397,0.00001377968,0.00007202775,0.00006911176,0.00003918453],"domain_scores_gemma":[0.9995652,0.0001572425,0.00008859422,0.00008683393,0.00006356506,0.00003858568],"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":[0.0003313603,0.0001048342,0.0008206766,0.0001100056,0.0000822379,0.0002642794,0.0001687993,0.7356625,0.05940922,0.01174899,0.002740969,0.1885562],"study_design_scores_gemma":[0.000004501156,0.00002479469,0.00007008888,0.000002835772,0.000006392456,0.00002821679,0.000003363176,0.9937901,0.004188865,0.001627246,0.0002498202,0.000003805261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03762838,0.0004210537,0.959338,0.0001630737,0.0000405102,0.00002811385,0.00007229717,0.001233053,0.001075474],"genre_scores_gemma":[0.7939578,0.000458411,0.1976976,0.0001716259,0.00007890046,0.00008975722,0.000279991,0.0002098956,0.007055924],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004029082,"threshold_uncertainty_score":0.008011281,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013074498","doi":"10.1109/jiot.2020.2983213","title":"Smart Meter Data Obfuscation Using Correlated Noise","year":2020,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Obfuscation; Computer science; Noise (video); Smart meter; Noise measurement; Data mining; Big data; Artificial intelligence; Noise reduction; Smart grid; Computer security","authors":[{"name":"Ahmed Shaharyar Khwaja","is_ca":true},{"name":"Alagan Anpalagan","is_ca":true},{"name":"Muhammad Naeem","is_ca":false},{"name":"Bala Venkatesh","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.07415349170297292,"gpt":0.2719266096692166,"spread":0.1977731179662437,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001263504,0.0008802002,0.0007087627,0.0007277573,0.0004745475,0.0007787009,0.0006937723,0.001047986,0.001008741],"category_scores_gemma":[0.007738412,0.0003056015,0.0006005865,0.0006634219,0.001345744,0.001918777,0.001897743,0.001498686,0.0004307959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005086646,"about_ca_system_score_gemma":0.0005007283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004170314,"about_ca_topic_score_gemma":0.0003735582,"domain_scores_codex":[0.9981224,0.0004890855,0.00008897841,0.0003109255,0.0008149113,0.0001736573],"domain_scores_gemma":[0.9951395,0.002412942,0.00064629,0.001342641,0.0003760914,0.00008252457],"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":[0.001643856,0.0002431715,0.01004852,0.0004334591,0.0003788526,0.001715372,0.0007328182,0.4244814,0.1873807,0.08619801,0.002937735,0.283806],"study_design_scores_gemma":[0.00002713042,0.0002160007,0.001430938,0.00009056653,0.00007759195,0.001262676,0.00009005185,0.8306369,0.1499269,0.0127239,0.003461853,0.00005545701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1125288,0.0006564899,0.8820733,0.0004579171,0.0001214305,0.00006519325,0.0001012821,0.0009915169,0.003004061],"genre_scores_gemma":[0.9068366,0.0004381064,0.0905553,0.0002070812,0.0000570602,0.00004250942,0.0001027913,0.00005924953,0.001701194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001263504,"threshold_uncertainty_score":0.006682098,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388023184","doi":"10.18280/ts.400521","title":"Real-Time Detection and Identification of Suspects in Forensic Imagery Using Advanced YOLOv8 Object Recognition Models","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Digital forensics; Identification (biology); Expediting; Field (mathematics); Machine learning; Object (grammar); Pattern recognition (psychology); Computer vision; Engineering; Computer security","authors":[{"name":"Serkan Karakuş","is_ca":false},{"name":"Mustafa Kaya","is_ca":false},{"name":"Seda Arslan Tuncer","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02477361431543234,"gpt":0.2399835304050656,"spread":0.2152099160896332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005753493,0.000743553,0.0005586316,0.0007339949,0.0001891705,0.0005700676,0.0009459858,0.0006602253,0.001241632],"category_scores_gemma":[0.001013361,0.0002707251,0.0005483885,0.0003254076,0.0002274839,0.0005505095,0.0006194973,0.0006253401,0.001118349],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004866567,"about_ca_system_score_gemma":0.0006620617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005170183,"about_ca_topic_score_gemma":0.006982815,"domain_scores_codex":[0.9997564,0.00002698208,0.00001450989,0.0000735049,0.00008763856,0.0000409349],"domain_scores_gemma":[0.9997582,0.00005233211,0.00003371074,0.00004238683,0.00009951625,0.00001386613],"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":[0.0006421463,0.0002559134,0.007675759,0.0001781182,0.0001384762,0.0002849181,0.0001434736,0.1953431,0.06180782,0.001850843,0.006137038,0.7255425],"study_design_scores_gemma":[0.000009036075,0.0001136745,0.001747663,0.0000194542,0.00002230095,0.0001323387,0.0000308873,0.9753446,0.02028429,0.0004243832,0.001857921,0.00001346532],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.441911,0.00210566,0.5381127,0.0003760958,0.0002730169,0.0002618321,0.0007683935,0.009438269,0.006753024],"genre_scores_gemma":[0.7915353,0.0007251129,0.1973976,0.0002011311,0.00003793874,0.0001252759,0.001950267,0.0001112527,0.007916096],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005170183,"threshold_uncertainty_score":0.01028019,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3136555065","doi":"10.1016/j.patrec.2021.03.009","title":"Perception matters: Exploring imperceptible and transferable anti-forensics for GAN-generated fake face imagery detection","year":2021,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Adversarial system; Perception; Face (sociological concept); Face detection; Deep learning; Benchmark (surveying); Computer vision; Facial recognition system; Machine learning; Pattern recognition (psychology); Psychology","authors":[{"name":"Yongwei Wang","is_ca":true},{"name":"Xin Ding","is_ca":true},{"name":"Yixin Yang","is_ca":false},{"name":"Li Ding","is_ca":true},{"name":"Rabab Ward","is_ca":true},{"name":"Z. Jane Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04359750057162896,"gpt":0.2272622417478511,"spread":0.1836647411762222,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004097635,0.0005304044,0.0003098264,0.0002096689,0.0001618148,0.0007383859,0.0005230248,0.0004693815,0.002311866],"category_scores_gemma":[0.001433688,0.0001478633,0.0003248193,0.0001380694,0.0004872787,0.0009654624,0.0005901881,0.0005770879,0.0004212887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189244,"about_ca_system_score_gemma":0.0003696321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007982255,"about_ca_topic_score_gemma":0.0008338908,"domain_scores_codex":[0.9997293,0.00006457809,0.00000415102,0.00004967213,0.0001023702,0.00004982186],"domain_scores_gemma":[0.9995589,0.0002053118,0.00004421076,0.00007595124,0.00008708226,0.00002848611],"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":[0.001368187,0.0006012595,0.004600804,0.0005477146,0.0001540063,0.0008684798,0.0004632732,0.2187112,0.3576588,0.04389372,0.003973039,0.3671595],"study_design_scores_gemma":[0.00001023231,0.0002252945,0.002378045,0.00001766257,0.00002875706,0.0003852756,0.0001032354,0.9484852,0.03601962,0.01087915,0.00144934,0.00001819065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3979897,0.0009570733,0.5773048,0.0008259612,0.0002010707,0.0001046621,0.0001702211,0.0006992348,0.02174733],"genre_scores_gemma":[0.9658796,0.0003619473,0.03039592,0.000122366,0.0000486938,0.00001469274,0.0000707822,0.00005212049,0.003053765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002311866,"threshold_uncertainty_score":0.007733941,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2802173845","doi":"10.1109/icassp.2018.8462057","title":"A Rotation-Invariant Convolutional Neural Network for Image Enhancement Forensics","year":2018,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Overfitting; Convolutional neural network; Computer science; Artificial intelligence; Robustness (evolution); Invariant (physics); Pattern recognition (psychology); Rotation (mathematics); Computer vision; Artificial neural network; Mathematics","authors":[{"name":"Yifang Chen","is_ca":false},{"name":"Zi Xian Lyu","is_ca":false},{"name":"Xiangui Kang","is_ca":false},{"name":"Zhuo Wang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01451261910649984,"gpt":0.2429311390566931,"spread":0.2284185199501932,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439766,0.0007050339,0.0004320699,0.0006161016,0.000222018,0.000363436,0.0009506589,0.0006152317,0.00131177],"category_scores_gemma":[0.0005612471,0.0002691441,0.000513872,0.0005532612,0.0003219895,0.0007136773,0.0004495929,0.0006466817,0.000576684],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00070005,"about_ca_system_score_gemma":0.0007183155,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005412411,"about_ca_topic_score_gemma":0.00554652,"domain_scores_codex":[0.9998286,0.00002161035,0.000007884137,0.00004026679,0.00006863972,0.00003300362],"domain_scores_gemma":[0.9998523,0.00002405043,0.00002221519,0.00003273532,0.00005854806,0.00001023871],"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":[0.0003325678,0.0001860729,0.002447909,0.000180881,0.0001484297,0.0003036799,0.00005473544,0.2602854,0.1089922,0.008626915,0.005194554,0.6132466],"study_design_scores_gemma":[0.000005140031,0.00005179843,0.0005829169,0.00000990116,0.0000293666,0.0001188499,0.000006094009,0.973153,0.02355456,0.0006601714,0.001815125,0.00001311782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05272466,0.001125114,0.9395388,0.0002514705,0.0001230551,0.0001027498,0.0001932297,0.001799762,0.00414122],"genre_scores_gemma":[0.6989208,0.001419731,0.2902877,0.0002734149,0.00007277134,0.0001097527,0.0006261779,0.00009835,0.008191298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005412411,"threshold_uncertainty_score":0.0107618,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4299806750","doi":"10.1109/icme52920.2022.9859621","title":"Mel-Spectrogram Image-Based End-to-End Audio Deepfake Detection Under Channel-Mismatched Conditions","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Multimedia and Expo (ICME)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spectrogram; Codec; Robustness (evolution); Speech recognition; Spoofing attack; Speech coding; Jitter; Artificial intelligence; Computer network; Telecommunications","authors":[{"name":"Abderrahim Fathan","is_ca":true},{"name":"Jahangir Alam","is_ca":true},{"name":"Woo Hyun Kang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03054497750112798,"gpt":0.2803384128655858,"spread":0.2497934353644578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000553678,0.001157639,0.0008170389,0.000960777,0.0003594495,0.0008008899,0.0009169198,0.001100713,0.003698501],"category_scores_gemma":[0.001782575,0.0001806353,0.0003163712,0.0002965262,0.0003302141,0.001069581,0.001088026,0.0008703853,0.002824427],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003574017,"about_ca_system_score_gemma":0.0005914792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001781408,"about_ca_topic_score_gemma":0.005318571,"domain_scores_codex":[0.9996212,0.0000403553,0.00001707988,0.00008127031,0.000139001,0.0001011719],"domain_scores_gemma":[0.9993306,0.000178223,0.00005736439,0.0001548359,0.0002241749,0.00005476244],"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":[0.001850243,0.0004671155,0.003088062,0.0002161279,0.0001044113,0.0004426363,0.00008018145,0.03583173,0.161109,0.001178401,0.006105442,0.7895268],"study_design_scores_gemma":[0.00003768244,0.0004277403,0.004515827,0.00003623795,0.0000487131,0.0007809073,0.00008750715,0.7230294,0.26608,0.001657445,0.003259711,0.00003881111],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4214332,0.001092505,0.5521539,0.0003700488,0.0004695335,0.0002629349,0.001317984,0.01333728,0.009562761],"genre_scores_gemma":[0.8322571,0.0002745593,0.1559108,0.0001843251,0.00005770915,0.00007323575,0.001524612,0.0001465093,0.009571101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003698501,"threshold_uncertainty_score":0.01237273,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100124582","doi":"10.1109/icassp.2009.4959883","title":"Feature based classification of computer graphics and real images","year":2009,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Histogram; Feature (linguistics); Artificial intelligence; Computer graphics; Feature selection; Graphics; Contextual image classification; Pattern recognition (psychology); Histogram of oriented gradients; Feature extraction; Computer vision; Image (mathematics); Computer graphics (images)","authors":[{"name":"G. Uvan Veera Sankar","is_ca":true},{"name":"Vicky Zhao","is_ca":true},{"name":"Yee‐Hong Yang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01078333483164279,"gpt":0.2251490207379073,"spread":0.2143656859062645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007860572,0.000538444,0.000553189,0.003149039,0.0002661049,0.0009915819,0.0007442074,0.0007070717,0.002483478],"category_scores_gemma":[0.003162043,0.0001235295,0.0005407115,0.00141658,0.0004010591,0.001086811,0.0005523539,0.0005174821,0.0008919231],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000605817,"about_ca_system_score_gemma":0.0003596941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001977313,"about_ca_topic_score_gemma":0.001781379,"domain_scores_codex":[0.9993256,0.00008690987,0.00004268113,0.0001340898,0.00028486,0.000125889],"domain_scores_gemma":[0.9986017,0.0003487557,0.0002020191,0.000322323,0.0004517936,0.00007346378],"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":[0.0005611962,0.0004035785,0.01598695,0.0001242296,0.00006572066,0.0002636462,0.00008404173,0.01529282,0.0573229,0.003984207,0.007250516,0.8986602],"study_design_scores_gemma":[0.00003791544,0.0003952252,0.03941542,0.00003930269,0.00005493579,0.001149728,0.0001938445,0.8454254,0.09938147,0.004437295,0.009411314,0.00005813255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5443963,0.000705144,0.4412585,0.0005628926,0.0002570123,0.0003242884,0.0009162691,0.005033783,0.006545702],"genre_scores_gemma":[0.8482864,0.0001481492,0.1481526,0.00006929105,0.00006962463,0.00008527165,0.001041302,0.00006674715,0.002080505],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003149039,"threshold_uncertainty_score":0.008308113,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140470795","doi":"10.1109/icassp.2007.365987","title":"Block Size Forensic Analysis in Digital Images","year":2007,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Block (permutation group theory); Computer science; Block size; Artificial intelligence; Context (archaeology); Pattern recognition (psychology); False alarm; Digital image; Computer vision; Image processing; Digital forensics; Image (mathematics); Mathematics; Key (lock); Computer security","authors":[{"name":"Steven K. Tjoa","is_ca":false},{"name":"W. Sabrina Lin","is_ca":false},{"name":"Hanqing Zhao","is_ca":true},{"name":"K. J. Ray Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.005319055626112228,"gpt":0.217362042221617,"spread":0.2120429865955047,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006301609,0.0002808609,0.0002908366,0.002911518,0.000355879,0.0004874455,0.0003488811,0.0005575236,0.001325822],"category_scores_gemma":[0.003707381,0.0001772548,0.0002192749,0.0007878597,0.0005545859,0.000903749,0.0006049547,0.0003465071,0.0004830348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002307213,"about_ca_system_score_gemma":0.0002098159,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003719628,"about_ca_topic_score_gemma":0.0003467384,"domain_scores_codex":[0.9996281,0.00007200214,0.00001812292,0.00004484114,0.0001997545,0.00003728741],"domain_scores_gemma":[0.9982892,0.0007570816,0.0002998175,0.0002806004,0.0003231573,0.00005026433],"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":[0.0009229233,0.000128966,0.01131223,0.0003056027,0.00005907024,0.001349181,0.0005891353,0.02632621,0.3166865,0.02041149,0.002829946,0.6190787],"study_design_scores_gemma":[0.00004240488,0.0004019651,0.01996053,0.0001321765,0.00008240802,0.006723837,0.0005283373,0.4015002,0.5365852,0.02450806,0.009439314,0.00009570207],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5034146,0.001538253,0.484565,0.0005217582,0.0001090171,0.0001185045,0.0002614222,0.001265079,0.008206335],"genre_scores_gemma":[0.8672656,0.0006991323,0.1297042,0.00007968667,0.00006366749,0.0000281482,0.0001280567,0.00006990199,0.001961634],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002911518,"threshold_uncertainty_score":0.004435301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3174762625","doi":"10.1007/s11042-021-11126-1","title":"Towards general object-based video forgery detection via dual-stream networks and depth information embedding","year":2021,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Tianjin Science and Technology Program; Natural Science Foundation of Tianjin City","keywords":"Computer science; Conditional random field; Artificial intelligence; Discriminative model; Focus (optics); Video tracking; Segmentation; Feature (linguistics); Embedding; Codec; Object (grammar); Pattern recognition (psychology); Computer vision","authors":[{"name":"Xiao Jin","is_ca":false},{"name":"Zhen He","is_ca":false},{"name":"Yongwei Wang","is_ca":true},{"name":"Jiawei Yu","is_ca":false},{"name":"Jing Xu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01070534111153067,"gpt":0.2331004745540335,"spread":0.2223951334425028,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006513319,0.00121004,0.0007696999,0.001230065,0.0003018665,0.001020303,0.00113905,0.001128631,0.001282089],"category_scores_gemma":[0.001591476,0.0003959085,0.0006046875,0.0007918209,0.000670345,0.00196627,0.001930655,0.0009189169,0.001087873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003958743,"about_ca_system_score_gemma":0.0005463824,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001087315,"about_ca_topic_score_gemma":0.001454353,"domain_scores_codex":[0.9993922,0.0001012517,0.00002551013,0.0001341857,0.0002847098,0.00006213644],"domain_scores_gemma":[0.9994407,0.0001337334,0.00008703901,0.0001339868,0.0001712412,0.00003322459],"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":[0.0006405376,0.0001980625,0.002281151,0.0003440365,0.0001252571,0.0003049499,0.0002306864,0.0787245,0.2899816,0.03172404,0.002483009,0.5929621],"study_design_scores_gemma":[0.00001144429,0.0001263842,0.0009576266,0.00002968178,0.00003727512,0.0004342969,0.00005474183,0.9022254,0.08390673,0.009038939,0.003149936,0.00002754052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01641981,0.0002927118,0.9815809,0.00006740158,0.00003277046,0.00004483875,0.0000497605,0.000284616,0.001227255],"genre_scores_gemma":[0.2802525,0.001211148,0.7109639,0.0001216128,0.00009505838,0.0000863508,0.0003479778,0.00007033566,0.006851073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001282089,"threshold_uncertainty_score":0.004289031,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4224918448","doi":"10.1109/icassp43922.2022.9746888","title":"ADT: Anti-Deepfake Transformer","year":2022,"lang":"en","type":"article","venue":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Fundamental Research Funds for the Central Universities; University of Science and Technology of China","keywords":"Leverage (statistics); Computer science; Convolutional neural network; Security token; Residual; Transformer; Artificial intelligence; Mainstream; Deep learning; Labeled data; Machine learning; Data mining; Pattern recognition (psychology); Computer security; Algorithm","authors":[{"name":"Ping Wang","is_ca":false},{"name":"Kunlin Liu","is_ca":false},{"name":"Wenbo Zhou","is_ca":false},{"name":"Hang Zhou","is_ca":true},{"name":"Honggu Liu","is_ca":false},{"name":"Weiming Zhang","is_ca":false},{"name":"Nenghai Yu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03506727168756474,"gpt":0.2771348645164651,"spread":0.2420675928289003,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100268,0.00149277,0.001011885,0.001242295,0.0006264055,0.00096481,0.002250179,0.001101739,0.007192575],"category_scores_gemma":[0.002427111,0.0004093762,0.00085772,0.0006145812,0.0007395282,0.002151551,0.002060415,0.001504634,0.00372934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006985005,"about_ca_system_score_gemma":0.001370027,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002756755,"about_ca_topic_score_gemma":0.004273604,"domain_scores_codex":[0.99936,0.00007664331,0.00003820578,0.0001702626,0.000255076,0.00009974345],"domain_scores_gemma":[0.9992886,0.0001360063,0.00006090529,0.0002819279,0.0001883861,0.00004428488],"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":[0.0007106648,0.000228684,0.002374723,0.0002580614,0.0001296217,0.0004027145,0.00007278311,0.02773868,0.02718186,0.01070069,0.03895751,0.891244],"study_design_scores_gemma":[0.0001203441,0.0003932528,0.001443634,0.00005796867,0.00007607393,0.001845006,0.00007049995,0.8390077,0.1023395,0.02360706,0.03097691,0.00006208121],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04616569,0.001763792,0.905328,0.0004599362,0.0005748637,0.0003453183,0.001382426,0.03588312,0.008096869],"genre_scores_gemma":[0.619587,0.0007526398,0.3505398,0.001016641,0.0001643726,0.0003280876,0.005118185,0.001179235,0.02131417],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007192575,"threshold_uncertainty_score":0.02406156,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W42110184","doi":"10.1007/978-3-642-24434-6_1","title":"Finding Homoglyphs - A Step towards Detecting Unicode-Based Visual Spoofing Attacks","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Unicode; Computer science; Spoofing attack; Artificial intelligence; Programming language; Computer security","authors":[{"name":"Narges Roshanbin","is_ca":true},{"name":"James Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02659705472081776,"gpt":0.2590963164364769,"spread":0.2324992617156592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002601004,0.0008657257,0.0008252576,0.001890751,0.0005709216,0.001345452,0.0006633286,0.00123049,0.003767887],"category_scores_gemma":[0.00169978,0.0004173584,0.0003942916,0.0009855514,0.0006368758,0.002210582,0.001376149,0.00109716,0.002401763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002134992,"about_ca_system_score_gemma":0.0003475212,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004575189,"about_ca_topic_score_gemma":0.0007341526,"domain_scores_codex":[0.9996088,0.00003789451,0.00001761838,0.00009434905,0.0001769053,0.00006442606],"domain_scores_gemma":[0.9992347,0.0002429774,0.0001051417,0.0002061369,0.0001454615,0.00006562358],"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":[0.0005994673,0.000157498,0.006707293,0.0003648362,0.00007406835,0.001035931,0.0005653563,0.004088386,0.315713,0.01142375,0.003583993,0.6556864],"study_design_scores_gemma":[0.00007688077,0.001121885,0.01624859,0.0002754011,0.0002536305,0.01046223,0.001579454,0.2698142,0.6168855,0.04291631,0.0402168,0.0001490944],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3801411,0.002957745,0.5921218,0.000503073,0.0003018414,0.000266552,0.0006178761,0.003158228,0.01993189],"genre_scores_gemma":[0.5775619,0.001773469,0.4087715,0.0002078394,0.0001190529,0.00006825828,0.0008338683,0.0003505225,0.01031366],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003767887,"threshold_uncertainty_score":0.01260483,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3091508658","doi":"10.1109/ijcnn48605.2020.9207309","title":"Cross-representation transferability of adversarial attacks: From spectrograms to audio waveforms","year":2020,"lang":"en","type":"article","venue":"Espace ÉTS (ETS)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal; McGill University","funders":"","keywords":"Spectrogram; Computer science; Transferability; Speech recognition; Convolutional neural network; Waveform; Artificial intelligence; Adversarial system; Fourier transform; Pattern recognition (psychology); Mathematics; Machine learning; Telecommunications","authors":[{"name":"Karl Michel Koerich","is_ca":true},{"name":"Mohammad Esmailpour","is_ca":true},{"name":"Sajjad Abdoli","is_ca":true},{"name":"Alceu de Souza Britto","is_ca":false},{"name":"Alessandro L. Koerich","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01899236776660037,"gpt":0.2721492946560581,"spread":0.2531569268894577,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001312708,0.001092211,0.0005634975,0.0007108516,0.0002706169,0.0007920797,0.0005470364,0.0009188075,0.002103988],"category_scores_gemma":[0.007307878,0.0002342678,0.0005199317,0.0003849038,0.0009477753,0.00145079,0.002024429,0.001415885,0.0009513184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004857565,"about_ca_system_score_gemma":0.000344656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000942859,"about_ca_topic_score_gemma":0.0006402025,"domain_scores_codex":[0.99874,0.0003002657,0.00006199152,0.0002702893,0.0004561717,0.0001713231],"domain_scores_gemma":[0.9978595,0.0009356279,0.0002387766,0.0006555775,0.0002196477,0.00009088845],"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":[0.0007851007,0.0002566023,0.005039077,0.0002046143,0.0001824897,0.001041822,0.0002072477,0.5232835,0.08452483,0.01043486,0.00424826,0.3697915],"study_design_scores_gemma":[0.00001170248,0.0002736036,0.003665483,0.00003383856,0.00003407463,0.0007993188,0.0000603088,0.943424,0.04389728,0.005327845,0.002440621,0.00003186554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3477705,0.001260604,0.6331863,0.0009740981,0.0003956031,0.0001571684,0.0003782417,0.003040942,0.01283659],"genre_scores_gemma":[0.9657615,0.0003919743,0.02974996,0.000200333,0.0000651754,0.00003883725,0.0003939197,0.00008903698,0.003309362],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002103988,"threshold_uncertainty_score":0.007038534,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220709567","doi":"10.1109/icais53314.2022.9742798","title":"Analysis of Deep Learning Methods for Detection of Bird Species","year":2022,"lang":"en","type":"article","venue":"2022 Second International Conference on Artificial Intelligence and Smart Energy (ICAIS)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence","authors":[{"name":"Subhashree Rath","is_ca":true},{"name":"Senthil Kumar","is_ca":true},{"name":"Venkata Sai Kumar Guntupalli","is_ca":true},{"name":"Suman Sourabh","is_ca":true},{"name":"Shaik Riyaz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0627383028276587,"gpt":0.318791137053182,"spread":0.2560528342255233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001648798,0.0006119591,0.0003614241,0.001180262,0.0002830939,0.0006485562,0.0005569458,0.00056435,0.001835863],"category_scores_gemma":[0.003914658,0.0002139549,0.0005699584,0.0006502408,0.000259997,0.0008213224,0.0003873301,0.0008299387,0.0004162441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009480597,"about_ca_system_score_gemma":0.0005654891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00556317,"about_ca_topic_score_gemma":0.005175781,"domain_scores_codex":[0.9995153,0.00009438433,0.00003065345,0.00008190014,0.0002073965,0.00007040506],"domain_scores_gemma":[0.9982717,0.0008923768,0.0001319008,0.0001114955,0.0005487308,0.00004387385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.0002872136,0.0002059921,0.01972352,0.0002887891,0.0002592612,0.0001948796,0.0001020908,0.49182,0.01214337,0.0150839,0.008080513,0.4518104],"study_design_scores_gemma":[0.000002868857,0.00003203316,0.003218166,0.0000173642,0.00001179962,0.00003640628,0.00001357955,0.9904423,0.002323006,0.003052718,0.0008436858,0.000005959912],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.302966,0.007314523,0.6746142,0.002174895,0.0003096777,0.00009888901,0.001246502,0.001214185,0.01006114],"genre_scores_gemma":[0.9246203,0.001409741,0.06619,0.000185156,0.00007096193,0.0000697794,0.001277965,0.00008576526,0.006090385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00556317,"threshold_uncertainty_score":0.01106155,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405843673","doi":"10.1038/s41598-024-82223-y","title":"Enhancing practicality and efficiency of deepfake detection","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de l'Économie, de l’Innovation et des Exportations du Québec","keywords":"Computer science; Data science","authors":[{"name":"Ismael Balafrej","is_ca":true},{"name":"Mohamed Dahmane","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008676008576843905,"gpt":0.2437657504445885,"spread":0.2350897418677446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002161667,0.001307966,0.0009629146,0.001295757,0.0005851162,0.001515384,0.001846848,0.001755419,0.005410763],"category_scores_gemma":[0.01850312,0.000521075,0.0005791961,0.0007913682,0.0007593366,0.003659206,0.002384676,0.001857006,0.002337698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008790826,"about_ca_system_score_gemma":0.001690788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004372698,"about_ca_topic_score_gemma":0.007127847,"domain_scores_codex":[0.998694,0.0002420081,0.00008410454,0.00033055,0.0004435525,0.0002058522],"domain_scores_gemma":[0.9945528,0.00307912,0.0002498713,0.00108603,0.0009121138,0.000120137],"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":[0.001345374,0.0003912993,0.006850128,0.0003989965,0.0001088353,0.0005596697,0.0002403157,0.1549652,0.07900387,0.01541116,0.009868066,0.7308571],"study_design_scores_gemma":[0.00005942701,0.0001174366,0.001175996,0.000024358,0.00001845423,0.000258399,0.00007034992,0.953941,0.03267875,0.009168449,0.002470039,0.0000173654],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2473541,0.001703446,0.7295285,0.002113136,0.0002506962,0.0002408508,0.0006695723,0.009014063,0.009125569],"genre_scores_gemma":[0.7904207,0.0004412957,0.204136,0.0002497902,0.00007239389,0.0001006703,0.0007112767,0.000239515,0.003628264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005410763,"threshold_uncertainty_score":0.0181008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2062233254","doi":"10.1109/icip.2011.6115853","title":"Modeling the EXIF-Image correlation for image manipulation detection","year":2011,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Feature (linguistics); Noise (video); Image (mathematics); Computer vision; Feature selection; Feature detection (computer vision); Correlation; Image file formats; Header; Statistical model; Image editing; Feature extraction; Image processing; Mathematics","authors":[{"name":"Jiayuan Fan","is_ca":false},{"name":"Alex C. Kot","is_ca":false},{"name":"Hong Cao","is_ca":false},{"name":"Farook Sattar","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04354613269985617,"gpt":0.2332412253540317,"spread":0.1896950926541755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001492616,0.0009693898,0.0005779293,0.0008087191,0.0003403497,0.0007096592,0.001294027,0.0007783867,0.0006751579],"category_scores_gemma":[0.005946129,0.0005650217,0.0006132118,0.0007856666,0.0006862682,0.001369952,0.0006132953,0.00111205,0.0003864202],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009557419,"about_ca_system_score_gemma":0.001185248,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006679556,"about_ca_topic_score_gemma":0.007360465,"domain_scores_codex":[0.9992492,0.000163991,0.00003024721,0.0002122578,0.0002532795,0.00009109917],"domain_scores_gemma":[0.9980806,0.0007394041,0.0005323514,0.0001949487,0.0004056186,0.00004715668],"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":[0.0001774634,0.0001691209,0.0102066,0.00008427278,0.0001101227,0.000166208,0.0001037566,0.8925803,0.01785463,0.01029462,0.001159435,0.06709348],"study_design_scores_gemma":[0.000001802709,0.00001055205,0.0007335848,0.000001535883,0.000005770402,0.00002689075,0.0000033475,0.9968495,0.001630492,0.0006093856,0.0001216399,0.000005608884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06565455,0.000112112,0.9328778,0.0001627905,0.00002023872,0.00003613992,0.00007734926,0.0004546268,0.0006043315],"genre_scores_gemma":[0.8769451,0.0002508567,0.1201661,0.00008039896,0.00004994123,0.0001161497,0.0002572284,0.0001357244,0.001998354],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006679556,"threshold_uncertainty_score":0.01328135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3042891026","doi":"10.1007/s42452-020-3181-6","title":"Blind copy-move forgery detection using SVD and KS test","year":2020,"lang":"en","type":"article","venue":"SN Applied Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Test (biology); Artificial intelligence; Pattern recognition (psychology); Biology","authors":[{"name":"Belal Ahmed","is_ca":true},{"name":"T. Aaron Gulliver","is_ca":true},{"name":"Saif alZahir","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0411237129089518,"gpt":0.2466280016156089,"spread":0.2055042887066572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009189195,0.0009099464,0.0009955078,0.002627908,0.000769124,0.00139424,0.0006002986,0.001073606,0.002941509],"category_scores_gemma":[0.00396805,0.0002623566,0.0007266187,0.001256999,0.0006946049,0.001717578,0.001060429,0.00068988,0.001730235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002491741,"about_ca_system_score_gemma":0.0009074321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000982489,"about_ca_topic_score_gemma":0.001291387,"domain_scores_codex":[0.9986627,0.0001826331,0.0001066931,0.0002362654,0.0006535771,0.0001581396],"domain_scores_gemma":[0.998021,0.0005393995,0.000247936,0.0003382687,0.0007148014,0.0001386543],"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":[0.002503254,0.0003780703,0.01685972,0.0004069297,0.0002654021,0.0006218216,0.0003184585,0.01321692,0.2099139,0.008343683,0.003132172,0.7440397],"study_design_scores_gemma":[0.00008969992,0.0009616603,0.0327378,0.00009069783,0.0002669775,0.00454708,0.0006066371,0.6346984,0.3109227,0.008399038,0.006462184,0.0002171406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3637254,0.001556534,0.6228203,0.0003325056,0.0003256418,0.0001143875,0.0004944832,0.002352454,0.008278346],"genre_scores_gemma":[0.8520995,0.0005792778,0.1410066,0.00007000734,0.0000967786,0.00003437825,0.0006033557,0.00007437716,0.005435694],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002941509,"threshold_uncertainty_score":0.009840369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2611740915","doi":"10.3390/s17051060","title":"A Novel Real-Time Reference Key Frame Scan Matching Method","year":2017,"lang":"en","type":"article","venue":"Sensors","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Key (lock); Matching (statistics); Computer science; Frame (networking); Key frame; Reference frame; Computer vision; Real-time computing; Artificial intelligence; Mathematics; Computer security; Telecommunications; Statistics","authors":[{"name":"H. A. Mohamed","is_ca":true},{"name":"Adel Moussa","is_ca":true},{"name":"Mohamed Elhabiby","is_ca":false},{"name":"Naser El‐Sheimy","is_ca":true},{"name":"A.B. Sesay","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02721186157052707,"gpt":0.2918743676559124,"spread":0.2646625060853853,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000361645,0.0006779191,0.0007757668,0.001490655,0.0004010142,0.0008188377,0.001412496,0.0009626022,0.003723056],"category_scores_gemma":[0.001582774,0.0003490815,0.0006828972,0.001437431,0.0003357393,0.001448368,0.0008930609,0.0007628908,0.002124135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004381767,"about_ca_system_score_gemma":0.0009834451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002153259,"about_ca_topic_score_gemma":0.001888657,"domain_scores_codex":[0.999164,0.00009025487,0.00003570758,0.0001720198,0.0004741857,0.0000638438],"domain_scores_gemma":[0.9995714,0.00006835492,0.00005680608,0.00008021607,0.0002003107,0.00002284717],"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":[0.0002135143,0.0000602091,0.0007424809,0.0001269832,0.00004908624,0.0001840405,0.0001002582,0.01784446,0.081823,0.008398728,0.004987278,0.88547],"study_design_scores_gemma":[0.00006978874,0.0002662288,0.001802461,0.00003539542,0.00006217406,0.001807008,0.00009306998,0.8739516,0.08278842,0.003960302,0.03508927,0.00007427251],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005028288,0.0002567819,0.992675,0.000054245,0.00008424898,0.00004420593,0.0000454386,0.0005401927,0.001271584],"genre_scores_gemma":[0.1291893,0.0005382325,0.863686,0.0001252291,0.0001353386,0.0001542487,0.0003903858,0.0001857803,0.005595569],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003723056,"threshold_uncertainty_score":0.01245487,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111007158","doi":"10.1109/isspit.2010.5711808","title":"Using the local information of image to identify the source camera","year":2010,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Digital camera; Computer science; Computer vision; Noise (video); Identification (biology); Pattern recognition (psychology); Noise reduction; Camera auto-calibration; Image (mathematics); Camera resectioning","authors":[{"name":"Fereshteh Gharibi","is_ca":false},{"name":"Fardin Akhlaghian","is_ca":false},{"name":"Javad RavanJamjah","is_ca":false},{"name":"Bahram ZahirAzami","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01113332540427561,"gpt":0.2662059209807495,"spread":0.2550725955764739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000455629,0.0004875046,0.0005496141,0.001817257,0.0002780514,0.000737708,0.0005687821,0.0006447696,0.002159363],"category_scores_gemma":[0.001709187,0.0002126082,0.0004006502,0.0008125172,0.0006294769,0.001553644,0.0006026162,0.0005090121,0.001073638],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002607527,"about_ca_system_score_gemma":0.0002554802,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003238916,"about_ca_topic_score_gemma":0.0004792995,"domain_scores_codex":[0.999605,0.00006075035,0.00001800834,0.0001102092,0.0001765395,0.0000295094],"domain_scores_gemma":[0.9993597,0.0002276206,0.0000999919,0.0001576074,0.0001272548,0.00002792595],"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":[0.000390353,0.00008726103,0.003539916,0.0004730848,0.0001265263,0.0004273439,0.0002241798,0.02115041,0.2583719,0.01133761,0.001433444,0.7024379],"study_design_scores_gemma":[0.00004799143,0.0005024399,0.01360883,0.0001238566,0.0003184754,0.004260394,0.0002507615,0.5048803,0.4468698,0.01363004,0.01534933,0.0001577311],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03452982,0.0006384496,0.9614096,0.0001047315,0.0000478865,0.00003637611,0.00006850057,0.0004664956,0.002698149],"genre_scores_gemma":[0.444245,0.001142213,0.5506784,0.0001303886,0.000145178,0.00005449471,0.0001963551,0.0001156295,0.003292416],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002159363,"threshold_uncertainty_score":0.007223785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W13310981","doi":"","title":"Detecting differences between photographs and computer generated images","year":2006,"lang":"en","type":"article","venue":"International Conference on Signal Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Computer science; Computer vision; Gabor filter; Pattern recognition (psychology); Feature extraction; Software; Rendering (computer graphics); Image texture; Feature (linguistics); Image processing; Image (mathematics)","authors":[{"name":"Jie Wu","is_ca":true},{"name":"Markad V. Kamath","is_ca":true},{"name":"Skip Poehlman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03106735655855839,"gpt":0.2603812679590382,"spread":0.2293139114004798,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008698177,0.0002578072,0.0003904791,0.002755009,0.0001918508,0.0007568558,0.0004213194,0.0005943808,0.003272387],"category_scores_gemma":[0.006043783,0.0001516323,0.000240503,0.001273384,0.0003609206,0.0008002277,0.0003724102,0.0002845882,0.0008939301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002925182,"about_ca_system_score_gemma":0.0001714008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007320275,"about_ca_topic_score_gemma":0.001050333,"domain_scores_codex":[0.9991688,0.0001160396,0.00007239323,0.0002307105,0.0003222905,0.00008981978],"domain_scores_gemma":[0.996927,0.001470662,0.0003556459,0.0003686637,0.0008051288,0.00007282593],"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":[0.003323392,0.0003896253,0.06164889,0.001300784,0.0001838295,0.001252761,0.001080798,0.002618791,0.3524858,0.002616857,0.002571997,0.5705264],"study_design_scores_gemma":[0.000113309,0.001489926,0.6017132,0.0001298539,0.0002684042,0.005988251,0.002341718,0.05942915,0.3141608,0.002304696,0.01193979,0.0001208907],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9247555,0.000725326,0.06416035,0.0001239455,0.0001748769,0.0002696822,0.0009623751,0.001160004,0.007667931],"genre_scores_gemma":[0.9357393,0.0002465036,0.06184599,0.00003538871,0.00003547386,0.00005692001,0.0007758637,0.00008007931,0.001184518],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003272387,"threshold_uncertainty_score":0.01094723,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4376865313","doi":"10.18280/isi.280228","title":"Deep Fake Image Classification Using VGG-19 Model","year":2023,"lang":"fr","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Computer vision","authors":[{"name":"Chandra Bhushana Rao Killi","is_ca":false},{"name":"Narayanan Balakrishnan","is_ca":false},{"name":"Chinta Someswara Rao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05439739302172529,"gpt":0.2700515188614606,"spread":0.2156541258397353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003179344,0.001181962,0.0005937322,0.001264167,0.0003165066,0.0008761754,0.001291077,0.001247039,0.002930165],"category_scores_gemma":[0.0005920293,0.0003060102,0.0008969381,0.0008268527,0.0003386196,0.0007669517,0.0004850798,0.001050651,0.001238127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001327091,"about_ca_system_score_gemma":0.0007967049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01716181,"about_ca_topic_score_gemma":0.01237129,"domain_scores_codex":[0.9998305,0.00001575117,0.000008781661,0.00004486395,0.00004196826,0.00005805306],"domain_scores_gemma":[0.9998635,0.000028662,0.000020106,0.0000233287,0.00005403161,0.0000103382],"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":[0.0005342294,0.0004593318,0.005570807,0.0001753298,0.0002426459,0.0004431547,0.00007045277,0.3519405,0.01854518,0.004246583,0.03174595,0.5860258],"study_design_scores_gemma":[0.000008337855,0.00004775799,0.0008703126,0.00001902974,0.0000205108,0.00006632513,0.00001326277,0.9888225,0.007153717,0.001230089,0.001740319,0.000007976168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4720349,0.005737045,0.4797817,0.002665697,0.001117006,0.0004291019,0.004568016,0.01301258,0.02065395],"genre_scores_gemma":[0.8982011,0.001322006,0.07048554,0.0005848153,0.0001263581,0.0001388285,0.006307116,0.0002216965,0.02261255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01716181,"threshold_uncertainty_score":0.03412384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137826911","doi":"10.1109/icip.2009.5414612","title":"Device temporal forensics: An information theoretic approach","year":2009,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Realization (probability); Digital forensics; Network forensics; Computer forensics; Simple (philosophy); Data mining; Markov process; Mathematics; Computer security","authors":[{"name":"Junwen Mao","is_ca":false},{"name":"Orhan Bulan","is_ca":false},{"name":"Gaurav Sharma","is_ca":false},{"name":"Suprakash Datta","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01049187999559111,"gpt":0.2182427924430177,"spread":0.2077509124474266,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008411072,0.001498753,0.001972485,0.005153711,0.001678755,0.005072827,0.004253345,0.004015599,0.003630175],"category_scores_gemma":[0.02912477,0.001222597,0.001885797,0.004099302,0.007065016,0.0141933,0.006022548,0.003877236,0.0006717815],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002591291,"about_ca_system_score_gemma":0.002525551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001375166,"about_ca_topic_score_gemma":0.0008300348,"domain_scores_codex":[0.9947632,0.002076907,0.0002976233,0.0006874743,0.001835143,0.0003396678],"domain_scores_gemma":[0.9780951,0.01443757,0.002021964,0.003701668,0.001378319,0.0003654408],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000899408,0.00006435747,0.000661598,0.0001956683,0.00007485945,0.0003055004,0.0002428972,0.1546865,0.001854273,0.7875497,0.00167332,0.05260133],"study_design_scores_gemma":[0.00001653454,0.00005337803,0.0002374694,0.00007566331,0.0000295286,0.0002906971,0.0001048299,0.5231947,0.00231347,0.4701543,0.003470317,0.00005906911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001963811,0.000298553,0.9954774,0.0004178552,0.00003398342,0.00003324873,0.00008824655,0.00005777991,0.001629129],"genre_scores_gemma":[0.3234276,0.002741103,0.6661552,0.0005099332,0.0008808343,0.0004334061,0.0006126996,0.0001747736,0.005064517],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008411072,"threshold_uncertainty_score":0.04448247,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4402964300","doi":"10.3390/s24196300","title":"SecureVision: Advanced Cybersecurity Deepfake Detection with Big Data Analytics","year":2024,"lang":"en","type":"article","venue":"Sensors","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Computer science; Scalability; Data science; Deception; Flexibility (engineering); Analytics; Field (mathematics); Big data; Computer security; Trustworthiness; Benchmark (surveying); Data mining; Database","authors":[{"name":"Naresh Kumar","is_ca":false},{"name":"Ankit Kundu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03105017441051629,"gpt":0.2491529323163604,"spread":0.2181027579058441,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001422633,0.001120755,0.0005879807,0.001743845,0.000534445,0.001771932,0.001797969,0.001576926,0.002296607],"category_scores_gemma":[0.004518898,0.0004837513,0.0005413727,0.0007254301,0.001099661,0.003381693,0.00393154,0.002499658,0.0010972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008744602,"about_ca_system_score_gemma":0.001213867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001363715,"about_ca_topic_score_gemma":0.002524478,"domain_scores_codex":[0.9990919,0.0001615542,0.00004001829,0.0001755736,0.0004121994,0.0001187329],"domain_scores_gemma":[0.9985373,0.0004042552,0.0002081785,0.0004355223,0.0002827183,0.0001320432],"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":[0.0009526595,0.0008817973,0.01957815,0.0005090197,0.0005216302,0.000766148,0.0004725821,0.09346902,0.04346082,0.03897348,0.0708404,0.7295743],"study_design_scores_gemma":[0.0000488402,0.0002094938,0.002189321,0.00005343404,0.00003258669,0.0003432215,0.00008370618,0.9092064,0.03463607,0.0389824,0.01416103,0.00005344938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0546902,0.001465824,0.9091473,0.001845685,0.000354476,0.0003126408,0.001269541,0.02290165,0.008012665],"genre_scores_gemma":[0.6360203,0.0006778873,0.350332,0.001453019,0.0001603083,0.0002550489,0.002944566,0.0006180557,0.007538819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002296607,"threshold_uncertainty_score":0.00768286,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382198865","doi":"10.18280/ts.400301","title":"Detecting Deepfakes: A Novel Framework Employing XceptionNet-Based Convolutional Neural Networks","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology)","authors":[{"name":"Akash Saxena","is_ca":false},{"name":"Dharmendra Kumar Yadav","is_ca":false},{"name":"Manish Gupta","is_ca":false},{"name":"Sunil Phulre","is_ca":false},{"name":"Tripti Arjariya","is_ca":false},{"name":"Varshali Jaiswal","is_ca":false},{"name":"Rakesh Kumar Bhujade","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02669259494866114,"gpt":0.2407383264036971,"spread":0.2140457314550359,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006252609,0.001347573,0.0006805952,0.001245818,0.000418473,0.0008985642,0.002624407,0.00118731,0.001809338],"category_scores_gemma":[0.001143415,0.0004876928,0.0006429759,0.0004948574,0.0006526221,0.001300847,0.001322081,0.001223888,0.0006420726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001542656,"about_ca_system_score_gemma":0.001216064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02148535,"about_ca_topic_score_gemma":0.02549671,"domain_scores_codex":[0.9995695,0.00004211923,0.00001817399,0.0001286194,0.0001401859,0.0001013894],"domain_scores_gemma":[0.9996082,0.0000827851,0.00007121253,0.00005353869,0.0001432092,0.00004096476],"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":[0.0005373904,0.0003232379,0.006118487,0.0001448307,0.000196853,0.0005376823,0.0001174053,0.3083444,0.0291225,0.007713043,0.008888027,0.6379561],"study_design_scores_gemma":[0.000005363784,0.00004598258,0.0005096428,0.00001041912,0.00001464701,0.00005483748,0.000009436583,0.9905262,0.006360082,0.001457685,0.0009966549,0.000009071517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07812651,0.0009606031,0.9090557,0.0005073182,0.0001580917,0.0001703879,0.0005353659,0.005270757,0.005215333],"genre_scores_gemma":[0.7498768,0.0006789237,0.2272442,0.0006912458,0.00009250666,0.0001504027,0.001798009,0.0001628944,0.01930495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02148535,"threshold_uncertainty_score":0.04272062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4382345092","doi":"10.1038/s41598-023-37142-9","title":"Deep neural network analysis models for complex random telegraph signals","year":2023,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Perimeter Institute; University of Waterloo","funders":"Canada First Research Excellence Fund; Industry Canada","keywords":"Computer science; Artificial neural network; Artificial intelligence; Complex network; World Wide Web","authors":[{"name":"Marcel Robitaille","is_ca":true},{"name":"HeeBong Yang","is_ca":true},{"name":"Lu Wang","is_ca":true},{"name":"Bowen Deng","is_ca":true},{"name":"Na Young Kim","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03317681720770999,"gpt":0.2571997950124555,"spread":0.2240229778047456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001132646,0.0009333512,0.0004692837,0.0006095803,0.0002494505,0.0009513334,0.001252289,0.001126164,0.002078142],"category_scores_gemma":[0.003422964,0.0003657408,0.0006629523,0.0005018057,0.0005847867,0.001071487,0.0008405352,0.001953578,0.0004897758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186489,"about_ca_system_score_gemma":0.0008604714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009965648,"about_ca_topic_score_gemma":0.01006473,"domain_scores_codex":[0.9997275,0.00006543953,0.00001410733,0.00009366623,0.0000575381,0.00004174978],"domain_scores_gemma":[0.9990675,0.0005498309,0.0001078273,0.00006423672,0.0001828308,0.00002786847],"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":[0.00004160436,0.00002951317,0.000723312,0.00003199093,0.00002642442,0.0000323221,0.00002720302,0.9682111,0.001338997,0.006181918,0.0008285777,0.02252699],"study_design_scores_gemma":[5.602462e-7,0.000001861998,0.00005270284,0.000001252394,0.000001161722,0.000001520472,9.502012e-7,0.9986585,0.0001123499,0.001117101,0.00005068426,0.000001235222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07278162,0.0006501469,0.9212782,0.0007413847,0.00006568148,0.00004815921,0.0005472311,0.0007263558,0.003161112],"genre_scores_gemma":[0.873418,0.000528625,0.1150771,0.0002272554,0.00006325427,0.0002213226,0.001098561,0.0001596896,0.009206156],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009965648,"threshold_uncertainty_score":0.01981533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4298342869","doi":"10.18280/ria.360407","title":"GAN-Based Encoding Model for Reversible Image Steganography","year":2022,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Steganography; Encoding (memory); Computer science; Cover (algebra); Image (mathematics); Artificial intelligence; Distortion (music); Pattern recognition (psychology); Metric (unit); Similarity (geometry); Computer vision; Telecommunications; Engineering","authors":[{"name":"Kuyoro Afolashade","is_ca":false},{"name":"Uchenna Jeremiah Nzenwata","is_ca":false},{"name":"Oludele Awodele","is_ca":false},{"name":"Sunday Idowu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03984179012861615,"gpt":0.2564952114098063,"spread":0.2166534212811901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004874622,0.0005064889,0.0005050946,0.0004175667,0.0001635275,0.0004250191,0.000700082,0.0006428277,0.001883171],"category_scores_gemma":[0.0009155999,0.0002412346,0.0006642691,0.0003154799,0.0005398652,0.0007588175,0.0003796736,0.001058197,0.0003716945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006990737,"about_ca_system_score_gemma":0.0003817911,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00341776,"about_ca_topic_score_gemma":0.003404232,"domain_scores_codex":[0.9997697,0.00006573227,0.000009422715,0.0000474792,0.00007122823,0.00003638451],"domain_scores_gemma":[0.9996887,0.0001593303,0.00003657317,0.00002940475,0.00007443281,0.00001146205],"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":[0.00007425495,0.00002245615,0.0005503147,0.00006609766,0.00003203775,0.0001197209,0.00004995278,0.9416115,0.00750001,0.02667781,0.0007995472,0.02249626],"study_design_scores_gemma":[0.000001959437,0.0000184326,0.00009573855,0.000004571039,0.000005164946,0.00003816488,0.000002655696,0.9966132,0.0007423895,0.002131555,0.0003414373,0.000004747158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04850176,0.001115724,0.938237,0.0004167186,0.0001004724,0.00006473702,0.0001720476,0.0005101906,0.01088138],"genre_scores_gemma":[0.9454091,0.0008997574,0.04262087,0.0001426588,0.0000401829,0.0001039925,0.0001794298,0.00006326917,0.01054074],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00341776,"threshold_uncertainty_score":0.006795704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2803263450","doi":"10.1007/s11042-018-5959-8","title":"Video logo removal detection based on sparse representation","year":2018,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Natural Science Foundation of Tianjin City; China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Logo (programming language); Artificial intelligence; Representation (politics); Popularity; Prior probability; Computer vision; The Internet; Pattern recognition (psychology); Multimedia; World Wide Web","authors":[{"name":"Xiao Jin","is_ca":true},{"name":"Yuting Su","is_ca":false},{"name":"Liang Zou","is_ca":true},{"name":"Chengqian Zhang","is_ca":false},{"name":"Peiguang Jing","is_ca":false},{"name":"Xuemeng Song","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02858618042671615,"gpt":0.2675505055514261,"spread":0.2389643251247099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002893876,0.0006197317,0.00054598,0.002068877,0.0003210721,0.0006004929,0.0005202211,0.0006228434,0.00125071],"category_scores_gemma":[0.001467123,0.0002026451,0.000459256,0.001103974,0.0003320853,0.001012398,0.0007497207,0.0006963275,0.0006877879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001508537,"about_ca_system_score_gemma":0.000483684,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009420212,"about_ca_topic_score_gemma":0.00148458,"domain_scores_codex":[0.9996642,0.00004020852,0.00001307136,0.00005033169,0.0001815415,0.00005068549],"domain_scores_gemma":[0.9994936,0.0001338649,0.00007719466,0.0000677307,0.0001963336,0.00003124794],"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":[0.0003900622,0.0002038677,0.002816704,0.000166041,0.00004871802,0.0003162029,0.000103272,0.01679591,0.2126831,0.004718842,0.004214778,0.7575424],"study_design_scores_gemma":[0.00002298309,0.0001648942,0.005829532,0.00004277998,0.00007790817,0.0009112285,0.0001359729,0.8985668,0.08515683,0.004356095,0.004693443,0.00004146809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06012908,0.000322676,0.935355,0.0002813526,0.0001035966,0.00006315927,0.0001446105,0.0007245436,0.002875936],"genre_scores_gemma":[0.4956284,0.000991344,0.4966762,0.0002337998,0.0002303394,0.00009280573,0.0008653301,0.0001213419,0.005160462],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002068877,"threshold_uncertainty_score":0.004184067,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4296700181","doi":"10.1016/j.scijus.2022.09.003","title":"An efficient method to detect series of fraudulent identity documents based on digitised forensic data","year":2022,"lang":"en","type":"article","venue":"Science & Justice","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Internal Security Fund - Police; Israel Science Foundation; Université de Lausanne; European Commission","keywords":"Computer science; False positive paradox; Profiling (computer programming); Forensic science; Information retrieval; Crime scene; Series (stratigraphy); Data mining; Identity (music); Computer security; Artificial intelligence; Criminology; Psychology","authors":[{"name":"Solène Lugon Moulin","is_ca":false},{"name":"Céline Weyermann","is_ca":false},{"name":"Simon Baechler","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02542539394928056,"gpt":0.3260618365553703,"spread":0.3006364426060897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001585952,0.0005968323,0.0004889439,0.01017362,0.000434252,0.001546269,0.0009110972,0.000775705,0.00227992],"category_scores_gemma":[0.004698147,0.0003925708,0.0003470074,0.003080454,0.0005449012,0.001443196,0.001166712,0.0006937743,0.001498471],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004158849,"about_ca_system_score_gemma":0.0005583942,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006343706,"about_ca_topic_score_gemma":0.001240896,"domain_scores_codex":[0.9986231,0.0002031037,0.0001102451,0.000318128,0.0006633366,0.0000821061],"domain_scores_gemma":[0.9955727,0.001356872,0.0007509638,0.0008474173,0.001318526,0.0001534521],"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":[0.000411866,0.0002006963,0.01346582,0.0006661724,0.0000763617,0.0004619985,0.0006492831,0.002297423,0.1694399,0.002117461,0.002348544,0.8078645],"study_design_scores_gemma":[0.0001493661,0.001293206,0.08514404,0.0003471714,0.0004396487,0.007964735,0.001968025,0.1893681,0.6655098,0.003732243,0.04373875,0.0003449095],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2512716,0.001363394,0.7312449,0.0002577687,0.0001965135,0.001335801,0.001980612,0.00500688,0.007342465],"genre_scores_gemma":[0.2415491,0.0006765645,0.7540131,0.00005705468,0.00006030855,0.0002962779,0.0009191235,0.0001520693,0.00227636],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01017362,"threshold_uncertainty_score":0.008387387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1906733910","doi":"","title":"Robust detection of copy-move forgery using texture features","year":2011,"lang":"en","type":"article","venue":"Iranian Conference on Electrical Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence; Gabor filter; Block (permutation group theory); Pattern recognition (psychology); Feature vector; Computer vision; Feature (linguistics); Lossy compression; Feature extraction; Image (mathematics); Digital image; Matching (statistics); Filter (signal processing); Image processing; Mathematics","authors":[{"name":"Fereshteh Gharibi","is_ca":false},{"name":"Javad RavanJamjah","is_ca":false},{"name":"Fardin Akhlaghian","is_ca":false},{"name":"Bahram Zahir Azami","is_ca":true},{"name":"Javad Alirezaie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04041664814264905,"gpt":0.2054189295025452,"spread":0.1650022813598962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003163663,0.0003370015,0.0005538843,0.001391828,0.0001887103,0.0006000961,0.0003681154,0.0004990401,0.001240776],"category_scores_gemma":[0.00185876,0.0001987968,0.0003556642,0.0005833827,0.0002960886,0.0007228605,0.0005009403,0.0003853725,0.0006399677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001728825,"about_ca_system_score_gemma":0.0002563315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005171006,"about_ca_topic_score_gemma":0.0005170447,"domain_scores_codex":[0.9996389,0.00003193484,0.00002142466,0.000055582,0.0002109209,0.00004113824],"domain_scores_gemma":[0.9992428,0.0001920251,0.0001352374,0.0001776024,0.0002121607,0.00004026535],"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":[0.0008279603,0.000115436,0.01238274,0.0001978722,0.0001051858,0.0007724304,0.0001196656,0.0157116,0.4710051,0.001661772,0.002472211,0.4946281],"study_design_scores_gemma":[0.0000491854,0.0004641707,0.04275271,0.00005765181,0.0001704277,0.004962476,0.0001548227,0.4734547,0.4679469,0.001855108,0.008050911,0.00008099779],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6120183,0.001401505,0.3809956,0.0002089063,0.0001770471,0.0000668081,0.0002254253,0.001347932,0.003558467],"genre_scores_gemma":[0.933598,0.0003972022,0.06388563,0.00004053615,0.00004992268,0.00001863837,0.0001923932,0.00004196089,0.001775599],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001391828,"threshold_uncertainty_score":0.004150867,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4233345373","doi":"10.20943/01201706.17","title":"Copy-Move Forgery Detection Based on Enhanced Patch-Match","year":2017,"lang":"en","type":"article","venue":"International Journal of Computer Science Issues","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Computer security","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.01235251385489955,"gpt":0.2984946380090211,"spread":0.2861421241541215,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006246658,0.0005168966,0.0008526268,0.002092703,0.0003166053,0.0007055901,0.0007348509,0.0007323135,0.001480538],"category_scores_gemma":[0.00179806,0.0002717856,0.0006917152,0.0009482956,0.0004597983,0.001396511,0.0007011901,0.0004345818,0.0006667754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003435092,"about_ca_system_score_gemma":0.0003502951,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008313341,"about_ca_topic_score_gemma":0.00092707,"domain_scores_codex":[0.9992687,0.00007259419,0.00003741993,0.0001921235,0.000359317,0.00006983873],"domain_scores_gemma":[0.998832,0.0002431265,0.0001957469,0.0002811539,0.000394913,0.00005301307],"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":[0.0007411972,0.0003057799,0.01305009,0.0003773055,0.0002418007,0.0005509589,0.0002790862,0.01312827,0.317618,0.003020496,0.001778197,0.6489089],"study_design_scores_gemma":[0.00006820494,0.001155773,0.03784303,0.00004996323,0.0002990256,0.006592882,0.0002582055,0.4142386,0.5305443,0.003195031,0.00562572,0.0001293228],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2973384,0.0008306149,0.697081,0.0001385584,0.00008834748,0.0001542605,0.0001687812,0.00146928,0.002730865],"genre_scores_gemma":[0.7245171,0.0005165729,0.2719632,0.00006818654,0.0000538442,0.00004420731,0.0002101478,0.00006389609,0.002562874],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002092703,"threshold_uncertainty_score":0.004952908,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}