{"meta":{"query_hash":"77b7d61c5f5f","filters":{"topic":"Digital Media Forensic Detection"},"cohort_total":175,"direct_labels_cover":0,"predictions_cover":175,"exported":175,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/77b7d61c5f5f","api":"https://metacan.xera.ac/api/v1/cohort?topic=Digital+Media+Forensic+Detection"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.031067356558558395,"score_gpt":0.2603812679590382,"score_spread":0.22931391140047983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W13310981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9247555,0.000725326,0.064160354,0.00012394555,0.00017487693,0.00026968218,0.0009623751,0.0011600043,0.0076679313],"genre_scores_gemma":[0.9357393,0.0002465036,0.061845988,0.000035388708,0.000035473862,0.00005692001,0.0007758637,0.00008007931,0.001184518],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99916875,0.00011603962,0.00007239323,0.00023071052,0.00032229046,0.00008981978],"domain_scores_gemma":[0.99692696,0.0014706621,0.00035564593,0.00036866372,0.00080512883,0.000072825926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00086981774,0.00025780723,0.00039047914,0.0027550089,0.00019185085,0.00075685576,0.0004213194,0.00059438084,0.0032723865],"category_scores_gemma":[0.006043783,0.00015163228,0.00024050295,0.0012733842,0.00036092056,0.00080022775,0.00037241023,0.0002845882,0.00089393015],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033233915,0.00038962526,0.061648894,0.0013007838,0.00018382946,0.0012527613,0.0010807983,0.0026187906,0.3524858,0.0026168572,0.0025719965,0.5705264],"study_design_scores_gemma":[0.00011330902,0.0014899261,0.60171324,0.00012985394,0.0002684042,0.005988251,0.0023417184,0.05942915,0.31416076,0.0023046958,0.011939792,0.000120890676],"about_ca_topic_score_codex":0.00073202746,"about_ca_topic_score_gemma":0.0010503328,"teacher_disagreement_score":0.0032723865,"about_ca_system_score_codex":0.00029251818,"about_ca_system_score_gemma":0.00017140084,"threshold_uncertainty_score":0.0109472275},"labels":[],"label_agreement":null},{"id":"W1528367647","doi":"10.1007/978-3-540-69812-8_1","title":"DIAR: Advances in Degradation Modeling and Processing","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Key (lock); Enhanced Data Rates for GSM Evolution; Artificial intelligence; Degradation (telecommunications); Process (computing); Software; Shadow (psychology); State (computer science); Computer vision; Algorithm; Telecommunications; Computer security","score_opus":0.014635738112283327,"score_gpt":0.23175221350149655,"score_spread":0.21711647538921322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1528367647","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007967179,0.00972904,0.9820349,0.00027272396,0.00044722605,0.000019414483,0.00020200762,0.0030012673,0.0034965393],"genre_scores_gemma":[0.03425708,0.025884982,0.89929295,0.00061161467,0.0021879538,0.00012302253,0.002406211,0.0022462658,0.03298997],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901605,0.00011659735,0.00006248927,0.00021338084,0.0005466948,0.00004465413],"domain_scores_gemma":[0.99861276,0.0004433081,0.00009852968,0.00035456326,0.00045274405,0.000038042697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014407145,0.0017777662,0.0017814832,0.0016891346,0.00032804967,0.0021944905,0.0021995364,0.0016012067,0.008321691],"category_scores_gemma":[0.0025346025,0.00081672287,0.00084021734,0.0027742404,0.00060720637,0.0028485074,0.0012523136,0.002514686,0.009171087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004864336,0.00006481085,0.00031936908,0.00035267894,0.000051045372,0.0000708832,0.00006399002,0.024185954,0.008489586,0.014871203,0.037957877,0.9135239],"study_design_scores_gemma":[0.000020170499,0.00011801066,0.0011102374,0.00019031238,0.00009137055,0.00081226125,0.00005202772,0.66170603,0.03264055,0.042311616,0.2608502,0.00009719612],"about_ca_topic_score_codex":0.0009528914,"about_ca_topic_score_gemma":0.0009253594,"teacher_disagreement_score":0.008321691,"about_ca_system_score_codex":0.00041594397,"about_ca_system_score_gemma":0.000565924,"threshold_uncertainty_score":0.027838886},"labels":[],"label_agreement":null},{"id":"W1536148330","doi":"","title":"Perceptual Effects of Visual Evidence of the Airstream","year":2010,"lang":"en","type":"article","venue":"Canadian acoustics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Computer science; Visual perception; Cognitive psychology; Psychology; Acoustics; Neuroscience; Physics","score_opus":0.005404334415776768,"score_gpt":0.2138807907342346,"score_spread":0.20847645631845785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1536148330","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96967083,0.0016184166,0.005496357,0.00045651387,0.0004913787,0.00009166642,0.00031806892,0.00020969729,0.021647],"genre_scores_gemma":[0.99296594,0.00089939125,0.0036914975,0.00018748284,0.00013582333,0.000014542776,0.00020691828,0.00010537144,0.0017930637],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99937844,0.0001274073,0.00003560132,0.00007047744,0.00029144663,0.00009656625],"domain_scores_gemma":[0.9927791,0.0045475536,0.00042213226,0.00025126684,0.0013071891,0.000692733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007145688,0.00064779515,0.00033641822,0.0011997764,0.0006299417,0.0020559486,0.00047062337,0.001207801,0.008534141],"category_scores_gemma":[0.019188643,0.0003748592,0.00025668,0.0004585115,0.00073154346,0.0010128649,0.0015362815,0.0012227958,0.00046209147],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.036917094,0.00036535857,0.009573344,0.0013383469,0.00019876764,0.0014448902,0.002100366,0.0030484477,0.8174441,0.0039096456,0.0039190003,0.11974062],"study_design_scores_gemma":[0.0021713453,0.010281143,0.668518,0.002047593,0.0027203623,0.008175236,0.008092922,0.052121848,0.20305987,0.011761348,0.03044749,0.000602851],"about_ca_topic_score_codex":0.013522344,"about_ca_topic_score_gemma":0.012124287,"teacher_disagreement_score":0.9864777,"about_ca_system_score_codex":0.00057945127,"about_ca_system_score_gemma":0.0010360739,"threshold_uncertainty_score":0.028549492},"labels":[],"label_agreement":null},{"id":"W1574310540","doi":"10.1214/074921708000000336","title":"On Detecting Fake Coin Flip Sequences","year":2008,"lang":"en","type":"book-chapter","venue":"Institute of Mathematical Statistics collections","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"INVIDI Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bernoulli's principle; Computer science; Data mining; Nonlinear system; Artificial intelligence; Pattern recognition (psychology); Algorithm; Machine learning; Engineering","score_opus":0.031471564809745556,"score_gpt":0.24373724899400584,"score_spread":0.21226568418426028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1574310540","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0676354,0.0031313908,0.91217417,0.0009882909,0.0002615912,0.000098019744,0.00023330818,0.00091089564,0.014566918],"genre_scores_gemma":[0.4185757,0.004908139,0.54015416,0.00054468267,0.0005089365,0.00012633666,0.0008110761,0.00018706147,0.03418379],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999183,0.0002042908,0.000031601776,0.0001411617,0.0003751954,0.00006479214],"domain_scores_gemma":[0.9964586,0.0024561149,0.00016353694,0.00038898794,0.00048063614,0.000052110623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001258006,0.0008979522,0.0008693455,0.0018957197,0.0006288556,0.0013270804,0.00085727556,0.001473409,0.0038954366],"category_scores_gemma":[0.00709867,0.0003119412,0.00038016637,0.0016353615,0.0013650196,0.0027681065,0.0009541438,0.00085625466,0.002215873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000223293,0.00008542296,0.0038076446,0.00019104726,0.000046337387,0.00023952093,0.00022621744,0.042815257,0.0148477405,0.035370234,0.008887896,0.8932594],"study_design_scores_gemma":[0.000024475825,0.00015012633,0.0050227293,0.00011769287,0.000047833444,0.0024417893,0.00014287962,0.8624091,0.039532606,0.07577897,0.014261505,0.00007032818],"about_ca_topic_score_codex":0.0011560958,"about_ca_topic_score_gemma":0.0010421675,"teacher_disagreement_score":0.0038954366,"about_ca_system_score_codex":0.0005185985,"about_ca_system_score_gemma":0.00039959233,"threshold_uncertainty_score":0.013031542},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04041664814264905,"score_gpt":0.20541892950254523,"score_spread":0.16500228135989617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1906733910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61201835,0.0014015049,0.38099557,0.00020890629,0.00017704707,0.000066808105,0.00022542533,0.0013479324,0.0035584671],"genre_scores_gemma":[0.93359804,0.00039720215,0.06388563,0.000040536146,0.000049922684,0.000018638366,0.00019239323,0.00004196089,0.0017755994],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996389,0.000031934836,0.000021424663,0.000055582004,0.00021092093,0.000041138235],"domain_scores_gemma":[0.9992428,0.00019202507,0.00013523737,0.00017760244,0.00021216071,0.00004026535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031636632,0.00033700146,0.0005538843,0.0013918278,0.00018871033,0.0006000961,0.00036811538,0.00049904006,0.0012407759],"category_scores_gemma":[0.0018587603,0.00019879683,0.0003556642,0.00058338273,0.00029608863,0.00072286045,0.00050094025,0.00038537252,0.0006399677],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008279603,0.00011543596,0.0123827355,0.00019787216,0.00010518576,0.00077243045,0.00011966558,0.015711596,0.47100508,0.0016617724,0.0024722111,0.49462813],"study_design_scores_gemma":[0.0000491854,0.0004641707,0.04275271,0.000057651814,0.00017042772,0.004962476,0.00015482269,0.47345465,0.46794686,0.0018551084,0.008050911,0.000080997794],"about_ca_topic_score_codex":0.0005171006,"about_ca_topic_score_gemma":0.0005170447,"teacher_disagreement_score":0.0013918278,"about_ca_system_score_codex":0.00017288252,"about_ca_system_score_gemma":0.00025633152,"threshold_uncertainty_score":0.0041508675},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.014855400756180434,"score_gpt":0.2952721653155663,"score_spread":0.2804167645593859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965285802","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0322791,0.00057827885,0.9629594,0.00014532362,0.000058464164,0.00005400393,0.00011937648,0.0008704151,0.0029356598],"genre_scores_gemma":[0.5282771,0.0019927833,0.44637966,0.00014373993,0.00008425137,0.000086977714,0.0006301309,0.0004481114,0.021957168],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997532,0.000027645256,0.000013335532,0.000047877034,0.00013483677,0.000023174487],"domain_scores_gemma":[0.9994838,0.00010410524,0.00005359098,0.00011344648,0.00022612557,0.000018885597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036680928,0.00058725715,0.00037877852,0.0005705416,0.00018986905,0.0011357355,0.0006009028,0.0006403313,0.0029759267],"category_scores_gemma":[0.0010894892,0.0003180896,0.0005560727,0.00043652285,0.00027540434,0.0009772875,0.00039489716,0.00059822557,0.0016231432],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042749668,0.00018073207,0.0018759336,0.00039312162,0.000064339234,0.0002793875,0.00013196595,0.13349469,0.41628027,0.0069933124,0.0033086673,0.4365701],"study_design_scores_gemma":[0.000012030439,0.00010884483,0.0016428058,0.000019582738,0.00005783782,0.0004675003,0.000030786123,0.7721009,0.21704137,0.0013497401,0.0071459427,0.000022656963],"about_ca_topic_score_codex":0.0013609204,"about_ca_topic_score_gemma":0.0013530118,"teacher_disagreement_score":0.0029759267,"about_ca_system_score_codex":0.0003279377,"about_ca_system_score_gemma":0.00032885504,"threshold_uncertainty_score":0.009955525},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.05353682242814526,"score_gpt":0.26228338664117146,"score_spread":0.2087465642130262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990643530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045863703,0.0009413082,0.9240068,0.0005568008,0.00037842127,0.00014829582,0.0006639886,0.014873086,0.012567629],"genre_scores_gemma":[0.22076403,0.0009757041,0.74389845,0.00016916642,0.0001685651,0.00010104162,0.0017714225,0.0009970007,0.031154694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99959034,0.000035251654,0.000018697994,0.000056146837,0.00026018545,0.00003940317],"domain_scores_gemma":[0.99943894,0.00006108794,0.0000674342,0.0002129019,0.00016630511,0.00005327626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005356598,0.0007653758,0.0005481999,0.0014796624,0.00033174828,0.0009631219,0.0009806027,0.00067185034,0.009491441],"category_scores_gemma":[0.00090345676,0.00026375786,0.00040233578,0.00068040256,0.00047144011,0.0008564175,0.00085655623,0.0007942447,0.004330365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007521756,0.00018518539,0.00065553887,0.00041203832,0.00004794111,0.0003184854,0.00012399393,0.0051899324,0.3066319,0.0066351895,0.019366631,0.65968096],"study_design_scores_gemma":[0.00008801315,0.0003105455,0.002950946,0.000062332685,0.00006022186,0.002596934,0.0000858597,0.2025597,0.7399481,0.0023250433,0.048948176,0.00006410443],"about_ca_topic_score_codex":0.0005678112,"about_ca_topic_score_gemma":0.0009608114,"teacher_disagreement_score":0.009491441,"about_ca_system_score_codex":0.00032675773,"about_ca_system_score_gemma":0.00051454443,"threshold_uncertainty_score":0.03175205},"labels":[],"label_agreement":null},{"id":"W2011855045","doi":"10.1109/iccchina.2014.7008276","title":"Natural image splicing detection based on defocus blur at edges","year":2014,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Consistency (knowledge bases); Gaussian blur; Edge detection; Image (mathematics); Feature (linguistics); RNA splicing; Pattern recognition (psychology); Enhanced Data Rates for GSM Evolution; Image restoration; Image processing; Mathematics","score_opus":0.004558079946051603,"score_gpt":0.19027893472918117,"score_spread":0.18572085478312958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011855045","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35557526,0.0008887071,0.63959897,0.00010785067,0.000046165416,0.000065660985,0.00011651476,0.00080049003,0.002800347],"genre_scores_gemma":[0.7923435,0.00077591656,0.20538345,0.0000613304,0.000035390058,0.00002553656,0.00018395288,0.000062390754,0.0011285746],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996246,0.000052068463,0.000027870772,0.00007232618,0.00017701073,0.000046096506],"domain_scores_gemma":[0.99878603,0.00028379753,0.0002807532,0.00014623463,0.00043733956,0.00006587358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004681821,0.00044705858,0.00039825882,0.001975871,0.00024860053,0.00048237017,0.0004964976,0.0005082396,0.00070918334],"category_scores_gemma":[0.0018877803,0.00020480859,0.00037093926,0.0006119924,0.00045816592,0.000981617,0.0005281946,0.00040856216,0.00032723407],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007547253,0.00012848384,0.019378677,0.00042134777,0.00009101047,0.001193899,0.00046102135,0.010774352,0.5027529,0.005029084,0.00117282,0.4578417],"study_design_scores_gemma":[0.000028220355,0.00031850828,0.0344756,0.000054946056,0.000113152266,0.005606457,0.00026724953,0.30609605,0.6446719,0.0035464861,0.004727701,0.000093703704],"about_ca_topic_score_codex":0.00058627373,"about_ca_topic_score_gemma":0.0008096344,"teacher_disagreement_score":0.001975871,"about_ca_system_score_codex":0.00021322905,"about_ca_system_score_gemma":0.0002735782,"threshold_uncertainty_score":0.002475977},"labels":[],"label_agreement":null},{"id":"W2034534808","doi":"10.1109/icpr.2008.4761394","title":"Detection of digital processing of images through a realistic model of CCD noise","year":2008,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais; Université de Sherbrooke","funders":"","keywords":"Compositing; Computer vision; Noise (video); Computer science; Artificial intelligence; Dark-frame subtraction; Image noise; Image processing; Charge-coupled device; Image sensor; Digital camera; Digital image processing; Digital image; Image (mathematics); Computer graphics (images); Median filter; Optics; Physics","score_opus":0.0277044090716672,"score_gpt":0.23426769110552034,"score_spread":0.20656328203385316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034534808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020390157,0.0001822552,0.9778259,0.000069619826,0.000036497444,0.000046752,0.000026213418,0.0001987177,0.0012237991],"genre_scores_gemma":[0.5070745,0.0007011096,0.4891301,0.000185043,0.00006286963,0.00010382961,0.00015302874,0.0000648993,0.0025245822],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894613,0.00014351113,0.00002896328,0.00019808709,0.00064000033,0.00004342359],"domain_scores_gemma":[0.9991078,0.00034102675,0.00013465481,0.00021801257,0.00016064434,0.000037817113],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069476647,0.0005778708,0.0006742184,0.00067072304,0.00037898638,0.0008620215,0.0009749588,0.001224568,0.0006835203],"category_scores_gemma":[0.0028699057,0.00036763703,0.0005707796,0.00031518648,0.000889004,0.0013724053,0.0005336066,0.0005439542,0.00026044456],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048408704,0.00031021217,0.006742055,0.0005656033,0.0001651342,0.0008466389,0.00035782953,0.29889125,0.46567148,0.07025015,0.0015804436,0.15413515],"study_design_scores_gemma":[0.000018899265,0.00016855754,0.001528199,0.000022553739,0.000030009867,0.0011101969,0.000039962873,0.9102917,0.077516526,0.0050446196,0.004173793,0.0000549985],"about_ca_topic_score_codex":0.0013597155,"about_ca_topic_score_gemma":0.0012296711,"teacher_disagreement_score":0.0013597155,"about_ca_system_score_codex":0.0008322583,"about_ca_system_score_gemma":0.00055559777,"threshold_uncertainty_score":0.006038487},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07153507446322221,"score_gpt":0.3140304619340112,"score_spread":0.24249538747078897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036651568","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021810116,0.17449896,0.27536148,0.16772585,0.0023462847,0.00055577804,0.00038964255,0.00023254773,0.35707942],"genre_scores_gemma":[0.72110385,0.08836311,0.15697548,0.010247665,0.00366008,0.0017413164,0.00028438075,0.00018230575,0.017441789],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98131585,0.014415317,0.00080504455,0.001079489,0.0018766177,0.0005076466],"domain_scores_gemma":[0.96455836,0.026883245,0.0022148837,0.003583247,0.0020205604,0.0007398131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024224285,0.00069806236,0.0009853195,0.010164187,0.0074844235,0.019304993,0.0022787633,0.0038318373,0.0050063306],"category_scores_gemma":[0.023575848,0.00050984323,0.00076241704,0.01298003,0.0649271,0.01955299,0.0075798198,0.007716693,0.0009607537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017305899,0.000009955068,0.00009751972,0.000091271904,0.00000246087,0.0000168038,0.0013645807,0.00007975817,0.000013458421,0.994221,0.0006308265,0.0034706497],"study_design_scores_gemma":[0.0000039026354,0.0000067194296,0.000147568,0.00032461865,0.0000035274054,0.000049344686,0.0024630334,0.00029307854,0.0000612509,0.9661481,0.030491656,0.000007242323],"about_ca_topic_score_codex":0.00455326,"about_ca_topic_score_gemma":0.003673296,"teacher_disagreement_score":0.024224285,"about_ca_system_score_codex":0.012190526,"about_ca_system_score_gemma":0.011054694,"threshold_uncertainty_score":0.12811178},"labels":[],"label_agreement":null},{"id":"W2037680939","doi":"10.5539/apr.v5n6p118","title":"Biometric-Like Approach for Verifying Artworks Authenticity","year":2013,"lang":"en","type":"article","venue":"Applied Physics Research","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Certificate; Affine transformation; Artificial intelligence; Computer vision; Authentication (law); Biometrics; Key (lock); Computer graphics (images); Computer security; Theoretical computer science; Mathematics","score_opus":0.09922021738146317,"score_gpt":0.3302293016677891,"score_spread":0.2310090842863259,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2037680939","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019559575,0.00033807824,0.97183514,0.00014144754,0.0001031219,0.00011711594,0.000105681596,0.00064018706,0.007159632],"genre_scores_gemma":[0.5313781,0.0006785926,0.45725718,0.00020334744,0.00014183801,0.00017942749,0.00030605504,0.000074086296,0.009781314],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976502,0.00051680085,0.00011113277,0.0005546325,0.0010489974,0.0001183036],"domain_scores_gemma":[0.998923,0.0001855111,0.00018577473,0.00040378456,0.00026004994,0.000041832987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089843525,0.00035907503,0.0005760358,0.0014922731,0.0005720848,0.0013873515,0.0010392695,0.0014950787,0.003625983],"category_scores_gemma":[0.0026615618,0.00021633398,0.0004725789,0.0009234767,0.0010057057,0.0014178893,0.00132197,0.00070706866,0.0030318894],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000429397,0.00023364731,0.0053255484,0.0005146316,0.00012402196,0.00084801647,0.00054104684,0.025984142,0.27360398,0.08656151,0.003964056,0.60187],"study_design_scores_gemma":[0.00005320591,0.0008804292,0.010724137,0.00019009718,0.0001351755,0.0074424814,0.00072020513,0.59913516,0.2747644,0.04792409,0.057827055,0.00020354502],"about_ca_topic_score_codex":0.00037483725,"about_ca_topic_score_gemma":0.000332294,"teacher_disagreement_score":0.003625983,"about_ca_system_score_codex":0.00047092335,"about_ca_system_score_gemma":0.00062106125,"threshold_uncertainty_score":0.012130141},"labels":[],"label_agreement":null},{"id":"W2060806746","doi":"10.1109/icce.2013.6486908","title":"A new low energy IMF based audio stenographic technique","year":2013,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Hilbert–Huang transform; Payload (computing); Computer science; Audio signal; Audio signal processing; Speech recognition; Mode (computer interface); Code (set theory); Signal processing; Energy (signal processing); Steganography; Speech coding; Artificial intelligence; Telecommunications; Embedding; Computer hardware; Mathematics; Computer network; White noise; Digital signal processing","score_opus":0.004512737638212107,"score_gpt":0.1751664590594882,"score_spread":0.17065372142127608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060806746","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021773422,0.00067765673,0.9748497,0.00009838606,0.00008778278,0.000030075038,0.000059683323,0.0005352094,0.0018880153],"genre_scores_gemma":[0.17729849,0.0010603653,0.81288135,0.00010771186,0.0001374367,0.00005657722,0.00017775221,0.000110377485,0.008169965],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997931,0.000029808234,0.000009304366,0.000031006835,0.00011786609,0.000018868863],"domain_scores_gemma":[0.9997594,0.000066762004,0.000030462681,0.000044138436,0.000081438826,0.00001784123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023459322,0.0004227986,0.00038901932,0.00089540577,0.00014705633,0.0003680198,0.00035681465,0.00048468923,0.002617955],"category_scores_gemma":[0.0005177719,0.00016680126,0.0003202256,0.00056853093,0.00032429423,0.00080121384,0.00046362577,0.00053607963,0.0012463073],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018944204,0.00004054824,0.00051799935,0.0001640241,0.000028557424,0.00018202848,0.00006581039,0.0038270552,0.61102194,0.0045224223,0.0010333862,0.37840673],"study_design_scores_gemma":[0.000066541426,0.00061348535,0.0033677174,0.00006190613,0.00011044774,0.0034580634,0.000096006814,0.36360326,0.58831084,0.003702688,0.036522757,0.000086212414],"about_ca_topic_score_codex":0.00016994806,"about_ca_topic_score_gemma":0.0003041351,"teacher_disagreement_score":0.002617955,"about_ca_system_score_codex":0.00012879312,"about_ca_system_score_gemma":0.00018658319,"threshold_uncertainty_score":0.008757949},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04354613269985617,"score_gpt":0.2332412253540317,"score_spread":0.18969509265417553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062233254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06565455,0.00011211198,0.93287784,0.00016279049,0.000020238718,0.00003613992,0.000077349265,0.0004546268,0.0006043315],"genre_scores_gemma":[0.87694514,0.00025085665,0.12016614,0.00008039896,0.000049941234,0.00011614974,0.00025722836,0.00013572443,0.0019983544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924916,0.00016399102,0.000030247207,0.0002122578,0.0002532795,0.000091099166],"domain_scores_gemma":[0.9980806,0.0007394041,0.0005323514,0.00019494875,0.00040561857,0.00004715668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014926164,0.0009693898,0.00057792926,0.00080871914,0.00034034968,0.00070965925,0.0012940266,0.0007783867,0.0006751579],"category_scores_gemma":[0.005946129,0.0005650217,0.00061321177,0.00078566663,0.0006862682,0.0013699515,0.0006132953,0.0011120505,0.0003864202],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017746336,0.00016912093,0.010206601,0.00008427278,0.00011012268,0.000166208,0.00010375658,0.8925803,0.017854633,0.010294616,0.0011594346,0.067093484],"study_design_scores_gemma":[0.0000018027091,0.000010552052,0.0007335848,0.0000015358834,0.0000057704024,0.000026890748,0.0000033474998,0.9968495,0.0016304917,0.0006093856,0.00012163994,0.000005608884],"about_ca_topic_score_codex":0.0066795563,"about_ca_topic_score_gemma":0.0073604654,"teacher_disagreement_score":0.0066795563,"about_ca_system_score_codex":0.00095574185,"about_ca_system_score_gemma":0.0011852477,"threshold_uncertainty_score":0.013281345},"labels":[],"label_agreement":null},{"id":"W2066929530","doi":"10.1109/smc.2014.6974049","title":"Skin lens: Skin assessment video filters","year":2014,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Computer vision; Lens (geology); Gaussian; Pattern recognition (psychology); Physics; Optics","score_opus":0.009531353584732323,"score_gpt":0.23166239427372315,"score_spread":0.22213104068899084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066929530","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016502038,0.0005178201,0.96587735,0.00012909048,0.00014288562,0.0002513544,0.0006458723,0.010529127,0.005404593],"genre_scores_gemma":[0.22265963,0.0009840588,0.754822,0.0003167631,0.00016523185,0.00026596338,0.0013053793,0.000995823,0.01848518],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996768,0.000034003395,0.000011068689,0.00007374457,0.0001623177,0.000042082997],"domain_scores_gemma":[0.999744,0.00005152005,0.000023524695,0.000034948953,0.00011123461,0.000034797235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038897264,0.00056057615,0.0004298532,0.001275435,0.00029222496,0.00089112925,0.0006563678,0.0006894877,0.009651465],"category_scores_gemma":[0.0008477014,0.00021539461,0.00039505513,0.00038555363,0.00019434061,0.00065924384,0.00055749045,0.0004200129,0.00348511],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004509506,0.00013648577,0.0021440266,0.00025629895,0.000053398617,0.000285635,0.00012498353,0.005040484,0.24220364,0.0048341844,0.016461596,0.7280083],"study_design_scores_gemma":[0.00010729834,0.0006575748,0.019999683,0.00016345455,0.0001027278,0.002919492,0.00024196213,0.4067112,0.4413333,0.0043768208,0.123208344,0.00017817221],"about_ca_topic_score_codex":0.0031747315,"about_ca_topic_score_gemma":0.0040295813,"teacher_disagreement_score":0.009651465,"about_ca_system_score_codex":0.00046079495,"about_ca_system_score_gemma":0.00045355738,"threshold_uncertainty_score":0.0322873},"labels":[],"label_agreement":null},{"id":"W2080694581","doi":"10.1111/1556-4029.12619","title":"Color Separation in Forensic Image Processing Using Interactive Differential Evolution","year":2014,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakeridge Health; Ontario Tech University","funders":"","keywords":"Computer science; Fingerprint (computing); Artificial intelligence; Computer vision; Sample (material); Differential (mechanical device); Process (computing); Pattern recognition (psychology); Engineering","score_opus":0.018227116415178657,"score_gpt":0.2981094609939705,"score_spread":0.27988234457879185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2080694581","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07336659,0.00023208755,0.9220888,0.00007937121,0.000023833085,0.000048482805,0.0000127578305,0.0006424276,0.003505658],"genre_scores_gemma":[0.5374417,0.00018635664,0.460245,0.000070949594,0.000010910231,0.00006511495,0.000036056146,0.000117727504,0.0018262473],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996431,0.00006997545,0.000012301418,0.000060775204,0.00018284758,0.00003104212],"domain_scores_gemma":[0.99962735,0.00018396691,0.000047973153,0.00004720121,0.00007415532,0.00001936168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055611855,0.0004800942,0.00031832018,0.0006020843,0.00029168525,0.00051460083,0.0007589933,0.00042453362,0.0010204284],"category_scores_gemma":[0.0013429213,0.00025150264,0.00037269166,0.00044238818,0.0005005517,0.00056748843,0.00097368564,0.000542364,0.00022055274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023348983,0.00021292687,0.0030224186,0.0001725219,0.000067273286,0.0002362633,0.00047801342,0.12526277,0.39429548,0.013498733,0.0007057375,0.46181443],"study_design_scores_gemma":[0.00001560191,0.00012182822,0.0010490684,0.000011092221,0.000019818122,0.00023609721,0.000040364976,0.8991254,0.093476295,0.0024992425,0.0033757014,0.000029422015],"about_ca_topic_score_codex":0.0007869918,"about_ca_topic_score_gemma":0.0009248322,"teacher_disagreement_score":0.0010204284,"about_ca_system_score_codex":0.00044150895,"about_ca_system_score_gemma":0.0002571513,"threshold_uncertainty_score":0.0034136772},"labels":[],"label_agreement":null},{"id":"W2083454618","doi":"10.1155/2007/47549","title":"Image Authentication Using Added Signal-Dependent Noise","year":2007,"lang":"en","type":"article","venue":"Research Letters in Signal Processing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Authentication (law); Noise (video); Computer vision; Key (lock); Image (mathematics); Artificial intelligence; Digital watermarking; SIGNAL (programming language); JPEG; Computer security","score_opus":0.05468721799344851,"score_gpt":0.3537832975122691,"score_spread":0.2990960795188206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083454618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1817582,0.00088170037,0.8133625,0.00016688059,0.00019160034,0.0000812604,0.00005473023,0.0007643452,0.002738873],"genre_scores_gemma":[0.86744547,0.0006172136,0.12534845,0.000118447046,0.00011344627,0.00003547963,0.00015171556,0.000041997188,0.0061278054],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991179,0.00015236528,0.000038740167,0.00016004484,0.00048316873,0.000047786285],"domain_scores_gemma":[0.9989292,0.00035746762,0.000121243196,0.00023794839,0.00031389727,0.000040201572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003865635,0.0006131191,0.00064908055,0.00070936343,0.00030025718,0.00046784128,0.0006077196,0.00095146307,0.0011122794],"category_scores_gemma":[0.0019196193,0.00025477362,0.00057727075,0.00051891175,0.0005978873,0.0010380355,0.00064726436,0.00046902656,0.0007680349],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013146319,0.00013327808,0.0025879466,0.0002684853,0.000113591836,0.0006960015,0.00010907113,0.028940376,0.795048,0.0051659048,0.0004379645,0.16518474],"study_design_scores_gemma":[0.000047691967,0.00096429227,0.0040448196,0.00004320164,0.00016298842,0.00206452,0.0000449815,0.41930303,0.56419885,0.0024082523,0.006626441,0.00009102715],"about_ca_topic_score_codex":0.00045295895,"about_ca_topic_score_gemma":0.00067563937,"teacher_disagreement_score":0.0011122794,"about_ca_system_score_codex":0.000280722,"about_ca_system_score_gemma":0.00018605414,"threshold_uncertainty_score":0.0037209392},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.010783334831642786,"score_gpt":0.2251490207379073,"score_spread":0.2143656859062645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100124582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54439634,0.000705144,0.44125855,0.0005628926,0.00025701226,0.00032428844,0.00091626914,0.005033783,0.0065457015],"genre_scores_gemma":[0.8482864,0.00014814916,0.14815265,0.000069291054,0.00006962463,0.00008527165,0.0010413015,0.000066747154,0.0020805048],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932563,0.00008690987,0.00004268113,0.00013408976,0.00028486003,0.00012588904],"domain_scores_gemma":[0.99860173,0.00034875565,0.00020201915,0.00032232303,0.00045179363,0.00007346378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007860572,0.000538444,0.00055318896,0.0031490389,0.0002661049,0.0009915819,0.00074420735,0.00070707174,0.0024834776],"category_scores_gemma":[0.0031620432,0.00012352949,0.0005407115,0.0014165802,0.00040105908,0.0010868111,0.00055235386,0.00051748205,0.00089192315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005611962,0.00040357848,0.015986953,0.00012422957,0.00006572066,0.00026364616,0.000084041734,0.015292824,0.0573229,0.003984207,0.0072505157,0.8986602],"study_design_scores_gemma":[0.000037915444,0.00039522516,0.039415423,0.00003930269,0.000054935794,0.0011497283,0.00019384448,0.84542537,0.09938147,0.004437295,0.009411314,0.000058132548],"about_ca_topic_score_codex":0.0019773128,"about_ca_topic_score_gemma":0.0017813788,"teacher_disagreement_score":0.0031490389,"about_ca_system_score_codex":0.00060581695,"about_ca_system_score_gemma":0.0003596941,"threshold_uncertainty_score":0.008308113},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01113332540427561,"score_gpt":0.2662059209807495,"score_spread":0.25507259557647394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111007158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03452982,0.0006384496,0.96140957,0.000104731495,0.000047886504,0.000036376114,0.00006850057,0.0004664956,0.002698149],"genre_scores_gemma":[0.44424495,0.0011422132,0.5506784,0.00013038862,0.00014517797,0.000054494714,0.00019635507,0.00011562946,0.0032924158],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999605,0.00006075035,0.000018008344,0.00011020923,0.00017653946,0.000029509398],"domain_scores_gemma":[0.99935967,0.00022762058,0.0000999919,0.00015760741,0.00012725481,0.000027925955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045562896,0.00048750456,0.0005496141,0.0018172571,0.0002780514,0.000737708,0.0005687821,0.0006447696,0.002159363],"category_scores_gemma":[0.0017091874,0.00021260823,0.00040065023,0.0008125172,0.00062947685,0.0015536442,0.00060261623,0.00050901214,0.0010736376],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000390353,0.000087261025,0.0035399161,0.0004730848,0.00012652625,0.00042734388,0.0002241798,0.021150412,0.25837192,0.011337609,0.0014334439,0.70243794],"study_design_scores_gemma":[0.000047991434,0.0005024399,0.013608834,0.0001238566,0.00031847542,0.0042603943,0.00025076146,0.5048803,0.4468698,0.013630041,0.015349331,0.00015773108],"about_ca_topic_score_codex":0.00032389164,"about_ca_topic_score_gemma":0.0004792995,"teacher_disagreement_score":0.002159363,"about_ca_system_score_codex":0.00026075265,"about_ca_system_score_gemma":0.00025548023,"threshold_uncertainty_score":0.007223785},"labels":[],"label_agreement":null},{"id":"W2126349270","doi":"","title":"Processing of low quality document images: Issues and directions","year":2008,"lang":"en","type":"article","venue":"European Signal Processing Conference","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Preprocessor; Quality (philosophy); Document image processing; Scale (ratio); Historical document; Information retrieval; Image quality; Degradation (telecommunications); Data mining; Artificial intelligence; Image (mathematics); Image segmentation; Geography","score_opus":0.03518356667216791,"score_gpt":0.279084193577136,"score_spread":0.24390062690496808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126349270","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016127493,0.65575594,0.25138682,0.045056242,0.0027037887,0.0003482837,0.0002389381,0.001060463,0.027322171],"genre_scores_gemma":[0.107265174,0.6005126,0.25820035,0.0043832804,0.0066342778,0.00042831627,0.0007205452,0.00020707755,0.02164829],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99831104,0.0004172511,0.00018025961,0.00027864944,0.00068235694,0.00013037102],"domain_scores_gemma":[0.9885318,0.004116108,0.00062964496,0.00057625776,0.005593229,0.00055288145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006317342,0.0010762116,0.001202721,0.002062352,0.0012259679,0.0053422907,0.0026692944,0.007176783,0.008121266],"category_scores_gemma":[0.0051112697,0.0007958608,0.0005820983,0.003219084,0.0026203478,0.009582705,0.0011599775,0.002214582,0.004254795],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033842516,0.00060092844,0.0028571622,0.005761227,0.00007981549,0.00078631367,0.000867906,0.007814895,0.007956273,0.05099225,0.027470235,0.89447457],"study_design_scores_gemma":[0.00018436588,0.0022058983,0.0067137247,0.0060160556,0.00024413381,0.00704659,0.00680604,0.14477144,0.028660472,0.23240225,0.56436443,0.0005845294],"about_ca_topic_score_codex":0.0035928276,"about_ca_topic_score_gemma":0.0023758656,"teacher_disagreement_score":0.008121266,"about_ca_system_score_codex":0.0010241078,"about_ca_system_score_gemma":0.002219413,"threshold_uncertainty_score":0.033409715},"labels":[],"label_agreement":null},{"id":"W2128531178","doi":"10.1109/icme.2007.4284853","title":"Image Source Coding Forensics via Intrinsic Fingerprints","year":2007,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Encoder; Coding (social sciences); Source code; Digital forensics; Discrete cosine transform; Distributed source coding; Multimedia; Artificial intelligence; Computer vision; Data mining; Decoding methods; Image (mathematics); Computer security; Variable-length code; Algorithm","score_opus":0.008812878456328584,"score_gpt":0.2231249389073847,"score_spread":0.2143120604510561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128531178","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29955387,0.0006545908,0.6936369,0.0003477139,0.000036172405,0.00007454073,0.00015159741,0.001050544,0.004494104],"genre_scores_gemma":[0.9278513,0.00031448033,0.07102448,0.000034100387,0.000018062057,0.000017968148,0.00005902693,0.000027202941,0.00065338664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898475,0.00031796657,0.000031227974,0.000085692656,0.00051144074,0.00006893365],"domain_scores_gemma":[0.9961845,0.0020852275,0.0005002391,0.0007530635,0.00041796223,0.0000589431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014172669,0.0003611651,0.0003906176,0.0015596205,0.00030587253,0.00094665575,0.0004888426,0.0008387591,0.0008878138],"category_scores_gemma":[0.010015301,0.00022327476,0.0002706502,0.0006624619,0.0009727394,0.0017429845,0.0011217133,0.00058184756,0.00027991194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008684807,0.00022884605,0.01967194,0.00041741974,0.00016058623,0.0013581297,0.000762405,0.21554981,0.15679099,0.098172374,0.0020830354,0.50393605],"study_design_scores_gemma":[0.000027457492,0.00023239547,0.0033361732,0.00009277472,0.000046543453,0.0021390966,0.00012922326,0.7670785,0.20276909,0.021716613,0.0023794866,0.000052644107],"about_ca_topic_score_codex":0.00042959934,"about_ca_topic_score_gemma":0.00023516476,"teacher_disagreement_score":0.0015596205,"about_ca_system_score_codex":0.00040111627,"about_ca_system_score_gemma":0.00044403592,"threshold_uncertainty_score":0.007495284},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.010491879995591112,"score_gpt":0.21824279244301772,"score_spread":0.2077509124474266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137826911","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001963811,0.00029855303,0.9954774,0.0004178552,0.000033983422,0.000033248725,0.000088246554,0.000057779915,0.0016291288],"genre_scores_gemma":[0.32342762,0.0027411033,0.6661552,0.00050993316,0.0008808343,0.00043340612,0.0006126996,0.00017477357,0.005064517],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947632,0.0020769066,0.00029762328,0.00068747427,0.0018351434,0.00033966784],"domain_scores_gemma":[0.97809505,0.014437575,0.0020219644,0.003701668,0.001378319,0.00036544082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008411072,0.0014987534,0.001972485,0.005153711,0.0016787554,0.0050728265,0.0042533446,0.0040155994,0.003630175],"category_scores_gemma":[0.029124768,0.0012225966,0.0018857968,0.0040993025,0.007065016,0.014193299,0.006022548,0.0038772358,0.0006717815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089940804,0.000064357475,0.000661598,0.00019566834,0.000074859454,0.0003055004,0.00024289718,0.15468651,0.0018542733,0.78754973,0.0016733203,0.052601326],"study_design_scores_gemma":[0.000016534545,0.000053378033,0.00023746943,0.00007566331,0.000029528597,0.00029069706,0.00010482994,0.5231947,0.0023134698,0.47015432,0.0034703175,0.00005906911],"about_ca_topic_score_codex":0.0013751659,"about_ca_topic_score_gemma":0.0008300348,"teacher_disagreement_score":0.008411072,"about_ca_system_score_codex":0.002591291,"about_ca_system_score_gemma":0.0025255508,"threshold_uncertainty_score":0.04448247},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.005319055626112228,"score_gpt":0.21736204222161698,"score_spread":0.21204298659550475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140470795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5034146,0.0015382528,0.484565,0.00052175816,0.00010901715,0.000118504475,0.00026142216,0.0012650795,0.008206335],"genre_scores_gemma":[0.8672656,0.0006991323,0.12970419,0.00007968667,0.00006366749,0.000028148197,0.00012805671,0.000069901995,0.0019616345],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99962807,0.00007200214,0.000018122917,0.000044841137,0.00019975452,0.00003728741],"domain_scores_gemma":[0.99828917,0.0007570816,0.00029981748,0.00028060042,0.00032315732,0.000050264334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063016085,0.0002808609,0.00029083664,0.002911518,0.00035587905,0.00048744553,0.00034888106,0.0005575236,0.0013258215],"category_scores_gemma":[0.0037073812,0.00017725483,0.00021927492,0.00078785967,0.0005545859,0.00090374897,0.00060495466,0.00034650706,0.00048303476],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00092292327,0.00012896604,0.011312229,0.00030560268,0.00005907024,0.001349181,0.00058913534,0.02632621,0.3166865,0.020411493,0.0028299456,0.6190787],"study_design_scores_gemma":[0.000042404885,0.00040196508,0.019960534,0.00013217646,0.00008240802,0.0067238365,0.0005283373,0.40150023,0.53658515,0.02450806,0.009439314,0.00009570207],"about_ca_topic_score_codex":0.00037196284,"about_ca_topic_score_gemma":0.00034673835,"teacher_disagreement_score":0.002911518,"about_ca_system_score_codex":0.00023072131,"about_ca_system_score_gemma":0.00020981586,"threshold_uncertainty_score":0.004435301},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.11795828822454608,"score_gpt":0.33456133149934647,"score_spread":0.2166030432748004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145022254","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001808712,0.5742799,0.41612065,0.0014244509,0.0003131348,0.000054841967,0.00007725163,0.0001956739,0.0057253405],"genre_scores_gemma":[0.02875414,0.78204757,0.18284065,0.0005410442,0.001244553,0.00012714624,0.0002880235,0.00011342481,0.004043479],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99802834,0.00067048706,0.00015853666,0.00028870144,0.00079539965,0.0000584781],"domain_scores_gemma":[0.99299014,0.0046245134,0.0003211463,0.0003508436,0.0016286339,0.000084788284],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054982603,0.0013226514,0.002717516,0.0037179284,0.0005522378,0.0014869828,0.0037092278,0.002891101,0.0032266758],"category_scores_gemma":[0.009215929,0.0010987463,0.0014531147,0.005574956,0.0014300492,0.0038012029,0.0012652882,0.0017774454,0.001811816],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006839616,0.00012112642,0.0007115459,0.0035382314,0.00018124694,0.00013679606,0.0001587478,0.011617535,0.0007044455,0.017063728,0.006097189,0.959601],"study_design_scores_gemma":[0.00019693589,0.00072683854,0.0074412436,0.008814206,0.0011182493,0.005594127,0.0009860203,0.17726205,0.009901265,0.15926234,0.62825876,0.00043790584],"about_ca_topic_score_codex":0.0052952375,"about_ca_topic_score_gemma":0.0044210264,"teacher_disagreement_score":0.0054982603,"about_ca_system_score_codex":0.0010161356,"about_ca_system_score_gemma":0.0018311221,"threshold_uncertainty_score":0.029077947},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.004765004067404885,"score_gpt":0.1949385777863559,"score_spread":0.19017357371895102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147386143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14070572,0.0004254159,0.85530394,0.00021709267,0.000028557322,0.00006206614,0.00008387799,0.00094819645,0.0022250896],"genre_scores_gemma":[0.7869829,0.00037155062,0.21142854,0.00005405197,0.000025745407,0.00003161103,0.00009304973,0.00004177195,0.0009707649],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99897635,0.00028496666,0.000037891263,0.00009455518,0.0005410735,0.00006515538],"domain_scores_gemma":[0.9968125,0.0015250414,0.00044329546,0.00063947536,0.0005045097,0.000075006916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015451469,0.00040268977,0.00055112405,0.0016773622,0.00032555996,0.00091380003,0.00057309854,0.00096455176,0.0007687891],"category_scores_gemma":[0.009326929,0.00023119962,0.00033664826,0.0006374175,0.00083253626,0.0016438384,0.0012198241,0.00058231753,0.0003339266],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086610665,0.00026135542,0.018230475,0.0003473039,0.00013925138,0.0010952761,0.0004742855,0.12838605,0.13570246,0.052622043,0.0022400704,0.65963525],"study_design_scores_gemma":[0.00002957784,0.00016995633,0.0016995156,0.000052956686,0.00003889788,0.001931448,0.00007395557,0.8217001,0.16120085,0.011051167,0.002009055,0.000042505253],"about_ca_topic_score_codex":0.0004076827,"about_ca_topic_score_gemma":0.00024828597,"teacher_disagreement_score":0.0016773622,"about_ca_system_score_codex":0.00037821254,"about_ca_system_score_gemma":0.0004932134,"threshold_uncertainty_score":0.008171618},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.010254037382766527,"score_gpt":0.232936739287884,"score_spread":0.22268270190511746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160197540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01782389,0.00013397336,0.9807648,0.0000408603,0.000045674384,0.00007490109,0.00003927612,0.0006126249,0.00046394957],"genre_scores_gemma":[0.12169537,0.00021958956,0.8754243,0.00005293456,0.000076859214,0.00009815334,0.00015898029,0.000069013935,0.0022049074],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996309,0.00004732642,0.000022156286,0.000080394166,0.00018950673,0.000029729876],"domain_scores_gemma":[0.99941754,0.000108400396,0.00010307077,0.00018578765,0.000154865,0.000030309311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004018488,0.00070802716,0.0006592102,0.00084123434,0.00033291802,0.00044082306,0.0012203894,0.00076591346,0.0013699803],"category_scores_gemma":[0.0010020909,0.00029817017,0.0005497157,0.00041063654,0.00038896705,0.0006497858,0.00052278634,0.00086695765,0.000756316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002477871,0.00018176323,0.0004698267,0.0001771152,0.00003639608,0.00026742756,0.00017347759,0.017975066,0.6068239,0.004995256,0.0023195278,0.36633235],"study_design_scores_gemma":[0.00007258687,0.00052194484,0.0016456727,0.000019915316,0.000050683226,0.0014024008,0.00003803115,0.55410784,0.4303728,0.002285249,0.00943114,0.000051685278],"about_ca_topic_score_codex":0.00036658082,"about_ca_topic_score_gemma":0.00051734986,"teacher_disagreement_score":0.0013699803,"about_ca_system_score_codex":0.00020217511,"about_ca_system_score_gemma":0.00036131163,"threshold_uncertainty_score":0.0045830607},"labels":[],"label_agreement":null},{"id":"W2229862379","doi":"","title":"LR-based forensic comparison under severe test-data scarcity","year":2014,"lang":"en","type":"article","venue":"ANU Open Research (Australian National University)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Test (biology); Scarcity; Forensic science; Computer security; Data science; Biology; History; Economics; Archaeology; Ecology","score_opus":0.26499148858750016,"score_gpt":0.3896173295830931,"score_spread":0.12462584099559293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2229862379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67606986,0.0015297366,0.30912846,0.00046132295,0.00024407555,0.00020770862,0.0011769437,0.00571976,0.0054621445],"genre_scores_gemma":[0.9503996,0.0001721376,0.047202628,0.000080036385,0.000045650788,0.00005057488,0.0009685775,0.00022882149,0.00085199263],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9918665,0.0037976769,0.0005417821,0.0012539729,0.0021162669,0.00042377724],"domain_scores_gemma":[0.9806472,0.011038405,0.0015520619,0.0030781436,0.0032050712,0.00047904285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0113309575,0.00093372917,0.0010492102,0.002915384,0.0006026452,0.0012146889,0.0014037511,0.0015481338,0.0018870743],"category_scores_gemma":[0.041947387,0.00020364024,0.00043447287,0.0011979847,0.00081757165,0.0028548883,0.0025684908,0.0007173513,0.0019512484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005363183,0.0005701562,0.062825024,0.0013076034,0.0005450309,0.0026487925,0.0013984736,0.14384472,0.10637893,0.006152657,0.00836652,0.66059893],"study_design_scores_gemma":[0.00010842419,0.001685853,0.038082507,0.00023572738,0.00020548314,0.0054551153,0.0016850776,0.7945311,0.14153013,0.008916615,0.0073523535,0.00021159142],"about_ca_topic_score_codex":0.000731265,"about_ca_topic_score_gemma":0.00078035676,"teacher_disagreement_score":0.0113309575,"about_ca_system_score_codex":0.0005455121,"about_ca_system_score_gemma":0.00042976753,"threshold_uncertainty_score":0.059924543},"labels":[],"label_agreement":null},{"id":"W2331443673","doi":"10.9790/0661-162111013","title":"Analysis of Digital Image Splicing Detection","year":2014,"lang":"en","type":"article","venue":"IOSR Journal of Computer Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science; Computer vision; Digital image; Artificial intelligence; Image (mathematics); RNA splicing; Digital image analysis; Pattern recognition (psychology); Data science; Image processing; Biology","score_opus":0.003189712134848575,"score_gpt":0.17952550526300154,"score_spread":0.17633579312815295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2331443673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83684695,0.0012631817,0.15441664,0.00015453021,0.000066841014,0.00009305905,0.00044182225,0.0010313973,0.005685638],"genre_scores_gemma":[0.93703353,0.0006832967,0.05888079,0.00003362015,0.00003664775,0.00004531007,0.0006560343,0.00007169617,0.0025589878],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991997,0.00005965958,0.000044220375,0.000101950565,0.0005121705,0.000082306426],"domain_scores_gemma":[0.99851626,0.00032763727,0.00027124133,0.00010852691,0.0007382448,0.00003807826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049621775,0.00045839263,0.00036392527,0.00393298,0.00028363176,0.00046734698,0.00040003998,0.00037613252,0.00093288044],"category_scores_gemma":[0.0018760829,0.00012608335,0.00048421588,0.0016363598,0.00028367748,0.00046483113,0.00023097818,0.000259222,0.00045546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006456165,0.00020565752,0.039461333,0.00037758017,0.00012137625,0.0013772349,0.00037288273,0.019681564,0.28159544,0.0033436297,0.003121868,0.6496959],"study_design_scores_gemma":[0.000025356825,0.00061324966,0.123082966,0.00006162076,0.00024121338,0.00494778,0.000525067,0.45549023,0.40107462,0.002521649,0.011323786,0.000092498776],"about_ca_topic_score_codex":0.0009961564,"about_ca_topic_score_gemma":0.00069526257,"teacher_disagreement_score":0.00393298,"about_ca_system_score_codex":0.00023354588,"about_ca_system_score_gemma":0.00025942622,"threshold_uncertainty_score":0.00312078},"labels":[],"label_agreement":null},{"id":"W2354219756","doi":"","title":"Objectionable Video Detection Algorithm Based on Motion Features","year":2010,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Motion vector; Computer vision; Quarter-pixel motion; Motion (physics); Smoothing; Block-matching algorithm; Motion compensation; Motion estimation; Motion detection; Algorithm; Video tracking; Video processing; Image (mathematics)","score_opus":0.003124945716158443,"score_gpt":0.20050075564809816,"score_spread":0.1973758099319397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2354219756","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04768874,0.0006489448,0.9494198,0.000104485676,0.00009685747,0.00011902986,0.000046032725,0.00077725726,0.0010988795],"genre_scores_gemma":[0.32169425,0.0008380003,0.6736834,0.00014594656,0.00014961262,0.00010854125,0.0002470457,0.0000853238,0.003047884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939144,0.00006250393,0.000041005387,0.00012537875,0.00032075052,0.000058978985],"domain_scores_gemma":[0.9990972,0.00024909477,0.00014971441,0.000084085405,0.00037063015,0.000049202445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006030627,0.0007156528,0.00075841957,0.0022224954,0.0003290473,0.00058685406,0.0010042833,0.00066999154,0.00084995],"category_scores_gemma":[0.0018266,0.00028879417,0.00046611234,0.0006813626,0.00044530205,0.0013138457,0.0004801356,0.0006580543,0.0003923676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037161456,0.00011563524,0.0032697967,0.00020281186,0.00010643596,0.00033042094,0.00014387084,0.010413417,0.19680654,0.0053646145,0.0014378759,0.781437],"study_design_scores_gemma":[0.00008838435,0.00067758554,0.008952519,0.000056599656,0.00020373303,0.0024399734,0.00009917968,0.62052524,0.3497297,0.0031377482,0.013959659,0.0001295982],"about_ca_topic_score_codex":0.0011345283,"about_ca_topic_score_gemma":0.0010265798,"teacher_disagreement_score":0.0022224954,"about_ca_system_score_codex":0.00032218546,"about_ca_system_score_gemma":0.0004041117,"threshold_uncertainty_score":0.0031893253},"labels":[],"label_agreement":null},{"id":"W2363373050","doi":"","title":"Digital image Hiding Technology based on neighbor mean Image Interpolation","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information hiding; Computer science; Image scaling; Interpolation (computer graphics); Image (mathematics); Computer vision; Artificial intelligence; Digital image; Bicubic interpolation; Image quality; Multivariate interpolation; Bilinear interpolation; Image processing","score_opus":0.004353359791090044,"score_gpt":0.21925620731268544,"score_spread":0.21490284752159539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2363373050","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06579394,0.0010391556,0.9246618,0.00021252163,0.00012577484,0.00007130092,0.0000708166,0.00093987485,0.007084788],"genre_scores_gemma":[0.5389907,0.0012093934,0.45043245,0.00008275015,0.000074920834,0.00010210116,0.0001698399,0.000058826,0.008879023],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99974877,0.000024370558,0.000009013334,0.000040635325,0.00016142611,0.000015748115],"domain_scores_gemma":[0.9998487,0.00003490026,0.000022885262,0.000028368537,0.000058540085,0.0000066105335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024461592,0.00020470396,0.0002693158,0.00062229997,0.00034298675,0.0002605772,0.00052403985,0.00030442775,0.0014708437],"category_scores_gemma":[0.00047320954,0.00020178167,0.00040875442,0.0005913859,0.00024330615,0.0009050994,0.00039909343,0.00038421425,0.0004238993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026158436,0.000105314844,0.0022419873,0.00037530743,0.00005932605,0.00018525984,0.0002658535,0.025698896,0.37265426,0.023164272,0.0022424965,0.5727454],"study_design_scores_gemma":[0.000078018806,0.00051303155,0.0043816557,0.000051889267,0.0001040654,0.0016363779,0.00009140244,0.57442385,0.37366548,0.010427503,0.034511656,0.00011508712],"about_ca_topic_score_codex":0.0007845403,"about_ca_topic_score_gemma":0.0009244776,"teacher_disagreement_score":0.0014708437,"about_ca_system_score_codex":0.00038022964,"about_ca_system_score_gemma":0.00035863815,"threshold_uncertainty_score":0.004920423},"labels":[],"label_agreement":null},{"id":"W2386105841","doi":"","title":"Video Tamper Detection Based on Inverse Gravity Density Semi-Supervised Learning","year":2013,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada)","funders":"","keywords":"Computer science; Sample (material); Artificial intelligence; Frame (networking); Noise (video); Variance (accounting); Pattern recognition (psychology); Computer vision; Image (mathematics)","score_opus":0.008289124158589,"score_gpt":0.19069045063725218,"score_spread":0.18240132647866317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2386105841","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043662958,0.00012666511,0.9548811,0.00010188781,0.000022551776,0.000051545278,0.000028653008,0.0005955174,0.0005292304],"genre_scores_gemma":[0.7530634,0.00018411619,0.24425279,0.00012893233,0.00008359811,0.00015406827,0.00024613467,0.00007226959,0.001814776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998711,0.00030810753,0.00008193247,0.00035765994,0.00044196664,0.00009939503],"domain_scores_gemma":[0.9975229,0.00096994627,0.0002886155,0.00028348158,0.00085532054,0.0000797672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013470908,0.00058997475,0.0013311749,0.001325449,0.0005546427,0.0007305093,0.0015500652,0.00087387586,0.0006283233],"category_scores_gemma":[0.004497752,0.0003078408,0.0007366321,0.0007621765,0.00096398214,0.001466591,0.0008681874,0.0008637346,0.00029824578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002615084,0.0004051936,0.0077630864,0.00021336113,0.0002662167,0.00017590068,0.0003195793,0.3435687,0.017427614,0.0064656823,0.00304349,0.6200897],"study_design_scores_gemma":[0.0000045784514,0.000025807818,0.00047405664,0.0000027741175,0.0000066215266,0.000036859674,0.000011644016,0.99582183,0.002428808,0.0010172499,0.00016255032,0.000007189121],"about_ca_topic_score_codex":0.0025491053,"about_ca_topic_score_gemma":0.002052908,"teacher_disagreement_score":0.0025491053,"about_ca_system_score_codex":0.0006156438,"about_ca_system_score_gemma":0.0009378671,"threshold_uncertainty_score":0.0071241856},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.026587484609427624,"score_gpt":0.2257852914226731,"score_spread":0.19919780681324548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407561938","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057565954,0.00070003496,0.9358151,0.00027057997,0.00006181001,0.000046864363,0.00013063932,0.0027532396,0.0026556992],"genre_scores_gemma":[0.7034728,0.00077384175,0.29037935,0.00019383052,0.00007833142,0.000056710927,0.00041212048,0.00010875706,0.0045243013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997061,0.000033035976,0.000013371337,0.00007343835,0.00011769195,0.000056280078],"domain_scores_gemma":[0.99951375,0.00016534005,0.000084005085,0.00007205958,0.00014218231,0.000022726552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006215421,0.0007548231,0.0007003896,0.0011539464,0.0003174534,0.0006379183,0.0010433646,0.0007803113,0.0014608358],"category_scores_gemma":[0.0014695002,0.0003777245,0.0006912121,0.00071410596,0.000501608,0.0011333822,0.0006220855,0.00069239025,0.00051896763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033559016,0.00009178843,0.002500992,0.0001056416,0.000106235355,0.00020106282,0.00006303301,0.2245762,0.03588784,0.005126958,0.0026378005,0.72836673],"study_design_scores_gemma":[0.0000033968704,0.000023381052,0.00050784287,0.0000073469587,0.000013032803,0.000079983445,0.0000063193384,0.9853476,0.012071717,0.0014096048,0.0005211727,0.000008583651],"about_ca_topic_score_codex":0.0060822507,"about_ca_topic_score_gemma":0.006418267,"teacher_disagreement_score":0.0060822507,"about_ca_system_score_codex":0.000921921,"about_ca_system_score_gemma":0.0007213923,"threshold_uncertainty_score":0.012093663},"labels":[],"label_agreement":null},{"id":"W2508426499","doi":"10.17265/1934-8975/2016.08.007","title":"A Parametric Autoregressive Model for the Extraction of Electric Network Frequency Fluctuations in Audio Forensic Authentication","year":2016,"lang":"en","type":"article","venue":"Journal of Energy and Power Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoregressive model; Parametric statistics; Authentication (law); Parametric model; Electric network; Extraction (chemistry); Computer science; Forensic science; Speech recognition; Engineering; Computer security; Statistics; Electrical engineering; Mathematics; Geography; Chemistry","score_opus":0.007811047777218374,"score_gpt":0.21580214492439476,"score_spread":0.2079910971471764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508426499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051847245,0.00036140005,0.9934651,0.00004873671,0.000030961717,0.000016576707,0.000041451392,0.0002702089,0.0005808078],"genre_scores_gemma":[0.4780244,0.002988334,0.5107416,0.00013220341,0.00021091537,0.000161662,0.00059296715,0.0001876152,0.006960351],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995765,0.00012311917,0.000024838037,0.00009493212,0.00015108663,0.000029520717],"domain_scores_gemma":[0.9995123,0.00029081097,0.000051062452,0.00004631923,0.000090500645,0.000008860368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085757213,0.0006182919,0.0004930532,0.00058166793,0.00019183,0.00053119566,0.00064260437,0.0006819099,0.0010302906],"category_scores_gemma":[0.00228639,0.00030852214,0.0006083063,0.0005874862,0.00028417393,0.0009836794,0.00033993786,0.0009331884,0.0009363252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028779215,0.00015326489,0.0023020813,0.0003548401,0.00015290678,0.00048542657,0.00020182521,0.32329932,0.07424527,0.018884096,0.0030868512,0.5765464],"study_design_scores_gemma":[0.0000051653255,0.00006862953,0.0010470499,0.00002032872,0.00003110061,0.00018159306,0.000021747495,0.98675764,0.0071220812,0.0019519575,0.0027639456,0.000028814873],"about_ca_topic_score_codex":0.00199574,"about_ca_topic_score_gemma":0.002267238,"teacher_disagreement_score":0.00199574,"about_ca_system_score_codex":0.00020752485,"about_ca_system_score_gemma":0.00039079308,"threshold_uncertainty_score":0.004535377},"labels":[],"label_agreement":null},{"id":"W2510139783","doi":"10.1109/antem.2016.7550111","title":"Information leakage detection from computer display in electromagnetic radiation","year":2016,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Information leakage; Computer science; Radiation; Leakage (economics); Information theory; Computer vision; Electromagnetic radiation; Artificial intelligence; Set (abstract data type); Probability distribution; Optics; Physics; Mathematics; Statistics; Computer security","score_opus":0.002682769554469661,"score_gpt":0.17033851769415445,"score_spread":0.16765574813968478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510139783","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25144938,0.000810327,0.7429919,0.0002161647,0.00007427466,0.000045434033,0.00007473922,0.0010334211,0.003304282],"genre_scores_gemma":[0.9010395,0.00053570914,0.09700902,0.00009819034,0.000032415923,0.000018589848,0.000067735025,0.00006917474,0.0011296576],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944836,0.000114234645,0.0000316222,0.00010527302,0.00024440253,0.000056158893],"domain_scores_gemma":[0.9989446,0.00040000762,0.00023875629,0.00018686887,0.00019450385,0.000035389367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047998482,0.0004207976,0.00051206554,0.0016033333,0.00039026779,0.00080759055,0.0005248509,0.0006572702,0.0006964905],"category_scores_gemma":[0.0024231821,0.00023327148,0.00045843696,0.00091549987,0.000617011,0.001587863,0.0008361274,0.00062221446,0.00034818792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013879031,0.00016563416,0.015230477,0.0004271417,0.00014015319,0.0014741175,0.0007974291,0.02621744,0.3968567,0.018683253,0.002155481,0.5364642],"study_design_scores_gemma":[0.000039105038,0.00038588734,0.013960902,0.000063674845,0.00014933203,0.004681122,0.0003175464,0.42639312,0.53520393,0.013586273,0.0051165395,0.00010249424],"about_ca_topic_score_codex":0.00022906336,"about_ca_topic_score_gemma":0.0001758594,"teacher_disagreement_score":0.0016033333,"about_ca_system_score_codex":0.00037171927,"about_ca_system_score_gemma":0.00023492586,"threshold_uncertainty_score":0.0026970506},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.027211861570527067,"score_gpt":0.2918743676559124,"score_spread":0.26466250608538533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611740915","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0050282883,0.00025678187,0.992675,0.000054245003,0.000084248975,0.00004420593,0.000045438603,0.0005401927,0.0012715844],"genre_scores_gemma":[0.12918928,0.0005382325,0.86368597,0.00012522911,0.00013533859,0.00015424874,0.00039038577,0.00018578027,0.0055955686],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999164,0.00009025487,0.000035707577,0.00017201978,0.00047418565,0.0000638438],"domain_scores_gemma":[0.9995714,0.00006835492,0.000056806082,0.00008021607,0.0002003107,0.000022847169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036164504,0.0006779191,0.00077576685,0.0014906554,0.0004010142,0.0008188377,0.0014124957,0.0009626022,0.0037230558],"category_scores_gemma":[0.0015827745,0.0003490815,0.0006828972,0.001437431,0.0003357393,0.0014483684,0.0008930609,0.00076289085,0.0021241351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021351434,0.0000602091,0.00074248086,0.00012698317,0.000049086244,0.00018404053,0.000100258156,0.017844459,0.081823,0.008398728,0.0049872776,0.88547],"study_design_scores_gemma":[0.00006978874,0.00026622877,0.0018024613,0.00003539542,0.00006217406,0.0018070076,0.000093069975,0.87395155,0.08278842,0.0039603016,0.035089266,0.00007427251],"about_ca_topic_score_codex":0.0021532592,"about_ca_topic_score_gemma":0.0018886566,"teacher_disagreement_score":0.0037230558,"about_ca_system_score_codex":0.00043817674,"about_ca_system_score_gemma":0.0009834451,"threshold_uncertainty_score":0.012454867},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014512619106499845,"score_gpt":0.24293113905669306,"score_spread":0.22841851995019322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802173845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.052724656,0.0011251139,0.9395388,0.00025147048,0.00012305514,0.000102749764,0.00019322973,0.0017997625,0.0041412204],"genre_scores_gemma":[0.69892085,0.0014197311,0.29028767,0.00027341495,0.00007277134,0.00010975273,0.0006261779,0.00009835,0.008191298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998286,0.000021610353,0.000007884137,0.000040266787,0.00006863972,0.000033003624],"domain_scores_gemma":[0.9998523,0.000024050425,0.000022215194,0.000032735323,0.00005854806,0.000010238709],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000439766,0.00070503395,0.00043206994,0.0006161016,0.00022201803,0.00036343603,0.0009506589,0.0006152317,0.0013117703],"category_scores_gemma":[0.00056124706,0.00026914407,0.000513872,0.0005532612,0.00032198953,0.0007136773,0.00044959286,0.0006466817,0.000576684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003325678,0.00018607291,0.002447909,0.00018088099,0.00014842965,0.00030367993,0.000054735443,0.26028544,0.10899221,0.008626915,0.005194554,0.6132466],"study_design_scores_gemma":[0.0000051400307,0.000051798426,0.0005829169,0.00000990116,0.000029366596,0.00011884991,0.0000060940088,0.973153,0.023554556,0.00066017144,0.0018151255,0.000013117819],"about_ca_topic_score_codex":0.005412411,"about_ca_topic_score_gemma":0.0055465205,"teacher_disagreement_score":0.005412411,"about_ca_system_score_codex":0.00070005003,"about_ca_system_score_gemma":0.00071831554,"threshold_uncertainty_score":0.010761797},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02858618042671615,"score_gpt":0.26755050555142607,"score_spread":0.23896432512470991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803263450","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060129084,0.000322676,0.935355,0.0002813526,0.00010359657,0.00006315927,0.00014461053,0.0007245436,0.0028759362],"genre_scores_gemma":[0.49562836,0.000991344,0.4966762,0.00023379983,0.00023033936,0.000092805734,0.0008653301,0.00012134189,0.0051604616],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996642,0.000040208517,0.000013071361,0.000050331688,0.00018154149,0.000050685492],"domain_scores_gemma":[0.9994936,0.00013386489,0.00007719466,0.000067730696,0.0001963336,0.000031247935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028938756,0.0006197317,0.00054598,0.0020688765,0.0003210721,0.0006004929,0.00052022113,0.0006228434,0.0012507102],"category_scores_gemma":[0.0014671233,0.00020264505,0.000459256,0.0011039743,0.00033208527,0.0010123979,0.0007497207,0.00069632754,0.0006877879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039006223,0.00020386766,0.0028167043,0.00016604099,0.000048718015,0.00031620287,0.00010327195,0.016795915,0.21268307,0.004718842,0.004214778,0.75754243],"study_design_scores_gemma":[0.000022983095,0.00016489415,0.005829532,0.00004277998,0.00007790817,0.0009112285,0.0001359729,0.8985668,0.08515683,0.0043560946,0.0046934434,0.000041468087],"about_ca_topic_score_codex":0.0009420212,"about_ca_topic_score_gemma":0.0014845805,"teacher_disagreement_score":0.0020688765,"about_ca_system_score_codex":0.00015085367,"about_ca_system_score_gemma":0.00048368398,"threshold_uncertainty_score":0.0041840672},"labels":[],"label_agreement":null},{"id":"W2806732649","doi":"","title":"Applications of perceptual sparse representation (Spikegram) for copyright protection of audio signals","year":2016,"lang":"en","type":"article","venue":"Knowledge UdeS (Institutional Deposit of the University of Sherbrooke)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Université de Sherbrooke","keywords":"Computer science; Representation (politics); Speech recognition; Perception; Psychology; Political science","score_opus":0.019115236420914356,"score_gpt":0.22004055708614684,"score_spread":0.20092532066523247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806732649","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018608825,0.00056081306,0.975437,0.00041206577,0.0001276592,0.000045865756,0.00028127953,0.0011147533,0.0034116784],"genre_scores_gemma":[0.42677656,0.001664294,0.55726254,0.000515661,0.00024647484,0.0001113257,0.0011984528,0.0003205445,0.011904086],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995042,0.000114749426,0.00002689482,0.00009747224,0.0002153506,0.000041383566],"domain_scores_gemma":[0.9989919,0.00043294043,0.0001020599,0.00024442887,0.0001900126,0.000038642815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000576927,0.0006593538,0.000416328,0.00093982427,0.0002834128,0.00080328214,0.00056977296,0.0008532185,0.0041293595],"category_scores_gemma":[0.0030747384,0.00019241436,0.0005019765,0.0009921971,0.00058093795,0.0011059153,0.0010610775,0.00095179083,0.0011619903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044443054,0.000108772154,0.0011013307,0.00028792038,0.00007340216,0.00033106236,0.00030454772,0.09274378,0.079771236,0.03248151,0.0080655925,0.7842864],"study_design_scores_gemma":[0.00004268799,0.0002984472,0.0022272177,0.000072928815,0.000052700965,0.000594015,0.00020817632,0.8783216,0.05623413,0.039010115,0.022880504,0.00005742555],"about_ca_topic_score_codex":0.0016502009,"about_ca_topic_score_gemma":0.002519306,"teacher_disagreement_score":0.0041293595,"about_ca_system_score_codex":0.0003775872,"about_ca_system_score_gemma":0.00058713683,"threshold_uncertainty_score":0.013814032},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.009953577584668239,"score_gpt":0.2505138867084685,"score_spread":0.24056030912380028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2888516611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012230884,0.0001787552,0.9865007,0.0001049975,0.000026593061,0.00004425421,0.00007073166,0.0003173421,0.0005257857],"genre_scores_gemma":[0.29608414,0.0008405051,0.6987728,0.0002139315,0.00022272613,0.00019572087,0.0008914298,0.0001991799,0.0025796243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989919,0.00023344083,0.000052706255,0.00022070708,0.00038352245,0.00011769675],"domain_scores_gemma":[0.997905,0.0007075037,0.00034204015,0.0002511986,0.0006748814,0.000119408054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011120415,0.0011801724,0.001307992,0.0015156969,0.00039478875,0.001035079,0.0010915712,0.0006363965,0.0011972944],"category_scores_gemma":[0.004548214,0.00039312994,0.0010411112,0.0014504443,0.0007148968,0.0010033523,0.0010063545,0.0015020102,0.0005747966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003852643,0.0002777012,0.003961707,0.00048947125,0.00022299196,0.000533626,0.0003482831,0.24342178,0.08023504,0.026461015,0.014832176,0.6288309],"study_design_scores_gemma":[0.000010517449,0.000055610562,0.00075308746,0.000010565934,0.000023033226,0.00016436295,0.000025713289,0.985213,0.009644867,0.0026461813,0.00143218,0.000020924523],"about_ca_topic_score_codex":0.0033103798,"about_ca_topic_score_gemma":0.005251994,"teacher_disagreement_score":0.0033103798,"about_ca_system_score_codex":0.00047371566,"about_ca_system_score_gemma":0.0015355283,"threshold_uncertainty_score":0.0065822005},"labels":[],"label_agreement":null},{"id":"W2901373932","doi":"10.20944/preprints201811.0310.v1","title":"Computational Topology Techniques Help to Solve a Long-Lasting Forensic Dilemma: Aldo Moro&amp;rsquo;s Death","year":2018,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Social connectedness; Terrorism; Topology (electrical circuits); Computer science; Planar; Law; Artificial intelligence; Mathematics; Computer graphics (images); Psychology; Political science; Social psychology; Combinatorics","score_opus":0.1098400715290658,"score_gpt":0.3482177465668509,"score_spread":0.2383776750377851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901373932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21498533,0.00079993135,0.7710939,0.0025738387,0.00018793638,0.00006865075,0.0001798316,0.0003798136,0.0097308615],"genre_scores_gemma":[0.75965583,0.00059892976,0.23560062,0.00015184835,0.00011777778,0.00004467208,0.00018045443,0.00014281711,0.003507056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992353,0.00028880534,0.000036291298,0.00017043758,0.00020685348,0.00006225712],"domain_scores_gemma":[0.9974618,0.0011684785,0.0004060124,0.0004452997,0.00031991332,0.00019853491],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016666037,0.0007185688,0.0005428856,0.0031753334,0.0013027833,0.0027203176,0.00084462384,0.0016483049,0.0029717588],"category_scores_gemma":[0.007349064,0.00036245183,0.0005116296,0.001168872,0.0026108762,0.003588303,0.0022889443,0.001146196,0.00061006186],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041279916,0.00009736024,0.022427425,0.00055381947,0.00017079587,0.0041320664,0.0044440553,0.11519504,0.03141107,0.50838745,0.008949078,0.30381912],"study_design_scores_gemma":[0.000036296307,0.00018633087,0.010092347,0.00019853706,0.000076193486,0.004934137,0.0040164688,0.44454914,0.024629286,0.4760557,0.035071585,0.00015401933],"about_ca_topic_score_codex":0.0006820064,"about_ca_topic_score_gemma":0.0008851738,"teacher_disagreement_score":0.0031753334,"about_ca_system_score_codex":0.0004983976,"about_ca_system_score_gemma":0.0005174268,"threshold_uncertainty_score":0.009941578},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014995731666543697,"score_gpt":0.28027117690029996,"score_spread":0.26527544523375624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2921092418","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016380996,0.0002886574,0.9800996,0.00012441976,0.00008229983,0.000079289915,0.00006742842,0.0011530869,0.0017242276],"genre_scores_gemma":[0.25125423,0.00053064903,0.73875433,0.0001991181,0.00013169616,0.00008770748,0.0003896692,0.0001812692,0.008471305],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99957556,0.000057838293,0.000020013176,0.00008074754,0.00018925747,0.00007666576],"domain_scores_gemma":[0.99944776,0.000096759904,0.000058600937,0.00011071774,0.00023154763,0.000054621665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008252682,0.0011551055,0.00081382366,0.002067117,0.0006100749,0.00084922585,0.0014767963,0.001323047,0.0026825035],"category_scores_gemma":[0.0010108338,0.00062145357,0.001077731,0.00089489185,0.0003922758,0.0012620161,0.0018011703,0.0011437769,0.0012157804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003375562,0.0002457004,0.0016715624,0.00013438344,0.00019244952,0.00033648225,0.00006276157,0.04450555,0.07822332,0.004779008,0.004166818,0.8653444],"study_design_scores_gemma":[0.000012639025,0.00006613836,0.0008433425,0.000013867255,0.000058729776,0.0004936776,0.000019185913,0.96098983,0.03353767,0.0018303703,0.0021103427,0.000024261179],"about_ca_topic_score_codex":0.0023476747,"about_ca_topic_score_gemma":0.0045651123,"teacher_disagreement_score":0.0026825035,"about_ca_system_score_codex":0.00040899354,"about_ca_system_score_gemma":0.0011107065,"threshold_uncertainty_score":0.0089738965},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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)","score_opus":0.018919167391559907,"score_gpt":0.2269450545083561,"score_spread":0.20802588711679618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922342173","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1703718,0.00094657467,0.81929266,0.00036067286,0.00017427756,0.00012115601,0.0002646326,0.0037316128,0.00473654],"genre_scores_gemma":[0.86189646,0.0004052219,0.13005339,0.00026316286,0.00005243548,0.00006803643,0.00051177485,0.00010737813,0.0066422704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997372,0.00003850347,0.000009787482,0.00009723349,0.00007092335,0.000046375622],"domain_scores_gemma":[0.9997669,0.00006533454,0.000033416334,0.00006914985,0.000051937892,0.000013305671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005688437,0.0010157005,0.00061721384,0.00051500177,0.00024706862,0.00043558635,0.0011445808,0.0007657821,0.0014522494],"category_scores_gemma":[0.00093663565,0.00039504626,0.0006055364,0.00032811068,0.00047121005,0.0007223502,0.001008564,0.0009611946,0.000474704],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005628595,0.00017907821,0.0023200954,0.00013011479,0.00017784888,0.0003284784,0.00008216118,0.55664676,0.041107453,0.003364504,0.00394119,0.39115942],"study_design_scores_gemma":[0.0000032639034,0.000025588797,0.00026288704,0.0000046327173,0.000009558497,0.000034798904,0.0000032320488,0.99410737,0.0048468695,0.00044911154,0.00024935737,0.0000034225056],"about_ca_topic_score_codex":0.0051737083,"about_ca_topic_score_gemma":0.007397148,"teacher_disagreement_score":0.0051737083,"about_ca_system_score_codex":0.0007725279,"about_ca_system_score_gemma":0.0005277374,"threshold_uncertainty_score":0.010287225},"labels":[],"label_agreement":null},{"id":"W2941649104","doi":"10.1109/tifs.2019.2956591","title":"A Robust Approach for Securing Audio Classification Against Adversarial Attacks","year":2019,"lang":"en","type":"preprint","venue":"IEEE Transactions on Information Forensics and Security","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Spectrogram; Artificial intelligence; Codebook; Audio signal; Speech recognition; Deep learning; Smoothing; Pattern recognition (psychology); Preprocessor; Support vector machine; Feature learning; Machine learning; Speech coding; Computer vision","score_opus":0.030064764888993376,"score_gpt":0.2290495888172815,"score_spread":0.19898482392828812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941649104","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009927457,0.00030348828,0.9870948,0.00011835075,0.00006537538,0.000034415927,0.000040959556,0.0013705797,0.0010445552],"genre_scores_gemma":[0.65736395,0.0006917604,0.3355744,0.00028638347,0.0002203873,0.00012108529,0.0002746557,0.00016297257,0.0053044627],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989042,0.00015240534,0.00006385837,0.00020141464,0.0005764774,0.000101647274],"domain_scores_gemma":[0.9989833,0.00027818928,0.00016174755,0.00032178234,0.00020661109,0.000048396938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007883538,0.000908542,0.00068926497,0.0009023392,0.0003279021,0.00084465975,0.0011974558,0.0010466689,0.0017565072],"category_scores_gemma":[0.0026573504,0.00035418555,0.00068380893,0.00043580105,0.000848017,0.0012928839,0.0015758909,0.0015540273,0.0011759778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037694068,0.00011578484,0.00073023373,0.00012791743,0.00010753028,0.0003001289,0.00008578778,0.3738408,0.15544261,0.019398656,0.0040518525,0.44542173],"study_design_scores_gemma":[0.000006504115,0.00010524012,0.0002699185,0.000010858706,0.00001516294,0.00013221172,0.0000116645215,0.9728705,0.02027841,0.0041953013,0.0020882068,0.000015921009],"about_ca_topic_score_codex":0.0008044806,"about_ca_topic_score_gemma":0.0008547136,"teacher_disagreement_score":0.0017565072,"about_ca_system_score_codex":0.0004972895,"about_ca_system_score_gemma":0.0005400713,"threshold_uncertainty_score":0.005876124},"labels":[],"label_agreement":null},{"id":"W2943381576","doi":"10.22214/ijraset.2019.4506","title":"Improving Video Classification Accuracy using Cloud","year":2019,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Cloud computing; Artificial intelligence; Operating system","score_opus":0.05961510992054689,"score_gpt":0.3669942075107602,"score_spread":0.3073790975902133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943381576","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36432785,0.016193882,0.50788665,0.0043287235,0.0048789484,0.0010842588,0.015315536,0.05167377,0.034310408],"genre_scores_gemma":[0.8381555,0.002805376,0.129075,0.00079696585,0.0009277579,0.00016892013,0.017209854,0.00066648074,0.010194243],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981207,0.00015308944,0.00010212233,0.0005349748,0.0007054328,0.00038362385],"domain_scores_gemma":[0.9975866,0.00043607474,0.00025402574,0.0006547683,0.0009057221,0.00016281586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012272783,0.001676276,0.0020840147,0.0032630544,0.0009700564,0.003045836,0.0025914884,0.0012722906,0.0078099305],"category_scores_gemma":[0.0065991366,0.0002895871,0.0009674638,0.0031152186,0.0003006026,0.0045728637,0.0017410129,0.0013054115,0.007037573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012220711,0.0007437003,0.019085886,0.00026547487,0.00014969864,0.00025398823,0.000049846916,0.026930539,0.0113039315,0.0028617254,0.07548819,0.8616449],"study_design_scores_gemma":[0.000060824786,0.00015849696,0.0053062877,0.00006615603,0.000056973855,0.0002531668,0.00013210296,0.967031,0.0133932,0.0031301691,0.010382763,0.000028861274],"about_ca_topic_score_codex":0.023781734,"about_ca_topic_score_gemma":0.017156957,"teacher_disagreement_score":0.023781734,"about_ca_system_score_codex":0.0019042197,"about_ca_system_score_gemma":0.0015217172,"threshold_uncertainty_score":0.04728663},"labels":[],"label_agreement":null},{"id":"W2952169655","doi":"10.1109/sibcon.2019.8729634","title":"Thermal Print Scanning Attacks in Theretail Environments","year":2019,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University of Edmonton","funders":"","keywords":"Computer science; Computer security; Punching; Key (lock); Chip; Embedded system; Engineering; Mechanical engineering; Telecommunications","score_opus":0.007723271077252589,"score_gpt":0.1994662325072997,"score_spread":0.1917429614300471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952169655","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7968535,0.0018784382,0.14389375,0.00074022094,0.0002236327,0.00018648966,0.00030074894,0.0018237345,0.05409959],"genre_scores_gemma":[0.9854718,0.00040302737,0.0073118918,0.00009974998,0.000025888194,0.000021278282,0.000079105455,0.000043253265,0.0065440666],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991905,0.00019037855,0.000023718505,0.00013108205,0.00029200467,0.00017243958],"domain_scores_gemma":[0.9990606,0.0003102177,0.00021089803,0.0002238836,0.00013845535,0.000055887536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030163839,0.00044823758,0.0003671056,0.0005044869,0.00082086946,0.0011911473,0.0005114719,0.0010760085,0.0037225788],"category_scores_gemma":[0.0013653154,0.00024284217,0.00031545767,0.00035730022,0.00079944346,0.0018428417,0.0012447063,0.00059648964,0.000955396],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002427349,0.0006412099,0.04750865,0.0011063708,0.0002442057,0.021271208,0.0037280116,0.14782827,0.402442,0.06214523,0.015191759,0.2954658],"study_design_scores_gemma":[0.000071589464,0.0017941245,0.057045143,0.00036996268,0.00020895197,0.024754276,0.0042908546,0.43759227,0.3750294,0.02942627,0.069123976,0.0002931358],"about_ca_topic_score_codex":0.000813422,"about_ca_topic_score_gemma":0.00077304814,"teacher_disagreement_score":0.0037225788,"about_ca_system_score_codex":0.00032710243,"about_ca_system_score_gemma":0.00024428288,"threshold_uncertainty_score":0.012453258},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.0110242690183514,"score_gpt":0.20542991331015983,"score_spread":0.19440564429180843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963433197","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001767575,0.000053890948,0.9974232,0.000049543276,0.000017033848,0.00001115741,0.000014186024,0.00018823642,0.00047528307],"genre_scores_gemma":[0.050165992,0.00023648067,0.9449117,0.00009570652,0.000057717672,0.00006919288,0.00008937442,0.00020535219,0.004168531],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994167,0.00012580605,0.00003016355,0.000097170065,0.00028233274,0.00004781061],"domain_scores_gemma":[0.9989091,0.00039808988,0.00015355411,0.00022010785,0.00026111543,0.00005797009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009266752,0.00092462293,0.00062785135,0.00083923194,0.00040302405,0.0009528125,0.0010914837,0.0016827008,0.002263929],"category_scores_gemma":[0.0033882228,0.00046764818,0.0007650353,0.00051865657,0.0012966217,0.00090441055,0.0014461178,0.0019495414,0.0015898152],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002864426,0.00013121786,0.0006504794,0.00053532165,0.00008733295,0.0003069749,0.00032135675,0.25812718,0.28656173,0.1524825,0.0052062226,0.2953032],"study_design_scores_gemma":[0.00001082214,0.00006352535,0.00020299382,0.00002230926,0.000010880268,0.00024318499,0.00001307,0.9354416,0.045300063,0.013565782,0.005078896,0.00004694293],"about_ca_topic_score_codex":0.0010621662,"about_ca_topic_score_gemma":0.0012163804,"teacher_disagreement_score":0.002263929,"about_ca_system_score_codex":0.00048136793,"about_ca_system_score_gemma":0.00073011575,"threshold_uncertainty_score":0.0075736046},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.016029824016923447,"score_gpt":0.2442405746136241,"score_spread":0.22821075059670065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963502975","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03762838,0.00042105367,0.959338,0.00016307374,0.0000405102,0.000028113845,0.000072297174,0.001233053,0.001075474],"genre_scores_gemma":[0.7939578,0.00045841103,0.1976976,0.00017162591,0.00007890046,0.000089757224,0.00027999104,0.00020989557,0.0070559243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997681,0.000037813967,0.0000137796815,0.000072027746,0.00006911176,0.000039184528],"domain_scores_gemma":[0.9995652,0.00015724254,0.00008859422,0.000086833934,0.000063565065,0.000038585684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005214809,0.000867742,0.0007321681,0.00033626126,0.0002501288,0.0006236212,0.0010618314,0.0007701981,0.0013211551],"category_scores_gemma":[0.0015748162,0.0004354931,0.0006709743,0.0003086751,0.00060038443,0.0009823986,0.0010857752,0.0011987814,0.00039867626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033136026,0.000104834166,0.0008206766,0.00011000555,0.0000822379,0.00026427943,0.00016879932,0.73566246,0.05940922,0.011748992,0.0027409694,0.18855616],"study_design_scores_gemma":[0.000004501156,0.000024794686,0.000070088885,0.0000028357724,0.0000063924563,0.000028216786,0.0000033631757,0.9937901,0.004188865,0.0016272465,0.00024982018,0.000003805261],"about_ca_topic_score_codex":0.004029082,"about_ca_topic_score_gemma":0.004714405,"teacher_disagreement_score":0.004029082,"about_ca_system_score_codex":0.0006323351,"about_ca_system_score_gemma":0.00053137087,"threshold_uncertainty_score":0.0080112815},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.007330237573003794,"score_gpt":0.1956074419454287,"score_spread":0.1882772043724249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972799026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21744667,0.00044677028,0.7789355,0.0003023103,0.000033333767,0.00006630374,0.00006949262,0.0008446877,0.0018549198],"genre_scores_gemma":[0.9239423,0.00015765273,0.07420354,0.000065804226,0.000011040809,0.000022022787,0.000094193885,0.000016167998,0.0014872551],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99960476,0.00009726883,0.000016569125,0.00011010394,0.000117561234,0.0000537601],"domain_scores_gemma":[0.9994393,0.00023867754,0.00011155749,0.0000968297,0.00008999504,0.00002371206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009805298,0.00066527614,0.0005397275,0.0006604925,0.00023395129,0.00054995366,0.00083315244,0.0008351507,0.00055302476],"category_scores_gemma":[0.0015853966,0.00030415712,0.00057755644,0.00029681952,0.00072235195,0.0008641597,0.0008736769,0.00087413733,0.0001907657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023388256,0.000109556044,0.003246918,0.00005042912,0.000091454785,0.00017893038,0.0000634812,0.84704566,0.020350555,0.0036296106,0.0005880202,0.124411516],"study_design_scores_gemma":[0.0000011340193,0.000020231404,0.0003972076,0.0000027863625,0.00000500027,0.00003320481,0.000003576341,0.9936724,0.005305982,0.00046257934,0.00009210672,0.0000038967332],"about_ca_topic_score_codex":0.0038064627,"about_ca_topic_score_gemma":0.0032448499,"teacher_disagreement_score":0.0038064627,"about_ca_system_score_codex":0.0009081327,"about_ca_system_score_gemma":0.00045840183,"threshold_uncertainty_score":0.0075686574},"labels":[],"label_agreement":null},{"id":"W2977667117","doi":"10.24018/ejece.2019.3.5.125","title":"Image Forgery Detection Based on Deep Transfer Learning","year":2019,"lang":"en","type":"article","venue":"European Journal of Electrical Engineering and Computer Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"Canadian Bureau for International Education","keywords":"Transfer of learning; Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Machine learning; Image (mathematics); Pattern recognition (psychology); Computation; Feature (linguistics); Computer vision; Algorithm","score_opus":0.0032486298823437365,"score_gpt":0.16015882627255534,"score_spread":0.15691019639021161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977667117","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19496931,0.00063348486,0.79826975,0.00030172124,0.00006794729,0.00009637642,0.000069444344,0.002549137,0.0030428509],"genre_scores_gemma":[0.937492,0.00019913969,0.0591364,0.000119259945,0.000023090664,0.000045927267,0.00012702298,0.000038080056,0.002818959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99965525,0.000054803644,0.000017388438,0.0000911202,0.000120819,0.000060651804],"domain_scores_gemma":[0.9993813,0.00019407016,0.00010315179,0.000102311,0.00018422866,0.00003498315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008271655,0.0007574066,0.00070499396,0.0010111073,0.00029999993,0.0005595925,0.0013305398,0.000842324,0.001094052],"category_scores_gemma":[0.0018727195,0.00029989384,0.0005898311,0.00044721738,0.00053507497,0.0013724667,0.0010098515,0.00095881923,0.00046600687],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034482757,0.00031702782,0.004527374,0.00007428529,0.00013715011,0.00023413963,0.00010470242,0.41112524,0.022148466,0.0026601118,0.0017154339,0.5566112],"study_design_scores_gemma":[0.0000020225896,0.000037936272,0.0003525757,0.0000031172613,0.000006382909,0.00003646939,0.0000055199976,0.9934477,0.0052631088,0.0007195697,0.00012051421,0.000005085861],"about_ca_topic_score_codex":0.0030122674,"about_ca_topic_score_gemma":0.0022607462,"teacher_disagreement_score":0.0030122674,"about_ca_system_score_codex":0.0008795848,"about_ca_system_score_gemma":0.0006397238,"threshold_uncertainty_score":0.0063818693},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.00806733060437596,"score_gpt":0.21480706987314713,"score_spread":0.20673973926877118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979300174","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16531797,0.002818998,0.8211647,0.00047447399,0.00019564196,0.00011280111,0.0003585205,0.0026983714,0.0068586073],"genre_scores_gemma":[0.844136,0.0010568472,0.14572437,0.00012424274,0.00004192647,0.00004766653,0.00049719727,0.00004775521,0.008323971],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999752,0.000035090135,0.000013436788,0.00005173385,0.00010723204,0.000040409956],"domain_scores_gemma":[0.9997346,0.000063019754,0.000036167326,0.000045836783,0.000108860026,0.000011604771],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054258615,0.00051956775,0.00033868145,0.00067768525,0.0002445994,0.00037632528,0.0006906343,0.00063781155,0.0016634436],"category_scores_gemma":[0.0010305635,0.0002272153,0.00033624202,0.00046623856,0.00023653396,0.0007090532,0.00040937893,0.0006114085,0.0005042982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042258363,0.00016654246,0.004492523,0.00016449923,0.00013888523,0.00020915298,0.000057276062,0.20162882,0.05866185,0.005378167,0.0047962605,0.72388345],"study_design_scores_gemma":[0.0000049533005,0.000048738548,0.0018083957,0.000013117213,0.000027918108,0.0000883737,0.000008694814,0.97044086,0.025059754,0.00091890915,0.001569431,0.000010959226],"about_ca_topic_score_codex":0.006668518,"about_ca_topic_score_gemma":0.0068098116,"teacher_disagreement_score":0.006668518,"about_ca_system_score_codex":0.0007129157,"about_ca_system_score_gemma":0.0006226339,"threshold_uncertainty_score":0.013259411},"labels":[],"label_agreement":null},{"id":"W2995555793","doi":"10.1016/j.aci.2019.12.001","title":"Inpainting forgery detection using hybrid generative/discriminative approach based on bounded generalized Gaussian mixture model","year":2019,"lang":"en","type":"article","venue":"Applied Computing and Informatics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Inpainting; Discriminative model; Computer science; Artificial intelligence; Generative grammar; Generative model; Probabilistic logic; Pattern recognition (psychology); Mixture model; Bounded function; Support vector machine; Gaussian; Image (mathematics); Statistical model; Machine learning; Computer vision; Mathematics","score_opus":0.013963648074361922,"score_gpt":0.2202785375486626,"score_spread":0.20631488947430068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995555793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021363148,0.00017421754,0.9776588,0.00006122986,0.000017200868,0.000014533204,0.000014220148,0.00041769023,0.0002788811],"genre_scores_gemma":[0.63003415,0.0004490478,0.3666192,0.00015487747,0.000053614287,0.000034833625,0.00013083212,0.00010468795,0.0024186918],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994593,0.000098846715,0.000022409613,0.00014522974,0.00020124884,0.00007292498],"domain_scores_gemma":[0.99958175,0.000110276575,0.00007320086,0.000100749436,0.0001074616,0.000026535423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074138824,0.00068976235,0.0009939593,0.0010156111,0.00023831439,0.00057761476,0.0012368313,0.00087874546,0.00055089826],"category_scores_gemma":[0.0010334157,0.00042856677,0.0011242406,0.00042647612,0.0005625077,0.0009684339,0.00073660753,0.0009390541,0.0003870143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000387729,0.00023222766,0.0062435223,0.00023972003,0.00023975581,0.00045113463,0.00036003315,0.23473267,0.15069368,0.013204413,0.0018875285,0.5913276],"study_design_scores_gemma":[0.0000055752166,0.000060693736,0.0011516296,0.0000065393456,0.000027269316,0.00032309408,0.000019773797,0.9750965,0.020735165,0.0019063386,0.00064841355,0.000018909199],"about_ca_topic_score_codex":0.0012755285,"about_ca_topic_score_gemma":0.001429175,"teacher_disagreement_score":0.0012755285,"about_ca_system_score_codex":0.0003102113,"about_ca_system_score_gemma":0.00036113514,"threshold_uncertainty_score":0.0039209127},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019908194783230033,"score_gpt":0.24864851190370413,"score_spread":0.2287403171204741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2999170936","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1114788,0.00074177,0.8779909,0.00021089599,0.00020027344,0.00011672659,0.00018302599,0.0033983842,0.005679156],"genre_scores_gemma":[0.48907226,0.00055631046,0.49876654,0.00022008306,0.000109928515,0.00008427041,0.00059948774,0.00024255231,0.010348462],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996076,0.000035939735,0.000022258824,0.00011713464,0.00016109101,0.000055994235],"domain_scores_gemma":[0.9996537,0.000066441324,0.000033440734,0.00006627179,0.00015743774,0.000022659178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047797867,0.000866097,0.0006667605,0.0010543248,0.00046455432,0.0006414729,0.00083378865,0.0009759161,0.0024386193],"category_scores_gemma":[0.00079749484,0.00036799625,0.00065817125,0.0007229807,0.00030480474,0.00077475136,0.0006118428,0.0005110355,0.0012279517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004491431,0.00013883975,0.003477385,0.00013266716,0.00010252525,0.00026754584,0.00008472975,0.012448892,0.21029656,0.0016555703,0.002462186,0.76848394],"study_design_scores_gemma":[0.000021310443,0.0002060194,0.006435706,0.000023895669,0.00014907957,0.00081523135,0.000045010984,0.8039488,0.18283594,0.0013620337,0.004117293,0.00003963797],"about_ca_topic_score_codex":0.0023548622,"about_ca_topic_score_gemma":0.0046453434,"teacher_disagreement_score":0.0024386193,"about_ca_system_score_codex":0.00032761367,"about_ca_system_score_gemma":0.0006882429,"threshold_uncertainty_score":0.0081579685},"labels":[],"label_agreement":null},{"id":"W3007532869","doi":"10.1080/17458927.2020.1715113","title":"Introducing audio-vision into evidence: the impact of audio recordings and their technical limitations in police use of force cases","year":2020,"lang":"en","type":"article","venue":"The Senses and Society","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Audio visual; Neglect; Officer; Sound recording and reproduction; Computer science; Psychology; Multimedia; Acoustics; Law; Political science","score_opus":0.06597555996222049,"score_gpt":0.29103629183891316,"score_spread":0.22506073187669268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007532869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47039464,0.030373499,0.25841066,0.07108098,0.0022130073,0.0005794257,0.000380406,0.0006101321,0.16595724],"genre_scores_gemma":[0.9568184,0.0052551785,0.030851852,0.003282038,0.00052445894,0.00014295324,0.000072983436,0.00015000012,0.002902098],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8656056,0.08362214,0.006750793,0.0048888847,0.03671629,0.0024162391],"domain_scores_gemma":[0.54621303,0.3858476,0.025709305,0.015983302,0.024675092,0.0015715952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07108031,0.0007624152,0.00054049515,0.0037531308,0.0039595217,0.014201502,0.0026124127,0.004312185,0.0036110189],"category_scores_gemma":[0.3360625,0.0010945508,0.0005625461,0.0016389646,0.016628314,0.015737811,0.01130694,0.00486419,0.00085987337],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014259994,0.00020576421,0.04137716,0.003987408,0.00022074215,0.005916819,0.16391025,0.0037614412,0.015540174,0.18230167,0.008580368,0.5727722],"study_design_scores_gemma":[0.00023275607,0.002925417,0.060205232,0.027321432,0.0008925554,0.03155118,0.2578969,0.012188376,0.06200796,0.25886792,0.28501195,0.0008984035],"about_ca_topic_score_codex":0.004146537,"about_ca_topic_score_gemma":0.0037103135,"teacher_disagreement_score":0.07108031,"about_ca_system_score_codex":0.0037006524,"about_ca_system_score_gemma":0.0035474303,"threshold_uncertainty_score":0.37591308},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07415349170297292,"score_gpt":0.2719266096692166,"score_spread":0.1977731179662437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013074498","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112528756,0.00065648986,0.8820733,0.00045791714,0.00012143053,0.00006519325,0.000101282094,0.0009915169,0.0030040608],"genre_scores_gemma":[0.9068366,0.00043810636,0.090555295,0.00020708123,0.0000570602,0.00004250942,0.000102791346,0.00005924953,0.0017011935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981224,0.0004890855,0.00008897841,0.00031092553,0.00081491127,0.00017365726],"domain_scores_gemma":[0.9951395,0.002412942,0.00064629,0.0013426408,0.0003760914,0.00008252457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012635045,0.00088020024,0.00070876273,0.00072775735,0.00047454747,0.0007787009,0.00069377234,0.0010479864,0.0010087413],"category_scores_gemma":[0.007738412,0.00030560145,0.00060058647,0.00066342193,0.0013457437,0.0019187771,0.0018977426,0.0014986857,0.00043079586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001643856,0.00024317147,0.010048523,0.00043345906,0.0003788526,0.0017153722,0.00073281815,0.42448142,0.18738072,0.08619801,0.0029377346,0.28380603],"study_design_scores_gemma":[0.000027130423,0.00021600067,0.001430938,0.00009056653,0.00007759195,0.0012626756,0.00009005185,0.8306369,0.14992692,0.012723896,0.003461853,0.00005545701],"about_ca_topic_score_codex":0.0004170314,"about_ca_topic_score_gemma":0.0003735582,"teacher_disagreement_score":0.0012635045,"about_ca_system_score_codex":0.00050866464,"about_ca_system_score_gemma":0.0005007283,"threshold_uncertainty_score":0.006682098},"labels":[],"label_agreement":null},{"id":"W3029709715","doi":"","title":"A first dataset for film age appropriateness investigation","year":2020,"lang":"en","type":"article","venue":"Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Artificial intelligence; Boosting (machine learning); Gradient boosting; Computer science; Deep learning; Machine learning; Natural language processing; Random forest","score_opus":0.02774214660252221,"score_gpt":0.1893584811438719,"score_spread":0.1616163345413497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029709715","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011277694,0.0005236034,0.0013676361,0.000481197,0.00028136416,0.00021916613,0.9730089,0.0016451216,0.01119538],"genre_scores_gemma":[0.009217082,0.00016754182,0.002859938,0.00012772313,0.0000780957,0.0002686795,0.98217195,0.00015405499,0.004955005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986847,0.00019011457,0.00012759063,0.00032917561,0.00044673114,0.00022168408],"domain_scores_gemma":[0.9956055,0.0007493403,0.0003728535,0.0011288342,0.001614769,0.00052865536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007226811,0.0011094771,0.0007244536,0.005581857,0.0010329176,0.0014184457,0.0012746274,0.0021704186,0.031174822],"category_scores_gemma":[0.0053155874,0.00028983987,0.0009044661,0.003340131,0.00035233382,0.001208426,0.0017876781,0.0014079363,0.0458251],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022797797,0.0002135133,0.008085816,0.00057798,0.00004981199,0.0002706265,0.0001888692,0.0005759983,0.0015757056,0.00082872744,0.9449133,0.042491604],"study_design_scores_gemma":[0.00009921651,0.00008266489,0.07293906,0.00038124234,0.000059852588,0.00083928,0.0010422571,0.0025636882,0.002680687,0.001441823,0.91779804,0.00007220248],"about_ca_topic_score_codex":0.016780533,"about_ca_topic_score_gemma":0.041073944,"teacher_disagreement_score":0.031174822,"about_ca_system_score_codex":0.00095460156,"about_ca_system_score_gemma":0.0014954887,"threshold_uncertainty_score":0.10429013},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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)","score_opus":0.01959542504845665,"score_gpt":0.23696067853727965,"score_spread":0.217365253488823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035170697","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016979167,0.00021488132,0.97936237,0.00015173896,0.00003474603,0.00007338534,0.00015074013,0.001554204,0.0014788315],"genre_scores_gemma":[0.5647575,0.00027850742,0.425013,0.0005569009,0.00010138892,0.00036564207,0.0017936293,0.00056043646,0.0065729665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987734,0.0003970715,0.000054131106,0.00043526257,0.00024544515,0.000094699935],"domain_scores_gemma":[0.9971023,0.001252445,0.000295817,0.00092301914,0.00030016527,0.00012620694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020298613,0.0018582764,0.0009269922,0.00088783796,0.0005186934,0.0011002189,0.002025211,0.001333833,0.0032439122],"category_scores_gemma":[0.0075735953,0.0006778137,0.0010736673,0.00073417707,0.0014882024,0.003115651,0.0027529895,0.0032816415,0.0012218207],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035807784,0.00028392416,0.0025185875,0.00019154776,0.00016311422,0.00016010506,0.00020355899,0.44754016,0.029024327,0.024971392,0.006202355,0.48838282],"study_design_scores_gemma":[0.000012125472,0.00005425425,0.00023033253,0.000009354982,0.000008369723,0.0000527552,0.000009303609,0.9780018,0.006300332,0.01425252,0.0010545045,0.0000143409725],"about_ca_topic_score_codex":0.0010705522,"about_ca_topic_score_gemma":0.0028430463,"teacher_disagreement_score":0.0032439122,"about_ca_system_score_codex":0.00069875893,"about_ca_system_score_gemma":0.00067424326,"threshold_uncertainty_score":0.010851979},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Test (biology); Artificial intelligence; Pattern recognition (psychology); Biology","score_opus":0.041123712908951796,"score_gpt":0.24662800161560894,"score_spread":0.20550428870665716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042891026","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36372536,0.001556534,0.6228203,0.0003325056,0.0003256418,0.00011438746,0.00049448316,0.0023524542,0.008278346],"genre_scores_gemma":[0.85209954,0.0005792778,0.14100659,0.000070007336,0.000096778596,0.000034378252,0.0006033557,0.00007437716,0.005435694],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986627,0.00018263307,0.00010669312,0.00023626543,0.0006535771,0.00015813958],"domain_scores_gemma":[0.998021,0.00053939945,0.000247936,0.00033826873,0.0007148014,0.00013865426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009189195,0.0009099464,0.0009955078,0.0026279083,0.000769124,0.0013942403,0.00060029863,0.0010736064,0.0029415092],"category_scores_gemma":[0.00396805,0.0002623566,0.00072661875,0.0012569993,0.00069460494,0.0017175776,0.0010604287,0.00068988005,0.0017302346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025032538,0.00037807034,0.016859718,0.00040692973,0.00026540214,0.00062182156,0.00031845854,0.0132169165,0.20991394,0.008343683,0.0031321724,0.74403965],"study_design_scores_gemma":[0.00008969992,0.00096166035,0.032737795,0.00009069783,0.00026697747,0.0045470805,0.0006066371,0.6346984,0.31092265,0.008399038,0.006462184,0.0002171406],"about_ca_topic_score_codex":0.000982489,"about_ca_topic_score_gemma":0.0012913868,"teacher_disagreement_score":0.0029415092,"about_ca_system_score_codex":0.00024917407,"about_ca_system_score_gemma":0.00090743206,"threshold_uncertainty_score":0.009840369},"labels":[],"label_agreement":null},{"id":"W3086773305","doi":"10.1007/978-3-030-66823-5_16","title":"L2-Constrained RemNet for Camera Model Identification and Image Manipulation Detection","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Preprocessor; Block (permutation group theory); Artificial intelligence; Convolutional neural network; Identification (biology); Categorical variable; Image (mathematics); Pattern recognition (psychology); Standard test image; Computer vision; Image processing; Machine learning; Mathematics","score_opus":0.024300206999211548,"score_gpt":0.26251434615863545,"score_spread":0.2382141391594239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3086773305","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018225893,0.00016384956,0.9962919,0.00007538873,0.000049255617,0.000031469586,0.0001834001,0.000603649,0.00077861757],"genre_scores_gemma":[0.17701589,0.000643981,0.7993037,0.00045910318,0.0002491677,0.0005022607,0.0034917374,0.0011453651,0.017188841],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986255,0.00035652734,0.000069182846,0.00033690172,0.00044263448,0.00016932181],"domain_scores_gemma":[0.9982596,0.0008285022,0.00012359384,0.0002853344,0.0004220514,0.000080852464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016631577,0.002081466,0.0027334394,0.0015159466,0.0007911993,0.0019753727,0.0030178907,0.0030065277,0.0112075005],"category_scores_gemma":[0.005594056,0.0010856843,0.0014718061,0.0019754386,0.0009113954,0.0019930785,0.0036219677,0.0025313774,0.004989643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014001229,0.0002381571,0.00089779444,0.00048061708,0.00023001603,0.00036427728,0.00008310379,0.40746137,0.013988846,0.024449911,0.015788201,0.53461754],"study_design_scores_gemma":[0.000009570396,0.000034149387,0.00012426711,0.000013349772,0.000007640467,0.000044663055,0.000008593882,0.99153805,0.0016635599,0.0053591477,0.0011855187,0.000011548869],"about_ca_topic_score_codex":0.0077379723,"about_ca_topic_score_gemma":0.007931895,"teacher_disagreement_score":0.0112075005,"about_ca_system_score_codex":0.0008237506,"about_ca_system_score_gemma":0.00216789,"threshold_uncertainty_score":0.03749281},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.018992367766600366,"score_gpt":0.2721492946560581,"score_spread":0.25315692688945773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091508658","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34777048,0.0012606041,0.6331863,0.0009740981,0.00039560307,0.00015716843,0.00037824168,0.003040942,0.012836587],"genre_scores_gemma":[0.9657615,0.00039197426,0.029749956,0.00020033302,0.0000651754,0.000038837254,0.00039391973,0.000089036985,0.0033093623],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874,0.0003002657,0.00006199152,0.00027028928,0.00045617166,0.00017132315],"domain_scores_gemma":[0.99785954,0.0009356279,0.00023877664,0.00065557746,0.00021964769,0.000090888454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013127077,0.0010922113,0.0005634975,0.0007108516,0.0002706169,0.00079207966,0.0005470364,0.00091880746,0.0021039876],"category_scores_gemma":[0.007307878,0.00023426779,0.00051993167,0.0003849038,0.0009477753,0.0014507896,0.0020244294,0.0014158849,0.0009513184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078510074,0.00025660227,0.005039077,0.00020461426,0.00018248969,0.0010418217,0.00020724772,0.52328354,0.08452483,0.010434861,0.00424826,0.36979154],"study_design_scores_gemma":[0.000011702482,0.00027360357,0.0036654826,0.000033838558,0.000034074634,0.00079931883,0.0000603088,0.94342405,0.04389728,0.0053278445,0.0024406207,0.00003186554],"about_ca_topic_score_codex":0.000942859,"about_ca_topic_score_gemma":0.00064020255,"teacher_disagreement_score":0.0021039876,"about_ca_system_score_codex":0.00048575646,"about_ca_system_score_gemma":0.000344656,"threshold_uncertainty_score":0.0070385337},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.015543654172116022,"score_gpt":0.23149406308390408,"score_spread":0.21595040891178804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094138310","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0068330267,0.1466843,0.8374991,0.0012334769,0.0004419254,0.00011611453,0.000160733,0.00055595784,0.0064753448],"genre_scores_gemma":[0.18744433,0.23079368,0.56547576,0.0011261184,0.003043437,0.0002637566,0.00093552214,0.00027155128,0.0106458925],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978168,0.00057698466,0.00021687913,0.00037311472,0.0009222423,0.00009403776],"domain_scores_gemma":[0.996128,0.0022110855,0.00022027594,0.0005713204,0.00079351495,0.000075840115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003304597,0.0012924039,0.0019614338,0.0033496195,0.00076343416,0.0023760758,0.0021149002,0.002085497,0.001976564],"category_scores_gemma":[0.005913109,0.0007769009,0.0013593386,0.004615038,0.0010624592,0.0034544787,0.001528494,0.002539422,0.0017424345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000093165734,0.00020421705,0.0014195413,0.0010081244,0.00015930124,0.000064469794,0.0000651303,0.04150212,0.0025348016,0.021635577,0.005535148,0.9257783],"study_design_scores_gemma":[0.000029494528,0.00036122132,0.003053439,0.0009591164,0.00016102137,0.001123065,0.00013445783,0.82476056,0.013077125,0.07398204,0.08224771,0.00011076856],"about_ca_topic_score_codex":0.0011832876,"about_ca_topic_score_gemma":0.00097340555,"teacher_disagreement_score":0.0033496195,"about_ca_system_score_codex":0.000666051,"about_ca_system_score_gemma":0.0008341808,"threshold_uncertainty_score":0.017476618},"labels":[],"label_agreement":null},{"id":"W3094464978","doi":"10.1109/icassp39728.2021.9413626","title":"Class-Conditional Defense GAN Against End-To-End Speech Attacks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Sentence; SIGNAL (programming language); Generative adversarial network; Speech recognition; Spectrogram; Discriminator; Adversarial system; Generative grammar; Algorithm; Artificial intelligence; Deep learning; Telecommunications","score_opus":0.01913107164434199,"score_gpt":0.2530109474255905,"score_spread":0.2338798757812485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094464978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02358301,0.00021065648,0.970951,0.00023250398,0.00008284336,0.00005040797,0.00008837051,0.0018595761,0.002941696],"genre_scores_gemma":[0.83839524,0.0001792283,0.15210795,0.0005402356,0.0000727652,0.00012583353,0.00041408843,0.0002447017,0.007920052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991653,0.00027260833,0.000025434876,0.00017548239,0.00026221838,0.00009899185],"domain_scores_gemma":[0.99885523,0.0005322448,0.000102611164,0.00031548794,0.00013854087,0.000055951234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011909776,0.0010795364,0.000617028,0.00032511677,0.0002620279,0.0005491148,0.00097407255,0.0012494165,0.0022878752],"category_scores_gemma":[0.0028767802,0.00023227565,0.00046021707,0.00015628368,0.0008059082,0.0009890076,0.0015341092,0.002190562,0.0013331618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006046801,0.00018436302,0.0017988498,0.00014490027,0.00013636965,0.00048237765,0.00018942832,0.5601107,0.10041613,0.048315942,0.008642129,0.27897415],"study_design_scores_gemma":[0.000007349331,0.00006754665,0.00021849624,0.000009021643,0.000009037952,0.00018530806,0.000013131371,0.9732817,0.018518241,0.005986152,0.0016941145,0.0000099256995],"about_ca_topic_score_codex":0.00032633185,"about_ca_topic_score_gemma":0.00049896206,"teacher_disagreement_score":0.0022878752,"about_ca_system_score_codex":0.00037328727,"about_ca_system_score_gemma":0.00038124758,"threshold_uncertainty_score":0.0076536536},"labels":[],"label_agreement":null},{"id":"W3119660979","doi":"10.18280/ts.370601","title":"Boosting up Source Scanner Identification Using Wavelets and Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l'Education Nationale, de l'Enseignement Superieur et de la Recherche","keywords":"Scanner; Computer science; Artificial intelligence; Convolutional neural network; Boosting (machine learning); Pattern recognition (psychology); Block (permutation group theory); Wavelet; Diagonal; Identification (biology); Computer vision; Artificial neural network; Mathematics","score_opus":0.027628411356862406,"score_gpt":0.2185169160580843,"score_spread":0.19088850470122187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119660979","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.067307904,0.0005993296,0.9288714,0.00015629019,0.00007811488,0.000033172208,0.000061788654,0.0009578913,0.0019341244],"genre_scores_gemma":[0.7570008,0.000677223,0.2372735,0.00015791896,0.000086153916,0.00004504915,0.00036147627,0.00012218251,0.004275684],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997204,0.000044850498,0.000012746371,0.0000627003,0.0001046226,0.000054618642],"domain_scores_gemma":[0.9994254,0.00022458541,0.00007478385,0.0000944358,0.00015259921,0.000028154403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007430373,0.00088990154,0.0006054069,0.00086767384,0.0001833629,0.0005156767,0.00074443675,0.0006899409,0.0009838763],"category_scores_gemma":[0.0020041228,0.00035234774,0.0006047889,0.00063498056,0.00033886216,0.0011759704,0.00094817043,0.000936071,0.00086256384],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029751824,0.000172653,0.00460536,0.00013376407,0.00013831246,0.0002527839,0.00008705049,0.2698178,0.054817073,0.0061345175,0.0023643074,0.6611789],"study_design_scores_gemma":[0.0000029856947,0.00004195764,0.0005383212,0.000007651358,0.000017932613,0.000061414255,0.000009739848,0.98877466,0.008417894,0.0014280345,0.0006932141,0.0000062842028],"about_ca_topic_score_codex":0.0015371632,"about_ca_topic_score_gemma":0.0018120205,"teacher_disagreement_score":0.0015371632,"about_ca_system_score_codex":0.0003352667,"about_ca_system_score_gemma":0.00036940118,"threshold_uncertainty_score":0.0039295554},"labels":[],"label_agreement":null},{"id":"W3131771048","doi":"10.1007/s10502-021-09358-z","title":"Decoding the Cauzin Softstrip: a case study in extracting information from old media","year":2021,"lang":"en","type":"article","venue":"Archival Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Digital curation; Scope (computer science); Decoding methods; Set (abstract data type); Encoding (memory); World Wide Web; Multimedia; Artificial intelligence; Telecommunications","score_opus":0.022379079347648725,"score_gpt":0.26286692407298207,"score_spread":0.24048784472533336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131771048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9284873,0.0020110442,0.04492568,0.0019217732,0.00032715334,0.00028436887,0.003485365,0.0012846777,0.017272651],"genre_scores_gemma":[0.81935537,0.0014428204,0.14109936,0.0012401893,0.00019687653,0.0003327955,0.009134207,0.0013933541,0.025805004],"study_design_codex":"design_other","study_design_gemma":"case_report","domain_scores_codex":[0.9980901,0.00076296483,0.00016530055,0.00037975874,0.0004835143,0.00011837417],"domain_scores_gemma":[0.98773396,0.009455898,0.0003758263,0.0011264192,0.0011097312,0.00019817652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015741085,0.0010009888,0.00049924635,0.0022644761,0.0013924489,0.001991809,0.0010303677,0.002803824,0.0024782938],"category_scores_gemma":[0.015183002,0.0003170599,0.00034270095,0.0024806703,0.0024073848,0.0034920902,0.0021877727,0.0015249692,0.0017890409],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013125723,0.0010973345,0.03169067,0.003610881,0.00018784517,0.052183796,0.09497128,0.012290575,0.07690928,0.015789649,0.06392778,0.64602834],"study_design_scores_gemma":[0.00020903489,0.0011547373,0.05399626,0.0012990918,0.00030738552,0.04683301,0.07739167,0.098840915,0.28142676,0.021472735,0.4165607,0.0005077896],"about_ca_topic_score_codex":0.0072791846,"about_ca_topic_score_gemma":0.013683177,"teacher_disagreement_score":0.0072791846,"about_ca_system_score_codex":0.0006792289,"about_ca_system_score_gemma":0.00048130937,"threshold_uncertainty_score":0.014473617},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.043597500571628964,"score_gpt":0.22726224174785115,"score_spread":0.18366474117622217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136555065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3979897,0.0009570733,0.5773048,0.00082596124,0.00020107067,0.00010466206,0.00017022109,0.00069923484,0.02174733],"genre_scores_gemma":[0.96587956,0.00036194734,0.030395921,0.00012236601,0.000048693797,0.000014692738,0.0000707822,0.00005212049,0.003053765],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972934,0.00006457809,0.0000041510198,0.00004967213,0.00010237025,0.000049821858],"domain_scores_gemma":[0.99955887,0.00020531178,0.000044210756,0.00007595124,0.00008708226,0.000028486114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004097635,0.0005304044,0.00030982643,0.00020966887,0.00016181482,0.00073838595,0.0005230248,0.00046938146,0.002311866],"category_scores_gemma":[0.0014336878,0.00014786328,0.0003248193,0.00013806939,0.0004872787,0.0009654624,0.00059018814,0.00057708786,0.00042128866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013681875,0.00060125947,0.0046008043,0.0005477146,0.00015400632,0.00086847984,0.00046327317,0.21871115,0.3576588,0.04389372,0.003973039,0.36715955],"study_design_scores_gemma":[0.000010232311,0.0002252945,0.002378045,0.000017662574,0.000028757062,0.00038527563,0.00010323541,0.9484852,0.03601962,0.010879154,0.0014493397,0.000018190653],"about_ca_topic_score_codex":0.0007982255,"about_ca_topic_score_gemma":0.00083389075,"teacher_disagreement_score":0.002311866,"about_ca_system_score_codex":0.00021892441,"about_ca_system_score_gemma":0.0003696321,"threshold_uncertainty_score":0.007733941},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01070534111153067,"score_gpt":0.2331004745540335,"score_spread":0.2223951334425028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174762625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016419811,0.00029271183,0.9815809,0.000067401576,0.000032770462,0.000044838747,0.000049760503,0.00028461605,0.0012272551],"genre_scores_gemma":[0.2802525,0.001211148,0.7109639,0.00012161284,0.00009505838,0.000086350796,0.0003479778,0.000070335656,0.0068510734],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939215,0.000101251666,0.000025510133,0.00013418567,0.00028470976,0.00006213644],"domain_scores_gemma":[0.9994407,0.00013373341,0.00008703901,0.00013398682,0.0001712412,0.000033224587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065133185,0.0012100397,0.0007696999,0.0012300648,0.00030186653,0.0010203025,0.0011390505,0.001128631,0.0012820886],"category_scores_gemma":[0.0015914759,0.0003959085,0.0006046875,0.0007918209,0.00067034503,0.0019662702,0.001930655,0.0009189169,0.0010878728],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064053765,0.00019806251,0.0022811505,0.0003440365,0.00012525705,0.0003049499,0.00023068636,0.0787245,0.2899816,0.03172404,0.002483009,0.59296215],"study_design_scores_gemma":[0.000011444294,0.00012638423,0.00095762656,0.000029681778,0.000037275116,0.00043429688,0.000054741828,0.90222543,0.083906725,0.009038939,0.003149936,0.00002754052],"about_ca_topic_score_codex":0.0010873155,"about_ca_topic_score_gemma":0.0014543531,"teacher_disagreement_score":0.0012820886,"about_ca_system_score_codex":0.00039587432,"about_ca_system_score_gemma":0.00054638245,"threshold_uncertainty_score":0.004289031},"labels":[],"label_agreement":null},{"id":"W3182090508","doi":"10.36001/phme.2021.v6i1.2867","title":"Generative Adversarial Networks used for latent space Optimization: a comparative study for the Classification of Partial Discharge Sources","year":2021,"lang":"en","type":"article","venue":"PHM Society European Conference","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Adversarial system; Generative grammar; Artificial intelligence; Space (punctuation); Generative adversarial network; Computer science; Machine learning; Deep learning","score_opus":0.079507124730251,"score_gpt":0.28243841075611986,"score_spread":0.20293128602586885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182090508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28164428,0.027691152,0.66994673,0.0043857116,0.0009814294,0.00035140492,0.001036864,0.0022271841,0.011735188],"genre_scores_gemma":[0.92949617,0.0036665136,0.05878775,0.0007659623,0.00038366124,0.00014212645,0.0019047372,0.0001779845,0.004675001],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973484,0.0015999645,0.00012401573,0.0003673922,0.00034326807,0.00021690552],"domain_scores_gemma":[0.98486996,0.013095299,0.00040439467,0.00047375655,0.0008691259,0.00028749974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073662894,0.0020473336,0.0020551416,0.0016292344,0.00053043215,0.0017469283,0.0016240065,0.001962317,0.0020482321],"category_scores_gemma":[0.010886409,0.0004124327,0.0017332154,0.0009474457,0.0010736699,0.0018875737,0.0014818939,0.003047054,0.0006528349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057673943,0.00029380232,0.0036976025,0.00022692636,0.00035525006,0.00010953806,0.000098875906,0.90708816,0.0005670952,0.004153488,0.0025202837,0.08031224],"study_design_scores_gemma":[0.00000876809,0.00004548086,0.00030659456,0.000015810401,0.000018925875,0.000012580041,0.000016957169,0.99803036,0.0001490869,0.001194742,0.00019395832,0.000006640276],"about_ca_topic_score_codex":0.009907246,"about_ca_topic_score_gemma":0.0049394546,"teacher_disagreement_score":0.009907246,"about_ca_system_score_codex":0.0013071235,"about_ca_system_score_gemma":0.0011531705,"threshold_uncertainty_score":0.03895712},"labels":[],"label_agreement":null},{"id":"W3182975606","doi":"10.5539/cis.v14n3p25","title":"Verifying the Audio Evidence to Assist Forensic Investigation","year":2021,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Authentication (law); Presentation (obstetrics); Computer forensics; Computer security; Field (mathematics); Multimedia; Digital forensics","score_opus":0.026654711005369088,"score_gpt":0.24555795906144384,"score_spread":0.21890324805607475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182975606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09843936,0.010586655,0.83073115,0.0029028326,0.0020617684,0.00087063096,0.0013960177,0.00459091,0.048420556],"genre_scores_gemma":[0.34225804,0.01067425,0.6253959,0.00088693213,0.0008278155,0.0001903665,0.0013952896,0.0005524472,0.017818969],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9977337,0.0004025186,0.00019093002,0.0002788984,0.0012316782,0.00016223257],"domain_scores_gemma":[0.993364,0.0023694532,0.0006773871,0.0013469242,0.0020538475,0.00018843901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023237306,0.0010018384,0.00080157927,0.0052724783,0.0010681796,0.002973029,0.0010525992,0.0022395763,0.010473854],"category_scores_gemma":[0.010953511,0.0003623342,0.000507042,0.0015927576,0.0010446308,0.0033039765,0.0021672547,0.0013406498,0.008381123],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008418934,0.0001910637,0.0043811705,0.0018098183,0.00006871762,0.0037160993,0.0009819835,0.003590299,0.333606,0.024463939,0.009020654,0.6173282],"study_design_scores_gemma":[0.00014695092,0.0011778467,0.010219159,0.0030211825,0.00038118457,0.015714481,0.0028348134,0.045902856,0.6107481,0.038077448,0.27146325,0.00031264705],"about_ca_topic_score_codex":0.00046094824,"about_ca_topic_score_gemma":0.00069581607,"teacher_disagreement_score":0.010473854,"about_ca_system_score_codex":0.00033569176,"about_ca_system_score_gemma":0.0013094704,"threshold_uncertainty_score":0.03503853},"labels":[],"label_agreement":null},{"id":"W3202461676","doi":"10.1007/s42979-021-00893-1","title":"Localization and Detection of Copy-Move Forgeries in Post-processed Images Using U-Net","year":2021,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Net (polyhedron); Artificial intelligence; Computer science; Pattern recognition (psychology); Computer vision; Mathematics","score_opus":0.008247694935197163,"score_gpt":0.22588689941884285,"score_spread":0.21763920448364568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202461676","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77040946,0.0010952831,0.22099563,0.00014886356,0.000112014175,0.00007594387,0.0003616091,0.002963001,0.0038382239],"genre_scores_gemma":[0.8701845,0.00026232848,0.1254846,0.000045717334,0.000023447781,0.000022972341,0.00030707105,0.000059604696,0.003609718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99978405,0.000023245393,0.0000120989025,0.000051169944,0.000086575834,0.00004291745],"domain_scores_gemma":[0.9996195,0.00009723298,0.00006612375,0.000053618143,0.00013293557,0.000030492858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036285858,0.000482002,0.00033904813,0.0017054911,0.00034840227,0.0005164736,0.00043927497,0.0008026081,0.0016976699],"category_scores_gemma":[0.00073481794,0.00018672843,0.00023072131,0.0006331055,0.00027214008,0.00063461816,0.00047282758,0.00022384153,0.0008445885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028071671,0.00027709536,0.0174365,0.00030265524,0.00009181635,0.0011628584,0.0002650245,0.008463554,0.42364848,0.0012802256,0.0017399183,0.5425247],"study_design_scores_gemma":[0.00004865371,0.0006695806,0.05757129,0.000066453365,0.0001239273,0.0025202297,0.00032768765,0.45426553,0.47981068,0.0007555823,0.003778247,0.00006203173],"about_ca_topic_score_codex":0.0014027689,"about_ca_topic_score_gemma":0.0026683956,"teacher_disagreement_score":0.0017054911,"about_ca_system_score_codex":0.0002076424,"about_ca_system_score_gemma":0.0002854186,"threshold_uncertainty_score":0.0056792498},"labels":[],"label_agreement":null},{"id":"W3202592801","doi":"10.18280/isi.260401","title":"Streamed Video Reconstruction for Firefox Browser Forensics","year":2021,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; World Wide Web; Suspect; Cache; The Internet; Popularity; Web browser; Digital forensics; Focus (optics); Multimedia; Computer security","score_opus":0.012442461366555031,"score_gpt":0.21445252466918083,"score_spread":0.2020100633026258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202592801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24676436,0.002222125,0.73115516,0.0008345399,0.00029224425,0.0004663899,0.0008243544,0.0032441097,0.014196764],"genre_scores_gemma":[0.5647372,0.0019815415,0.42677623,0.00013452415,0.0000958293,0.00010551976,0.00088601554,0.00029813,0.0049850373],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99944,0.00012701284,0.000026434274,0.00007970767,0.0002601193,0.000066686596],"domain_scores_gemma":[0.9986181,0.00036255695,0.00016780515,0.00034742223,0.00043550835,0.00006857963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010175878,0.0005554434,0.0002880278,0.0024524704,0.00047215764,0.0011116449,0.00057206326,0.00091147877,0.0028819386],"category_scores_gemma":[0.0048691384,0.00021999721,0.00033286374,0.0009036082,0.0005392796,0.0015750051,0.0009421509,0.0006931343,0.0013954506],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008822461,0.00022326084,0.011867374,0.000517811,0.00007000068,0.002095425,0.0012885518,0.015156257,0.15246765,0.018955834,0.0067291595,0.78974646],"study_design_scores_gemma":[0.000089591784,0.00070909207,0.016088594,0.0006378887,0.00013427711,0.010016858,0.0029275154,0.47950554,0.40673417,0.025514223,0.057473734,0.00016856263],"about_ca_topic_score_codex":0.0013667113,"about_ca_topic_score_gemma":0.0020163984,"teacher_disagreement_score":0.0028819386,"about_ca_system_score_codex":0.00036772015,"about_ca_system_score_gemma":0.0008345808,"threshold_uncertainty_score":0.009641051},"labels":[],"label_agreement":null},{"id":"W3210281694","doi":"10.1007/978-3-030-89880-9_7","title":"Enhancing Micro-location Accuracy for Asset Tracking: An Evaluation of Two Fingerprinting Approaches Using Three Machine Learning Algorithms","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sheridan College","funders":"","keywords":"Beacon; Computer science; Algorithm; Granularity; Global Positioning System; Real-time computing; Artificial intelligence; Bottleneck; Machine learning; Embedded system; Telecommunications","score_opus":0.09236233541728936,"score_gpt":0.2953787503540439,"score_spread":0.2030164149367545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210281694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5340155,0.0036774287,0.4544744,0.00021959096,0.00025889443,0.0001994759,0.00025690187,0.0024925706,0.0044053136],"genre_scores_gemma":[0.8269816,0.00097266195,0.16937162,0.00007008554,0.000060213486,0.00004810335,0.00029292237,0.000097755335,0.00210496],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9981054,0.00040496074,0.00012475994,0.00043102686,0.0007382564,0.00019548624],"domain_scores_gemma":[0.99288976,0.004484945,0.00046995858,0.00065505906,0.001348062,0.00015223195],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003170937,0.0012621231,0.001089773,0.0014876102,0.0003909721,0.0014194997,0.0015100123,0.0018679642,0.0012920789],"category_scores_gemma":[0.0075483383,0.00031915915,0.0005469895,0.0014777678,0.0004912424,0.0022761317,0.0009646221,0.0006463536,0.0005896889],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036682202,0.0008997838,0.013940837,0.00044391176,0.00039237033,0.000105777,0.00011473447,0.06910274,0.032428112,0.00083995145,0.00091542664,0.87714815],"study_design_scores_gemma":[0.0001651229,0.0032955352,0.022037374,0.000059601087,0.0006465483,0.0006293374,0.00018216706,0.8774331,0.0930382,0.0009025852,0.0015174618,0.000093032606],"about_ca_topic_score_codex":0.0024396053,"about_ca_topic_score_gemma":0.0020643577,"teacher_disagreement_score":0.003170937,"about_ca_system_score_codex":0.00049146905,"about_ca_system_score_gemma":0.00053932384,"threshold_uncertainty_score":0.016769707},"labels":[],"label_agreement":null},{"id":"W4206514958","doi":"10.31235/osf.io/fzyp4","title":"Image Copy Detection and Evolution Visualisation Using Tree Graphs","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Image (mathematics); Visualization; Search engine indexing; Tree (set theory); Artificial intelligence; Graph; Theoretical computer science; Computer vision; Mathematics; Combinatorics","score_opus":0.01967224106752754,"score_gpt":0.260648808453507,"score_spread":0.24097656738597947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206514958","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036633246,0.00047473045,0.9521315,0.00035646083,0.00006733219,0.00011629013,0.0007639279,0.0065204767,0.0029361753],"genre_scores_gemma":[0.33284515,0.00087707274,0.6598926,0.00012325805,0.000053430194,0.00010379903,0.0015934409,0.0013548492,0.0031562757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993998,0.00013510248,0.000038938248,0.00012481873,0.0002291686,0.00007211928],"domain_scores_gemma":[0.9977063,0.0010867425,0.00030979837,0.0003325335,0.00042466732,0.0001398783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007368069,0.00083317,0.00048070785,0.0069991504,0.00052174943,0.0025378247,0.0010469421,0.0013100941,0.0040106704],"category_scores_gemma":[0.0047689695,0.00051543786,0.00090420205,0.002803344,0.0006257115,0.0024817123,0.0015106775,0.0012475057,0.0010312172],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063006004,0.0001678087,0.010058748,0.0007843176,0.00020024211,0.001425467,0.0020862683,0.1374784,0.0967955,0.05878875,0.013654618,0.67792976],"study_design_scores_gemma":[0.000026898388,0.00008055588,0.00443445,0.00011083609,0.000052111765,0.00087425526,0.00045194602,0.88869774,0.032429263,0.054583084,0.018174188,0.0000846789],"about_ca_topic_score_codex":0.005260872,"about_ca_topic_score_gemma":0.0050857784,"teacher_disagreement_score":0.0069991504,"about_ca_system_score_codex":0.00082009536,"about_ca_system_score_gemma":0.00074860814,"threshold_uncertainty_score":0.013417065},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Unicode; Computer science; Spoofing attack; Artificial intelligence; Programming language; Computer security","score_opus":0.026597054720817758,"score_gpt":0.2590963164364769,"score_spread":0.23249926171565916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W42110184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38014108,0.0029577455,0.5921218,0.00050307304,0.00030184138,0.00026655197,0.0006178761,0.0031582275,0.019931892],"genre_scores_gemma":[0.5775619,0.0017734688,0.4087715,0.00020783937,0.00011905286,0.00006825828,0.0008338683,0.00035052252,0.010313655],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9996088,0.000037894508,0.000017618382,0.00009434905,0.00017690535,0.00006442606],"domain_scores_gemma":[0.9992347,0.0002429774,0.00010514166,0.00020613695,0.00014546154,0.00006562358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026010038,0.0008657257,0.00082525756,0.0018907514,0.00057092163,0.0013454522,0.0006633286,0.00123049,0.0037678867],"category_scores_gemma":[0.0016997805,0.00041735836,0.00039429156,0.0009855514,0.0006368758,0.0022105817,0.001376149,0.00109716,0.0024017629],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005994673,0.00015749795,0.006707293,0.0003648362,0.00007406835,0.0010359308,0.00056535634,0.004088386,0.315713,0.011423754,0.0035839926,0.65568644],"study_design_scores_gemma":[0.00007688077,0.0011218847,0.01624859,0.00027540114,0.00025363048,0.010462233,0.001579454,0.2698142,0.61688554,0.04291631,0.040216796,0.00014909441],"about_ca_topic_score_codex":0.00045751888,"about_ca_topic_score_gemma":0.0007341526,"teacher_disagreement_score":0.0037678867,"about_ca_system_score_codex":0.0002134992,"about_ca_system_score_gemma":0.00034752119,"threshold_uncertainty_score":0.012604833},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence","score_opus":0.0627383028276587,"score_gpt":0.318791137053182,"score_spread":0.25605283422552333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220709567","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30296603,0.0073145228,0.6746142,0.0021748946,0.00030967768,0.00009888901,0.0012465023,0.0012141855,0.010061144],"genre_scores_gemma":[0.9246203,0.0014097409,0.06619,0.00018515598,0.000070961934,0.0000697794,0.001277965,0.000085765256,0.006090385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9995153,0.000094384326,0.000030653446,0.00008190014,0.00020739646,0.00007040506],"domain_scores_gemma":[0.9982717,0.0008923768,0.00013190083,0.000111495516,0.00054873084,0.000043873853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016487978,0.00061195914,0.0003614241,0.0011802618,0.00028309386,0.00064855616,0.0005569458,0.00056435,0.0018358635],"category_scores_gemma":[0.003914658,0.00021395487,0.0005699584,0.0006502408,0.00025999697,0.00082132244,0.00038733007,0.0008299387,0.00041624406],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028721357,0.00020599207,0.019723518,0.0002887891,0.00025926123,0.0001948796,0.00010209082,0.49182,0.01214337,0.015083902,0.008080513,0.45181045],"study_design_scores_gemma":[0.0000028688569,0.00003203316,0.0032181656,0.000017364202,0.000011799624,0.000036406283,0.00001357955,0.99044234,0.0023230056,0.0030527178,0.0008436858,0.0000059599124],"about_ca_topic_score_codex":0.00556317,"about_ca_topic_score_gemma":0.0051757805,"teacher_disagreement_score":0.00556317,"about_ca_system_score_codex":0.0009480597,"about_ca_system_score_gemma":0.00056548906,"threshold_uncertainty_score":0.011061549},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03506727168756474,"score_gpt":0.2771348645164651,"score_spread":0.24206759282890034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224918448","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04616569,0.0017637917,0.905328,0.0004599362,0.00057486375,0.00034531832,0.0013824264,0.035883117,0.008096869],"genre_scores_gemma":[0.619587,0.0007526398,0.35053977,0.0010166409,0.0001643726,0.0003280876,0.0051181847,0.0011792353,0.02131417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99936,0.00007664331,0.000038205777,0.00017026259,0.00025507598,0.000099743454],"domain_scores_gemma":[0.99928856,0.00013600629,0.000060905295,0.00028192793,0.00018838607,0.000044284876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010026796,0.0014927697,0.0010118855,0.0012422955,0.00062640547,0.00096480997,0.0022501787,0.0011017387,0.0071925754],"category_scores_gemma":[0.0024271114,0.0004093762,0.00085772004,0.0006145812,0.0007395282,0.002151551,0.0020604148,0.0015046342,0.0037293402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071066484,0.00022868403,0.0023747233,0.00025806142,0.00012962167,0.0004027145,0.000072783114,0.027738675,0.027181856,0.010700691,0.038957514,0.891244],"study_design_scores_gemma":[0.00012034411,0.00039325276,0.0014436344,0.00005796867,0.00007607393,0.0018450064,0.00007049995,0.83900774,0.10233946,0.02360706,0.030976906,0.000062081206],"about_ca_topic_score_codex":0.0027567546,"about_ca_topic_score_gemma":0.004273604,"teacher_disagreement_score":0.0071925754,"about_ca_system_score_codex":0.00069850055,"about_ca_system_score_gemma":0.0013700266,"threshold_uncertainty_score":0.02406156},"labels":[],"label_agreement":null},{"id":"W4225166627","doi":"10.1149/10701.4517ecst","title":"Technology Innovation: Detection of Counterfeit Region in an Image","year":2022,"lang":"en","type":"article","venue":"ECS Transactions","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Counterfeit; Computer science; Computer security; Digital image; Image (mathematics); Counterfeit Drugs; TRACE (psycholinguistics); Artificial intelligence; Computer vision; Internet privacy; Image processing; Geography","score_opus":0.01316376962031907,"score_gpt":0.23038085740715006,"score_spread":0.217217087786831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225166627","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33704466,0.014740111,0.5963436,0.00258697,0.00065655523,0.0006026113,0.0005236327,0.002256249,0.04524561],"genre_scores_gemma":[0.8305337,0.008007767,0.1502419,0.00054193236,0.000266351,0.00015924731,0.0005008825,0.00006631873,0.009681884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982693,0.00024153311,0.00009129471,0.00032240167,0.0008704264,0.00020510341],"domain_scores_gemma":[0.9978947,0.0005580209,0.0004395315,0.00032313037,0.00070459064,0.00008007555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094418984,0.00064267236,0.0005882779,0.003660895,0.0006004351,0.0014977547,0.0010156202,0.0014405025,0.0016083531],"category_scores_gemma":[0.004462396,0.00023147797,0.000540859,0.0016708203,0.00090315583,0.0024400477,0.0010879309,0.0007005212,0.001428443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000268451,0.00019211254,0.025795154,0.001173734,0.00011732935,0.0029387008,0.0010805223,0.005123795,0.13008064,0.014376838,0.007582284,0.8112703],"study_design_scores_gemma":[0.000034482022,0.0011858172,0.04673654,0.00067492604,0.00044312314,0.03056659,0.0023361205,0.21309452,0.59687716,0.02040814,0.087439574,0.00020297078],"about_ca_topic_score_codex":0.0006590949,"about_ca_topic_score_gemma":0.0005757707,"teacher_disagreement_score":0.003660895,"about_ca_system_score_codex":0.0005113661,"about_ca_system_score_gemma":0.00074586086,"threshold_uncertainty_score":0.0053804517},"labels":[],"label_agreement":null},{"id":"W4229048469","doi":"10.32473/flairs.v35i.130722","title":"Generative Adversarial learning with Negative Data Augmentation for Semi-supervised Text Classification","year":2022,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Discriminator; Generator (circuit theory); Computer science; Generative grammar; Manifold (fluid mechanics); Representation (politics); Boundary (topology); Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Mode (computer interface); Generative model; Decision boundary; Matching (statistics); Mixing (physics); Key (lock); Power (physics); Machine learning; Mathematics; Statistics; Physics; Support vector machine","score_opus":0.214596084131797,"score_gpt":0.3702213578985494,"score_spread":0.15562527376675236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229048469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055027425,0.0010670997,0.93366015,0.0008503127,0.00019210094,0.00013654513,0.00042130638,0.004530338,0.0041146423],"genre_scores_gemma":[0.79199857,0.0003160998,0.1993062,0.0008224951,0.00014759271,0.00029906846,0.001772543,0.00037266163,0.0049647857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979493,0.0009979914,0.000078640696,0.0004769943,0.0003629411,0.00013413525],"domain_scores_gemma":[0.99506617,0.0032219747,0.0003627353,0.00082382036,0.00036641865,0.00015889922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002523105,0.0014229965,0.0011937681,0.0006089273,0.0004904991,0.00082824996,0.0016873572,0.0012492227,0.0025587378],"category_scores_gemma":[0.0067067184,0.00041268737,0.0009913344,0.0005742011,0.0014580971,0.0017122347,0.001518738,0.0031551097,0.0013241689],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061923283,0.0003863774,0.002965853,0.00028897086,0.000113947746,0.0002750733,0.00031164123,0.74120224,0.010848692,0.014629399,0.011873124,0.21648546],"study_design_scores_gemma":[0.00000783578,0.000025158497,0.00014077655,0.0000068720433,0.0000031965772,0.000026839454,0.0000080850705,0.9926885,0.0015757058,0.0049857507,0.0005244234,0.000006911755],"about_ca_topic_score_codex":0.0015182333,"about_ca_topic_score_gemma":0.001893615,"teacher_disagreement_score":0.0025587378,"about_ca_system_score_codex":0.0008705503,"about_ca_system_score_gemma":0.0006544998,"threshold_uncertainty_score":0.013343632},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Computer security","score_opus":0.012352513854899551,"score_gpt":0.2984946380090211,"score_spread":0.28614212415412155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233345373","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29733843,0.0008306149,0.69708097,0.00013855837,0.00008834748,0.00015426055,0.00016878119,0.0014692795,0.002730865],"genre_scores_gemma":[0.7245171,0.00051657285,0.27196324,0.00006818654,0.000053844204,0.000044207307,0.00021014777,0.00006389609,0.0025628745],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992687,0.00007259419,0.000037419934,0.00019212347,0.000359317,0.00006983873],"domain_scores_gemma":[0.99883205,0.00024312655,0.00019574688,0.00028115386,0.00039491305,0.000053013067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006246658,0.0005168966,0.0008526268,0.0020927028,0.0003166053,0.0007055901,0.0007348509,0.0007323135,0.0014805377],"category_scores_gemma":[0.0017980601,0.00027178563,0.00069171516,0.0009482956,0.0004597983,0.0013965108,0.00070119015,0.0004345818,0.0006667754],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007411972,0.00030577986,0.013050092,0.00037730552,0.00024180068,0.0005509589,0.00027908618,0.013128269,0.317618,0.0030204959,0.0017781965,0.64890885],"study_design_scores_gemma":[0.000068204936,0.001155773,0.037843026,0.00004996323,0.00029902556,0.0065928823,0.0002582055,0.4142386,0.53054434,0.0031950313,0.0056257197,0.00012932277],"about_ca_topic_score_codex":0.0008313341,"about_ca_topic_score_gemma":0.00092707,"teacher_disagreement_score":0.0020927028,"about_ca_system_score_codex":0.0003435092,"about_ca_system_score_gemma":0.00035029513,"threshold_uncertainty_score":0.0049529076},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.021640889926766212,"score_gpt":0.27526006696280847,"score_spread":0.25361917703604225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285176942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71478397,0.002413996,0.25958142,0.0011350008,0.0007485796,0.00043026643,0.006540913,0.006828918,0.00753694],"genre_scores_gemma":[0.8267377,0.0011348528,0.15537812,0.00034420568,0.00014080846,0.00017648406,0.011905707,0.00054123846,0.0036409167],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992895,0.000112950234,0.000045730863,0.00019930997,0.00026575336,0.000086704655],"domain_scores_gemma":[0.997781,0.0007089401,0.00030842243,0.0006135731,0.00050831214,0.00007970067],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014421983,0.0007646344,0.00044424844,0.0018745388,0.0003462115,0.00087957614,0.0007780074,0.00086699857,0.0013119559],"category_scores_gemma":[0.0045003984,0.00022017956,0.00060657674,0.00069298275,0.0007359816,0.00064000126,0.0006611739,0.0006918774,0.0010066398],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023895514,0.00077063823,0.026418775,0.0017307921,0.00038231525,0.003827908,0.00070543814,0.12573706,0.30773667,0.012345419,0.040231433,0.47772396],"study_design_scores_gemma":[0.00008171898,0.0004971953,0.03298273,0.00025255547,0.00014978637,0.0075642755,0.0005953393,0.58359236,0.3322356,0.0080488855,0.03387628,0.00012327508],"about_ca_topic_score_codex":0.00095748325,"about_ca_topic_score_gemma":0.000887934,"teacher_disagreement_score":0.999133,"about_ca_system_score_codex":0.0005403836,"about_ca_system_score_gemma":0.0003807937,"threshold_uncertainty_score":0.0076271296},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.032370393361630084,"score_gpt":0.2338795054782328,"score_spread":0.20150911211660272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288075323","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59481716,0.0028911543,0.38650995,0.0008900368,0.0005365111,0.00014652054,0.0014156082,0.004452714,0.008340268],"genre_scores_gemma":[0.9551352,0.00055755296,0.03621307,0.0001397904,0.000076795724,0.000035702633,0.0013795384,0.00003782468,0.0064246273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996412,0.000041242154,0.000014485464,0.000090030466,0.00011723054,0.000095753894],"domain_scores_gemma":[0.9997143,0.00007526566,0.00003924656,0.000050057617,0.0001026346,0.00001848943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005739694,0.0010531754,0.000564665,0.0011528165,0.0003116537,0.00059306994,0.00075499894,0.0006772891,0.0016289543],"category_scores_gemma":[0.0009947825,0.0002809257,0.00076297927,0.0003971118,0.00031649575,0.00081894,0.0005692567,0.000948061,0.0006925975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007345424,0.00031887504,0.011289588,0.000099655495,0.00018633337,0.00032990368,0.00010841451,0.24622251,0.029049963,0.0036541692,0.010396981,0.69760907],"study_design_scores_gemma":[0.0000029834994,0.0000279107,0.001583718,0.00000726783,0.000011081452,0.00004761814,0.000014607247,0.9906923,0.0063550672,0.00077686564,0.0004725415,0.000007938309],"about_ca_topic_score_codex":0.010207696,"about_ca_topic_score_gemma":0.010192204,"teacher_disagreement_score":0.010207696,"about_ca_system_score_codex":0.0010302523,"about_ca_system_score_gemma":0.00050990324,"threshold_uncertainty_score":0.020296514},"labels":[],"label_agreement":null},{"id":"W4288365067","doi":"10.48550/arxiv.1904.10990","title":"A Robust Approach for Securing Audio Classification Against Adversarial\\n Attacks","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Spectrogram; Artificial intelligence; Codebook; Speech recognition; Audio signal; Deep learning; Smoothing; Pattern recognition (psychology); Preprocessor; Support vector machine; Feature learning; Machine learning; Speech coding; Computer vision","score_opus":0.1417010169164836,"score_gpt":0.19006390269767057,"score_spread":0.04836288578118697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288365067","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008824686,0.0003625291,0.98699003,0.00017311973,0.000103226535,0.0000521279,0.000054591444,0.0013685243,0.0020711874],"genre_scores_gemma":[0.6657925,0.0009845411,0.322136,0.00043722923,0.0003661806,0.00018834484,0.00031044698,0.00017759492,0.0096072],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986765,0.00017977938,0.000079361314,0.00027829802,0.0006555306,0.00013048966],"domain_scores_gemma":[0.9988312,0.00032274684,0.00016902703,0.00040701017,0.00021212269,0.00005787531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008017302,0.0009294106,0.0007080194,0.0008188109,0.0004064111,0.0010741844,0.0012817114,0.0012896771,0.0025020929],"category_scores_gemma":[0.0030688331,0.00036549193,0.0007712506,0.00039231958,0.001003347,0.0014084942,0.0018883636,0.0017547882,0.0017788606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047358335,0.00012820224,0.0008947966,0.00019474486,0.00012948542,0.00049271603,0.00013114912,0.34834915,0.1899049,0.051153492,0.0066424813,0.40150532],"study_design_scores_gemma":[0.000010146867,0.00014329895,0.00033343275,0.000020005049,0.000019666988,0.0002349044,0.00001780311,0.96044123,0.025782371,0.007848658,0.0051247417,0.000023713077],"about_ca_topic_score_codex":0.0007323418,"about_ca_topic_score_gemma":0.0006775848,"teacher_disagreement_score":0.0025020929,"about_ca_system_score_codex":0.00058590947,"about_ca_system_score_gemma":0.0006323716,"threshold_uncertainty_score":0.00837028},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.025425393949280565,"score_gpt":0.3260618365553703,"score_spread":0.30063644260608974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296700181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25127164,0.0013633941,0.73124486,0.0002577687,0.00019651355,0.0013358007,0.0019806116,0.0050068796,0.0073424648],"genre_scores_gemma":[0.24154915,0.00067656446,0.75401306,0.00005705468,0.000060308546,0.0002962779,0.0009191235,0.00015206935,0.0022763596],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99862313,0.00020310373,0.00011024513,0.00031812803,0.0006633366,0.0000821061],"domain_scores_gemma":[0.9955727,0.001356872,0.0007509638,0.0008474173,0.0013185262,0.00015345206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015859522,0.0005968323,0.00048894394,0.010173623,0.00043425197,0.0015462686,0.00091109716,0.00077570503,0.0022799203],"category_scores_gemma":[0.0046981466,0.0003925708,0.0003470074,0.0030804544,0.00054490124,0.0014431964,0.0011667118,0.0006937743,0.0014984715],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041186603,0.00020069626,0.013465818,0.00066617236,0.0000763617,0.00046199848,0.0006492831,0.0022974226,0.16943985,0.0021174606,0.0023485443,0.80786455],"study_design_scores_gemma":[0.00014936614,0.0012932061,0.085144036,0.00034717142,0.00043964875,0.007964735,0.0019680252,0.18936805,0.66550976,0.0037322433,0.043738745,0.00034490952],"about_ca_topic_score_codex":0.0006343706,"about_ca_topic_score_gemma":0.0012408958,"teacher_disagreement_score":0.010173623,"about_ca_system_score_codex":0.0004158849,"about_ca_system_score_gemma":0.00055839424,"threshold_uncertainty_score":0.008387387},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.01717738125733426,"score_gpt":0.22326347762734564,"score_spread":0.20608609637001138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297988790","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03591277,0.0015235265,0.95173043,0.000582927,0.00026986797,0.00014013123,0.00072726514,0.0049734144,0.004139799],"genre_scores_gemma":[0.58038515,0.0014049418,0.38605565,0.0009412232,0.00019095193,0.00027503844,0.0034795816,0.00030358494,0.026963888],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99961096,0.000034480257,0.000020695346,0.00010754082,0.00011495063,0.000111278685],"domain_scores_gemma":[0.9996612,0.00007377389,0.000039103183,0.00004748342,0.0001467299,0.000031773267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004829422,0.0014430804,0.00086535455,0.0011663463,0.0004714673,0.0009173896,0.0019680434,0.001637291,0.0038043712],"category_scores_gemma":[0.0011382294,0.0005213599,0.0010375585,0.0007799901,0.0004241976,0.0014120264,0.001218993,0.0020625452,0.001700848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027217306,0.00026587705,0.0022862847,0.0001534252,0.00015011527,0.0002871152,0.00006364791,0.12676144,0.026087696,0.0040541044,0.014543187,0.825075],"study_design_scores_gemma":[0.0000074399522,0.000056645127,0.00045056277,0.000015842063,0.000016813556,0.00010373701,0.000015281405,0.986697,0.008118658,0.00200225,0.0025040468,0.000011702277],"about_ca_topic_score_codex":0.00891095,"about_ca_topic_score_gemma":0.012776588,"teacher_disagreement_score":0.00891095,"about_ca_system_score_codex":0.0009888107,"about_ca_system_score_gemma":0.0012177796,"threshold_uncertainty_score":0.017718196},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.039841790128616154,"score_gpt":0.2564952114098063,"score_spread":0.21665342128119014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298342869","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048501763,0.0011157236,0.938237,0.00041671863,0.00010047244,0.00006473702,0.00017204757,0.00051019056,0.010881382],"genre_scores_gemma":[0.94540906,0.0008997574,0.042620875,0.00014265884,0.000040182902,0.0001039925,0.00017942983,0.000063269166,0.010540744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99976975,0.00006573227,0.000009422715,0.0000474792,0.000071228234,0.000036384514],"domain_scores_gemma":[0.99968874,0.00015933029,0.000036573172,0.000029404751,0.000074432806,0.000011462048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048746224,0.0005064889,0.00050509465,0.00041756668,0.00016352753,0.0004250191,0.00070008205,0.00064282765,0.0018831714],"category_scores_gemma":[0.00091559987,0.00024123464,0.0006642691,0.0003154799,0.00053986517,0.00075881754,0.00037967364,0.0010581969,0.00037169448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007425495,0.000022456148,0.0005503147,0.00006609766,0.00003203775,0.00011972095,0.00004995278,0.9416115,0.0075000096,0.026677806,0.00079954724,0.02249626],"study_design_scores_gemma":[0.0000019594372,0.000018432604,0.00009573855,0.000004571039,0.0000051649463,0.000038164875,0.0000026556963,0.9966132,0.00074238953,0.002131555,0.00034143732,0.0000047471576],"about_ca_topic_score_codex":0.0034177601,"about_ca_topic_score_gemma":0.0034042315,"teacher_disagreement_score":0.0034177601,"about_ca_system_score_codex":0.00069907366,"about_ca_system_score_gemma":0.00038179115,"threshold_uncertainty_score":0.0067957044},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.030544977501127984,"score_gpt":0.28033841286558575,"score_spread":0.24979343536445778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4299806750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42143318,0.0010925053,0.5521539,0.0003700488,0.00046953352,0.00026293495,0.0013179838,0.013337278,0.009562761],"genre_scores_gemma":[0.8322571,0.0002745593,0.15591085,0.00018432512,0.00005770915,0.00007323575,0.0015246117,0.00014650928,0.009571101],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99962115,0.000040355302,0.000017079885,0.000081270315,0.00013900099,0.00010117186],"domain_scores_gemma":[0.99933064,0.00017822298,0.000057364392,0.00015483587,0.00022417489,0.000054762444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055367796,0.0011576391,0.00081703893,0.00096077705,0.00035944954,0.0008008899,0.0009169198,0.0011007132,0.0036985008],"category_scores_gemma":[0.0017825748,0.00018063531,0.00031637115,0.0002965262,0.00033021413,0.0010695807,0.0010880262,0.00087038527,0.0028244266],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0018502431,0.0004671155,0.0030880617,0.00021612791,0.000104411294,0.00044263626,0.00008018145,0.035831727,0.16110902,0.001178401,0.0061054416,0.78952676],"study_design_scores_gemma":[0.000037682436,0.00042774033,0.0045158267,0.000036237947,0.000048713104,0.0007809073,0.00008750715,0.7230294,0.26608002,0.0016574446,0.0032597112,0.000038811108],"about_ca_topic_score_codex":0.0017814084,"about_ca_topic_score_gemma":0.005318571,"teacher_disagreement_score":0.0036985008,"about_ca_system_score_codex":0.00035740173,"about_ca_system_score_gemma":0.0005914792,"threshold_uncertainty_score":0.012372732},"labels":[],"label_agreement":null},{"id":"W4313504021","doi":"10.2139/ssrn.4185232","title":"The Red Hen Anonymizer and the Red Hen Protocol for De-Identifying Audiovisual Recordings","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Computer science; Software; Identification (biology); Protocol (science); Multimedia; Face (sociological concept); Speech recognition; Human–computer interaction; Linguistics; Programming language","score_opus":0.013227217621052093,"score_gpt":0.27433865333276725,"score_spread":0.26111143571171513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313504021","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.014171031,0.00050320703,0.86347795,0.0017028315,0.0016924562,0.013396968,0.02100064,0.033618674,0.05043631],"genre_scores_gemma":[0.16155967,0.00097321597,0.62576973,0.0023984117,0.0015134081,0.028835889,0.03855197,0.008731675,0.13166599],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98872966,0.004086023,0.001487476,0.0016060659,0.003170847,0.0009199832],"domain_scores_gemma":[0.9605854,0.0055777575,0.0017777177,0.02535792,0.0061320527,0.0005691727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008555749,0.0013463047,0.0011292681,0.0027536245,0.0024136594,0.004244432,0.001757219,0.0028239458,0.077545635],"category_scores_gemma":[0.028663758,0.0010252827,0.00086686225,0.0014439326,0.0019527263,0.0036102126,0.004755396,0.0034982038,0.052055493],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034486996,0.0006616595,0.0040301164,0.0013010814,0.00021002453,0.0032668733,0.0035529514,0.0048022494,0.114774056,0.15404044,0.3766846,0.33322722],"study_design_scores_gemma":[0.00034910184,0.0003622635,0.0074670427,0.00086867914,0.0001591883,0.003510253,0.0016025318,0.02939916,0.1609515,0.06169082,0.73326105,0.0003784703],"about_ca_topic_score_codex":0.0008756784,"about_ca_topic_score_gemma":0.0012676446,"teacher_disagreement_score":0.077545635,"about_ca_system_score_codex":0.0007274231,"about_ca_system_score_gemma":0.0036770585,"threshold_uncertainty_score":0.25941604},"labels":[],"label_agreement":null},{"id":"W4317555243","doi":"10.1109/pcs56426.2022.10018066","title":"Privacy-Preserving Feature Coding for Machines","year":2022,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Autoencoder; Artificial intelligence; Coding (social sciences); Task (project management); Representation (politics); Encoder; Feature (linguistics); Visualization; Deep neural networks; Feature extraction; Artificial neural network; Machine learning; Pattern recognition (psychology); Computer vision","score_opus":0.015406525266868322,"score_gpt":0.2408764374383845,"score_spread":0.22546991217151618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317555243","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021667339,0.00041371555,0.9740174,0.0005335436,0.000041468076,0.000027061309,0.00017072703,0.00076090416,0.0023679389],"genre_scores_gemma":[0.78665316,0.0005065529,0.2078087,0.0002810403,0.00010921929,0.0001225587,0.00044317354,0.00011996284,0.003955544],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990721,0.00023415257,0.000046915982,0.0001641411,0.00036380402,0.00011879466],"domain_scores_gemma":[0.99791247,0.0008542486,0.00019234951,0.00082565146,0.00017464053,0.0000405918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001061215,0.0004929423,0.00043875852,0.00044278917,0.00038465366,0.0009573966,0.0008265687,0.0008926471,0.0026082343],"category_scores_gemma":[0.0055768304,0.00026001062,0.0004068449,0.00061910687,0.0012642996,0.0021771416,0.0015215628,0.0016677871,0.000737019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042518674,0.00011432069,0.001040039,0.00018446702,0.000048627775,0.00020543802,0.00016300006,0.36360237,0.029727764,0.22716503,0.006676339,0.37064734],"study_design_scores_gemma":[0.00001554034,0.000061028266,0.0002757277,0.000030751773,0.000007567736,0.000112119036,0.000020546102,0.8499297,0.020270634,0.12557067,0.00368854,0.000017173428],"about_ca_topic_score_codex":0.00093969406,"about_ca_topic_score_gemma":0.00078789715,"teacher_disagreement_score":0.0026082343,"about_ca_system_score_codex":0.00078667764,"about_ca_system_score_gemma":0.0007605829,"threshold_uncertainty_score":0.008725405},"labels":[],"label_agreement":null},{"id":"W4323972003","doi":"10.48550/arxiv.2303.05498","title":"Mark My Words: Dangers of Watermarked Images in ImageNet","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Banting and Best Diabetes Centre, University of Toronto; European Commission; Ministry of Science and ICT, South Korea; Berlin Center for Machine Learning; Deutsche Forschungsgemeinschaft; Institute for Information and Communications Technology Promotion; Korea University","keywords":"Computer science; Artificial intelligence; Watermark; Feature (linguistics); Variety (cybernetics); Class (philosophy); Spurious relationship; Extractor; Digital watermarking; Pattern recognition (psychology); Image (mathematics); Machine learning; Engineering","score_opus":0.05328125916906568,"score_gpt":0.17953372828011194,"score_spread":0.12625246911104626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323972003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.57497245,0.0054346253,0.33680692,0.033638228,0.0073954193,0.00032971552,0.002757477,0.00987242,0.028792711],"genre_scores_gemma":[0.9506882,0.0007023156,0.029358653,0.004134055,0.0006889257,0.000065797365,0.0009105531,0.00065746275,0.012794083],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988759,0.0002236199,0.00008638516,0.00026143613,0.00045965705,0.00009305929],"domain_scores_gemma":[0.9901758,0.0042545395,0.00214601,0.0018346363,0.0013287456,0.0002601605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018521353,0.00062155456,0.00042915874,0.0012965748,0.00066128734,0.0019397025,0.0008672328,0.002055434,0.0080427425],"category_scores_gemma":[0.023385305,0.00029739397,0.00036241297,0.0009030539,0.0018596991,0.0036195405,0.0013055588,0.002003459,0.0031718747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004316715,0.00028432792,0.042537592,0.0010477616,0.00050012395,0.0041781943,0.0019271688,0.074503876,0.09060349,0.063211575,0.134192,0.5826972],"study_design_scores_gemma":[0.00018995914,0.0011671078,0.020227581,0.0006778078,0.00030883885,0.007145657,0.0012393545,0.49080485,0.28109068,0.11356472,0.083405465,0.00017797286],"about_ca_topic_score_codex":0.00079799164,"about_ca_topic_score_gemma":0.001318654,"teacher_disagreement_score":0.0080427425,"about_ca_system_score_codex":0.00069555984,"about_ca_system_score_gemma":0.00037267554,"threshold_uncertainty_score":0.026905715},"labels":[],"label_agreement":null},{"id":"W4324353508","doi":"10.1016/j.fsidi.2023.301539","title":"Transformer for authenticating the source microphone in digital audio forensics","year":2023,"lang":"en","type":"article","venue":"Forensic Science International Digital Investigation","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Computer science; Microphone; Digital audio; Digital forensics; Transformer; Sound recording and reproduction; Speech recognition; Network forensics; Architecture; Artificial intelligence; Audio signal; Speech coding; Computer security; Acoustics; Engineering; Telecommunications","score_opus":0.020450349004934847,"score_gpt":0.25206110444225405,"score_spread":0.2316107554373192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324353508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03186458,0.00045226765,0.95882463,0.00020504509,0.00025604034,0.00012954473,0.000109533765,0.0015968091,0.006561671],"genre_scores_gemma":[0.6911299,0.000758142,0.2984385,0.00022030331,0.00013343936,0.00007971183,0.00021758764,0.00017328831,0.008849069],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988549,0.00024495207,0.00006690738,0.00019995669,0.0005113677,0.00012193255],"domain_scores_gemma":[0.9989341,0.0002877208,0.00010228102,0.00024622437,0.0003561175,0.00007351992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009900243,0.0006053056,0.0005404446,0.0010666151,0.0007598682,0.0014447428,0.0012064552,0.0013150257,0.007271412],"category_scores_gemma":[0.0029460771,0.00033120124,0.00039651225,0.0005837206,0.0007318674,0.0025694745,0.0019142376,0.00094413635,0.0043844427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013329925,0.00014123626,0.0023306927,0.00056006125,0.000052331474,0.0012082788,0.0004958556,0.0044992487,0.5632121,0.03885857,0.003219563,0.38408914],"study_design_scores_gemma":[0.00010196489,0.0006855305,0.0013922848,0.0001099597,0.00015379026,0.006732528,0.0006156133,0.13292757,0.808903,0.01597613,0.032330267,0.00007133635],"about_ca_topic_score_codex":0.0003437218,"about_ca_topic_score_gemma":0.00046995722,"teacher_disagreement_score":0.007271412,"about_ca_system_score_codex":0.00033268862,"about_ca_system_score_gemma":0.00076862174,"threshold_uncertainty_score":0.024325311},"labels":[],"label_agreement":null},{"id":"W4360605113","doi":"10.1109/icnc57223.2023.10074246","title":"Shallow- and Deep- fake Image Manipulation Localization Using Deep Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Artificial intelligence; Deep learning; Computer science; Task (project management); Code (set theory); Inference; Image (mathematics); Computer vision; Image manipulation; Image editing; Engineering","score_opus":0.02041804617560285,"score_gpt":0.24447559881056374,"score_spread":0.22405755263496088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360605113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2196337,0.005097475,0.726429,0.0023874165,0.00058922585,0.000398889,0.006716441,0.026237907,0.012509919],"genre_scores_gemma":[0.7254283,0.0015542737,0.24161488,0.00078818225,0.00018264762,0.00019743285,0.014855149,0.00049482717,0.014884366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992969,0.0000970558,0.000037279005,0.00021624676,0.00018502689,0.00016750925],"domain_scores_gemma":[0.9986994,0.00031889568,0.00019933993,0.00050593977,0.00019467247,0.00008171958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000754744,0.0021373578,0.0013038849,0.0015150142,0.0006015022,0.0015051034,0.0022795843,0.0019994902,0.0035441502],"category_scores_gemma":[0.0035207726,0.00057507306,0.0011507071,0.0009220313,0.00080511294,0.0032777695,0.0021301026,0.0026404595,0.0025830078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083433697,0.00061085774,0.0117132,0.00067351345,0.00033652413,0.00072256755,0.00021287332,0.10377969,0.018882703,0.007950677,0.052352905,0.8019301],"study_design_scores_gemma":[0.00002801216,0.000119421886,0.001973791,0.00009029786,0.000060671122,0.00035824443,0.000104548744,0.95971185,0.018179543,0.012796688,0.0065421443,0.000034769262],"about_ca_topic_score_codex":0.0054174443,"about_ca_topic_score_gemma":0.008425254,"teacher_disagreement_score":0.0054174443,"about_ca_system_score_codex":0.0010120079,"about_ca_system_score_gemma":0.0010893071,"threshold_uncertainty_score":0.011856377},"labels":[],"label_agreement":null},{"id":"W4360989186","doi":"10.18280/ria.370124","title":"Image Counterfeiting Detection and Localization Using Deep Learning Algorithms","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Deep learning; Image (mathematics); Computer vision; Pattern recognition (psychology); Algorithm","score_opus":0.03027157267377261,"score_gpt":0.2656719639298126,"score_spread":0.23540039125604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360989186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17939392,0.0033009627,0.80150825,0.001032612,0.00018297847,0.00021207279,0.0008391022,0.0076806834,0.0058494364],"genre_scores_gemma":[0.74449134,0.0010597764,0.24268083,0.0004467633,0.00010562379,0.00013150458,0.002579364,0.00012738936,0.008377471],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994079,0.00009332167,0.00003598921,0.00017199303,0.00016650895,0.0001242134],"domain_scores_gemma":[0.99931586,0.00018106903,0.00010165726,0.00011605494,0.00024546322,0.000039921135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009109353,0.0015325579,0.0010790346,0.0022301865,0.00038389117,0.0011400128,0.0018264158,0.0014814346,0.0014145855],"category_scores_gemma":[0.002098168,0.00046117484,0.00084219035,0.0011790594,0.0005175965,0.00120468,0.0010391952,0.0014931737,0.001102337],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035060392,0.00041568434,0.003346263,0.00011549986,0.000117993295,0.00018716467,0.00006336577,0.22328913,0.01026594,0.0021912842,0.008076431,0.7515807],"study_design_scores_gemma":[0.0000065603153,0.000033195134,0.00039892684,0.000010854841,0.00001036367,0.000035385066,0.000016203863,0.9936718,0.004073564,0.0011502003,0.0005868855,0.000006117441],"about_ca_topic_score_codex":0.010357829,"about_ca_topic_score_gemma":0.008993954,"teacher_disagreement_score":0.010357829,"about_ca_system_score_codex":0.0013773509,"about_ca_system_score_gemma":0.0010331656,"threshold_uncertainty_score":0.020595074},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Pattern recognition (psychology); Computer science; Computer vision","score_opus":0.05439739302172529,"score_gpt":0.2700515188614606,"score_spread":0.2156541258397353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376865313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47203493,0.005737045,0.47978166,0.0026656971,0.0011170063,0.00042910187,0.004568016,0.013012582,0.020653946],"genre_scores_gemma":[0.8982011,0.001322006,0.07048554,0.00058481534,0.00012635814,0.00013882849,0.006307116,0.0002216965,0.022612555],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998305,0.000015751175,0.000008781661,0.00004486395,0.00004196826,0.000058053058],"domain_scores_gemma":[0.9998635,0.000028662003,0.000020105997,0.000023328703,0.000054031607,0.000010338197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031793438,0.0011819617,0.0005937322,0.0012641673,0.0003165066,0.0008761754,0.0012910769,0.0012470394,0.0029301653],"category_scores_gemma":[0.0005920293,0.00030601016,0.0008969381,0.0008268527,0.0003386196,0.0007669517,0.00048507977,0.001050651,0.0012381272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005342294,0.00045933176,0.0055708075,0.00017532975,0.00024264585,0.00044315465,0.00007045277,0.35194054,0.018545182,0.004246583,0.031745948,0.5860258],"study_design_scores_gemma":[0.0000083378545,0.000047757985,0.00087031256,0.000019029743,0.000020510797,0.00006632513,0.000013262773,0.98882246,0.0071537173,0.0012300895,0.0017403191,0.0000079761685],"about_ca_topic_score_codex":0.017161807,"about_ca_topic_score_gemma":0.012371292,"teacher_disagreement_score":0.017161807,"about_ca_system_score_codex":0.0013270911,"about_ca_system_score_gemma":0.0007967049,"threshold_uncertainty_score":0.034123838},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.023224306610429266,"score_gpt":0.23493429521448744,"score_spread":0.21170998860405818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377250587","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80969214,0.003154467,0.019223204,0.010166952,0.0003255602,0.00023462976,0.00008469879,0.00013328232,0.15698498],"genre_scores_gemma":[0.9920318,0.00050024566,0.0018542678,0.0009461045,0.00007227749,0.000056492627,0.00001160707,0.0000149937,0.004512194],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9717424,0.014987773,0.0014391281,0.001588498,0.008189768,0.0020524284],"domain_scores_gemma":[0.9016658,0.05149699,0.024711076,0.013407593,0.007249873,0.0014687618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011879589,0.00075470837,0.00041939656,0.0036658393,0.0055291574,0.010038636,0.0015985059,0.004246407,0.0044145645],"category_scores_gemma":[0.07259297,0.00045342834,0.0005524415,0.0013751639,0.009773362,0.008217478,0.0061547244,0.0034491182,0.0010152294],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038297081,0.0005971349,0.16218683,0.0016131686,0.00022367224,0.0105493395,0.16614453,0.0015219158,0.013472842,0.3107228,0.009619033,0.32296577],"study_design_scores_gemma":[0.00006180424,0.0021891969,0.11960789,0.009826961,0.00040019027,0.04159453,0.3059013,0.0067703244,0.034550615,0.10921171,0.36944625,0.00043934703],"about_ca_topic_score_codex":0.0012515219,"about_ca_topic_score_gemma":0.0012055449,"teacher_disagreement_score":0.011879589,"about_ca_system_score_codex":0.0025484022,"about_ca_system_score_gemma":0.002031395,"threshold_uncertainty_score":0.06282604},"labels":[],"label_agreement":null},{"id":"W4380995398","doi":"10.3390/app13127112","title":"Source Microphone Identification Using Swin Transformer","year":2023,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"King Saud University","keywords":"Microphone; Computer science; Transformer; Digital audio; Identification (biology); Speech recognition; Audio analyzer; Artificial intelligence; Audio signal; Engineering; Telecommunications; Speech coding; Electrical engineering","score_opus":0.02935601443706471,"score_gpt":0.2557583507319746,"score_spread":0.2264023362949099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380995398","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017477665,0.0003118738,0.9729769,0.00013388896,0.00019056283,0.00009947156,0.00023080852,0.0055120443,0.0030668264],"genre_scores_gemma":[0.52101105,0.00085327146,0.4627001,0.0004823895,0.00016311626,0.00016518641,0.0015540917,0.00056958204,0.012501249],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999495,0.00007385503,0.000026741911,0.00015463789,0.00019617424,0.00005362159],"domain_scores_gemma":[0.9995876,0.00008238613,0.000040882816,0.000079973164,0.00017163607,0.000037576443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006280824,0.0008673936,0.0008424701,0.0009704026,0.0003335054,0.0010089427,0.0010127915,0.0008870714,0.0059389183],"category_scores_gemma":[0.0019091944,0.00029657737,0.00072121905,0.000554496,0.0003504481,0.0012726246,0.0016278295,0.00081571296,0.0050647967],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008729094,0.00014091545,0.0021740973,0.00024777962,0.00010181197,0.00048806545,0.00014872284,0.025340402,0.11603994,0.0035122067,0.0070397872,0.84389335],"study_design_scores_gemma":[0.00006553421,0.00025088812,0.0017272255,0.00004884973,0.0000869178,0.0017683785,0.0001179889,0.85768485,0.11931617,0.004887812,0.013980937,0.00006446776],"about_ca_topic_score_codex":0.0012761287,"about_ca_topic_score_gemma":0.0020382118,"teacher_disagreement_score":0.0059389183,"about_ca_system_score_codex":0.0003204348,"about_ca_system_score_gemma":0.0006181635,"threshold_uncertainty_score":0.019867659},"labels":[],"label_agreement":null},{"id":"W4382118245","doi":"10.1007/978-3-031-34776-4_26","title":"InnerEye: A Tale on Images Filtered Using Instagram Filters - How Do We Interact with them and How Can We Automatically Identify the Extent of Filtering?","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Set (abstract data type); Computer science; Artificial intelligence; Computer vision; Image (mathematics); Filter (signal processing); The Internet; Pattern recognition (psychology); World Wide Web","score_opus":0.03182785607131606,"score_gpt":0.2445528846807986,"score_spread":0.21272502860948256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382118245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071899313,0.00588884,0.9057379,0.0040654624,0.0013501071,0.00007845626,0.00070298574,0.017943384,0.05704297],"genre_scores_gemma":[0.061454058,0.00743501,0.78069866,0.0035023652,0.0014601646,0.00016541957,0.0014713332,0.0119435135,0.13186947],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999532,0.00009739308,0.000016402686,0.000094367184,0.00020326221,0.000056542634],"domain_scores_gemma":[0.99855417,0.00071709557,0.00004105364,0.00030286753,0.00027875905,0.000105968385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016201216,0.0013151059,0.0008408389,0.00219039,0.0011664607,0.0047569307,0.0019372423,0.001993774,0.03358675],"category_scores_gemma":[0.0044245617,0.0007011941,0.0009914695,0.0013763302,0.0015632281,0.008099474,0.0029615937,0.0020081373,0.017137945],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016798107,0.00004802088,0.0010424072,0.00035000147,0.00008286336,0.00023371937,0.0009539802,0.0014830077,0.020314356,0.06122845,0.14700018,0.7670951],"study_design_scores_gemma":[0.000024621026,0.00012254606,0.0027443767,0.000423884,0.00010409417,0.0021032346,0.0009939743,0.03523609,0.049278956,0.14958695,0.7591967,0.00018466281],"about_ca_topic_score_codex":0.0016066342,"about_ca_topic_score_gemma":0.002689608,"teacher_disagreement_score":0.03358675,"about_ca_system_score_codex":0.0005812592,"about_ca_system_score_gemma":0.00031116357,"threshold_uncertainty_score":0.11235887},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.026692594948661143,"score_gpt":0.24073832640369705,"score_spread":0.21404573145503591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382198865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078126505,0.0009606031,0.90905565,0.00050731824,0.00015809172,0.00017038792,0.0005353659,0.005270757,0.005215333],"genre_scores_gemma":[0.7498768,0.0006789237,0.2272442,0.0006912458,0.00009250666,0.00015040266,0.001798009,0.00016289444,0.019304954],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995695,0.000042119227,0.000018173985,0.00012861937,0.0001401859,0.00010138936],"domain_scores_gemma":[0.9996082,0.0000827851,0.000071212526,0.000053538693,0.00014320921,0.00004096476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006252609,0.0013475734,0.0006805952,0.0012458183,0.000418473,0.0008985642,0.0026244072,0.0011873099,0.0018093375],"category_scores_gemma":[0.0011434153,0.00048769277,0.0006429759,0.00049485744,0.00065262214,0.0013008466,0.0013220814,0.0012238875,0.00064207264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053739036,0.00032323794,0.006118487,0.00014483073,0.00019685298,0.0005376823,0.00011740534,0.30834442,0.0291225,0.007713043,0.008888027,0.63795614],"study_design_scores_gemma":[0.000005363784,0.000045982582,0.0005096428,0.00001041912,0.000014647006,0.000054837477,0.000009436583,0.9905262,0.0063600824,0.001457685,0.0009966549,0.000009071517],"about_ca_topic_score_codex":0.021485353,"about_ca_topic_score_gemma":0.025496708,"teacher_disagreement_score":0.021485353,"about_ca_system_score_codex":0.0015426559,"about_ca_system_score_gemma":0.0012160635,"threshold_uncertainty_score":0.042720616},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03317681720770999,"score_gpt":0.25719979501245555,"score_spread":0.22402297780474556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382345092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07278162,0.00065014686,0.92127824,0.0007413847,0.00006568148,0.000048159207,0.0005472311,0.0007263558,0.0031611123],"genre_scores_gemma":[0.87341803,0.000528625,0.11507711,0.00022725537,0.00006325427,0.00022132261,0.0010985606,0.00015968962,0.009206156],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99972755,0.00006543953,0.000014107325,0.00009366623,0.0000575381,0.00004174978],"domain_scores_gemma":[0.9990675,0.0005498309,0.00010782731,0.00006423672,0.00018283085,0.000027868471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011326461,0.00093335117,0.0004692837,0.00060958025,0.00024945053,0.00095133344,0.001252289,0.0011261641,0.0020781416],"category_scores_gemma":[0.0034229644,0.00036574077,0.0006629523,0.00050180574,0.0005847867,0.0010714873,0.0008405352,0.0019535776,0.00048977585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041604362,0.000029513167,0.000723312,0.00003199093,0.000026424419,0.0000323221,0.000027203016,0.9682111,0.0013389967,0.0061819176,0.00082857773,0.022526989],"study_design_scores_gemma":[5.6024624e-7,0.0000018619976,0.000052702842,0.0000012523938,0.000001161722,0.0000015204719,9.5020124e-7,0.99865854,0.000112349866,0.0011171006,0.000050684263,0.0000012352217],"about_ca_topic_score_codex":0.009965648,"about_ca_topic_score_gemma":0.010064728,"teacher_disagreement_score":0.009965648,"about_ca_system_score_codex":0.0011864885,"about_ca_system_score_gemma":0.0008604714,"threshold_uncertainty_score":0.019815326},"labels":[],"label_agreement":null},{"id":"W4383376013","doi":"10.1142/9789811273209_0009","title":"Optimizing IoT Device Fingerprinting Using Machine Learning","year":2023,"lang":"en","type":"book-chapter","venue":"World Scientific series in digital forensics and cybersecurity","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology; University of Regina","funders":"","keywords":"Internet of Things; Computer science; Artificial intelligence; Embedded system","score_opus":0.025721249361645774,"score_gpt":0.22891619600283666,"score_spread":0.2031949466411909,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383376013","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033003982,0.0005115593,0.9592146,0.00011172869,0.0000660121,0.00003010793,0.00007918883,0.001851513,0.005131209],"genre_scores_gemma":[0.6467908,0.00045108356,0.34364167,0.000099731835,0.00006289366,0.000049673476,0.00029328334,0.00031222022,0.008298718],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997416,0.0000424468,0.000014379803,0.00006329788,0.00009744297,0.00004075791],"domain_scores_gemma":[0.9993943,0.00028600876,0.00006534944,0.00011572617,0.00012514308,0.000013508828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032679542,0.00088273635,0.0006615694,0.00050934823,0.0002632893,0.0007810795,0.0006355664,0.0006328826,0.0030920443],"category_scores_gemma":[0.001728798,0.00034263692,0.00040272626,0.0006630376,0.0002348045,0.0011856863,0.0005110126,0.00056928926,0.0011576478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008999095,0.00010271195,0.0015046041,0.00006149105,0.000036667527,0.000043559467,0.00001591534,0.46798655,0.02170371,0.0019428438,0.0020750295,0.5044369],"study_design_scores_gemma":[0.0000021504854,0.000023766244,0.0003227504,0.000004962429,0.000008599941,0.000033478464,0.000006896901,0.9911117,0.00646748,0.0012997355,0.0007145032,0.00000402422],"about_ca_topic_score_codex":0.001514467,"about_ca_topic_score_gemma":0.0021845482,"teacher_disagreement_score":0.0030920443,"about_ca_system_score_codex":0.0004635462,"about_ca_system_score_gemma":0.00046019643,"threshold_uncertainty_score":0.010343969},"labels":[],"label_agreement":null},{"id":"W4385386606","doi":"10.18280/ria.370318","title":"Deep Ensemble Learning for Fake Digital Image Detection: A Convolutional Neural Network-Based Approach","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convolutional neural network; Artificial intelligence; Deep learning; Computer science; Ensemble learning; Image (mathematics); Pattern recognition (psychology); Machine learning","score_opus":0.031801482791652166,"score_gpt":0.24538654058700315,"score_spread":0.21358505779535097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385386606","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17889391,0.0031817711,0.80751723,0.0008575316,0.0001804921,0.00012390746,0.00031985957,0.0031927524,0.0057324534],"genre_scores_gemma":[0.9112508,0.00066253403,0.08351332,0.00019814039,0.00009411798,0.000049563587,0.0005616926,0.000051549974,0.003618212],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995937,0.00007409062,0.0000179314,0.00009856365,0.00012060677,0.00009516055],"domain_scores_gemma":[0.99937564,0.00018507411,0.00006473063,0.000104037994,0.00022812012,0.00004248245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011839026,0.0009837464,0.0010152226,0.0011485016,0.00035261485,0.00070886436,0.0012598959,0.0007768121,0.00074594084],"category_scores_gemma":[0.0018728843,0.000333743,0.00063431344,0.0007052701,0.00028101305,0.0013154674,0.0009999889,0.001548902,0.00032991488],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021341819,0.00027274963,0.0080611305,0.000059097933,0.00022851185,0.00014751343,0.00009717665,0.45228767,0.0068530226,0.004329821,0.0046265847,0.52282333],"study_design_scores_gemma":[0.0000012912026,0.00002310019,0.00038641016,0.0000042729307,0.000012718264,0.000019222605,0.000007769516,0.9974855,0.0010049961,0.0007697512,0.00028168134,0.0000033167928],"about_ca_topic_score_codex":0.009508437,"about_ca_topic_score_gemma":0.010251557,"teacher_disagreement_score":0.009508437,"about_ca_system_score_codex":0.0008070063,"about_ca_system_score_gemma":0.0007477083,"threshold_uncertainty_score":0.018906176},"labels":[],"label_agreement":null},{"id":"W4385776918","doi":"10.1016/j.fsidi.2023.301616","title":"CAMID: An assuasive approach to reveal source camera through inconspicuous evidence","year":2023,"lang":"en","type":"article","venue":"Forensic Science International Digital Investigation","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Hong Kong Government; Hong Kong Polytechnic University; Glaucoma Research Foundation","keywords":"Artificial intelligence; Computer vision; Computer science; Robustness (evolution); Carving; Digital camera; Confusion; Identification (biology); Camera auto-calibration; Camera resectioning; Pattern recognition (psychology); Geography; Archaeology","score_opus":0.05439263144801229,"score_gpt":0.2949232492614984,"score_spread":0.2405306178134861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385776918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0134313395,0.000519647,0.9439721,0.0007966017,0.00042065824,0.00043069795,0.00020246695,0.006991661,0.033234794],"genre_scores_gemma":[0.17339896,0.000585192,0.7942443,0.0010397382,0.00020764662,0.00022191838,0.0003385517,0.00060686853,0.029356798],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9976956,0.0003804796,0.000055143708,0.00027393003,0.0014538411,0.00014089083],"domain_scores_gemma":[0.99814796,0.00044764904,0.00012462221,0.0006706231,0.00045163868,0.00015747444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015663189,0.0011292541,0.0006520424,0.002443532,0.0015805794,0.003149392,0.0027475595,0.0021046763,0.012310877],"category_scores_gemma":[0.0048917243,0.0005506242,0.00067132385,0.0006775438,0.0016495225,0.0032167807,0.0070627723,0.0020681934,0.0037529331],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007326037,0.0003427357,0.0037528616,0.00044657997,0.00014042872,0.0023754684,0.0015856267,0.0031581747,0.11780867,0.12373616,0.032135013,0.7137857],"study_design_scores_gemma":[0.00019424675,0.0009574729,0.003996283,0.0005546721,0.00034247097,0.01982545,0.0020658234,0.26345098,0.2954083,0.114906125,0.29799765,0.00030048078],"about_ca_topic_score_codex":0.0006677407,"about_ca_topic_score_gemma":0.0018221117,"teacher_disagreement_score":0.012310877,"about_ca_system_score_codex":0.00040751544,"about_ca_system_score_gemma":0.0012449494,"threshold_uncertainty_score":0.041184008},"labels":[],"label_agreement":null},{"id":"W4385882008","doi":"10.1109/bmsb58369.2023.10211506","title":"Machine Learning Classification for Video Cleaning","year":2023,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Generality; Artificial intelligence; Training set; Computer vision; Machine learning; Pattern recognition (psychology)","score_opus":0.03694506523271427,"score_gpt":0.2610364646366686,"score_spread":0.2240913994039543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385882008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012502863,0.004346382,0.97471267,0.0014300441,0.00039290654,0.00017370412,0.0005648096,0.0020525628,0.0038240813],"genre_scores_gemma":[0.27027714,0.0034267239,0.71344936,0.0006043335,0.00081801834,0.00053082436,0.002607661,0.0002067241,0.008079229],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816436,0.0005760407,0.0001401891,0.00042484264,0.0005784572,0.000116189054],"domain_scores_gemma":[0.9960253,0.0020415885,0.0002912721,0.00057011674,0.0009985431,0.00007319644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023154512,0.0009340166,0.0011960196,0.002345299,0.0007913483,0.0014390855,0.0015413124,0.002066589,0.003037093],"category_scores_gemma":[0.0099728685,0.00034915222,0.00086776563,0.0028784096,0.0005697667,0.0016484995,0.00094177754,0.0027036977,0.002418623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010139759,0.000264073,0.002795787,0.00027572608,0.00010183795,0.00014284767,0.00008670085,0.12795402,0.0031491355,0.014203474,0.021715859,0.829209],"study_design_scores_gemma":[0.0000074664445,0.000037270147,0.0008908446,0.000047607096,0.000010995601,0.00008273034,0.000046233115,0.9669356,0.00218849,0.022098718,0.007632984,0.000020975958],"about_ca_topic_score_codex":0.0033912335,"about_ca_topic_score_gemma":0.003059896,"teacher_disagreement_score":0.0033912335,"about_ca_system_score_codex":0.0010838779,"about_ca_system_score_gemma":0.00090184837,"threshold_uncertainty_score":0.012245417},"labels":[],"label_agreement":null},{"id":"W4386091953","doi":"10.3390/a16090399","title":"Detecting Image Forgery over Social Media Using U-NET with Grasshopper Optimization","year":2023,"lang":"en","type":"article","venue":"Algorithms","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Computer science; Artificial intelligence; Elastic net regularization; F1 score; Segmentation; Convolutional neural network; Pattern recognition (psychology); Machine learning; Feature selection","score_opus":0.0226730800973824,"score_gpt":0.24946474004068045,"score_spread":0.22679165994329806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386091953","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32381198,0.0019408596,0.6632941,0.0005676422,0.00015916572,0.00027745948,0.00026938278,0.004544983,0.005134364],"genre_scores_gemma":[0.84494054,0.00034811455,0.14894122,0.00031846415,0.000051835756,0.00008653356,0.00048185556,0.00012411021,0.0047072484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99954516,0.00007509972,0.000024694695,0.00014291327,0.00012792522,0.00008416321],"domain_scores_gemma":[0.9994149,0.00023006002,0.00012278798,0.000073000505,0.000118499425,0.00004060351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001009472,0.0014633344,0.0011397803,0.0016112607,0.00051162014,0.00084267725,0.0015087934,0.0015053857,0.0012439501],"category_scores_gemma":[0.0020773208,0.0004156786,0.00077945594,0.000553849,0.00069297187,0.0013120351,0.00095913804,0.00071018725,0.00039028563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085165136,0.00031098945,0.0056386786,0.00014083902,0.00021160688,0.00046087807,0.00012859398,0.55567497,0.010738475,0.0024102968,0.003752981,0.41968003],"study_design_scores_gemma":[0.000004585371,0.000037997554,0.0003695055,0.000004431487,0.00001068102,0.000039488186,0.000011885701,0.99647886,0.0024032684,0.0004601885,0.0001741885,0.0000049912337],"about_ca_topic_score_codex":0.009939036,"about_ca_topic_score_gemma":0.010214448,"teacher_disagreement_score":0.009939036,"about_ca_system_score_codex":0.0013046259,"about_ca_system_score_gemma":0.00079353777,"threshold_uncertainty_score":0.019762397},"labels":[],"label_agreement":null},{"id":"W4386800686","doi":"10.59380/crj.v1i1.2688","title":"Protection of documents against sophisticated photocopying and scanning","year":2023,"lang":"en","type":"article","venue":"CRJ","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"","keywords":"Computer science; Pantograph; Void (composites); Distribution (mathematics); Algorithm; Iterative method; Mathematics; Engineering drawing; Engineering; Materials science","score_opus":0.024372967334687835,"score_gpt":0.253309190458273,"score_spread":0.22893622312358516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386800686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009529067,0.0002394651,0.98585135,0.00010130978,0.000056724,0.000058599948,0.00003273585,0.0014060676,0.0027246154],"genre_scores_gemma":[0.21718636,0.0005357497,0.7736602,0.0001303738,0.00008373153,0.000116511095,0.00010933458,0.0006067292,0.007570966],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99878865,0.000231886,0.0000702182,0.00023943471,0.00059733225,0.000072398274],"domain_scores_gemma":[0.9975593,0.00060867117,0.00021004981,0.001118316,0.00043799396,0.000065693486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078505295,0.00083932275,0.00058045366,0.0015106637,0.00097529,0.001332116,0.001120165,0.0007851862,0.004540304],"category_scores_gemma":[0.003321127,0.0005620712,0.00047994254,0.0011287277,0.0010840967,0.0015699645,0.0010476101,0.0010945988,0.002777007],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036674694,0.00009557658,0.0010598075,0.00029882515,0.000052424813,0.00041586751,0.0003215718,0.011642063,0.2882427,0.030326918,0.00481118,0.6623663],"study_design_scores_gemma":[0.000076451644,0.00048280993,0.0018797482,0.00009836714,0.0001135551,0.0058171884,0.00015855778,0.20497258,0.696247,0.02387851,0.066132315,0.0001429035],"about_ca_topic_score_codex":0.00030114705,"about_ca_topic_score_gemma":0.00048792156,"teacher_disagreement_score":0.004540304,"about_ca_system_score_codex":0.0005706615,"about_ca_system_score_gemma":0.0007298903,"threshold_uncertainty_score":0.015188813},"labels":[],"label_agreement":null},{"id":"W4387310441","doi":"10.1007/s11042-023-16791-y","title":"A perceptual entanglement-based image authentication with tamper localisation","year":2023,"lang":"en","type":"article","venue":"Multimedia Tools and Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Authentication (law); Artificial intelligence; Computer vision; Image (mathematics); Image editing; Pixel; Residual; Perception; Process (computing); Digital image; Encoding (memory); Key (lock); Pattern recognition (psychology); Image processing; Computer security; Algorithm","score_opus":0.017342453490064497,"score_gpt":0.23849784767510238,"score_spread":0.22115539418503788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387310441","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04017812,0.0003374052,0.9531122,0.00018440594,0.00016027884,0.00015042021,0.00009876395,0.0017094656,0.004069012],"genre_scores_gemma":[0.7169016,0.00036454425,0.27545038,0.00013257949,0.00010684561,0.000098055934,0.00021057828,0.00012691316,0.006608615],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9989355,0.00023404488,0.000053021693,0.00020362661,0.00044207193,0.0001318196],"domain_scores_gemma":[0.9986557,0.00029738297,0.000121816076,0.0005183393,0.00028621935,0.00012058118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007439116,0.00079705915,0.0011307865,0.0011145215,0.0008331366,0.0012167223,0.001206075,0.0012473458,0.006694031],"category_scores_gemma":[0.0021499884,0.00035870858,0.0005952229,0.0009547304,0.0013816041,0.0025611997,0.004318151,0.0008825555,0.0032090035],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0023739478,0.0003941222,0.001253561,0.00038844993,0.0001357163,0.00064248516,0.00026507443,0.020131998,0.45976064,0.043710317,0.0039461586,0.46699762],"study_design_scores_gemma":[0.00014815005,0.0011330827,0.0016542812,0.00006943998,0.00016568428,0.0020027477,0.00013766711,0.64021045,0.32498032,0.019488553,0.0098431725,0.00016656007],"about_ca_topic_score_codex":0.00031885927,"about_ca_topic_score_gemma":0.00039613328,"teacher_disagreement_score":0.006694031,"about_ca_system_score_codex":0.00027780997,"about_ca_system_score_gemma":0.00056008983,"threshold_uncertainty_score":0.022393703},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.024773614315432336,"score_gpt":0.2399835304050656,"score_spread":0.21520991608963325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388023184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44191098,0.0021056603,0.5381127,0.00037609582,0.00027301692,0.00026183206,0.00076839345,0.009438269,0.006753024],"genre_scores_gemma":[0.7915353,0.00072511286,0.19739762,0.00020113107,0.00003793874,0.0001252759,0.001950267,0.0001112527,0.007916096],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997564,0.000026982081,0.000014509893,0.000073504896,0.00008763856,0.000040934898],"domain_scores_gemma":[0.9997582,0.000052332114,0.000033710745,0.000042386833,0.00009951625,0.000013866127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005753493,0.000743553,0.0005586316,0.00073399494,0.00018917046,0.0005700676,0.00094598584,0.00066022534,0.0012416318],"category_scores_gemma":[0.001013361,0.00027072505,0.0005483885,0.0003254076,0.00022748388,0.00055050955,0.0006194973,0.0006253401,0.0011183487],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00064214633,0.00025591336,0.0076757586,0.00017811824,0.00013847621,0.0002849181,0.00014347365,0.19534309,0.06180782,0.0018508432,0.006137038,0.7255425],"study_design_scores_gemma":[0.000009036075,0.000113674476,0.0017476635,0.000019454199,0.000022300948,0.00013233865,0.0000308873,0.9753446,0.02028429,0.00042438318,0.0018579205,0.000013465318],"about_ca_topic_score_codex":0.0051701833,"about_ca_topic_score_gemma":0.006982815,"teacher_disagreement_score":0.0051701833,"about_ca_system_score_codex":0.00048665673,"about_ca_system_score_gemma":0.00066206174,"threshold_uncertainty_score":0.010280192},"labels":[],"label_agreement":null},{"id":"W4388094857","doi":"10.18280/ts.400520","title":"A Robust Algorithm for Digital Image Copyright Protection and Tampering Detection: Employing DWT, DCT, and Blowfish Techniques","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Gachon University","keywords":"Discrete cosine transform; Computer science; Algorithm; Image (mathematics); Computer vision; Artificial intelligence","score_opus":0.021049016301607167,"score_gpt":0.2156682323228519,"score_spread":0.19461921602124474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388094857","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017825395,0.0007058708,0.9793438,0.00010222395,0.00010468686,0.000087262175,0.000028455874,0.0006988745,0.0011035119],"genre_scores_gemma":[0.2156916,0.0011717103,0.7784308,0.000137292,0.000096140764,0.00008933641,0.0001472931,0.00011466976,0.004121102],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99928445,0.00006992473,0.00005852613,0.00013603647,0.0004145188,0.0000365829],"domain_scores_gemma":[0.9990852,0.0001802154,0.00017368457,0.00021343245,0.00031738594,0.000030089142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006937909,0.00068846997,0.0006749591,0.0013774977,0.00035318715,0.00081934663,0.00076362805,0.0009613585,0.0012614736],"category_scores_gemma":[0.00255429,0.00024436184,0.0006156194,0.00078526925,0.0006786198,0.0016477016,0.0006277119,0.0007701812,0.0008094909],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025539007,0.00008959753,0.001063156,0.00031922103,0.000091580405,0.00035480672,0.00013675717,0.029575773,0.34778476,0.011869892,0.001654126,0.6068049],"study_design_scores_gemma":[0.00009165458,0.0007559341,0.0023631314,0.0000894837,0.00010814566,0.0032982344,0.00009540872,0.61635774,0.34681094,0.0047861123,0.025105907,0.0001373668],"about_ca_topic_score_codex":0.00086370006,"about_ca_topic_score_gemma":0.00074480753,"teacher_disagreement_score":0.0013774977,"about_ca_system_score_codex":0.0004171177,"about_ca_system_score_gemma":0.0006990829,"threshold_uncertainty_score":0.0042200685},"labels":[],"label_agreement":null},{"id":"W4390010782","doi":"10.1049/pbpc061e_ch3","title":"Machine/Deep learning techniques for multimedia security","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Scalability; Multimedia; Field (mathematics); Encryption; Deep learning; Digital watermarking; Machine learning; Artificial intelligence; Computer security; Database; Image (mathematics)","score_opus":0.014542618046132237,"score_gpt":0.23553569391204332,"score_spread":0.22099307586591108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390010782","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005441031,0.005926566,0.9768406,0.0024439476,0.00022122981,0.00006252136,0.0001688394,0.0009258622,0.007969383],"genre_scores_gemma":[0.41405338,0.017695332,0.5411507,0.0015683528,0.00082381116,0.000264027,0.0011547998,0.00036064425,0.022928935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993223,0.00016201782,0.000049389706,0.00010680381,0.00029177536,0.000067739624],"domain_scores_gemma":[0.99892265,0.00048728322,0.00010813995,0.00018948157,0.00025001288,0.000042376174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013059978,0.0008216673,0.0006328898,0.0014609791,0.0003294494,0.0014995307,0.001176775,0.0013711414,0.0042178584],"category_scores_gemma":[0.0033725004,0.00037937966,0.00087626884,0.0012999839,0.00088764046,0.0023338764,0.0015660282,0.003089285,0.0013182096],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086926455,0.00013233052,0.0016062489,0.00053338206,0.00016637365,0.0002027421,0.00014060394,0.255027,0.0070443507,0.14742029,0.01808049,0.5695593],"study_design_scores_gemma":[0.000008401652,0.00004242205,0.00042946532,0.00009516966,0.000022431774,0.000102546925,0.00003745175,0.8726983,0.0040951953,0.10370366,0.018744282,0.000020589421],"about_ca_topic_score_codex":0.0028994817,"about_ca_topic_score_gemma":0.002828687,"teacher_disagreement_score":0.0042178584,"about_ca_system_score_codex":0.0012638692,"about_ca_system_score_gemma":0.00097576407,"threshold_uncertainty_score":0.014110148},"labels":[],"label_agreement":null},{"id":"W4392402449","doi":"10.5220/0012473700003660","title":"Enhanced Deepfake Detection Using Frequency Domain Upsampling","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Upsampling; Computer science; Frequency domain; Domain (mathematical analysis); Artificial intelligence; Computer vision; Mathematics","score_opus":0.016341012452593066,"score_gpt":0.24973604684161885,"score_spread":0.23339503438902579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392402449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06579051,0.0003851582,0.9283385,0.00021984677,0.00016172869,0.000040161663,0.00012570398,0.0008653705,0.004073043],"genre_scores_gemma":[0.4702264,0.0005201022,0.51714045,0.0002721206,0.000119578224,0.000046713674,0.00045302146,0.00010005419,0.01112154],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996946,0.00003983934,0.000012837119,0.000040532534,0.00015986913,0.00005244294],"domain_scores_gemma":[0.99955815,0.00015373509,0.000032073076,0.0000884748,0.00014448687,0.000023018592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039344243,0.00072951865,0.00045723506,0.0008132798,0.00031296205,0.0006646525,0.00038432635,0.00078290666,0.0029498248],"category_scores_gemma":[0.0011531481,0.00021959045,0.00036937374,0.00039468508,0.00024220096,0.0009439376,0.00082709535,0.0007104476,0.0010358006],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006020172,0.00020319098,0.0021229407,0.000121527744,0.000052160372,0.00027662527,0.000088615656,0.015329274,0.27802935,0.006308334,0.0020958849,0.6947701],"study_design_scores_gemma":[0.000030621355,0.00023463268,0.0046650604,0.000048134567,0.0000690662,0.0012431483,0.000070553724,0.77161145,0.2059215,0.0066047614,0.009450783,0.000050252915],"about_ca_topic_score_codex":0.0010261579,"about_ca_topic_score_gemma":0.0027811697,"teacher_disagreement_score":0.0029498248,"about_ca_system_score_codex":0.00018383925,"about_ca_system_score_gemma":0.00052164425,"threshold_uncertainty_score":0.009868205},"labels":[],"label_agreement":null},{"id":"W4393170705","doi":"10.1109/access.2024.3381521","title":"Advocating Pixel-Level Authentication of Camera-Captured Images","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); Centre for Social Innovation","funders":"","keywords":"Computer vision; Computer science; Pixel; Artificial intelligence; Authentication (law); Computer graphics (images); Computer security","score_opus":0.03980776779076873,"score_gpt":0.3109796661338178,"score_spread":0.27117189834304906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393170705","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.087746605,0.00066717976,0.8849472,0.0014432841,0.0002476271,0.00023915684,0.00012883358,0.0019260759,0.022654094],"genre_scores_gemma":[0.65677077,0.00059546146,0.33209187,0.0004931987,0.00019446891,0.000113060014,0.00017253624,0.00024209298,0.009326545],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99773383,0.0005826868,0.00014528407,0.00043346043,0.0009084975,0.00019637652],"domain_scores_gemma":[0.9910659,0.0014128648,0.0009494856,0.0048630447,0.0015180365,0.00019064998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021480466,0.00038147587,0.00043001957,0.0005772787,0.00079347997,0.0025080708,0.0014249132,0.0013739844,0.003548246],"category_scores_gemma":[0.013160829,0.00040837,0.0003137971,0.00043559552,0.0021672351,0.0048757945,0.003016548,0.0014038933,0.0025416273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010822004,0.0001904365,0.007464969,0.0009243284,0.00009609894,0.0013899454,0.0053375224,0.008573052,0.33383173,0.12423146,0.007060903,0.50981736],"study_design_scores_gemma":[0.00006475657,0.00080902147,0.008094209,0.0004438741,0.000118561926,0.004546714,0.0016829101,0.09852391,0.7200774,0.036151037,0.12934245,0.00014524972],"about_ca_topic_score_codex":0.0005476938,"about_ca_topic_score_gemma":0.00049363746,"teacher_disagreement_score":0.003548246,"about_ca_system_score_codex":0.00044179545,"about_ca_system_score_gemma":0.00061465555,"threshold_uncertainty_score":0.011870027},"labels":[],"label_agreement":null},{"id":"W4395690619","doi":"10.22214/ijraset.2024.60765","title":"Exposing Fake Faces Through Deep Neural Networks Combining Content and Trace Feature Extractors","year":2024,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Impact","funders":"","keywords":"TRACE (psycholinguistics); Computer science; Feature (linguistics); Content (measure theory); Artificial intelligence; Artificial neural network; Pattern recognition (psychology); Mathematics; Philosophy","score_opus":0.06297834367051158,"score_gpt":0.3483267855278048,"score_spread":0.28534844185729324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395690619","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62144554,0.0022139743,0.35476363,0.0011900739,0.00048472284,0.00025407798,0.0012508614,0.0076849116,0.0107123],"genre_scores_gemma":[0.9199154,0.0004969568,0.071787305,0.000236616,0.0000846175,0.000044900604,0.0010613499,0.00008811525,0.0062847384],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994518,0.0000971555,0.000021826148,0.00014408803,0.00017299222,0.00011216344],"domain_scores_gemma":[0.9989722,0.00035750924,0.00018194946,0.0001996225,0.00024302851,0.000045628705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095490145,0.0011234152,0.0006094272,0.0013155513,0.00034194285,0.0007248572,0.0008908122,0.0009735239,0.0021792422],"category_scores_gemma":[0.002837199,0.00031508735,0.00049736496,0.00048079333,0.0004656676,0.0014075502,0.0009702658,0.0011318523,0.0013151009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008388688,0.0004023384,0.007987849,0.00014514803,0.00015919212,0.00041142438,0.00014143265,0.08215552,0.035388887,0.0016740065,0.009063292,0.8616321],"study_design_scores_gemma":[0.000006890035,0.00008304659,0.0023464253,0.000025694877,0.000030243933,0.00015243841,0.000046794677,0.97519386,0.01981145,0.0010887826,0.0012009441,0.000013537512],"about_ca_topic_score_codex":0.0046265153,"about_ca_topic_score_gemma":0.0049647954,"teacher_disagreement_score":0.0046265153,"about_ca_system_score_codex":0.00090056984,"about_ca_system_score_gemma":0.00043998548,"threshold_uncertainty_score":0.009199142},"labels":[],"label_agreement":null},{"id":"W4396607259","doi":"10.23977/acss.2024.080305","title":"Video matting tampering detection based on time and space domain traces","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Space (punctuation); Domain (mathematical analysis); Computer vision; Computer graphics (images); Artificial intelligence; Mathematics; Mathematical analysis; Operating system","score_opus":0.006352617243128427,"score_gpt":0.2225903928825657,"score_spread":0.21623777563943727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396607259","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22488402,0.0010333948,0.76716304,0.0002012248,0.000109903995,0.00009231653,0.00033721447,0.0027822664,0.0033966373],"genre_scores_gemma":[0.8926737,0.0007683868,0.102489255,0.00008364781,0.000042130934,0.000031256215,0.00059339084,0.000106847176,0.0032115],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9997819,0.000021843727,0.000013390753,0.00005747344,0.00008098951,0.000044444994],"domain_scores_gemma":[0.9994381,0.00009638412,0.00012511895,0.00009061396,0.00020451647,0.000045157536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003038047,0.0007937086,0.0005056064,0.0014943086,0.00018312878,0.00058496284,0.00064263004,0.0004535446,0.0008938007],"category_scores_gemma":[0.0017834269,0.00017910155,0.00036773502,0.0006079322,0.00043346247,0.0011306561,0.0006752612,0.00064362056,0.0005465723],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006888134,0.00013538003,0.009090161,0.0002352769,0.00008424492,0.000663372,0.0001767749,0.08490869,0.122483656,0.0041353167,0.0027306539,0.7746677],"study_design_scores_gemma":[0.000008234127,0.000121567864,0.003986818,0.000036931633,0.00004039924,0.00045554098,0.00007784062,0.8969721,0.093796656,0.002294743,0.0021890902,0.000020074516],"about_ca_topic_score_codex":0.0018198106,"about_ca_topic_score_gemma":0.0024428475,"teacher_disagreement_score":0.0018198106,"about_ca_system_score_codex":0.0003852983,"about_ca_system_score_gemma":0.00043898073,"threshold_uncertainty_score":0.0036184192},"labels":[],"label_agreement":null},{"id":"W4396611084","doi":"10.21203/rs.3.rs-4320842/v1","title":"Enhancing Practicality and Efficiency of Deepfake Detection.","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Key (lock); Inference; Convolutional neural network; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Image (mathematics); Machine learning; Core (optical fiber); Computer security","score_opus":0.04351096778690593,"score_gpt":0.37838183135981224,"score_spread":0.3348708635729063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396611084","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070243716,0.0012455194,0.91282195,0.0012199264,0.00027997766,0.00022908408,0.00025943184,0.0035062735,0.010194151],"genre_scores_gemma":[0.6255075,0.0006926962,0.36528656,0.00028781407,0.0001822311,0.00012578031,0.0004653825,0.00032272525,0.007129338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952187,0.0015415886,0.0002110294,0.0006512775,0.00184661,0.00053078163],"domain_scores_gemma":[0.9820973,0.009782371,0.0006896529,0.0042312527,0.0028232157,0.0003761246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035424582,0.0017841284,0.0010945956,0.0023966373,0.0013245676,0.002841072,0.0022235624,0.0026682143,0.012064266],"category_scores_gemma":[0.030944685,0.0007258478,0.00059531257,0.0012053502,0.0015789429,0.0057217116,0.0054535875,0.0021519882,0.0047751293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0024369948,0.00059009704,0.0063385507,0.0006675614,0.00013571119,0.000614814,0.00034347852,0.039769374,0.11613071,0.049469434,0.014679536,0.76882374],"study_design_scores_gemma":[0.00019021475,0.00041551312,0.0019077156,0.000116639996,0.00008368479,0.0025382314,0.0002977426,0.75547856,0.14770159,0.08075094,0.010439636,0.00007955113],"about_ca_topic_score_codex":0.0011347174,"about_ca_topic_score_gemma":0.0022342827,"teacher_disagreement_score":0.012064266,"about_ca_system_score_codex":0.00072100776,"about_ca_system_score_gemma":0.0019841753,"threshold_uncertainty_score":0.04035902},"labels":[],"label_agreement":null},{"id":"W4396826777","doi":"10.55041/ijsrem33801","title":"Identification of Counterfeit Videos using Deep Learning Methodology","year":2024,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Deep learning; Recurrent neural network; Artificial intelligence; Leverage (statistics); Convolutional neural network; Credibility; Machine learning; Software deployment; Pattern recognition (psychology); Artificial neural network","score_opus":0.08525273530843322,"score_gpt":0.3738012177668186,"score_spread":0.2885484824583854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396826777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1721603,0.0020373682,0.81447035,0.0008479596,0.00015302633,0.00025251295,0.0012623685,0.003609225,0.0052068727],"genre_scores_gemma":[0.8218223,0.00077958923,0.16916426,0.00022013811,0.00009141956,0.00010640484,0.0019868247,0.00009686054,0.005732256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99947125,0.000100773956,0.000034202447,0.00013968506,0.00015490655,0.00009920733],"domain_scores_gemma":[0.9988644,0.00031058898,0.00027488617,0.00017998203,0.00031049683,0.000059491635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078189495,0.0012236643,0.00063020864,0.0021614353,0.0003192742,0.0011232268,0.00096843165,0.0009785501,0.0016497124],"category_scores_gemma":[0.0031798298,0.00039296862,0.00066399184,0.00073005515,0.0004210879,0.0015909502,0.00075315475,0.0014181039,0.0008122834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029673666,0.0003824726,0.015641712,0.00035284823,0.00022691868,0.00058905396,0.00016254664,0.23723221,0.023175746,0.011220335,0.009314924,0.7014045],"study_design_scores_gemma":[0.0000031403208,0.000028395407,0.0009743251,0.000020277574,0.000008295505,0.000056728808,0.000024436458,0.9914868,0.0041024904,0.0024993275,0.00078788545,0.000007865382],"about_ca_topic_score_codex":0.0063936557,"about_ca_topic_score_gemma":0.0071140723,"teacher_disagreement_score":0.0063936557,"about_ca_system_score_codex":0.0011937028,"about_ca_system_score_gemma":0.0008950296,"threshold_uncertainty_score":0.012712836},"labels":[],"label_agreement":null},{"id":"W4396887657","doi":"10.1016/j.eswa.2024.124201","title":"A novel robust black-box fingerprinting scheme for deep classification neural networks","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Agriculture","funders":"","keywords":"Computer science; Black box; Artificial intelligence; Deep neural networks; Artificial neural network; Scheme (mathematics); Pattern recognition (psychology); Classification scheme; Deep learning; Machine learning; Data mining; Mathematics","score_opus":0.02777965028994986,"score_gpt":0.25420990466357873,"score_spread":0.22643025437362888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396887657","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011417591,0.00034330014,0.98575586,0.0001186038,0.000074301664,0.00004248599,0.000099388315,0.0010755887,0.0010728437],"genre_scores_gemma":[0.36820272,0.00047823816,0.62082404,0.00031907758,0.00010681794,0.00012761996,0.00041608876,0.00015930756,0.009366137],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914384,0.00013324474,0.00004742984,0.0001819915,0.0003537935,0.00013975229],"domain_scores_gemma":[0.99903715,0.00018157664,0.00010548391,0.00031058548,0.0003067944,0.000058434918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009540579,0.0010803316,0.0011616893,0.0008710598,0.00060618605,0.0010548488,0.0021520117,0.0014090717,0.004326532],"category_scores_gemma":[0.002209833,0.0004429733,0.000612432,0.0009694826,0.0005403112,0.0020176913,0.0022858786,0.0015588654,0.0016016184],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005799901,0.00015883276,0.00079679355,0.0001269751,0.000093428265,0.00009010385,0.00004553552,0.054456394,0.060526457,0.013063438,0.0045722765,0.8654898],"study_design_scores_gemma":[0.000018643595,0.00009717923,0.00032884246,0.000018546803,0.000029916628,0.00011718778,0.000009268801,0.9638365,0.028347988,0.0050928574,0.0020797024,0.000023349901],"about_ca_topic_score_codex":0.0027421007,"about_ca_topic_score_gemma":0.0041192006,"teacher_disagreement_score":0.004326532,"about_ca_system_score_codex":0.00074220006,"about_ca_system_score_gemma":0.0012231563,"threshold_uncertainty_score":0.014473677},"labels":[],"label_agreement":null},{"id":"W4396918594","doi":"10.1109/isdfs60797.2024.10527295","title":"Multimedia Forensics: Preserving Video Integrity with Blockchain","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"University of Winnipeg","keywords":"Computer science; Blockchain; Credibility; Video quality; Data integrity; Hash function; Process (computing); Video tracking; Trustworthiness; Video processing; Multimedia; Computer security; Computer hardware","score_opus":0.012735502443492853,"score_gpt":0.23175210527855875,"score_spread":0.21901660283506588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396918594","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16268194,0.0010744809,0.82377714,0.00092019857,0.00013871858,0.0003311033,0.00016669104,0.0018861019,0.009023699],"genre_scores_gemma":[0.8570715,0.000558044,0.13735971,0.00010706212,0.000074317504,0.000090691196,0.00013193025,0.00007623517,0.0045304196],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99860317,0.00042190604,0.00005514862,0.00014110602,0.0006209346,0.00015782882],"domain_scores_gemma":[0.9976593,0.0008690562,0.00024039859,0.0007740401,0.00033447638,0.00012283032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022308368,0.000379213,0.00045866886,0.0009718626,0.00097375334,0.0010989431,0.0010042638,0.0012116906,0.0034746507],"category_scores_gemma":[0.00509738,0.0002376756,0.00023423966,0.0009384745,0.0009949665,0.003268844,0.0018744076,0.0006809998,0.00079425797],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014988836,0.00037803568,0.003521033,0.00041586664,0.00008220966,0.0011840985,0.0007792816,0.12929858,0.16063572,0.07557045,0.0040953895,0.6225405],"study_design_scores_gemma":[0.0001939501,0.00078240316,0.0009789544,0.000096755335,0.00004226476,0.0014015133,0.00026442835,0.73275465,0.18692467,0.056560695,0.01991491,0.00008481978],"about_ca_topic_score_codex":0.0010790239,"about_ca_topic_score_gemma":0.00066173903,"teacher_disagreement_score":0.0034746507,"about_ca_system_score_codex":0.00048203228,"about_ca_system_score_gemma":0.000995977,"threshold_uncertainty_score":0.011797965},"labels":[],"label_agreement":null},{"id":"W4399157574","doi":"10.18280/mmep.110511","title":"Detecting Hidden Data in Images Using Convolutional Neural Networks","year":2024,"lang":"en","type":"article","venue":"Mathematical Modelling and Engineering Problems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Institut Teknologi Sepuluh Nopember","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Steganalysis; Pattern recognition (psychology); Feature extraction; Normalization (sociology); Correctness; Preprocessor; Softmax function; Probabilistic logic; Feature (linguistics); Deep learning; Payload (computing); Data mining; Steganography; Embedding; Algorithm","score_opus":0.04382765822814239,"score_gpt":0.23672707561579023,"score_spread":0.19289941738764785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399157574","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1045573,0.0011357737,0.88882166,0.0003276389,0.00005279771,0.000046285746,0.00020166716,0.0020676167,0.0027893214],"genre_scores_gemma":[0.86763036,0.00085590803,0.12838292,0.00014132216,0.000034952976,0.000042178912,0.0003117432,0.000056383513,0.0025442052],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997181,0.00003966101,0.000016334381,0.00008022363,0.00010600099,0.000039745333],"domain_scores_gemma":[0.9994797,0.00023611933,0.00011379156,0.000064029424,0.00009138936,0.000014958795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005125082,0.000675972,0.00035072985,0.0008184762,0.00019636586,0.00074788043,0.00067155075,0.00064916775,0.00074056425],"category_scores_gemma":[0.002191149,0.00037030733,0.0004893818,0.0005976437,0.0004993432,0.0011298303,0.0006344664,0.00070386176,0.00033773624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026466305,0.000117078045,0.007666192,0.00022498792,0.00014915376,0.00029621777,0.00013338396,0.5046744,0.05409996,0.011939148,0.0017669342,0.41866794],"study_design_scores_gemma":[0.0000016860766,0.000019387153,0.0009664805,0.000011039852,0.000007855898,0.000038464288,0.0000070019823,0.98913026,0.0071452786,0.0022591858,0.00040742476,0.0000059300896],"about_ca_topic_score_codex":0.007790803,"about_ca_topic_score_gemma":0.008843003,"teacher_disagreement_score":0.007790803,"about_ca_system_score_codex":0.0009278454,"about_ca_system_score_gemma":0.00051638746,"threshold_uncertainty_score":0.01549089},"labels":[],"label_agreement":null},{"id":"W4399169440","doi":"10.1109/smc-iot62253.2023.00013","title":"Multi-Source Fusion User Authentication Based on Channel and Image Features","year":2023,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Feature extraction; Artificial intelligence; Channel (broadcasting); Feature (linguistics); Authentication (law); Image fusion; Image (mathematics); Pattern recognition (psychology); Artificial neural network; Feature learning; Transmission (telecommunications); Deep learning; Computer vision; Data mining","score_opus":0.012873061218768541,"score_gpt":0.23695487063534282,"score_spread":0.22408180941657427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399169440","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05805545,0.00035637812,0.93813616,0.00013801639,0.000099851386,0.00005573325,0.00007352931,0.0009980383,0.002086894],"genre_scores_gemma":[0.890852,0.00028224324,0.106103964,0.000103220846,0.00007313355,0.000033978424,0.00016389367,0.00006224227,0.0023253092],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989976,0.00017351207,0.00004673307,0.00019209336,0.00046490828,0.00012518255],"domain_scores_gemma":[0.9989544,0.00027165006,0.00015294767,0.00024707193,0.00032849167,0.000045447927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008205328,0.0007346818,0.0009623882,0.001029877,0.0003668717,0.00076128665,0.0005824946,0.00080732664,0.0011543906],"category_scores_gemma":[0.0025673076,0.0002409889,0.00068533624,0.0007447472,0.0005646002,0.0023870934,0.0016850446,0.00093435263,0.00075144996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010733259,0.0002201447,0.0066916104,0.00024743084,0.00018624998,0.00043224456,0.00024738698,0.07022567,0.13592954,0.008432633,0.0022968377,0.7740169],"study_design_scores_gemma":[0.000015787706,0.0002517272,0.005180718,0.000032117507,0.00009664531,0.000841094,0.0000873939,0.8735609,0.11225825,0.005296676,0.002314199,0.00006442683],"about_ca_topic_score_codex":0.0005890827,"about_ca_topic_score_gemma":0.00075176905,"teacher_disagreement_score":0.0011543906,"about_ca_system_score_codex":0.00031084218,"about_ca_system_score_gemma":0.0005243386,"threshold_uncertainty_score":0.0043394566},"labels":[],"label_agreement":null},{"id":"W4399311019","doi":"10.1109/lsp.2024.3408676","title":"Multi-Level Information Aggregation Based Graph Attention Networks Towards Fake Speech Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Signal Processing Letters","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Science Foundation of Anhui Province; National Natural Science Foundation of China","keywords":"Computer science; Graph; Attention network; Voice activity detection; Graph theory; Speech recognition; Artificial intelligence; Theoretical computer science; Speech processing; Mathematics","score_opus":0.020140919160847304,"score_gpt":0.2324139981366507,"score_spread":0.2122730789758034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399311019","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.112636864,0.0014987679,0.8794576,0.00056243315,0.00010091148,0.00009269179,0.00029094578,0.00199801,0.003361816],"genre_scores_gemma":[0.89398843,0.00055511034,0.10104357,0.00032924817,0.0001143207,0.00007223179,0.00058024295,0.00009641073,0.0032203733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995309,0.00012540966,0.00001735361,0.00014648178,0.000106390056,0.0000733986],"domain_scores_gemma":[0.9990558,0.00046639887,0.00010560678,0.000111556496,0.00020546107,0.000055172775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006372948,0.0011633553,0.0006984976,0.0016200483,0.0004737974,0.00075449876,0.0011265208,0.00071315555,0.0013701603],"category_scores_gemma":[0.002485014,0.00032340566,0.00066298456,0.0010667056,0.0006453106,0.0015607554,0.0013534139,0.0009431487,0.00031424587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052225095,0.00022073988,0.0037126616,0.00021706928,0.00019399323,0.00030232107,0.00029899506,0.41189072,0.026726402,0.016891338,0.0061414926,0.532882],"study_design_scores_gemma":[0.0000054765756,0.000047413287,0.000802477,0.0000062848076,0.000036564423,0.00003895274,0.000022182776,0.98810065,0.003664879,0.006379693,0.00088687113,0.000008498124],"about_ca_topic_score_codex":0.008113058,"about_ca_topic_score_gemma":0.009551064,"teacher_disagreement_score":0.008113058,"about_ca_system_score_codex":0.0012057154,"about_ca_system_score_gemma":0.0006743515,"threshold_uncertainty_score":0.01613164},"labels":[],"label_agreement":null},{"id":"W4400041451","doi":"10.18280/ts.410317","title":"Enhanced Detection of Text and Image Spam Using Cost-Sensitive Deep Learning","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning; Image (mathematics); Machine learning; Pattern recognition (psychology)","score_opus":0.01064726042974942,"score_gpt":0.23303490441559963,"score_spread":0.2223876439858502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400041451","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31319946,0.0013281513,0.6739454,0.0007783061,0.0001408811,0.00018011336,0.0002868834,0.005120895,0.0050198603],"genre_scores_gemma":[0.91312915,0.00025942957,0.08169514,0.00039589932,0.00009694943,0.000083479004,0.0005963595,0.000072338546,0.0036711867],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995981,0.00007250879,0.000020039066,0.00007859938,0.00015731147,0.0000734934],"domain_scores_gemma":[0.9992198,0.00022532453,0.00016148895,0.00007868766,0.00026860015,0.000046043573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008043637,0.0008746164,0.0008166832,0.0011121501,0.00029496022,0.0008286656,0.0010317247,0.0010191377,0.00081473653],"category_scores_gemma":[0.0027218512,0.00026135423,0.00040169118,0.000572078,0.00045932605,0.0014345052,0.0008728698,0.00075231976,0.0006536352],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080268894,0.0007450906,0.010683663,0.00024196171,0.0001270829,0.00047310145,0.00017441981,0.25327218,0.055015918,0.0041342084,0.009453078,0.66487664],"study_design_scores_gemma":[0.000006026173,0.00005175741,0.0006673022,0.0000048618876,0.000009071462,0.00004063567,0.000014869121,0.9918995,0.005932636,0.0008887093,0.00047890225,0.000005786864],"about_ca_topic_score_codex":0.002935034,"about_ca_topic_score_gemma":0.0033462085,"teacher_disagreement_score":0.002935034,"about_ca_system_score_codex":0.0008688159,"about_ca_system_score_gemma":0.0006592357,"threshold_uncertainty_score":0.0063037276},"labels":[],"label_agreement":null},{"id":"W4400129865","doi":"10.1007/978-3-031-61489-7_18","title":"Applying Self-recognition Biometrics to Live Deepfake Detection in Video Conferences","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"","keywords":"Biometrics; Computer science; Artificial intelligence; Computer vision","score_opus":0.022230981941597727,"score_gpt":0.23921912825366648,"score_spread":0.21698814631206875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400129865","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44680977,0.0027715266,0.51785636,0.00031388443,0.00046641388,0.00012660846,0.00080921024,0.0028210538,0.02802509],"genre_scores_gemma":[0.87122715,0.0011312658,0.10678687,0.000110775334,0.00010088287,0.000032452273,0.0003972971,0.00014386697,0.020069333],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9998091,0.000024717332,0.000008067205,0.000041893665,0.00007757287,0.000038582035],"domain_scores_gemma":[0.9997782,0.00005266561,0.000027122707,0.000039150156,0.000086948,0.000015791353],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028163666,0.00032313014,0.00034104817,0.0011114987,0.00024996954,0.0007790004,0.00046297876,0.0007304066,0.0027570638],"category_scores_gemma":[0.00061273796,0.00014785849,0.0002581491,0.0006927067,0.00021075783,0.0007593912,0.0005006204,0.00037575027,0.0018727052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000215636,0.00012660398,0.005534749,0.00014324018,0.000028821416,0.0002234386,0.000107690634,0.0045694,0.36820602,0.0018427595,0.0028826422,0.61611897],"study_design_scores_gemma":[0.00001544591,0.00048396914,0.031887304,0.00010943994,0.00008388723,0.002028515,0.0004126039,0.41819656,0.5269945,0.0038984169,0.015810192,0.00007919215],"about_ca_topic_score_codex":0.0009952722,"about_ca_topic_score_gemma":0.0021847768,"teacher_disagreement_score":0.0027570638,"about_ca_system_score_codex":0.0002829223,"about_ca_system_score_gemma":0.00016583785,"threshold_uncertainty_score":0.009223342},"labels":[],"label_agreement":null},{"id":"W4401069923","doi":"10.1109/access.2024.3435027","title":"ChaSAM: An Architecture Based on Perceptual Hashing for Image Detection in Computer Forensics","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Hash function; Computer forensics; Digital forensics; Cryptography; Child pornography; Child sexual abuse; Cryptographic hash function; Perception; Computer security; Information retrieval; Theoretical computer science; Data mining; Sexual abuse; The Internet; World Wide Web; Poison control; Psychology","score_opus":0.02614662962249236,"score_gpt":0.29970223271430874,"score_spread":0.27355560309181637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401069923","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026574604,0.0009153141,0.9612215,0.00011197132,0.00015710201,0.00033426133,0.00008645487,0.0077518416,0.0028469416],"genre_scores_gemma":[0.4031937,0.000628449,0.5891851,0.0002719787,0.00012633405,0.00037250656,0.00036218017,0.00016874357,0.0056909206],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99934274,0.00010631637,0.0000395062,0.00012362638,0.0003120006,0.0000757813],"domain_scores_gemma":[0.99916947,0.00018646337,0.00007870591,0.00019296848,0.00031649228,0.00005595117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010736233,0.0006592564,0.0006288796,0.001792254,0.0005928803,0.0009254369,0.0023880294,0.0009352606,0.0035366374],"category_scores_gemma":[0.0020166403,0.00037583127,0.00039213523,0.00092450314,0.00064466236,0.0016108856,0.0016584299,0.0005873896,0.0017957439],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00096841407,0.0002986496,0.0029106638,0.00035297294,0.000137773,0.00020010213,0.00023158059,0.020283425,0.11335763,0.009218521,0.006543122,0.8454972],"study_design_scores_gemma":[0.00010366123,0.0010230484,0.002765043,0.00006377327,0.00010951564,0.0010077877,0.00015773305,0.8037271,0.15866208,0.00594095,0.026314825,0.0001244598],"about_ca_topic_score_codex":0.0017018262,"about_ca_topic_score_gemma":0.001716917,"teacher_disagreement_score":0.0035366374,"about_ca_system_score_codex":0.00058672094,"about_ca_system_score_gemma":0.0009443257,"threshold_uncertainty_score":0.011831224},"labels":[],"label_agreement":null},{"id":"W4401214906","doi":"10.1007/s42979-024-03105-8","title":"Cyber Security Focused Deepfake Detection System Using Big Data","year":2024,"lang":"en","type":"article","venue":"SN Computer Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"New York Institute of Technology","funders":"","keywords":"Computer science; Big data; Deep learning; Artificial intelligence; Convolutional neural network; Data science; Machine learning; Frame (networking); Resource (disambiguation); Recurrent neural network; Face (sociological concept); Artificial neural network; Data mining","score_opus":0.05037629488268712,"score_gpt":0.2585827877599457,"score_spread":0.20820649287725856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401214906","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5193754,0.0018971643,0.41017517,0.0017903433,0.0010577532,0.0007119884,0.008879695,0.03274218,0.023370318],"genre_scores_gemma":[0.91609365,0.0003037276,0.06865631,0.0006149,0.00015964235,0.00016281911,0.0038054218,0.00017700196,0.010026539],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995553,0.000043845514,0.00003333015,0.000099174336,0.00018027631,0.000087970664],"domain_scores_gemma":[0.99911755,0.00013136456,0.00011299047,0.00021453196,0.00034570205,0.00007780533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005117311,0.0008458501,0.00055504567,0.0024246098,0.00061199034,0.0008684058,0.00081593456,0.0007626143,0.002728337],"category_scores_gemma":[0.0011550785,0.00024726518,0.0003141623,0.00071783544,0.00021086779,0.0015734147,0.0012524567,0.00059366116,0.0013954219],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001427343,0.00095832447,0.09448969,0.00045915926,0.00029797916,0.0016083182,0.00028799937,0.012219004,0.10013699,0.003595465,0.04937384,0.73514587],"study_design_scores_gemma":[0.000109716704,0.0006671799,0.048820596,0.00012206653,0.0002709164,0.0020086216,0.0005725267,0.68739754,0.21124668,0.01364561,0.03496143,0.00017712453],"about_ca_topic_score_codex":0.00094793824,"about_ca_topic_score_gemma":0.0023357314,"teacher_disagreement_score":0.002728337,"about_ca_system_score_codex":0.00029350515,"about_ca_system_score_gemma":0.00069117785,"threshold_uncertainty_score":0.0091272},"labels":[],"label_agreement":null},{"id":"W4401752674","doi":"10.1109/eurosp60621.2024.00011","title":"Fingerprinting Image-to-Image Generative Adversarial Networks","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Adversarial system; Computer science; Image (mathematics); Generative grammar; Artificial intelligence; Computer vision; Pattern recognition (psychology); Generative adversarial network","score_opus":0.007303655993452783,"score_gpt":0.23284505661188706,"score_spread":0.22554140061843428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401752674","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023450274,0.00014111129,0.97394615,0.00013459887,0.00003169218,0.000025366417,0.000027277647,0.0004782035,0.0017653501],"genre_scores_gemma":[0.90280396,0.00020020793,0.09259684,0.00022921074,0.00003694683,0.000048542355,0.000087796216,0.00009151129,0.0039050807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999426,0.00018304338,0.000016657414,0.00012356395,0.00016824194,0.00008253165],"domain_scores_gemma":[0.998835,0.0006099531,0.00012649271,0.00029448242,0.000093775845,0.000040300347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011379339,0.0007640746,0.0006240071,0.00033765673,0.00022881255,0.00051479024,0.00091901195,0.000837236,0.0014446457],"category_scores_gemma":[0.00330327,0.0003013383,0.00053175236,0.00025728397,0.0012730288,0.0010119186,0.0014802665,0.001541107,0.00042170653],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015609928,0.000052133048,0.001121878,0.0000631566,0.00006062484,0.00020721252,0.000084044616,0.8537628,0.018759288,0.03841593,0.0016262326,0.085690685],"study_design_scores_gemma":[0.0000026104406,0.000016105074,0.00008416362,0.0000037529805,0.00000449092,0.000043680666,0.000004101754,0.98998624,0.003946408,0.00556838,0.00033606502,0.0000040233554],"about_ca_topic_score_codex":0.00075663143,"about_ca_topic_score_gemma":0.0007450756,"teacher_disagreement_score":0.0014446457,"about_ca_system_score_codex":0.0005451602,"about_ca_system_score_gemma":0.00035346235,"threshold_uncertainty_score":0.006017983},"labels":[],"label_agreement":null},{"id":"W4401825518","doi":"10.18280/ria.380407","title":"Unmasking Deepfakes: Advances in Fake Video Detection","year":2024,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.018206696774021907,"score_gpt":0.26089951496117986,"score_spread":0.24269281818715796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401825518","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10176743,0.022630986,0.8451086,0.008182858,0.0008033474,0.00022382181,0.000462853,0.0019887798,0.018831346],"genre_scores_gemma":[0.73319304,0.010313433,0.24777266,0.0011141524,0.00057295256,0.00009307995,0.0005193905,0.00020964329,0.0062116683],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99662775,0.0011306152,0.00013236655,0.00046207252,0.0014264632,0.00022072508],"domain_scores_gemma":[0.9794276,0.012374713,0.0021759274,0.0029789857,0.002603231,0.00043970326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00433981,0.0012413758,0.0008867701,0.0035221884,0.0009986901,0.0036087565,0.0015631388,0.002506233,0.0021185544],"category_scores_gemma":[0.029346224,0.00058220566,0.00061844103,0.0012329057,0.0021849452,0.006352241,0.0025480422,0.0030497713,0.0011734784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025201586,0.00020685827,0.010486721,0.0008610394,0.00014881066,0.00031706408,0.00090349943,0.037570603,0.016737457,0.032598987,0.008976477,0.89094055],"study_design_scores_gemma":[0.00003630781,0.0005023894,0.009959334,0.0008695496,0.0001290305,0.002467919,0.0009321008,0.78865296,0.05932566,0.080083214,0.05681629,0.00022537529],"about_ca_topic_score_codex":0.0020242927,"about_ca_topic_score_gemma":0.0021360393,"teacher_disagreement_score":0.00433981,"about_ca_system_score_codex":0.0012412032,"about_ca_system_score_gemma":0.0008896344,"threshold_uncertainty_score":0.022951424},"labels":[],"label_agreement":null},{"id":"W4402159673","doi":"10.1109/icc51166.2024.10622796","title":"Subject Identification Using Behavioral Cues and Machine Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Computer science; Artificial intelligence; Subject (documents); Machine learning; World Wide Web","score_opus":0.03664372111783929,"score_gpt":0.28526580277748215,"score_spread":0.24862208165964286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402159673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26592425,0.0034390087,0.7132075,0.00048916944,0.00043723173,0.00030255644,0.0012040496,0.0040442245,0.010952055],"genre_scores_gemma":[0.88226813,0.0009901491,0.10939862,0.0002487935,0.00022644139,0.00016093033,0.0013282471,0.00013036861,0.0052482747],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991412,0.00023162656,0.0000505839,0.00025756625,0.00021399555,0.000104944615],"domain_scores_gemma":[0.99920493,0.00032535987,0.00012814696,0.00007629816,0.00019865515,0.00006652978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006912424,0.00080270786,0.0008791835,0.0021110484,0.00023020692,0.0007096302,0.0004522372,0.00056715676,0.0018477822],"category_scores_gemma":[0.00214834,0.00019510665,0.00064154726,0.0011753395,0.000343957,0.0008029726,0.00065499113,0.00038040077,0.0015106415],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046563317,0.00039177467,0.030915977,0.00043181318,0.00016823974,0.00040389725,0.00026167973,0.038215067,0.052005634,0.0016095414,0.0032419674,0.8718888],"study_design_scores_gemma":[0.000016900503,0.00043031687,0.078090735,0.00010481925,0.0000901426,0.0006561614,0.00028876815,0.8835848,0.025743421,0.005684746,0.0052328794,0.000076359654],"about_ca_topic_score_codex":0.002517307,"about_ca_topic_score_gemma":0.0034920007,"teacher_disagreement_score":0.002517307,"about_ca_system_score_codex":0.00031756723,"about_ca_system_score_gemma":0.0004010874,"threshold_uncertainty_score":0.006181419},"labels":[],"label_agreement":null},{"id":"W4402464101","doi":"10.11159/mvml24.115","title":"Development of a Multimodal Framework for Deepfake Detection: Combining Visual and Audio Analysis","year":2024,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Audio visual; Audio analyzer; Speech recognition; Artificial intelligence; Human–computer interaction; Multimedia; Audio signal processing; Audio signal; Speech coding","score_opus":0.006963104688251368,"score_gpt":0.22695248332594575,"score_spread":0.21998937863769438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402464101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06604612,0.0025130715,0.90284806,0.00079990976,0.00034946136,0.0003883069,0.0031535202,0.014727656,0.009173915],"genre_scores_gemma":[0.57127976,0.0010236154,0.40346524,0.0007173921,0.00017016835,0.00044480886,0.0072659054,0.0003244697,0.015308647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945194,0.000078452875,0.000025077652,0.00015770167,0.00015943329,0.0001274699],"domain_scores_gemma":[0.9995371,0.000105080755,0.000050466257,0.00009933809,0.00016028312,0.00004771733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006890719,0.0018127812,0.0009875845,0.0018584542,0.0003792043,0.0009855626,0.0015332147,0.0012146003,0.0038420546],"category_scores_gemma":[0.0019757363,0.0003414887,0.0008860792,0.00075895817,0.00040543114,0.0015199134,0.001951213,0.001621106,0.0019800891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004646678,0.00038613682,0.003992135,0.00027496627,0.00019599464,0.0002980154,0.00009277594,0.0527626,0.041836124,0.003098564,0.018363817,0.8782343],"study_design_scores_gemma":[0.000029086843,0.00017732025,0.0025566744,0.00006155718,0.00005636863,0.00030611292,0.00006698826,0.95430154,0.02953534,0.0050030528,0.007868168,0.00003777851],"about_ca_topic_score_codex":0.0054499283,"about_ca_topic_score_gemma":0.00956433,"teacher_disagreement_score":0.0054499283,"about_ca_system_score_codex":0.0006863575,"about_ca_system_score_gemma":0.0009051498,"threshold_uncertainty_score":0.012852967},"labels":[],"label_agreement":null},{"id":"W4402830630","doi":"10.1109/tcad.2024.3468016","title":"Interpretable CNN-Based Lithographic Hotspot Detection Through Error Marker Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Hotspot (geology); Computer science; Artificial intelligence; Lithography; Pattern recognition (psychology); Optics; Physics; Geophysics","score_opus":0.026920212640926405,"score_gpt":0.23475099731477128,"score_spread":0.2078307846738449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402830630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15714037,0.0005357267,0.83367735,0.00024699437,0.00008058629,0.00006294678,0.0003661127,0.0053136786,0.0025762967],"genre_scores_gemma":[0.8536929,0.0002832973,0.1413577,0.00013043244,0.000028911505,0.000053672746,0.0008362479,0.00022259766,0.003394298],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997483,0.000030567222,0.000014969736,0.00007524971,0.000093255665,0.00003772749],"domain_scores_gemma":[0.9994211,0.00016696498,0.00011818122,0.00013092339,0.00014327093,0.000019482606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039168855,0.0010560876,0.00049179216,0.0009565236,0.00016688208,0.00056854065,0.0011902319,0.0005246196,0.0016048889],"category_scores_gemma":[0.0018394347,0.00033179254,0.0004092211,0.0003819451,0.00038460505,0.00079284125,0.0008833105,0.0005802775,0.00045929343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045215877,0.00010290144,0.011314659,0.00024915606,0.00011834985,0.00087348104,0.00022754366,0.33139682,0.06548122,0.004314354,0.0043849503,0.5810845],"study_design_scores_gemma":[0.0000064281276,0.000039442788,0.0014311317,0.000014448702,0.000024823408,0.00014590542,0.00002324973,0.9616054,0.032832302,0.0026002186,0.0012671527,0.000009532419],"about_ca_topic_score_codex":0.0017559294,"about_ca_topic_score_gemma":0.003317319,"teacher_disagreement_score":0.0017559294,"about_ca_system_score_codex":0.0005452143,"about_ca_system_score_gemma":0.0004901838,"threshold_uncertainty_score":0.0053688884},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.031050174410516287,"score_gpt":0.24915293231636038,"score_spread":0.2181027579058441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402964300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054690197,0.001465824,0.90914726,0.0018456851,0.00035447595,0.00031264083,0.0012695411,0.022901649,0.008012665],"genre_scores_gemma":[0.6360203,0.0006778873,0.350332,0.0014530191,0.00016030831,0.00025504892,0.002944566,0.0006180557,0.0075388188],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99909186,0.00016155421,0.000040018294,0.00017557362,0.0004121994,0.0001187329],"domain_scores_gemma":[0.9985373,0.00040425523,0.0002081785,0.0004355223,0.00028271828,0.00013204316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014226333,0.0011207552,0.0005879807,0.0017438451,0.000534445,0.0017719319,0.0017979695,0.0015769257,0.002296607],"category_scores_gemma":[0.0045188977,0.0004837513,0.0005413727,0.0007254301,0.0010996615,0.0033816933,0.00393154,0.0024996581,0.0010972003],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009526595,0.00088179734,0.019578153,0.00050901965,0.00052163017,0.000766148,0.00047258215,0.09346902,0.04346082,0.03897348,0.070840396,0.72957426],"study_design_scores_gemma":[0.000048840197,0.0002094938,0.0021893207,0.000053434036,0.00003258669,0.0003432215,0.00008370618,0.90920645,0.034636065,0.038982403,0.014161029,0.000053449377],"about_ca_topic_score_codex":0.0013637149,"about_ca_topic_score_gemma":0.0025244781,"teacher_disagreement_score":0.002296607,"about_ca_system_score_codex":0.0008744602,"about_ca_system_score_gemma":0.0012138671,"threshold_uncertainty_score":0.00768286},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08163808677441459,"score_gpt":0.34300358626874244,"score_spread":0.26136549949432786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403221680","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011101342,0.79236025,0.1646719,0.0059622205,0.0013003165,0.00030529432,0.0010272923,0.0011581618,0.022113245],"genre_scores_gemma":[0.12321983,0.80217695,0.061198562,0.0024583165,0.0022515743,0.00026199996,0.0027051724,0.00039662168,0.0053309244],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99332845,0.0017138729,0.0005780734,0.0013169575,0.0027344131,0.00032826993],"domain_scores_gemma":[0.9574715,0.031209212,0.0019944953,0.002326206,0.006634526,0.00036410807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009055037,0.002481789,0.0022013132,0.010649219,0.0010070144,0.0036053292,0.0037779303,0.002819199,0.004024037],"category_scores_gemma":[0.047316793,0.0013183149,0.0016264266,0.0055308095,0.001950825,0.008830711,0.0027413617,0.0022087777,0.003258817],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007333967,0.00007143547,0.008127249,0.007519667,0.00018151083,0.00015088127,0.00030631662,0.006032055,0.0006991279,0.01434555,0.026754763,0.9357379],"study_design_scores_gemma":[0.00004564188,0.0006973318,0.017206857,0.024325844,0.0013236327,0.00761892,0.0028734738,0.073270455,0.013002882,0.10404654,0.7551632,0.00042512064],"about_ca_topic_score_codex":0.0031774126,"about_ca_topic_score_gemma":0.0027001642,"teacher_disagreement_score":0.010649219,"about_ca_system_score_codex":0.0014625201,"about_ca_system_score_gemma":0.0030892966,"threshold_uncertainty_score":0.04788816},"labels":[],"label_agreement":null},{"id":"W4403534917","doi":"10.1109/codit62066.2024.10708133","title":"On Securing Sensitive Data Using Deep Convolutional Autoencoders","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.04183970875315974,"score_gpt":0.2807442373835023,"score_spread":0.23890452863034256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403534917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20762026,0.0021209088,0.7820487,0.00048914226,0.00015431858,0.000072649535,0.0001316605,0.0018388329,0.0055235373],"genre_scores_gemma":[0.9012788,0.0011999125,0.09132224,0.0001988385,0.00004446323,0.000033924014,0.00022080685,0.000050162846,0.005650804],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997707,0.000040212883,0.000012752739,0.000038759335,0.00009165664,0.00004595544],"domain_scores_gemma":[0.999398,0.00029952027,0.000064591906,0.00007759868,0.00014172589,0.00001853873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006007147,0.00068700337,0.0004029747,0.00046058724,0.00018163255,0.0004464666,0.0004560448,0.00066529424,0.00093741325],"category_scores_gemma":[0.0014007997,0.00023149145,0.00042974294,0.00032131738,0.00043848506,0.00091664505,0.00043787528,0.0007742325,0.00032461778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019977917,0.000113087284,0.0015498801,0.00009391918,0.0001100191,0.00014184715,0.000050574312,0.78498554,0.026664322,0.0048638904,0.00093595864,0.18029127],"study_design_scores_gemma":[0.0000017454585,0.000037469683,0.0002622346,0.000008126449,0.000009358144,0.000029926703,0.0000041423827,0.99273866,0.0061156116,0.00053675484,0.00025107383,0.0000048379598],"about_ca_topic_score_codex":0.0065614823,"about_ca_topic_score_gemma":0.0064471676,"teacher_disagreement_score":0.0065614823,"about_ca_system_score_codex":0.0006194684,"about_ca_system_score_gemma":0.0006426904,"threshold_uncertainty_score":0.013046563},"labels":[],"label_agreement":null},{"id":"W4403535153","doi":"10.1109/codit62066.2024.10708195","title":"The Good and Bad Seeds of CNN Parallelization in Forensic Facial Recognition","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Computer science; Facial recognition system; Forensic science; Artificial intelligence; Speech recognition; Parallel computing; Pattern recognition (psychology); History; Archaeology","score_opus":0.01201550011681762,"score_gpt":0.22107229962432706,"score_spread":0.20905679950750944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403535153","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58036715,0.0024860464,0.39909852,0.0018380515,0.00045510475,0.00031090432,0.00052156625,0.004909784,0.010012913],"genre_scores_gemma":[0.90945566,0.000575134,0.0862028,0.00025969595,0.00006624586,0.00012882453,0.00066044356,0.0002848296,0.002366334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991037,0.0002431827,0.00007658946,0.0002884827,0.00017333204,0.0001147471],"domain_scores_gemma":[0.99659735,0.0012875118,0.00027887477,0.0011692581,0.00055950513,0.00010759765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020802836,0.0014339718,0.00063836714,0.00051629957,0.0006836932,0.0011879818,0.0011684485,0.0007591246,0.0029801982],"category_scores_gemma":[0.012363227,0.00049575494,0.000578367,0.00062476494,0.00094738434,0.0024099995,0.0012265057,0.0015025195,0.0013283209],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014815276,0.0004403311,0.014927923,0.00036462696,0.0002686963,0.0006771866,0.00029843603,0.39833474,0.06827664,0.00918017,0.0076665403,0.49808317],"study_design_scores_gemma":[0.000061634106,0.0004225939,0.0045612315,0.000062782994,0.000109200904,0.0005529388,0.00018766007,0.90365475,0.06890704,0.01394989,0.007496852,0.000033508255],"about_ca_topic_score_codex":0.003715215,"about_ca_topic_score_gemma":0.0063939556,"teacher_disagreement_score":0.003715215,"about_ca_system_score_codex":0.0007506197,"about_ca_system_score_gemma":0.0009809233,"threshold_uncertainty_score":0.011001706},"labels":[],"label_agreement":null},{"id":"W4405062478","doi":"10.1080/09332480.2024.2434437","title":"The Use of Unstructured Data to Study Police Use of Force","year":2024,"lang":"en","type":"article","venue":"CHANCE","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Unstructured data; Use of force; Computer science; Data science; Data mining; Big data; Political science; Law","score_opus":0.14676188945169436,"score_gpt":0.30922440882926244,"score_spread":0.1624625193775681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405062478","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38964292,0.009151633,0.47456273,0.022677243,0.0013962712,0.0016467165,0.0154992,0.0005395188,0.08488384],"genre_scores_gemma":[0.81621635,0.0037051747,0.16917597,0.0018315498,0.0005808149,0.00079926394,0.004329287,0.00014971137,0.0032119877],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9896745,0.006376809,0.00052310794,0.0006731181,0.002512916,0.00023949309],"domain_scores_gemma":[0.9198306,0.06115891,0.006258564,0.007520523,0.004260189,0.0009712168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007058948,0.0004297669,0.00040670976,0.009675949,0.0018335616,0.0038857812,0.00087424985,0.0014127817,0.001197923],"category_scores_gemma":[0.03473731,0.00027741454,0.00042559038,0.009403413,0.0038618867,0.0047559263,0.0032916367,0.0016239964,0.000353827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039835396,0.00048887986,0.20592248,0.0020329193,0.0003524919,0.0033631818,0.04474379,0.014432684,0.005090647,0.3172084,0.02943432,0.37653178],"study_design_scores_gemma":[0.000059844228,0.00047448685,0.08025462,0.0037189713,0.00015875095,0.004630794,0.07152677,0.04195841,0.007162317,0.4760799,0.31365764,0.00031747538],"about_ca_topic_score_codex":0.0036986612,"about_ca_topic_score_gemma":0.005489665,"teacher_disagreement_score":0.009675949,"about_ca_system_score_codex":0.0010802267,"about_ca_system_score_gemma":0.0019226924,"threshold_uncertainty_score":0.03733176},"labels":[],"label_agreement":null},{"id":"W4405180694","doi":"10.1016/j.neucom.2024.129116","title":"Exploring the Landscape of Compressed DeepFakes: Generation, Dataset and Detection","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor; University of New Brunswick; Canadian Wood Council","funders":"Harrison McCain Foundation; New Brunswick Innovation Foundation","keywords":"Computer science; Compressed sensing; Artificial intelligence","score_opus":0.06597217717459004,"score_gpt":0.24114027855834197,"score_spread":0.17516810138375194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405180694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74006647,0.0036029157,0.21824412,0.006098736,0.00074645045,0.00018423844,0.011518049,0.011763033,0.00777607],"genre_scores_gemma":[0.8600051,0.00060030835,0.11489154,0.0005070641,0.00015565801,0.00008913771,0.018949376,0.00058266724,0.004219206],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905115,0.00021373661,0.00003744791,0.00021175075,0.00033880686,0.00014718495],"domain_scores_gemma":[0.9956131,0.0021430654,0.00014251882,0.0008995518,0.0010006703,0.00020113736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019370238,0.00087858894,0.000562102,0.0019517767,0.0007249256,0.0014407357,0.00179488,0.0014273124,0.0019668345],"category_scores_gemma":[0.012139281,0.00032890614,0.0005126836,0.0011090065,0.0007908549,0.002401788,0.001491589,0.0015014661,0.0007362963],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022136206,0.00075157866,0.021983061,0.00057707285,0.00018161589,0.0006805049,0.0004964835,0.22282009,0.037065,0.024952045,0.08874169,0.59953725],"study_design_scores_gemma":[0.000058374273,0.00018284521,0.00381669,0.00004922005,0.000028054797,0.0003286747,0.0002076891,0.9467314,0.016029285,0.023837917,0.008692506,0.000037375783],"about_ca_topic_score_codex":0.011536347,"about_ca_topic_score_gemma":0.022772113,"teacher_disagreement_score":0.011536347,"about_ca_system_score_codex":0.0010870704,"about_ca_system_score_gemma":0.0013923163,"threshold_uncertainty_score":0.02293843},"labels":[],"label_agreement":null},{"id":"W4405795762","doi":"10.1007/978-981-97-4892-1_5","title":"Examinations of Offline Signature Forgery Detection from Classical to Deep Learning Techniques","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Hyperion Technologies (Canada)","funders":"","keywords":"Signature (topology); Computer science; Artificial intelligence; Online and offline; Deep learning; Pattern recognition (psychology); Mathematics; Operating system; Geometry","score_opus":0.008903342565731446,"score_gpt":0.2121837486552739,"score_spread":0.20328040608954245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405795762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35608953,0.004885351,0.58697164,0.0017024226,0.00036420755,0.000106666994,0.00040733835,0.0022887287,0.047184218],"genre_scores_gemma":[0.8792911,0.0012364452,0.10438436,0.00016378135,0.00017694401,0.000028190398,0.00046805548,0.0001942553,0.014056853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975593,0.00067654415,0.000107736225,0.0003484504,0.0011055392,0.00020231854],"domain_scores_gemma":[0.9858423,0.008259177,0.0006332323,0.0027355491,0.002305426,0.00022436024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036685523,0.00084479,0.0006217248,0.0015584448,0.0005806687,0.002177508,0.0013611095,0.0013811365,0.0054132915],"category_scores_gemma":[0.017198708,0.00032970135,0.00054033747,0.000851984,0.0011974981,0.004152285,0.0015744675,0.0016880962,0.0014762938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017715878,0.0004605149,0.012533891,0.0003727283,0.00015495085,0.0004133938,0.000303329,0.084333785,0.0305219,0.07264538,0.00828709,0.78820145],"study_design_scores_gemma":[0.000024247158,0.0003956498,0.0052323593,0.00011716502,0.000056324796,0.00059256813,0.0001755872,0.89907867,0.04675793,0.043670554,0.0038611216,0.00003792038],"about_ca_topic_score_codex":0.0009407485,"about_ca_topic_score_gemma":0.0012338808,"teacher_disagreement_score":0.0054132915,"about_ca_system_score_codex":0.0011643748,"about_ca_system_score_gemma":0.0011188431,"threshold_uncertainty_score":0.019401371},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.008676008576843905,"score_gpt":0.24376575044458854,"score_spread":0.23508974186774462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405843673","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24735413,0.0017034456,0.7295285,0.0021131358,0.00025069623,0.0002408508,0.00066957227,0.009014063,0.009125569],"genre_scores_gemma":[0.7904207,0.0004412957,0.20413601,0.00024979023,0.00007239389,0.00010067031,0.0007112767,0.00023951496,0.0036282637],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998694,0.00024200807,0.00008410454,0.00033054996,0.00044355248,0.00020585218],"domain_scores_gemma":[0.9945528,0.0030791196,0.0002498713,0.0010860302,0.00091211376,0.00012013699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021616668,0.0013079658,0.0009629146,0.0012957569,0.0005851162,0.0015153844,0.0018468484,0.0017554191,0.0054107634],"category_scores_gemma":[0.018503116,0.000521075,0.00057919614,0.0007913682,0.0007593366,0.0036592064,0.002384676,0.001857006,0.002337698],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013453738,0.00039129934,0.006850128,0.00039899646,0.00010883527,0.0005596697,0.00024031571,0.15496518,0.07900387,0.015411164,0.009868066,0.7308571],"study_design_scores_gemma":[0.000059427013,0.00011743658,0.0011759965,0.000024358,0.000018454226,0.00025839903,0.00007034992,0.953941,0.032678753,0.009168449,0.0024700386,0.000017365397],"about_ca_topic_score_codex":0.004372698,"about_ca_topic_score_gemma":0.007127847,"teacher_disagreement_score":0.0054107634,"about_ca_system_score_codex":0.0008790826,"about_ca_system_score_gemma":0.0016907878,"threshold_uncertainty_score":0.018100798},"labels":[],"label_agreement":null},{"id":"W4406016334","doi":"10.18280/ijsse.140606","title":"Convolutional Neural Network to Detect the Secret Data in the Spatial Domain Images","year":2024,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Institut Teknologi Sepuluh Nopember","keywords":"Convolutional neural network; Computer science; Artificial intelligence; Domain (mathematical analysis); Spatial analysis; Pattern recognition (psychology); Remote sensing; Geography; Mathematics","score_opus":0.008076807317637642,"score_gpt":0.23128378061841337,"score_spread":0.22320697330077574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406016334","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3492865,0.002016191,0.6371564,0.0006192622,0.00033102283,0.00007014858,0.00067133055,0.0018375651,0.00801146],"genre_scores_gemma":[0.90353143,0.0008621066,0.08347135,0.00014262598,0.00007098969,0.000026465834,0.000785437,0.000054126558,0.011055457],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9998827,0.0000102934855,0.0000053405925,0.000024570847,0.00004586789,0.000031135733],"domain_scores_gemma":[0.99982786,0.000045289587,0.000018375225,0.000023696497,0.00007329784,0.000011444516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024742953,0.00046350734,0.00031725765,0.0005846836,0.00015019959,0.0003185442,0.0004656046,0.00043401337,0.0012869653],"category_scores_gemma":[0.00053670316,0.0001828449,0.00037889552,0.00044757265,0.00019908135,0.00041688434,0.0004012702,0.0005732455,0.00037876877],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00078537123,0.0003980677,0.0051229806,0.00015975359,0.0002690706,0.00031825405,0.000060834747,0.2213762,0.13144797,0.005926275,0.006838632,0.6272966],"study_design_scores_gemma":[0.0000050076833,0.00003305216,0.0011041197,0.0000050071767,0.000024611192,0.00004283554,0.000005588723,0.98497665,0.012709424,0.00054330507,0.0005456913,0.0000047277063],"about_ca_topic_score_codex":0.007992938,"about_ca_topic_score_gemma":0.010545766,"teacher_disagreement_score":0.007992938,"about_ca_system_score_codex":0.00042394822,"about_ca_system_score_gemma":0.00058916135,"threshold_uncertainty_score":0.015892804},"labels":[],"label_agreement":null},{"id":"W4406499763","doi":"10.1109/cascon62161.2024.10838130","title":"Integrating Feature Selection in Counterfactual Generation: An Optimized Framework Using Simulated Annealing","year":2024,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Counterfactual thinking; Computer science; Simulated annealing; Feature selection; Artificial intelligence; Selection (genetic algorithm); Machine learning; Pattern recognition (psychology)","score_opus":0.03052974926972293,"score_gpt":0.30140939110442344,"score_spread":0.27087964183470054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406499763","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006805821,0.00012207327,0.99169475,0.00025276444,0.000024020486,0.000113384536,0.000037865502,0.00023531831,0.00071407453],"genre_scores_gemma":[0.4016526,0.00018582513,0.59524965,0.0003420601,0.00008386682,0.0007582779,0.00023242713,0.00019218994,0.0013031263],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956785,0.0029298584,0.00015915568,0.00054618716,0.0004741367,0.00021216173],"domain_scores_gemma":[0.97784925,0.018599141,0.0009415266,0.0013195073,0.0009949198,0.000295621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010229846,0.0016155366,0.0021134326,0.0017572958,0.0008287786,0.0021267466,0.0032300318,0.0022061153,0.0036715777],"category_scores_gemma":[0.032056455,0.0011704074,0.0017349297,0.001008884,0.0023950292,0.0020583244,0.002721771,0.0030272393,0.0004229854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009315703,0.000055787204,0.0010292424,0.00007271341,0.000097470605,0.00010347263,0.00013946582,0.9296553,0.0005517564,0.04339018,0.00044974053,0.024361642],"study_design_scores_gemma":[0.000015108167,0.000018484046,0.000057337216,0.00000947025,0.000011597927,0.000010455804,0.000008460281,0.9813918,0.00022278195,0.017973136,0.0002743125,0.000007041325],"about_ca_topic_score_codex":0.004651428,"about_ca_topic_score_gemma":0.0045348722,"teacher_disagreement_score":0.010229846,"about_ca_system_score_codex":0.0019237859,"about_ca_system_score_gemma":0.0029561862,"threshold_uncertainty_score":0.05410123},"labels":[],"label_agreement":null},{"id":"W4407238156","doi":"10.1111/1556-4029.15703","title":"Examination of customized questioned digital documents","year":2025,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"University of Winnipeg","keywords":"Digitization; Computer science; Data science; Digital forensics; Process (computing); Domain (mathematical analysis); Field (mathematics); Perspective (graphical); Recreation; Globe; World Wide Web; Information retrieval; Computer security; Artificial intelligence; Law","score_opus":0.009629577846445546,"score_gpt":0.26288242800091793,"score_spread":0.2532528501544724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407238156","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6053389,0.0009546162,0.3762864,0.00059954775,0.00013103591,0.0004529869,0.000531808,0.0010263487,0.014678399],"genre_scores_gemma":[0.7397568,0.00043000528,0.25151718,0.00020377629,0.000030346613,0.000064109074,0.00044642572,0.00017289685,0.0073785433],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982077,0.0003916961,0.0001398172,0.0004473359,0.00070552726,0.00010791138],"domain_scores_gemma":[0.99164623,0.003280009,0.00075072097,0.0024820203,0.0016749412,0.00016596433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015504261,0.00023699764,0.00032157174,0.0014527783,0.0006743637,0.0019910983,0.00075125054,0.00087113905,0.0026961903],"category_scores_gemma":[0.009144214,0.00018175747,0.0003079403,0.0010558038,0.0009248987,0.0018447012,0.0017948698,0.0006103113,0.0008183078],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009209003,0.00019607136,0.030192005,0.0010144284,0.0000736904,0.004668229,0.010837016,0.008151643,0.2099183,0.026623722,0.0042110956,0.703193],"study_design_scores_gemma":[0.000090613146,0.00066424004,0.069558695,0.00058470585,0.00016984958,0.018672422,0.015903892,0.13786913,0.5975227,0.033473626,0.12522718,0.00026297814],"about_ca_topic_score_codex":0.000525671,"about_ca_topic_score_gemma":0.00084479246,"teacher_disagreement_score":0.0026961903,"about_ca_system_score_codex":0.0005161554,"about_ca_system_score_gemma":0.00047341053,"threshold_uncertainty_score":0.009019613},"labels":[],"label_agreement":null},{"id":"W4407417126","doi":"10.69525/jasqde.107","title":"Methods of Forgery in Counterfeit Travel Documents","year":2004,"lang":"en","type":"article","venue":"Journal of the American Society of Questioned Document Examiners","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Counterfeit; Advertising; Internet privacy; Computer security; Business; Computer science; History; Archaeology","score_opus":0.014502944342212564,"score_gpt":0.30989445523552006,"score_spread":0.2953915108933075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407417126","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49323288,0.012998152,0.45308352,0.0009554507,0.00032506674,0.0011523551,0.00044827393,0.0008544006,0.036949888],"genre_scores_gemma":[0.72212327,0.003573784,0.25565156,0.0001608162,0.00006206584,0.00022302539,0.00014378154,0.00010776681,0.017953888],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99585706,0.0013666895,0.0002768898,0.00058574317,0.0016356647,0.00027796952],"domain_scores_gemma":[0.9909533,0.0035898606,0.0010908169,0.0031597659,0.001096746,0.000109468536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035369804,0.00070665707,0.0005448031,0.0047173863,0.0015860111,0.0028135132,0.0012073744,0.0014712275,0.0024485176],"category_scores_gemma":[0.013718849,0.0005362777,0.0005483478,0.0017781529,0.0022582125,0.003128463,0.0021866206,0.0008944447,0.0012091991],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000886551,0.0002707662,0.02842984,0.0016396433,0.0002289288,0.0027317693,0.020599816,0.003062864,0.077088274,0.06644509,0.003824143,0.7947922],"study_design_scores_gemma":[0.00013345687,0.0015004794,0.043127123,0.0014666591,0.00036799372,0.055104926,0.010634632,0.035887226,0.6555101,0.046836138,0.14894925,0.00048202992],"about_ca_topic_score_codex":0.0004972303,"about_ca_topic_score_gemma":0.00073281856,"teacher_disagreement_score":0.0047173863,"about_ca_system_score_codex":0.00062413025,"about_ca_system_score_gemma":0.0005246571,"threshold_uncertainty_score":0.018705606},"labels":[],"label_agreement":null},{"id":"W4407926778","doi":"10.18280/ijsse.150108","title":"Deep Learning – Augmented Block Analysis for Detecting Advanced Video Forgeries","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Block (permutation group theory); Computer science; Deep learning; Artificial intelligence","score_opus":0.003370457350340036,"score_gpt":0.21858517390642382,"score_spread":0.2152147165560838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407926778","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10522897,0.0011402264,0.8885036,0.0002134684,0.00007368186,0.00009721101,0.0004402022,0.0021518338,0.002150842],"genre_scores_gemma":[0.7101097,0.00068783236,0.2829874,0.00014090762,0.00006065415,0.000069270136,0.001111627,0.00010216571,0.004730408],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966455,0.00006965569,0.000016700189,0.00007056737,0.00011723026,0.00006135047],"domain_scores_gemma":[0.9995578,0.00013055351,0.00008540795,0.00008121,0.00011646626,0.00002859815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006181281,0.0008611181,0.00062713097,0.0012668945,0.00022821665,0.0005002441,0.0006914496,0.00055465807,0.0013192458],"category_scores_gemma":[0.0013444198,0.00023244224,0.00044493776,0.0005784001,0.0003331606,0.0008523831,0.00074993406,0.00073744997,0.0008052618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007068226,0.00021235866,0.007193098,0.00016078114,0.00014233922,0.00028874137,0.00008933308,0.1482384,0.090577394,0.0044383234,0.0043890905,0.74356335],"study_design_scores_gemma":[0.000008185005,0.00010444025,0.0017657698,0.000013283762,0.000022977052,0.00013835506,0.000019411551,0.96877354,0.025352543,0.0017950019,0.0019948601,0.000011641095],"about_ca_topic_score_codex":0.0037054992,"about_ca_topic_score_gemma":0.00606025,"teacher_disagreement_score":0.0037054992,"about_ca_system_score_codex":0.00043587317,"about_ca_system_score_gemma":0.00070062897,"threshold_uncertainty_score":0.0073678493},"labels":[],"label_agreement":null},{"id":"W4408010933","doi":"10.18280/isi.300223","title":"A CNN-Based Framework for Enhancing Image Segmentation and Scene Interpretation in Fake Colorized Images: Addressing Challenges in Image Analysis and Understanding","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Interpretation (philosophy); Image (mathematics); Artificial intelligence; Computer vision; Segmentation; Computer science; Image segmentation","score_opus":0.030292849851745768,"score_gpt":0.28193157015919534,"score_spread":0.2516387203074496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408010933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032222886,0.0009322484,0.9589869,0.0004086396,0.0001709859,0.00010885059,0.00037130143,0.0025963387,0.004201795],"genre_scores_gemma":[0.40102497,0.0018126742,0.5810264,0.0005253246,0.00022398295,0.000118723256,0.0013328113,0.00043590917,0.013499237],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997311,0.000026693211,0.000008028281,0.00007862919,0.000088758374,0.000066769666],"domain_scores_gemma":[0.9997254,0.00003805934,0.000029807523,0.000046953694,0.00013212214,0.000027665477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004310388,0.0011243916,0.00071833126,0.00092858076,0.0003317385,0.0010813026,0.0015264673,0.0010289615,0.0027761448],"category_scores_gemma":[0.0007760474,0.0004494495,0.0007617761,0.0008042993,0.0004331475,0.0009474872,0.00095326966,0.0009736866,0.0010871197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003281168,0.0002573091,0.0016355647,0.00023955385,0.00022037252,0.00027889913,0.00008628883,0.12978688,0.14948164,0.0070718317,0.010151168,0.7004624],"study_design_scores_gemma":[0.0000049349965,0.00004218867,0.000632808,0.000014426404,0.000036150777,0.000098740325,0.0000141311375,0.9726943,0.022519082,0.0015884853,0.0023443715,0.00001042088],"about_ca_topic_score_codex":0.017583199,"about_ca_topic_score_gemma":0.02502634,"teacher_disagreement_score":0.017583199,"about_ca_system_score_codex":0.0008728294,"about_ca_system_score_gemma":0.0012053043,"threshold_uncertainty_score":0.0349617},"labels":[],"label_agreement":null},{"id":"W4408024913","doi":"10.1145/3721129","title":"LithoExp: Explainable Two-stage CNN-based Lithographic Hotspot Detection with Layout Defect Localization","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Design Automation of Electronic Systems","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Science Foundation of Hubei Province; National Natural Science Foundation of China","keywords":"Computer science; Hotspot (geology); Lithography; Stage (stratigraphy); Artificial intelligence; Pattern recognition (psychology); Optoelectronics; Materials science; Geology","score_opus":0.010960169906900886,"score_gpt":0.232513131831324,"score_spread":0.22155296192442311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408024913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11761091,0.00032404825,0.8688999,0.00018428496,0.000065495486,0.00010874855,0.00032669853,0.010234607,0.0022453896],"genre_scores_gemma":[0.7942302,0.00019376003,0.19992648,0.00018008515,0.000023935605,0.00008718869,0.00083000096,0.00031487452,0.0042134225],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99984944,0.000014204211,0.0000060072075,0.000046582525,0.000055407138,0.000028427245],"domain_scores_gemma":[0.99967,0.000092498005,0.00006628943,0.00009359842,0.000061287414,0.000016315036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000249971,0.00092011015,0.00034614617,0.00046188914,0.00011992931,0.00045107558,0.001402049,0.00056903646,0.002069755],"category_scores_gemma":[0.0008711544,0.0003536695,0.00046800228,0.00023312563,0.00032004277,0.0008140327,0.0007687565,0.00050511584,0.00034654638],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042674568,0.0001626257,0.009070839,0.000297538,0.00023190796,0.00070894335,0.00015485492,0.40063298,0.10606581,0.0036663548,0.00600666,0.47257468],"study_design_scores_gemma":[0.000008875985,0.000057479618,0.001685279,0.0000084915955,0.000018148103,0.000122040445,0.000011124033,0.97100407,0.024976935,0.0010760223,0.0010212612,0.0000102579725],"about_ca_topic_score_codex":0.0027681869,"about_ca_topic_score_gemma":0.005881122,"teacher_disagreement_score":0.0027681869,"about_ca_system_score_codex":0.0006396037,"about_ca_system_score_gemma":0.0005270015,"threshold_uncertainty_score":0.0069239736},"labels":[],"label_agreement":null},{"id":"W4408041597","doi":"10.18280/ts.420118","title":"A Hybrid Approach of Traditional Block-Based Deep Learning for Video Forgery Detection","year":2025,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Block (permutation group theory); Artificial intelligence; Deep learning; Computer vision; Pattern recognition (psychology); Mathematics","score_opus":0.017308701305008764,"score_gpt":0.21081651654795172,"score_spread":0.19350781524294297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408041597","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028265981,0.0009924342,0.9667976,0.00016481025,0.00013564552,0.00007562601,0.00014347682,0.0012147231,0.0022097386],"genre_scores_gemma":[0.5289057,0.0012202504,0.44819573,0.00048978906,0.00022189447,0.00016092963,0.000956748,0.00016616021,0.01968283],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994993,0.00006753913,0.00002470548,0.00011431959,0.00020041052,0.00009377935],"domain_scores_gemma":[0.9995049,0.00009903523,0.000033848115,0.00007707857,0.00024198386,0.000043169584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007174084,0.000877727,0.0010357226,0.0010814958,0.00034604076,0.0006603323,0.001400281,0.0009777294,0.0028388696],"category_scores_gemma":[0.0009355355,0.00031606967,0.00075664336,0.00073690206,0.00026277092,0.001216231,0.0012403487,0.0009669979,0.00143693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030922442,0.00032915198,0.0017339825,0.00010919679,0.00015936069,0.000076400574,0.000043633398,0.064838246,0.040559415,0.002902419,0.0039131683,0.88502586],"study_design_scores_gemma":[0.0000069099033,0.00009548229,0.0006088627,0.000008205777,0.000032488904,0.00006306584,0.000009076359,0.9880426,0.00884892,0.0009532503,0.0013209981,0.000010120303],"about_ca_topic_score_codex":0.0049449066,"about_ca_topic_score_gemma":0.008145166,"teacher_disagreement_score":0.0049449066,"about_ca_system_score_codex":0.00045017415,"about_ca_system_score_gemma":0.0010278866,"threshold_uncertainty_score":0.009832263},"labels":[],"label_agreement":null},{"id":"W4409245932","doi":"10.55041/ijsrem44082","title":"Towards Secure Audio: Deepfake Detection with CNN and LSTM Networks","year":2025,"lang":"en","type":"article","venue":"INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.013059663631614558,"score_gpt":0.2701197869948419,"score_spread":0.25706012336322737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409245932","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045259677,0.0014108715,0.94630575,0.0006584135,0.00013299385,0.000060367496,0.00017830249,0.0029813512,0.0030121997],"genre_scores_gemma":[0.7218011,0.0009902607,0.26767933,0.00051336363,0.000102592705,0.000069734466,0.0005551915,0.00011042621,0.008177884],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99968314,0.000048007183,0.000013766913,0.000078824516,0.00011510846,0.00006115446],"domain_scores_gemma":[0.9995473,0.00015802987,0.00008294989,0.000055543474,0.00012920059,0.000027046066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008144877,0.0010652229,0.00044940345,0.00088967767,0.0002542395,0.00077901565,0.0011056077,0.0010686981,0.0016765264],"category_scores_gemma":[0.0017884015,0.00038144662,0.00046077542,0.00054897164,0.0005711303,0.001464923,0.0011748457,0.001459982,0.0008386824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039288047,0.00016605157,0.0023368928,0.00016209319,0.00010372628,0.00026632292,0.00010740652,0.19751078,0.05039629,0.007086077,0.0049542915,0.73651725],"study_design_scores_gemma":[0.0000057107704,0.000041155912,0.00035905404,0.000018157327,0.000012744147,0.00005712451,0.000019028861,0.98209286,0.012400024,0.0037641644,0.0012209549,0.000009162176],"about_ca_topic_score_codex":0.00450311,"about_ca_topic_score_gemma":0.0062904293,"teacher_disagreement_score":0.00450311,"about_ca_system_score_codex":0.00094421284,"about_ca_system_score_gemma":0.0007114822,"threshold_uncertainty_score":0.00895381},"labels":[],"label_agreement":null},{"id":"W4409793555","doi":"10.61091/jcmcc127a-246","title":"Remote Image Tampering Detection Combining Deep Neural Networks","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Image (mathematics); Artificial neural network; Computer vision; Deep neural networks; Deep learning; Pattern recognition (psychology)","score_opus":0.007108687707499136,"score_gpt":0.2322582543934362,"score_spread":0.22514956668593705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409793555","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13875565,0.0013380119,0.85292137,0.0003141289,0.000088485154,0.00006978343,0.00009614421,0.0029645204,0.0034518037],"genre_scores_gemma":[0.9085966,0.0006554174,0.08698848,0.00018309518,0.00004745173,0.000050634415,0.00022140091,0.00005012174,0.0032068081],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99941075,0.00007240628,0.00003696948,0.00014389699,0.00025696386,0.00007908914],"domain_scores_gemma":[0.99944514,0.00013062386,0.000096395204,0.000067744724,0.00023490844,0.000025157968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000584536,0.0008643846,0.00072539895,0.0010546915,0.00025801107,0.00068714423,0.00096133014,0.0007107903,0.0006867802],"category_scores_gemma":[0.0015959752,0.0003470416,0.00057447376,0.00059411005,0.0003364397,0.0016327624,0.00083953195,0.00071460905,0.00028578864],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002710871,0.00024049234,0.005069017,0.00011930388,0.0001792754,0.00021504637,0.00006844984,0.18359745,0.041235123,0.0017665202,0.0020970644,0.76514125],"study_design_scores_gemma":[0.000004607126,0.000057004763,0.001061805,0.0000075138973,0.000029166486,0.000057545352,0.000011042503,0.98429596,0.012977968,0.0010809993,0.00040420852,0.00001221937],"about_ca_topic_score_codex":0.004357226,"about_ca_topic_score_gemma":0.003518682,"teacher_disagreement_score":0.004357226,"about_ca_system_score_codex":0.0008253318,"about_ca_system_score_gemma":0.0005388527,"threshold_uncertainty_score":0.008663714},"labels":[],"label_agreement":null},{"id":"W4410415687","doi":"10.47392/irjaeh.2025.0334","title":"Deep Deception Detector: Exposing AI Generated Fake Video","year":2025,"lang":"en","type":"article","venue":"International Research Journal on Advanced Engineering Hub (IRJAEH)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deception; Detector; Computer security; Internet privacy; Fake news; Computer science; Psychology; Artificial intelligence; Social psychology; Telecommunications","score_opus":0.01832153045594137,"score_gpt":0.3311018492114223,"score_spread":0.31278031875548096,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410415687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35989568,0.0014790504,0.61093843,0.0016247244,0.00063091045,0.000332876,0.0009057902,0.008494075,0.015698474],"genre_scores_gemma":[0.90158206,0.0004022102,0.09134897,0.00047245185,0.00007419267,0.00006033835,0.0004319363,0.00008772649,0.0055401246],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99919957,0.00012666515,0.00003132293,0.00013033781,0.0003804792,0.0001316784],"domain_scores_gemma":[0.9986493,0.00045411757,0.00022530007,0.00027431743,0.0003047737,0.000092187634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089126686,0.00070558646,0.00066595356,0.0009833093,0.00036194426,0.0010605105,0.0008483855,0.0011713443,0.0015305832],"category_scores_gemma":[0.004831771,0.00024021626,0.00037724842,0.00028497347,0.00046719282,0.0015874397,0.0012262331,0.0012252044,0.00088032265],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009106727,0.0004966761,0.01042835,0.00027998938,0.00017175384,0.001652139,0.00039468493,0.030546322,0.07708158,0.009967189,0.018791705,0.8492789],"study_design_scores_gemma":[0.000025581172,0.0003003652,0.0042535346,0.000078288234,0.000038984243,0.0013466596,0.00013293956,0.8919789,0.09070385,0.005268555,0.005828787,0.00004349828],"about_ca_topic_score_codex":0.0013315071,"about_ca_topic_score_gemma":0.0014544666,"teacher_disagreement_score":0.0015305832,"about_ca_system_score_codex":0.00070675876,"about_ca_system_score_gemma":0.0005111558,"threshold_uncertainty_score":0.0051279664},"labels":[],"label_agreement":null},{"id":"W4412475991","doi":"10.3390/math13142285","title":"Toward Adaptive Unsupervised and Blind Image Forgery Localization with ViT-VAE and a Gaussian Mixture Model","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"Mixture model; Computer science; Artificial intelligence; Pattern recognition (psychology); Gaussian; Convolutional neural network; Divergence (linguistics); Autoencoder; Benchmark (surveying); Expectation–maximization algorithm; Artificial neural network; Mathematics","score_opus":0.01584347309708426,"score_gpt":0.22269261030816173,"score_spread":0.20684913721107748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412475991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004189398,0.00026394826,0.9940584,0.000055352208,0.00002216796,0.000023675755,0.000030487194,0.0010114977,0.00034511762],"genre_scores_gemma":[0.22220442,0.00041722122,0.7715846,0.0003267996,0.00006310113,0.0001291456,0.00044069526,0.00027863702,0.0045554494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989097,0.00024893877,0.0000672818,0.00033640646,0.00031228148,0.00012547332],"domain_scores_gemma":[0.9987663,0.00047142818,0.00012081291,0.000287995,0.0002909952,0.00006248605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016496724,0.0014502875,0.0019318848,0.0012191847,0.00052675995,0.0011278378,0.002743358,0.0018409936,0.0017461352],"category_scores_gemma":[0.0044493135,0.0010399227,0.0014919733,0.00080843247,0.0011876763,0.002053509,0.002888794,0.0022473736,0.0013894148],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038760251,0.00014987894,0.0013803999,0.00018216303,0.00021190551,0.0001869102,0.00022605527,0.4034006,0.028325036,0.015049584,0.0044165854,0.54608333],"study_design_scores_gemma":[0.000010954064,0.000030381589,0.0001557967,0.0000099917725,0.000013595537,0.00010792082,0.000010362261,0.9865601,0.0075848843,0.0046076705,0.0008891343,0.00001930921],"about_ca_topic_score_codex":0.004374031,"about_ca_topic_score_gemma":0.0059270225,"teacher_disagreement_score":0.004374031,"about_ca_system_score_codex":0.0007344664,"about_ca_system_score_gemma":0.0015009857,"threshold_uncertainty_score":0.008724451},"labels":[],"label_agreement":null},{"id":"W4412958403","doi":"10.36548/jtcsst.2025.3.002","title":"FLIDS: Fuzzy Logic-based Framework for Interpretable Image Manipulation Detection","year":2025,"lang":"en","type":"article","venue":"Journal of Trends in Computer Science and Smart Technology","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Fuzzy logic; Artificial intelligence; Image (mathematics); Computer science; Pattern recognition (psychology); Computer vision","score_opus":0.01320203454382884,"score_gpt":0.2853001604606163,"score_spread":0.27209812591678745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412958403","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039377282,0.00017128943,0.9912009,0.00013664213,0.000032919077,0.000082387014,0.00026361656,0.0026666096,0.0015078209],"genre_scores_gemma":[0.26821426,0.00037892262,0.7248673,0.00045557765,0.0000795364,0.00024368857,0.0010764232,0.00022280599,0.0044614566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999421,0.000086885855,0.000041283787,0.00014706008,0.00025085645,0.000052824627],"domain_scores_gemma":[0.99943286,0.00018269829,0.000074657844,0.000062338164,0.00021208636,0.00003532255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011523508,0.0009649258,0.00070811016,0.0016688069,0.00039281073,0.0012680239,0.0018896223,0.0009496378,0.005416237],"category_scores_gemma":[0.0027038495,0.00037291026,0.0010553674,0.0005005458,0.0008632799,0.0014178272,0.0010517151,0.0013516145,0.0011862472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003717965,0.00019263453,0.0027107645,0.00032896112,0.00017057541,0.00035518772,0.00022625364,0.23535348,0.037960056,0.042512972,0.013277575,0.6665398],"study_design_scores_gemma":[0.000015574942,0.00006689662,0.00041377332,0.000041376697,0.000024584628,0.000103672006,0.000023214052,0.9656414,0.008839522,0.020737013,0.00406977,0.000023249191],"about_ca_topic_score_codex":0.0071590594,"about_ca_topic_score_gemma":0.009647351,"teacher_disagreement_score":0.0071590594,"about_ca_system_score_codex":0.0014236165,"about_ca_system_score_gemma":0.0013489698,"threshold_uncertainty_score":0.018119156},"labels":[],"label_agreement":null},{"id":"W4413147453","doi":"10.1109/cvpr52734.2025.02128","title":"Efficient Long Video Tokenization via Coordinate-based Patch Reconstruction","year":2025,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Samsung; Arm","keywords":"Computer science; Computer vision; Lexical analysis; Computer graphics (images); Artificial intelligence","score_opus":0.004106213569763425,"score_gpt":0.20266559609403464,"score_spread":0.19855938252427122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413147453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030116895,0.00025258807,0.96331346,0.00020107448,0.000097633005,0.000069972804,0.0002283027,0.0046149828,0.001105188],"genre_scores_gemma":[0.47220176,0.00045805686,0.51672053,0.0003169034,0.00009259592,0.0001877304,0.0020141455,0.0009991075,0.0070090983],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995672,0.000066276734,0.000022241842,0.00017990216,0.00008528658,0.000079039986],"domain_scores_gemma":[0.99898356,0.00040539316,0.00011474588,0.00027189494,0.00013568134,0.00008862783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067251973,0.0010307127,0.0010405559,0.00057501957,0.00039634728,0.0008555684,0.0016942273,0.00087679015,0.004849306],"category_scores_gemma":[0.0037027153,0.0005724326,0.0008098767,0.00067943777,0.0008734172,0.0024039175,0.0014567288,0.001848125,0.0024884215],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072178507,0.0001928179,0.0024547863,0.00020862102,0.000104986255,0.000376764,0.00020656869,0.3109451,0.05638731,0.020615187,0.01130929,0.5964768],"study_design_scores_gemma":[0.000017128936,0.000071067916,0.00020370165,0.0000093460185,0.000013785346,0.00011518807,0.000041078896,0.97481155,0.01773496,0.005003895,0.0019641486,0.000014296537],"about_ca_topic_score_codex":0.0043354686,"about_ca_topic_score_gemma":0.005551272,"teacher_disagreement_score":0.004849306,"about_ca_system_score_codex":0.0007591242,"about_ca_system_score_gemma":0.0011242598,"threshold_uncertainty_score":0.016222596},"labels":[],"label_agreement":null},{"id":"W4413179682","doi":"10.1109/netcrypt65877.2025.11102700","title":"Crime Scene Object Detection for Forensic Investigations Using Faster R-CNN and YOLOv5 Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Crime scene; Artificial intelligence; Object detection; Forensic science; Object (grammar); Computer vision; Pattern recognition (psychology); Criminology; Archaeology; History; Psychology","score_opus":0.035910285966975375,"score_gpt":0.26132362173796886,"score_spread":0.22541333577099348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413179682","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20599107,0.0034265155,0.76970476,0.0009839729,0.0004693724,0.00024303369,0.001108094,0.00814382,0.009929297],"genre_scores_gemma":[0.7598436,0.0014964481,0.22426717,0.0005238394,0.00009430952,0.00014201498,0.0023086278,0.00020154836,0.011122477],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996753,0.000040792733,0.00001883279,0.0001053795,0.000093231785,0.00006651097],"domain_scores_gemma":[0.9995591,0.00010304467,0.00007189768,0.00006774741,0.00017255815,0.000025672289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077363185,0.0011920343,0.0006568469,0.0010524703,0.0002467421,0.0009985613,0.0017274366,0.0009777509,0.0025334985],"category_scores_gemma":[0.0016544565,0.00043241048,0.0010397512,0.0004902759,0.00027220236,0.001182401,0.00075608294,0.0009332809,0.0012566294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005506542,0.0002670816,0.008013695,0.00027439118,0.0002670037,0.00030348738,0.00010055451,0.3843694,0.0244899,0.0043528317,0.008586361,0.5684247],"study_design_scores_gemma":[0.000006380523,0.00007988782,0.00095254474,0.000023838988,0.000037492187,0.000077121214,0.000015616377,0.9914346,0.0053782477,0.0006369586,0.001347289,0.00001010433],"about_ca_topic_score_codex":0.014389021,"about_ca_topic_score_gemma":0.016655307,"teacher_disagreement_score":0.014389021,"about_ca_system_score_codex":0.0012484565,"about_ca_system_score_gemma":0.0010777792,"threshold_uncertainty_score":0.028610528},"labels":[],"label_agreement":null},{"id":"W4413211245","doi":"10.1007/978-3-031-94962-3_2","title":"Leveraging Bayer Pattern Analysis for Authenticity Detection of Real and Fake Images","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; Artificial intelligence","score_opus":0.02760109058008395,"score_gpt":0.2741720442620276,"score_spread":0.24657095368194368,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413211245","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09890573,0.00096791226,0.88831526,0.000324006,0.0001684408,0.00010836924,0.00023539433,0.0024588786,0.008516016],"genre_scores_gemma":[0.56031364,0.0011268579,0.42569515,0.00020970839,0.00014703172,0.000058251386,0.00056558044,0.00028705006,0.01159677],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9993468,0.00006928037,0.000026941461,0.000106757136,0.00038059716,0.000069603084],"domain_scores_gemma":[0.9989329,0.00031689781,0.00015608071,0.0002773784,0.00027616002,0.00004055294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057520706,0.000697131,0.0006313364,0.0021098745,0.00034720742,0.0012840084,0.0007028081,0.00093042466,0.002971572],"category_scores_gemma":[0.0021958451,0.0003278952,0.00042917716,0.0011739553,0.000515457,0.0017169833,0.0013127945,0.00091556495,0.0024542396],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036393493,0.00016668385,0.0035826017,0.00015491429,0.000053890195,0.0004339068,0.00017790677,0.008035331,0.21156406,0.007912614,0.0041327896,0.76342124],"study_design_scores_gemma":[0.000025710391,0.00031955278,0.0071667577,0.00004593052,0.00008192586,0.00292688,0.0001692038,0.7551786,0.20269084,0.019266777,0.012058135,0.00006974847],"about_ca_topic_score_codex":0.0004772277,"about_ca_topic_score_gemma":0.00085401844,"teacher_disagreement_score":0.002971572,"about_ca_system_score_codex":0.00022738824,"about_ca_system_score_gemma":0.0002608603,"threshold_uncertainty_score":0.009940863},"labels":[],"label_agreement":null},{"id":"W4413325618","doi":"10.1145/3760260","title":"RDIAS: Robust and Decentralized Image Authentication System","year":2025,"lang":"en","type":"article","venue":"ACM Transactions on Multimedia Computing Communications and Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Authentication (law); Image (mathematics); Computer vision; Robustness (evolution); Artificial intelligence; Computer security; Human–computer interaction; Distributed computing","score_opus":0.015198939998373972,"score_gpt":0.26657271044131214,"score_spread":0.2513737704429382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413325618","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035560302,0.0010489308,0.8470056,0.000594007,0.00030203862,0.000671869,0.0008060268,0.10389255,0.010118609],"genre_scores_gemma":[0.78521633,0.00043550236,0.1921335,0.00062738656,0.00023178506,0.0005090533,0.0018600555,0.0004725629,0.018513871],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9985165,0.00017934204,0.00014361668,0.0003892751,0.0005988801,0.0001723397],"domain_scores_gemma":[0.9982994,0.0001704492,0.0002416533,0.00065564376,0.0004977485,0.00013504978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010866765,0.0008332962,0.0011384598,0.0014026259,0.0008251954,0.0013457175,0.0026574563,0.0011980821,0.0075400975],"category_scores_gemma":[0.0027690753,0.00040728046,0.00049470674,0.0006017823,0.00069766265,0.0028150268,0.00307644,0.0010897082,0.006029411],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034494994,0.0004940315,0.0031238555,0.0005349396,0.00015991417,0.0011023602,0.00037475166,0.031205924,0.16331239,0.021475732,0.063606255,0.7111603],"study_design_scores_gemma":[0.00039883907,0.0007780323,0.002300819,0.00006348482,0.0001204944,0.0014992638,0.00010520538,0.8074259,0.12223057,0.012929949,0.051928483,0.00021895864],"about_ca_topic_score_codex":0.001245848,"about_ca_topic_score_gemma":0.00078198774,"teacher_disagreement_score":0.0075400975,"about_ca_system_score_codex":0.0008995561,"about_ca_system_score_gemma":0.0011489678,"threshold_uncertainty_score":0.02522415},"labels":[],"label_agreement":null},{"id":"W4413639965","doi":"10.1109/compsac65507.2025.00186","title":"Towards Explainable AI in Continuous Smartphone Authentication: Leveraging CNN, BiLSTM, and Attention Techniques","year":2025,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Computer science; Authentication (law); Computer security; Artificial intelligence","score_opus":0.0075708501293538545,"score_gpt":0.2386055329685471,"score_spread":0.23103468283919326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413639965","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06602944,0.00072546885,0.92537266,0.0012664384,0.00013304323,0.00006009775,0.00028030653,0.003578424,0.0025541473],"genre_scores_gemma":[0.93280303,0.00029873868,0.0632201,0.00037035518,0.00007153125,0.000048434635,0.00039097184,0.00009310822,0.0027037815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996364,0.00008627534,0.00001856773,0.00013110755,0.00006698343,0.000060617356],"domain_scores_gemma":[0.9986589,0.0006902808,0.00019390897,0.00021181726,0.00017892204,0.00006613528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093032763,0.0010852809,0.0004641743,0.00061664387,0.00026529352,0.0009212094,0.0012346314,0.0009970536,0.0026391388],"category_scores_gemma":[0.00395537,0.00036929236,0.0008560511,0.00039401103,0.000783712,0.002091616,0.0015038055,0.0027186417,0.000662634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005107693,0.00021542294,0.007034732,0.00027886537,0.00022178554,0.00058041554,0.0004990301,0.5817112,0.025102673,0.02994752,0.0059658885,0.3479317],"study_design_scores_gemma":[0.0000049371356,0.00003569202,0.0003248037,0.000008534715,0.000016287382,0.000032602227,0.000011920787,0.98881733,0.0014398962,0.008871937,0.00042975653,0.000006286824],"about_ca_topic_score_codex":0.0048270915,"about_ca_topic_score_gemma":0.0058484687,"teacher_disagreement_score":0.0048270915,"about_ca_system_score_codex":0.0007955647,"about_ca_system_score_gemma":0.0007430419,"threshold_uncertainty_score":0.009597957},"labels":[],"label_agreement":null},{"id":"W4414027464","doi":"10.18280/ijsse.150715","title":"A Deep Learning-Based Approach for Gender Prediction in Digital Forensics","year":2025,"lang":"en","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Digital forensics; Deep learning; Artificial intelligence; Computer security; Machine learning","score_opus":0.005398005323637983,"score_gpt":0.20476373631809458,"score_spread":0.1993657309944566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414027464","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1965053,0.0032622823,0.7835394,0.0014533356,0.00064945425,0.00017027184,0.0018648942,0.0028182315,0.009736747],"genre_scores_gemma":[0.847968,0.00093541085,0.12974344,0.0006265496,0.00028017853,0.000111527064,0.0018904596,0.00011009619,0.018334342],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999566,0.00008255983,0.000015897842,0.00010912561,0.0000995143,0.00012697642],"domain_scores_gemma":[0.99953187,0.00013682866,0.000038647773,0.000040431205,0.0001919896,0.0000603533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078642624,0.0007713902,0.00073672616,0.0013605477,0.0004893158,0.00052252307,0.0012259188,0.0010152415,0.003488848],"category_scores_gemma":[0.001324478,0.00026613765,0.0005703584,0.00080110977,0.0002953063,0.00069413875,0.0012357922,0.0010215972,0.0015960033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057481555,0.00061788835,0.008859304,0.0000827326,0.000096184434,0.0002294245,0.00009217727,0.0524826,0.014890759,0.0033588496,0.015097701,0.90361756],"study_design_scores_gemma":[0.000010767775,0.00008135315,0.0022094136,0.00002382015,0.000026491414,0.00009027363,0.000059176586,0.98815256,0.0037267276,0.0036085972,0.001998129,0.000012698217],"about_ca_topic_score_codex":0.006724085,"about_ca_topic_score_gemma":0.012047949,"teacher_disagreement_score":0.006724085,"about_ca_system_score_codex":0.00050374574,"about_ca_system_score_gemma":0.0009891561,"threshold_uncertainty_score":0.013369918},"labels":[],"label_agreement":null},{"id":"W4414538852","doi":"10.1109/icc52391.2025.11161627","title":"Generative and Explainable AI for High-Dimensional Channel Estimation","year":2025,"lang":"en","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Channel (broadcasting); Adversarial system; Generative grammar; Generator (circuit theory); Moment (physics); Exploit; Realization (probability); Function (biology)","score_opus":0.007590738983717452,"score_gpt":0.23678687629149073,"score_spread":0.22919613730777327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414538852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008138187,0.00012299507,0.9901765,0.00027432854,0.000021456011,0.000012701263,0.000026422673,0.00014420367,0.0010832293],"genre_scores_gemma":[0.8661383,0.00034422954,0.1282844,0.0004173074,0.0001339006,0.000118551994,0.00013775716,0.00010911299,0.0043165726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99939656,0.00027044502,0.00001799961,0.00011586657,0.00013885212,0.00006031936],"domain_scores_gemma":[0.99690753,0.002355828,0.00023586502,0.00028294057,0.00014972189,0.000068021116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015528123,0.00079619716,0.0006739602,0.0005034867,0.0003892486,0.00069575076,0.0013636006,0.0011437415,0.0016492851],"category_scores_gemma":[0.005335304,0.0004366623,0.0005598865,0.0004277338,0.002054725,0.0014087048,0.00158101,0.0025722696,0.00024502768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000291525,0.000019007795,0.00036890525,0.000031347943,0.000036887654,0.00005400274,0.000056802295,0.92256856,0.0013636055,0.06190362,0.0005017673,0.013066267],"study_design_scores_gemma":[0.0000018901203,0.0000063124353,0.0000395872,0.0000023080079,0.0000026414416,0.000010486902,0.0000023792718,0.9874256,0.00022669724,0.012107573,0.00017122224,0.0000032236064],"about_ca_topic_score_codex":0.001871506,"about_ca_topic_score_gemma":0.0022081041,"teacher_disagreement_score":0.001871506,"about_ca_system_score_codex":0.0008874396,"about_ca_system_score_gemma":0.0006456164,"threshold_uncertainty_score":0.00821209},"labels":[],"label_agreement":null},{"id":"W4414706199","doi":"10.3390/math13193136","title":"MMFD-Net: A Novel Network for Image Forgery Detection and Localization via Multi-Stream Edge Feature Learning and Multi-Dimensional Information Fusion","year":2025,"lang":"en","type":"article","venue":"Mathematics","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"123 Certification (Canada)","funders":"","keywords":"Image (mathematics); Feature (linguistics); Pattern recognition (psychology); Image fusion; Edge detection; Feature extraction; Enhanced Data Rates for GSM Evolution; Deep learning; Image processing","score_opus":0.008937624251233038,"score_gpt":0.23303981945178756,"score_spread":0.22410219520055452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414706199","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04475913,0.00091994414,0.9491587,0.00034488333,0.00012380908,0.0000713346,0.0003607554,0.0023265325,0.001934815],"genre_scores_gemma":[0.68565536,0.0006964072,0.304237,0.0005232724,0.00011861474,0.0001705399,0.0013155217,0.000107057946,0.0071762297],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997402,0.00003804673,0.000011752812,0.000094043426,0.00007547923,0.00004044202],"domain_scores_gemma":[0.99960846,0.00011668907,0.000062827356,0.00006330719,0.00011798095,0.00003076942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067677005,0.0011553752,0.00083330815,0.0009007127,0.00035802324,0.00069838343,0.002167165,0.0012335882,0.0011968338],"category_scores_gemma":[0.0016261023,0.00039309508,0.00060171407,0.0005668022,0.0005869508,0.0016876439,0.0013893691,0.0010399816,0.00044768164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043243638,0.00028016695,0.0041204407,0.00013963884,0.00020727483,0.0002414962,0.00008502243,0.36492473,0.015816562,0.006204644,0.0078107296,0.5997368],"study_design_scores_gemma":[0.000005468866,0.000049278744,0.00034348835,0.0000071233453,0.000016695103,0.000058110756,0.0000071029,0.9918166,0.0046380684,0.0021996268,0.00084879104,0.000009666532],"about_ca_topic_score_codex":0.0037752662,"about_ca_topic_score_gemma":0.0057106,"teacher_disagreement_score":0.0037752662,"about_ca_system_score_codex":0.00088772463,"about_ca_system_score_gemma":0.0006708564,"threshold_uncertainty_score":0.007506609},"labels":[],"label_agreement":null},{"id":"W4415360017","doi":"10.59934/jaiea.v5i1.1502","title":"Random Forest-Based DDOS Detection from Cpanel Logs with Real-Time Notification Integration","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence and Engineering Applications (JAIEA)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Denial-of-service attack; Preprocessor; Cloud computing; Server; Random access; Random forest; Service (business)","score_opus":0.013231840116268486,"score_gpt":0.2297979468043605,"score_spread":0.216566106688092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415360017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25902945,0.0003762963,0.71745884,0.00020828992,0.00009840646,0.0002695423,0.0007604563,0.020054141,0.0017445126],"genre_scores_gemma":[0.8213013,0.00012206836,0.17517173,0.00008084709,0.000053224572,0.000185839,0.0017478251,0.0001257313,0.0012113961],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930406,0.00013493735,0.00005194911,0.00017630159,0.00022507313,0.000107772226],"domain_scores_gemma":[0.9983028,0.00069579826,0.00022775226,0.00020376619,0.00050810963,0.000061667975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012873753,0.000809221,0.0006761956,0.0019955405,0.00035155454,0.0005591945,0.00072666723,0.000460605,0.00068309275],"category_scores_gemma":[0.0035168168,0.00018903757,0.00045935056,0.0008838073,0.00018238695,0.0008306294,0.00040783957,0.00047538892,0.0006482274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009950399,0.000962622,0.028492935,0.00016269408,0.00014101717,0.00038910695,0.00012393673,0.2031268,0.03004837,0.0009219231,0.006382419,0.7282532],"study_design_scores_gemma":[0.000018506496,0.00009481486,0.003332663,0.0000057849684,0.000015417094,0.00009926501,0.000015634332,0.98816097,0.0071683065,0.0005413639,0.000534359,0.000012945652],"about_ca_topic_score_codex":0.0053061815,"about_ca_topic_score_gemma":0.0064277397,"teacher_disagreement_score":0.0053061815,"about_ca_system_score_codex":0.00036576344,"about_ca_system_score_gemma":0.0009587019,"threshold_uncertainty_score":0.010550618},"labels":[],"label_agreement":null},{"id":"W4415649506","doi":"10.1111/1556-4029.70203","title":"Learning to localize image forgery using boundary‐preserving mask R‐ <scp>CNN</scp>","year":2025,"lang":"en","type":"article","venue":"Journal of Forensic Sciences","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Preprocessor; Benchmark (surveying); Compositing; Segmentation; Domain (mathematical analysis); Image (mathematics); Digital forensics; Channel (broadcasting)","score_opus":0.017790936024147618,"score_gpt":0.2804418975105068,"score_spread":0.2626509614863592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415649506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10899141,0.0012923764,0.87239295,0.00049099507,0.00018577973,0.0002007785,0.0007178112,0.009573885,0.0061540194],"genre_scores_gemma":[0.64136195,0.0009189525,0.34558815,0.0005843981,0.000103909886,0.00012681549,0.0022814742,0.00039572475,0.008638701],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995696,0.00004153241,0.000019864512,0.00015888146,0.00013496111,0.00007506253],"domain_scores_gemma":[0.99941015,0.00010714202,0.00010522062,0.00018378263,0.0001581606,0.00003547508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008066772,0.0014839692,0.00085254107,0.000957117,0.00029946328,0.0007366826,0.0018659898,0.0011477241,0.0019783296],"category_scores_gemma":[0.002306694,0.00038839012,0.00077719486,0.0005676486,0.0005889494,0.0014489314,0.0012016378,0.00083572156,0.0014780943],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031819465,0.00015155156,0.0037719691,0.0001724167,0.00014904584,0.00035710583,0.000089850866,0.118546985,0.059343617,0.002797128,0.009900303,0.8044018],"study_design_scores_gemma":[0.000009768717,0.00012082266,0.001730803,0.000028331413,0.0000534868,0.00039338417,0.000029242126,0.94717765,0.045130514,0.0024010772,0.0029055888,0.000019270847],"about_ca_topic_score_codex":0.0052193506,"about_ca_topic_score_gemma":0.0069768126,"teacher_disagreement_score":0.0052193506,"about_ca_system_score_codex":0.000734638,"about_ca_system_score_gemma":0.00096838095,"threshold_uncertainty_score":0.0103779435},"labels":[],"label_agreement":null},{"id":"W4416113538","doi":"10.22178/pos.122-98","title":"Deepfake Detection and Authentication Using Hybrid Artificial Intelligence Models: A Case Study","year":2025,"lang":"en","type":"article","venue":"Path of Science","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Robustness (evolution); Digital watermarking; Artificial neural network; Authentication (law); Watermark; Convolutional neural network; Deep learning; Classifier (UML)","score_opus":0.04870831055417567,"score_gpt":0.29617274023540924,"score_spread":0.24746442968123356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416113538","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9231102,0.0012621636,0.0684037,0.0013463304,0.00012347654,0.00026137216,0.0005311926,0.0010943552,0.003867287],"genre_scores_gemma":[0.9677173,0.00024603563,0.0297309,0.0001274126,0.000021349022,0.00004164291,0.00033046168,0.00002528455,0.0017597079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985638,0.00057307066,0.00010425251,0.00021807432,0.00037833938,0.00016245693],"domain_scores_gemma":[0.99639374,0.0020536208,0.0002693461,0.0006604574,0.0004813957,0.00014136468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025055467,0.0009579284,0.00058515806,0.00075168913,0.0005244259,0.0013455522,0.0011892493,0.0020228163,0.00077040255],"category_scores_gemma":[0.0053053764,0.00026726563,0.0006953047,0.0005484962,0.0011198967,0.0017148971,0.0010132978,0.0013973595,0.0003812343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003132511,0.0019694965,0.055613253,0.0009219443,0.00043395255,0.009706209,0.001569159,0.53912234,0.026316896,0.013028302,0.0102413315,0.33794463],"study_design_scores_gemma":[0.00007619811,0.00054733246,0.0037386124,0.00004417501,0.000055975415,0.0008723881,0.0003352613,0.96262205,0.025368573,0.0032411788,0.0030597239,0.00003861536],"about_ca_topic_score_codex":0.0057019237,"about_ca_topic_score_gemma":0.0064245462,"teacher_disagreement_score":0.0057019237,"about_ca_system_score_codex":0.0012829192,"about_ca_system_score_gemma":0.0005278327,"threshold_uncertainty_score":0.013250709},"labels":[],"label_agreement":null},{"id":"W4417313900","doi":"10.18280/isi.301017","title":"Fusing Frequency and Spatial Transformers for Robust Detection of AI-Generated Images","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Robustness (evolution); Noise (video); Object detection; Image processing","score_opus":0.010988184019769932,"score_gpt":0.22201867699494326,"score_spread":0.21103049297517334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417313900","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05211723,0.00019488427,0.94400907,0.00014543954,0.000047634265,0.000050970353,0.00004693424,0.001446706,0.0019411088],"genre_scores_gemma":[0.85514474,0.00023115119,0.14084874,0.000189769,0.000037610916,0.000041303017,0.00017883765,0.0001002622,0.0032275512],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996196,0.00008246235,0.0000122037245,0.00009767929,0.0001326376,0.00005538864],"domain_scores_gemma":[0.9994661,0.00019185526,0.00006956447,0.00011848233,0.00012077656,0.000033125074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009202189,0.0007533966,0.000438938,0.0007302385,0.00018702867,0.00056954136,0.0008469837,0.00054122973,0.0011753422],"category_scores_gemma":[0.0021902088,0.0002877306,0.00046415665,0.0003188444,0.00062812096,0.0009790102,0.001155734,0.00096879987,0.00086762256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051745016,0.00020198627,0.0048113842,0.00011652482,0.00010034085,0.00029649315,0.00016040937,0.20699246,0.11689262,0.009421639,0.0024879675,0.65800065],"study_design_scores_gemma":[0.000005277131,0.00007121533,0.00067583553,0.0000070880164,0.00001463731,0.00021470738,0.000018783569,0.9659006,0.02931837,0.0029474583,0.00081635383,0.000009705166],"about_ca_topic_score_codex":0.0011833925,"about_ca_topic_score_gemma":0.0017838896,"teacher_disagreement_score":0.0011833925,"about_ca_system_score_codex":0.0003947801,"about_ca_system_score_gemma":0.00040272973,"threshold_uncertainty_score":0.0048666596},"labels":[],"label_agreement":null},{"id":"W4417473487","doi":"10.5120/ijca2025926005","title":"GRAVITI: Grounded Retrieval Generation Framework for VideoLLM Hallucination Mitigation","year":2025,"lang":"","type":"article","venue":"International Journal of Computer Applications","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Grounded theory; Perspective (graphical)","score_opus":0.016914982495426223,"score_gpt":0.31007649551273836,"score_spread":0.29316151301731214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417473487","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034748102,0.0002757735,0.971884,0.0001993501,0.000051185183,0.0002072156,0.0006521725,0.022171823,0.0010836887],"genre_scores_gemma":[0.15693434,0.00037274713,0.828168,0.00063795707,0.00009337386,0.00068499445,0.0050500985,0.00263142,0.00542705],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885416,0.00034637807,0.00006599277,0.00027478955,0.00035727312,0.00010145265],"domain_scores_gemma":[0.9984445,0.0006951895,0.0001112812,0.0003446136,0.0003361696,0.00006830286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021233207,0.0018063053,0.0009610155,0.0013635124,0.00053495896,0.0015172485,0.0040488197,0.0017899565,0.0068795383],"category_scores_gemma":[0.007397354,0.00056456006,0.0013860626,0.0007112673,0.0010472748,0.0022953006,0.0035589072,0.0022354405,0.0043245815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072557974,0.00031537848,0.0015763444,0.0009229309,0.00022842945,0.0008388176,0.00090899447,0.11014441,0.042300906,0.023909137,0.04835026,0.76977885],"study_design_scores_gemma":[0.000092837065,0.00023204187,0.0003165967,0.00006901427,0.0000708765,0.0004663618,0.00019750372,0.91693044,0.030763974,0.036024682,0.0147718815,0.00006383221],"about_ca_topic_score_codex":0.0049014594,"about_ca_topic_score_gemma":0.006452378,"teacher_disagreement_score":0.0068795383,"about_ca_system_score_codex":0.001119044,"about_ca_system_score_gemma":0.0016087138,"threshold_uncertainty_score":0.023014367},"labels":[],"label_agreement":null},{"id":"W6889143697","doi":"10.25384/sage.c.4948017","title":"Management of Patients With Sepsis in Canadian Community Emergency Departments: A Retrospective Multicenter Observational Study","year":2020,"lang":"en","type":"other","venue":"Sage Journals Data","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Triage; Observational study; Sepsis; Resuscitation; Intensive care unit; Emergency department; Psychological intervention; Mortality rate","score_opus":0.06782850599060788,"score_gpt":0.3068889965923151,"score_spread":0.23906049060170723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889143697","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9903487,0.0011719969,0.00016837737,0.00028986434,0.000021606304,0.00022630164,0.0065407185,0.000012112146,0.0012203192],"genre_scores_gemma":[0.9942356,0.00066691934,0.0003875108,0.0003202173,0.000029795163,0.00013356091,0.004093285,0.0000051259813,0.00012805106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964799,0.00030045747,0.0003898774,0.0007532685,0.0013077272,0.00076874974],"domain_scores_gemma":[0.99306583,0.0004387919,0.0026174465,0.0002877562,0.0024213796,0.0011687678],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021817456,0.0010187363,0.0010760588,0.0025308656,0.0030896862,0.0016653318,0.002154111,0.0010435843,0.0017430052],"category_scores_gemma":[0.0062262057,0.000660874,0.0009819762,0.00839248,0.0008988818,0.000741414,0.0012889876,0.0011222686,0.00021926136],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007037331,0.00004404404,0.99806374,0.000055096018,0.00007754919,0.00008104524,0.00017204418,0.00003250315,0.000047391586,0.000024855757,0.00055013224,0.0007811971],"study_design_scores_gemma":[0.000024644514,0.00005911404,0.99822396,0.000046228477,0.000060327635,0.0001772046,0.00058726774,0.00017418084,0.0000213985,0.0000111655045,0.0005986784,0.000015810998],"about_ca_topic_score_codex":0.9215566,"about_ca_topic_score_gemma":0.92875713,"teacher_disagreement_score":0.07844341,"about_ca_system_score_codex":0.021826973,"about_ca_system_score_gemma":0.031305093,"threshold_uncertainty_score":0.1583665},"labels":[],"label_agreement":null},{"id":"W6931359986","doi":"10.5281/zenodo.6158756","title":"TopiOCQA DPR Retriever passage embeddings (original (2))","year":2022,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Object (grammar); Set (abstract data type); Labrador Retriever; Sequence (biology); Representation (politics)","score_opus":0.018171679290916724,"score_gpt":0.22531794006169745,"score_spread":0.20714626077078072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931359986","genre_codex":"software","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00863239,0.0008329073,0.26753274,0.0019977111,0.002853837,0.0006572942,0.1734622,0.45621786,0.087813124],"genre_scores_gemma":[0.09844789,0.00062851247,0.38320014,0.0014503227,0.0007900778,0.00095596217,0.29135877,0.116434745,0.10673357],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99817836,0.00021129497,0.00015598646,0.00050091057,0.00068263535,0.0002708051],"domain_scores_gemma":[0.9970783,0.0005284946,0.00008242593,0.0008793031,0.0013281854,0.000103399485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143504,0.0029379881,0.0010994006,0.0030806225,0.0008988197,0.002906662,0.002043737,0.002008921,0.21594001],"category_scores_gemma":[0.009142598,0.0008953519,0.0014930058,0.0019286154,0.00076260814,0.0038259407,0.0028454007,0.0022903637,0.13766061],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030807246,0.00006276146,0.000384396,0.0005252232,0.00004274269,0.0002315786,0.00019032303,0.001245572,0.0073119914,0.012291707,0.89270455,0.08470117],"study_design_scores_gemma":[0.0002420995,0.000108284745,0.0012598567,0.00018588633,0.00006224826,0.0007566999,0.00025441157,0.048629723,0.04569185,0.020505339,0.8821256,0.00017788792],"about_ca_topic_score_codex":0.013846044,"about_ca_topic_score_gemma":0.016096182,"teacher_disagreement_score":0.21594001,"about_ca_system_score_codex":0.0015169356,"about_ca_system_score_gemma":0.0015406528,"threshold_uncertainty_score":0.7223913},"labels":[],"label_agreement":null},{"id":"W6955215979","doi":"10.58079/ni4k","title":"Identification d'images - test de TinEye sur PhotosNormandie","year":2008,"lang":"fr","type":"article","venue":"Industrias Culturais (Universidade de Coimbra)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Identification (biology); Pattern recognition (psychology); Test (biology); Relation (database)","score_opus":0.03549357073650337,"score_gpt":0.23207541343282867,"score_spread":0.1965818426963253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6955215979","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92326486,0.00061290525,0.04418605,0.00078607566,0.0015227179,0.00027044024,0.00094530586,0.0017649718,0.026646722],"genre_scores_gemma":[0.92345,0.00035655135,0.039583564,0.00036267826,0.00010831864,0.00005911431,0.0012765215,0.00022166611,0.034581624],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995766,0.000030379715,0.000019824945,0.000107812426,0.00019905092,0.00006639161],"domain_scores_gemma":[0.999017,0.00025412856,0.00003849665,0.00011565457,0.0004769844,0.00009783066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057926984,0.00033046323,0.00030993015,0.0011283691,0.0004928358,0.0005729276,0.00032917215,0.0012242087,0.009248589],"category_scores_gemma":[0.0021400577,0.00013707529,0.00026223133,0.0004609674,0.00032674932,0.000891794,0.0005796838,0.00037334088,0.0024346868],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020886264,0.00034239935,0.013238921,0.00037735852,0.000083672516,0.004439237,0.0011177037,0.0014636866,0.7310545,0.0016332824,0.010771649,0.23338898],"study_design_scores_gemma":[0.00009898594,0.0025584744,0.17707355,0.00015946438,0.00015320616,0.014617892,0.0027816375,0.054359235,0.70286137,0.0011937252,0.044007596,0.00013485666],"about_ca_topic_score_codex":0.0023237017,"about_ca_topic_score_gemma":0.0031575148,"teacher_disagreement_score":0.009248589,"about_ca_system_score_codex":0.00021483898,"about_ca_system_score_gemma":0.00019922016,"threshold_uncertainty_score":0.030939579},"labels":[],"label_agreement":null},{"id":"W6968718384","doi":"10.5281/zenodo.4560204","title":"A survey of machine learning techniques in adversarial image forensics","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Adversarial system; Robustness (evolution); Adversarial machine learning; Image (mathematics); Focus (optics); Binary classification; Narrative; Contextual image classification","score_opus":0.034592528891876695,"score_gpt":0.23553092291750538,"score_spread":0.20093839402562869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968718384","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004858104,0.069881655,0.9144371,0.0012715239,0.00037459674,0.000117945856,0.00010250901,0.00063678226,0.008319801],"genre_scores_gemma":[0.26034468,0.15558492,0.56819695,0.001245402,0.00242451,0.0004480658,0.00060102437,0.0004450797,0.010709413],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971431,0.00090558577,0.00026730212,0.00042735517,0.0011263386,0.00013032807],"domain_scores_gemma":[0.9944804,0.0036767446,0.00036649784,0.0006842727,0.00070980075,0.00008245026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00422555,0.0017081496,0.0020055072,0.0030503003,0.0008048855,0.002107987,0.002080922,0.0026760395,0.0019709105],"category_scores_gemma":[0.00917442,0.0009236288,0.0017682634,0.003390336,0.001800422,0.0029718478,0.0017736752,0.0035235342,0.001689586],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012416732,0.00021521712,0.0016081063,0.0012391543,0.00022616658,0.00016391979,0.00016233097,0.17431553,0.003673911,0.05827249,0.0072190906,0.75277984],"study_design_scores_gemma":[0.000024517529,0.00025620783,0.001737944,0.00079689507,0.00010793815,0.000802597,0.000087470515,0.84290963,0.011522915,0.08287111,0.05875731,0.00012548229],"about_ca_topic_score_codex":0.001144916,"about_ca_topic_score_gemma":0.000644448,"teacher_disagreement_score":0.00422555,"about_ca_system_score_codex":0.0012229531,"about_ca_system_score_gemma":0.00090615207,"threshold_uncertainty_score":0.022347152},"labels":[],"label_agreement":null},{"id":"W6981196323","doi":"","title":"Duplicate Detection for Quality Assurance of Document Image Collections: Paper - iPRES 2012 - Digital Curation Institute, iSchool, Toronto","year":2012,"lang":"en","type":"article","venue":"Phaidra (Universität Wien)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workflow; Robustness (evolution); Digital image; Image file formats; Document image processing; Quality assurance; Image processing; Automatic image annotation","score_opus":0.014506869905412912,"score_gpt":0.2576323233897625,"score_spread":0.24312545348434958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981196323","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18088198,0.0053977347,0.8004443,0.000656561,0.00025200343,0.0004242409,0.000590957,0.0054446347,0.0059076436],"genre_scores_gemma":[0.49682358,0.0022260807,0.4901529,0.0000964476,0.000121379395,0.000135114,0.0011943555,0.00068067905,0.008569478],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99582255,0.0007072106,0.0002088039,0.0006254307,0.0024261742,0.00020982533],"domain_scores_gemma":[0.98976594,0.002640774,0.0010181682,0.0034004096,0.0029392105,0.00023553825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034559744,0.00058897294,0.0009053033,0.004057543,0.0010369295,0.0023305567,0.0014537901,0.0010895291,0.0053599672],"category_scores_gemma":[0.012753243,0.00047035067,0.0006878741,0.0021886367,0.001397128,0.0018125406,0.001888555,0.00069118605,0.0027046725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00057551137,0.00013131973,0.010586309,0.0006772521,0.00015247148,0.00041309118,0.000557651,0.0061142044,0.15238649,0.0030256005,0.0069799214,0.81840014],"study_design_scores_gemma":[0.00009168546,0.0007401327,0.031190744,0.00019934351,0.00033653033,0.0055922177,0.00060404383,0.15922506,0.76033133,0.0058620693,0.0356638,0.00016296575],"about_ca_topic_score_codex":0.0023006662,"about_ca_topic_score_gemma":0.0033007322,"teacher_disagreement_score":0.0053599672,"about_ca_system_score_codex":0.001121732,"about_ca_system_score_gemma":0.0016161113,"threshold_uncertainty_score":0.018277168},"labels":[],"label_agreement":null},{"id":"W7020735802","doi":"","title":"Modeling and Evaluation of Quebec’s Air Quality due to an Increase in the Electric Vehicle Fleet Combined with Off-Road Emission Reductions","year":2018,"lang":"en","type":"report","venue":"eScholarship@McGill (McGill)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Air quality index; Quality (philosophy); Air pollution; Electric vehicle; Diesel fuel","score_opus":0.04663934578014794,"score_gpt":0.3020983993205036,"score_spread":0.25545905354035564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7020735802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96190464,0.00032044042,0.006257245,0.0013711269,0.000114124225,0.000102888225,0.0061906883,0.00021903023,0.023519853],"genre_scores_gemma":[0.991595,0.000102821534,0.0008979195,0.000073763804,0.000007689663,0.000024089757,0.0011457457,0.000021156773,0.0061317966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9997366,0.000045548837,0.000007046254,0.00005797055,0.00005936441,0.000093430834],"domain_scores_gemma":[0.9994802,0.0001419701,0.00003232935,0.000020929829,0.00027269972,0.000051925083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048468274,0.00075011776,0.000371215,0.00055944,0.001083566,0.001264961,0.0012355308,0.0012904782,0.0029408073],"category_scores_gemma":[0.0009393776,0.00043341122,0.0010300287,0.00057630957,0.0005201237,0.00056521426,0.00035968915,0.00090666936,0.00028058497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101893835,0.000071521776,0.012439204,0.000022620572,0.000049406506,0.00012363207,0.000031942895,0.980717,0.0010950755,0.0010320585,0.002094,0.002221624],"study_design_scores_gemma":[0.000025962272,0.000035411776,0.013370996,0.000007034441,0.000030652096,0.000010484686,0.00008904617,0.9848894,0.00045484453,0.000159622,0.0009065972,0.000020045965],"about_ca_topic_score_codex":0.9817616,"about_ca_topic_score_gemma":0.9712539,"teacher_disagreement_score":0.018238425,"about_ca_system_score_codex":0.01624851,"about_ca_system_score_gemma":0.009049921,"threshold_uncertainty_score":0.11789173},"labels":[],"label_agreement":null},{"id":"W7023219901","doi":"","title":"drone bølge","year":2016,"lang":"en","type":"other","venue":"Falmouth University Research Repository (FURR) (Falmouth University)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Drone; Field (mathematics)","score_opus":0.022782261129016993,"score_gpt":0.24307148775897303,"score_spread":0.22028922662995604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023219901","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03708675,0.0034326261,0.015679063,0.0034779045,0.008497796,0.00026083674,0.11675524,0.013699191,0.8011106],"genre_scores_gemma":[0.081562564,0.001880516,0.01446354,0.0006816079,0.00069908565,0.00006682934,0.05874885,0.005799865,0.83609706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99975616,0.000014847508,0.00001091788,0.00004137387,0.00013900238,0.00003770757],"domain_scores_gemma":[0.99965465,0.000056770088,0.000021079024,0.00005908089,0.00013152746,0.00007679674],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002883317,0.00060198334,0.0003480016,0.0022564717,0.0011904915,0.0021169833,0.00040373145,0.00063686614,0.3163192],"category_scores_gemma":[0.001096715,0.00026686332,0.00025837147,0.0013730753,0.00037379243,0.0011704871,0.0016058062,0.0007247982,0.14365609],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003803444,0.0000310987,0.0016345973,0.0002944352,0.000021850892,0.0006112563,0.0006455177,0.000462189,0.003793842,0.002738255,0.8350304,0.15435621],"study_design_scores_gemma":[0.000014010001,0.000015525993,0.003813789,0.00011483079,0.0000062066224,0.00029005946,0.0003961982,0.00033298956,0.001337968,0.00045638243,0.99320567,0.00001646651],"about_ca_topic_score_codex":0.014203965,"about_ca_topic_score_gemma":0.043095764,"teacher_disagreement_score":0.3163192,"about_ca_system_score_codex":0.0003927872,"about_ca_system_score_gemma":0.00053358986,"threshold_uncertainty_score":0.97518766},"labels":[],"label_agreement":null},{"id":"W7033068100","doi":"","title":"Placement and source effects of phosphate fertilizers on phosphorus availability and reaction products in two reduced-till soils: A greenhouse study","year":2015,"lang":"en","type":"other","venue":"K-State Research Exchange (Kansas State University)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Office of Science; King Saud University; Argonne National Laboratory; International Plant Nutrition Institute; U.S. Department of Energy","keywords":"Soil water; Fertilizer; Nutrient; Greenhouse; Phosphorus","score_opus":0.03612106124336337,"score_gpt":0.28086552137422127,"score_spread":0.2447444601308579,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033068100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99939907,0.000057299374,0.0001858427,0.000010674842,0.000005021707,0.000026923093,0.00012545518,0.000010773126,0.00017891536],"genre_scores_gemma":[0.9959428,0.00022837805,0.0019641146,0.00004630706,0.0000059497643,0.00008726696,0.0004723095,0.000021632475,0.0012312761],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99977463,0.000032278822,0.000018411045,0.00007834204,0.000042123138,0.00005438054],"domain_scores_gemma":[0.9994554,0.00021124272,0.0000890169,0.000042775508,0.000083896426,0.0001177015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023820806,0.00046834906,0.00053342024,0.0003066521,0.00031750396,0.00031298533,0.0004787176,0.00036055702,0.0006150749],"category_scores_gemma":[0.00021991311,0.00029788577,0.00036560727,0.00020863111,0.00036080065,0.00031882038,0.00029203054,0.0006569849,0.00013866773],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007738135,0.00032397066,0.0018613804,0.00005341707,0.000013389322,0.000095036594,0.000066885674,0.00018332974,0.99548906,0.00002117942,0.000028760063,0.0010897592],"study_design_scores_gemma":[0.00022505692,0.009685769,0.08296832,0.000009871021,0.00011661899,0.00023370859,0.00049311,0.0036617261,0.90082854,0.000078143836,0.0016359605,0.00006308847],"about_ca_topic_score_codex":0.012866266,"about_ca_topic_score_gemma":0.02308628,"teacher_disagreement_score":0.012866266,"about_ca_system_score_codex":0.0011581458,"about_ca_system_score_gemma":0.00061296776,"threshold_uncertainty_score":0.02558273},"labels":[],"label_agreement":null},{"id":"W7034645597","doi":"","title":"Virtual heritage: global perspectives for creative modes of heritage visualisation","year":2017,"lang":"en","type":"book","venue":"Nottingham Trent University's Institutional Repository (Nottingham Trent Repository)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; University of Wolverhampton; Trent University; National Research Institute of Astronomy and Geophysics; Arts and Humanities Research Council; Queen's University Belfast; Nottingham Trent University","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Durvalumab","score_opus":0.01450425084858455,"score_gpt":0.23830759568625018,"score_spread":0.22380334483766562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034645597","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020044686,0.035614062,0.0101837935,0.0036053706,0.001337762,0.000027493947,0.00007048566,0.00025071,0.9469059],"genre_scores_gemma":[0.07175436,0.055617813,0.0120316,0.0015073381,0.0012780393,0.00008883957,0.000239339,0.00084524334,0.8566375],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920446,0.00025372117,0.00002602355,0.00007128769,0.00032642635,0.00011822166],"domain_scores_gemma":[0.99910766,0.0004687682,0.00003178715,0.00014955373,0.00011962153,0.00012260726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012335354,0.0009317571,0.0005666502,0.0026739088,0.0023966874,0.023715092,0.0014021131,0.0021416498,0.055385984],"category_scores_gemma":[0.0017590357,0.00056995515,0.00041575724,0.0052017844,0.008308,0.009339146,0.0059865187,0.0031129345,0.0069344174],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021856615,0.000018560333,0.00008729074,0.00053525734,0.000007870294,0.00017732999,0.007999756,0.0004489385,0.0003977156,0.7362841,0.104570486,0.14945096],"study_design_scores_gemma":[0.00000405684,0.0000069662474,0.000151242,0.0003672406,0.0000046654823,0.00024301042,0.002479749,0.00015895802,0.00014052165,0.070084035,0.92635095,0.00000871576],"about_ca_topic_score_codex":0.006815054,"about_ca_topic_score_gemma":0.017984534,"teacher_disagreement_score":0.055385984,"about_ca_system_score_codex":0.0034832042,"about_ca_system_score_gemma":0.0028783467,"threshold_uncertainty_score":0.18528455},"labels":[],"label_agreement":null},{"id":"W7034674032","doi":"","title":"Town of Plainfield, New Hampshire annual report 2004 annual reports of the officers and selectmen and the school district.","year":2005,"lang":"en","type":"article","venue":"University of New Hampshire Scholars Repository (University of New Hampshire at Manchester)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"U.S. Department of Housing and Urban Development","keywords":"Annual report; Year-ending; Work (physics); Preliminary report; Quarter (Canadian coin)","score_opus":0.0052410587543272776,"score_gpt":0.16873423625667594,"score_spread":0.16349317750234865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034674032","genre_codex":"dataset","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021468636,0.005593776,0.0006326569,0.008005953,0.0028494457,0.00031074707,0.7162366,0.00065105787,0.24425107],"genre_scores_gemma":[0.066742696,0.008186809,0.001407975,0.0007293792,0.00050333043,0.00033473928,0.21094523,0.00026931474,0.7108806],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995956,0.000032493237,0.000030842057,0.000048280515,0.0002050573,0.00008770706],"domain_scores_gemma":[0.99746454,0.00012502108,0.00020072462,0.0000731723,0.0018300159,0.00030657565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002766578,0.0005690801,0.0003216404,0.002699915,0.00094637973,0.0012468565,0.0007161088,0.0003137274,0.11307679],"category_scores_gemma":[0.002369067,0.0004405544,0.00014098697,0.004115687,0.00021080769,0.0010231131,0.0006090869,0.0005403764,0.02631526],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023008433,0.000010074453,0.0030576603,0.000082362036,0.0000034622149,0.00007384477,0.00008481295,0.00003685749,0.000041734827,0.00020845914,0.98406154,0.012316227],"study_design_scores_gemma":[0.00001761522,0.000018023513,0.10902295,0.00017461435,0.00001582226,0.00012821073,0.0011136947,0.00005970591,0.00019109153,0.000112604524,0.88912886,0.000016864902],"about_ca_topic_score_codex":0.6011898,"about_ca_topic_score_gemma":0.7846965,"teacher_disagreement_score":0.6011898,"about_ca_system_score_codex":0.004622907,"about_ca_system_score_gemma":0.0067325933,"threshold_uncertainty_score":0.80231774},"labels":[],"label_agreement":null},{"id":"W7039064541","doi":"","title":"La cuestión catalana a la luz de la experiencia de Quebec y Escocia","year":2021,"lang":"es","type":"other","venue":"View","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Population; Subject (documents); Work (physics)","score_opus":0.008695466926718153,"score_gpt":0.2665039524793045,"score_spread":0.25780848555258634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039064541","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30868423,0.007989074,0.0019793666,0.057798453,0.0010665949,0.0000672783,0.0023667233,0.00021060945,0.6198377],"genre_scores_gemma":[0.76995045,0.0037187226,0.0008697427,0.003401701,0.00011478464,0.000025244772,0.00034754508,0.000085731874,0.2214861],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995247,0.00012184245,0.000007575214,0.000045537796,0.00014018283,0.00016011675],"domain_scores_gemma":[0.9986701,0.00030814638,0.00009709136,0.000059400703,0.0005421641,0.00032312222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007188188,0.00035982204,0.00015329877,0.0014452608,0.008355241,0.005541725,0.00056171475,0.0016060339,0.025107918],"category_scores_gemma":[0.0021926945,0.000116124786,0.00016317442,0.0026218188,0.0032990135,0.001662963,0.0020790396,0.001770148,0.0011261555],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028124262,0.00014133811,0.060636338,0.000370938,0.000052613766,0.003528594,0.17539361,0.0007573652,0.0022783077,0.14799596,0.32321215,0.2853515],"study_design_scores_gemma":[0.000009748874,0.00002157415,0.06127424,0.0004686011,0.000018419905,0.0003339875,0.17792624,0.00048597396,0.0007142312,0.0024914253,0.7562014,0.000054188073],"about_ca_topic_score_codex":0.9759973,"about_ca_topic_score_gemma":0.98858684,"teacher_disagreement_score":0.026718456,"about_ca_system_score_codex":0.026718456,"about_ca_system_score_gemma":0.020786135,"threshold_uncertainty_score":0.19385684},"labels":[],"label_agreement":null},{"id":"W7042380058","doi":"","title":"Perturbação de jogos de internet e sua relação com a personalidade e substâncias psicoativas numa amostra de adultos portugueses","year":2023,"lang":"pt","type":"dissertation","venue":"Repositório Institucional da Universidade Católica Portuguesa (Universidade Católica Portuguesa)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Association (psychology); Sample (material); The Internet; Scale (ratio)","score_opus":0.028452330881217888,"score_gpt":0.25823507528417416,"score_spread":0.22978274440295626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042380058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9944935,0.0023034187,0.00014712705,0.00025799425,0.00002486283,0.000072315815,0.0004672577,0.000004449497,0.0022291979],"genre_scores_gemma":[0.99315006,0.0034179157,0.00045656494,0.0002077829,0.0000248211,0.000080040394,0.00032436367,0.000008115084,0.0023303116],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990188,0.0001986744,0.00009534993,0.00017582047,0.00032473914,0.00018650494],"domain_scores_gemma":[0.9978248,0.0003740456,0.0009140208,0.00014353142,0.000512122,0.00023158955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001484352,0.0003888951,0.0006972625,0.0011966805,0.0015240082,0.0015444572,0.00052542606,0.0006157499,0.0022808036],"category_scores_gemma":[0.0062512252,0.000621185,0.00071942055,0.0015735301,0.0012499011,0.0010930893,0.0015218736,0.00078572467,0.00038953035],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002596863,0.00021628311,0.9008056,0.0005138382,0.00010853525,0.0015366571,0.07192362,0.000039105755,0.0010098154,0.00031389232,0.0006740219,0.02259896],"study_design_scores_gemma":[0.0000048519364,0.0003055261,0.9577669,0.00019979227,0.000077459496,0.0011371163,0.035447635,0.00004894262,0.00014683326,0.00012699484,0.004716764,0.00002123706],"about_ca_topic_score_codex":0.05025867,"about_ca_topic_score_gemma":0.075323895,"teacher_disagreement_score":0.05025867,"about_ca_system_score_codex":0.0013316605,"about_ca_system_score_gemma":0.0015565634,"threshold_uncertainty_score":0.09993225},"labels":[],"label_agreement":null},{"id":"W7045945317","doi":"","title":"Decoding of Dynamic Video Evoked by fMRI based on Dilated Long and Short Term Memory Neural Network","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Decoding methods; Long short term memory; Artificial neural network; Encoding (memory); Short-term memory; Term (time); Pattern recognition (psychology)","score_opus":0.008096149994085743,"score_gpt":0.22838173466600953,"score_spread":0.22028558467192377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7045945317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6008184,0.0007919985,0.37937206,0.0014288048,0.00038036963,0.00010577644,0.00062764226,0.00054672686,0.015928281],"genre_scores_gemma":[0.87189996,0.000498268,0.11577329,0.00020790362,0.0001464137,0.000032189397,0.0003913536,0.0000636175,0.010986936],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9999597,0.0000069757343,0.00000201815,0.000012684985,0.000011706346,0.000006866839],"domain_scores_gemma":[0.99985766,0.000070065675,0.0000093558465,0.000009146041,0.000035157227,0.000018696968],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018449109,0.00022782358,0.00012336117,0.00025408008,0.00013218471,0.0002571172,0.00018383295,0.0003405696,0.0034251737],"category_scores_gemma":[0.00092575746,0.00006909573,0.00015161133,0.0002186872,0.00011068894,0.00039326615,0.0001340547,0.0003148267,0.00041142272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054869533,0.00012488342,0.0041537015,0.0001146982,0.000055047705,0.00050494744,0.0001465867,0.013225392,0.619371,0.0060723163,0.002984,0.35269868],"study_design_scores_gemma":[0.000035260793,0.00035756637,0.033430927,0.000036071684,0.000078172736,0.001066451,0.00010124508,0.75895923,0.19558565,0.005677612,0.0046228487,0.000048888185],"about_ca_topic_score_codex":0.001193422,"about_ca_topic_score_gemma":0.002897617,"teacher_disagreement_score":0.0034251737,"about_ca_system_score_codex":0.00015417862,"about_ca_system_score_gemma":0.00016638555,"threshold_uncertainty_score":0.011458397},"labels":[],"label_agreement":null},{"id":"W7129547315","doi":"10.1109/icipw68931.2025.11386324","title":"Real Images Hold the Key to Detecting AI-Generated Images Using Bayer Pattern Analysis","year":2025,"lang":"","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Autoencoder; Key (lock); Pixel; Pattern recognition (psychology); Generalization; Digital image; Invariant (physics); Image (mathematics)","score_opus":0.017996810305188706,"score_gpt":0.27284743428129055,"score_spread":0.25485062397610186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7129547315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06619499,0.0005004345,0.926179,0.00040412953,0.000092826915,0.00012256076,0.00018150378,0.0015296146,0.0047948975],"genre_scores_gemma":[0.45326722,0.00060842844,0.5406949,0.00030471903,0.000118375305,0.000072609124,0.0004512191,0.000249841,0.004232661],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9994593,0.000080137805,0.00002227831,0.00015902173,0.00023067596,0.000048538262],"domain_scores_gemma":[0.9986197,0.00036830347,0.0002180732,0.00043795136,0.0002874443,0.00006849189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070354826,0.0006731251,0.0004883801,0.001076973,0.00029551418,0.00093222864,0.0007634487,0.00094963185,0.00156351],"category_scores_gemma":[0.0029606407,0.00033302087,0.00034907035,0.00050027936,0.0009853838,0.0015038041,0.0008380233,0.0014502213,0.0015414555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000242705,0.0001144383,0.003856003,0.00024374627,0.000056321227,0.00036049687,0.00021651556,0.02073709,0.2701835,0.012012262,0.0030614692,0.68891543],"study_design_scores_gemma":[0.000034449095,0.00029884218,0.01305139,0.00008830068,0.00006592497,0.003255888,0.00024792706,0.5564649,0.3819285,0.02294326,0.021535002,0.00008566978],"about_ca_topic_score_codex":0.00049569795,"about_ca_topic_score_gemma":0.000866494,"teacher_disagreement_score":0.00156351,"about_ca_system_score_codex":0.0003308352,"about_ca_system_score_gemma":0.0003376144,"threshold_uncertainty_score":0.0052304864},"labels":[],"label_agreement":null},{"id":"W7133234219","doi":"10.18280/ijsse.151205","title":"Detecting Digital Image Forgeries Using Error Level Analysis Features and Neural Network Classification Enhanced by Synthetic Minority Over-Sampling Technique","year":2025,"lang":"","type":"article","venue":"International Journal of Safety and Security Engineering","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pattern recognition (psychology); Artificial neural network; Image (mathematics); Digital image; Feature extraction; Contextual image classification","score_opus":0.013071493858293938,"score_gpt":0.26061684017742964,"score_spread":0.24754534631913572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133234219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6398447,0.00037800835,0.35766265,0.00016770173,0.0000890708,0.000042820928,0.000063197775,0.00047272662,0.0012791657],"genre_scores_gemma":[0.95737183,0.00009366222,0.041397654,0.000027731105,0.000022238582,0.0000133134,0.00008260989,0.000013136552,0.0009778497],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9995491,0.000075189375,0.000034296834,0.00008375631,0.00020280293,0.000054831697],"domain_scores_gemma":[0.99897987,0.0003276525,0.00015098002,0.00011329719,0.0003880584,0.000040051153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010168963,0.00041872126,0.00054822705,0.0007500738,0.0002689014,0.00044022797,0.0004189069,0.00047251515,0.00048451734],"category_scores_gemma":[0.002365622,0.000118157375,0.00032352252,0.00036314232,0.00025938964,0.0007636087,0.00047415885,0.0004939326,0.0001538699],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017593082,0.0005849969,0.029055342,0.00013398458,0.00013753655,0.00049491966,0.00027645697,0.053577077,0.14673685,0.0022148176,0.0014297155,0.763599],"study_design_scores_gemma":[0.000009243203,0.00023075745,0.0111211,0.000008224125,0.0000401271,0.0002770484,0.000051938034,0.94752014,0.039789304,0.00046599688,0.00046978946,0.000016386632],"about_ca_topic_score_codex":0.0012770857,"about_ca_topic_score_gemma":0.0016208544,"teacher_disagreement_score":0.0012770857,"about_ca_system_score_codex":0.00022341637,"about_ca_system_score_gemma":0.00027402616,"threshold_uncertainty_score":0.0053779483},"labels":[],"label_agreement":null},{"id":"W7147441325","doi":"10.1109/iccspci68199.2025.11451645","title":"Securing Digital Images with AI-Augmented NonNegative Matrix Factorization for Tamper Detection","year":2025,"lang":"","type":"article","venue":"","topic":"Digital Media Forensic Detection","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Image (mathematics); Hash function; Pattern recognition (psychology); Digital image; Authentication (law); Hamming distance; Matrix decomposition; Factorization; Identification (biology)","score_opus":0.004194569648514932,"score_gpt":0.2406193525748183,"score_spread":0.23642478292630337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7147441325","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01471569,0.00041158698,0.98258406,0.00013451761,0.00008041243,0.00007528661,0.00009381614,0.0009154589,0.0009891059],"genre_scores_gemma":[0.39052248,0.0005600939,0.60431254,0.00022561949,0.00015369091,0.00015269237,0.00054109807,0.00006563935,0.0034662723],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9992855,0.00013603571,0.000037098132,0.00017036553,0.00030171603,0.00006932358],"domain_scores_gemma":[0.99923563,0.00020476228,0.00014062737,0.00013635935,0.00023670461,0.00004595126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000727954,0.00091970264,0.0006079757,0.00065689534,0.0003673228,0.00056508096,0.00062553264,0.0005268064,0.0014815426],"category_scores_gemma":[0.0024328504,0.00018368594,0.00063862605,0.000555638,0.0004710459,0.0009828705,0.0007407721,0.0008777589,0.001048682],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004104367,0.00017923249,0.0013939184,0.0002349984,0.00008203709,0.00019029516,0.00014690685,0.049133714,0.103319295,0.008071507,0.0058941306,0.83094347],"study_design_scores_gemma":[0.000023610291,0.00025585687,0.0014130925,0.00002255356,0.00003060047,0.0004149265,0.00006435496,0.95749545,0.029150585,0.0061295447,0.004951179,0.000048158832],"about_ca_topic_score_codex":0.0015102194,"about_ca_topic_score_gemma":0.002430484,"teacher_disagreement_score":0.0015102194,"about_ca_system_score_codex":0.00028345524,"about_ca_system_score_gemma":0.0005778686,"threshold_uncertainty_score":0.0049562454},"labels":[],"label_agreement":null}]}