{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":367,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":367,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a52474026efd","filters":{"venue":"IEEE Transactions on Image Processing"}},"results":[{"id":"W2114582993","doi":"10.1109/tip.2010.2092435","title":"Information Content Weighting for Perceptual Image Quality Assessment","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":1306,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Pooling; Weighting; Image quality; Computer science; Distortion (music); Artificial intelligence; Pattern recognition (psychology); Data mining; Quality (philosophy); Image (mathematics); Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.05876528498935366,"gpt":0.3557996794699934,"spread":0.2970343944806397,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001155122,0.0002640372,0.0002714659,0.0002135538,0.0008760736,0.001341088,0.0005832242,0.0001125902,0.00005175847],"category_scores_gemma":[0.00003975157,0.00024985,0.0001908155,0.0003009171,0.0001220572,0.006454908,0.000007841302,0.0006102385,0.00005242663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001163268,"about_ca_system_score_gemma":0.0003421133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006000223,"about_ca_topic_score_gemma":0.00002964688,"domain_scores_codex":[0.9978462,0.00009904119,0.0007109063,0.0003580737,0.000523616,0.000462157],"domain_scores_gemma":[0.9982032,0.000214605,0.0002950242,0.0005139141,0.0006300148,0.0001432852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003967485,0.0004330299,0.00001092155,0.0003491945,0.00003248793,0.000002195889,0.004924958,0.0000691872,0.3036987,0.002625941,0.0001921421,0.6876216],"study_design_scores_gemma":[0.004761851,0.0005708414,0.00237775,0.0002516801,0.000119647,0.00007187268,0.007755387,0.4198512,0.5539103,0.003113497,0.005377352,0.001838559],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0122472,0.000006121625,0.9828057,0.00183953,0.0008478981,0.0005092759,0.00003049739,0.0003537271,0.001360034],"genre_scores_gemma":[0.5980624,0.000002496051,0.4008958,0.0006869263,0.00006481302,0.0001585149,0.000006868729,0.00001266299,0.0001095569],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.685783,"threshold_uncertainty_score":0.9999954,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011768656","doi":"10.1109/tip.2020.2977573","title":"DDcGAN: A Dual-Discriminator Conditional Generative Adversarial Network for Multi-Resolution Image Fusion","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":1271,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Discriminator; Artificial intelligence; Dual (grammatical number); Image fusion; Computer science; Generative adversarial network; Adversarial system; Image (mathematics); Pattern recognition (psychology); Computer vision; Fusion; Image processing; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02848865391470798,"gpt":0.2827802321423681,"spread":0.2542915782276602,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000102376,0.0003407787,0.000285615,0.0001061244,0.0005699504,0.0001259493,0.0001335374,0.0001413042,0.0001293266],"category_scores_gemma":[0.00003145479,0.0003678364,0.0001564822,0.0003425004,0.0001304989,0.0009921767,0.000003332774,0.000400266,0.00003514093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535309,"about_ca_system_score_gemma":0.00006774451,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002790167,"about_ca_topic_score_gemma":0.000005774637,"domain_scores_codex":[0.9984537,0.00003769881,0.000397907,0.0004330524,0.0002460854,0.000431506],"domain_scores_gemma":[0.9992844,0.00006665887,0.00008992103,0.000145591,0.000239639,0.0001738096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003255334,0.0001589873,5.663118e-7,0.0004426611,0.00005594954,0.00002192082,0.001267802,0.1940042,0.7598936,0.00002835223,0.00693203,0.03686838],"study_design_scores_gemma":[0.001059945,0.000106429,0.000006072706,0.00008108334,0.00005785082,0.000009026931,0.0001395909,0.6796135,0.3176075,0.0002612649,0.0007218791,0.0003358981],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006617384,0.0001538227,0.9958939,0.000351413,0.0003989667,0.0007374628,0.0002950903,0.001361852,0.0001457786],"genre_scores_gemma":[0.2912788,0.00004437896,0.7071444,0.000399346,0.0004786716,0.0003913164,0.00007719619,0.000111876,0.00007391768],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4856093,"threshold_uncertainty_score":0.9998773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1580436348","doi":"10.1109/tip.2015.2442920","title":"Perceptual Quality Assessment for Multi-Exposure Image Fusion","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":1131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Image quality; Computer science; Image fusion; Artificial intelligence; Quality (philosophy); Consistency (knowledge bases); Image (mathematics); Perception; Fusion; Similarity (geometry); Pattern recognition (psychology); Computer vision; Data mining; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.06301080638396696,"gpt":0.3634518059197961,"spread":0.3004409995358292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004014138,0.0003207632,0.0003042539,0.0001868279,0.0002843689,0.0001563266,0.0002060625,0.0001374289,0.00006782453],"category_scores_gemma":[0.00002848084,0.0003264453,0.0001351749,0.0002559453,0.000110307,0.001025552,0.000002809912,0.0004272008,0.00002838593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002993697,"about_ca_system_score_gemma":0.0001030362,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008503403,"about_ca_topic_score_gemma":0.00001234748,"domain_scores_codex":[0.9983779,0.00005127187,0.000461341,0.0003781051,0.0003340515,0.0003973632],"domain_scores_gemma":[0.9989682,0.00006173951,0.00007728288,0.0003208545,0.0003778204,0.0001941283],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006976977,0.0003255622,0.000007068026,0.0003883616,0.00002159053,0.000006127458,0.001183903,0.005166802,0.6763085,0.000004067534,0.0007846619,0.3157336],"study_design_scores_gemma":[0.002656321,0.0003199268,0.0001667559,0.0002185933,0.00007259339,0.0000220935,0.002171857,0.3646564,0.6271741,0.0003738672,0.001226536,0.0009409997],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.007748726,0.0001185322,0.9884374,0.00007110876,0.000380561,0.0005634171,0.0000762309,0.001787823,0.000816196],"genre_scores_gemma":[0.4579014,0.00002513769,0.5413892,0.00005721095,0.00005217685,0.0002271945,0.000008826124,0.0000810956,0.0002578177],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4501526,"threshold_uncertainty_score":0.9999188,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117865218","doi":"10.1109/tip.2011.2108306","title":"Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Deblurring; Sparse approximation; Regularization (linguistics); Pattern recognition (psychology); Image restoration; Image (mathematics); Image processing; Representation (politics); Iterative reconstruction","retraction":null,"screen_n_in":null,"score":{"opus":0.02018690805244431,"gpt":0.2426133886187176,"spread":0.2224264805662733,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002753495,0.0003155891,0.0002256593,0.00029387,0.0007966837,0.0003455058,0.0002519333,0.0001285179,0.000006617491],"category_scores_gemma":[0.00001388178,0.0003359267,0.00003898233,0.000623423,0.0002696949,0.004622643,0.00001344711,0.0003746483,0.000004074057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001346296,"about_ca_system_score_gemma":0.0000832342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004587876,"about_ca_topic_score_gemma":0.00001499664,"domain_scores_codex":[0.9981605,0.0001037787,0.0003124991,0.0007706202,0.0002622663,0.0003902723],"domain_scores_gemma":[0.999133,0.00004070882,0.0001737198,0.0002321105,0.0002857942,0.0001346909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002782706,0.0004135066,0.00002334034,0.0001689756,0.00004479463,0.0000201824,0.007029419,0.00006928476,0.5585184,0.0008604359,0.00009804592,0.4324754],"study_design_scores_gemma":[0.000578673,0.0003629894,0.00007006415,0.0002666469,0.00004319037,0.0001547916,0.0003137642,0.6248389,0.3550688,0.01771744,0.00003673337,0.0005479527],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002309002,0.0003566262,0.9956127,0.0001118253,0.00006757552,0.0002997179,0.000007160587,0.0007677296,0.0004676071],"genre_scores_gemma":[0.3983666,0.00004166584,0.6013886,0.00005743567,0.00001238129,0.00005399659,9.145774e-7,0.00002696622,0.00005146814],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6247696,"threshold_uncertainty_score":0.9999093,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2157190232","doi":"10.1109/tip.2006.877407","title":"An edge-guided image interpolation algorithm via directional filtering and data fusion","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1040,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Interpolation (computer graphics); Stairstep interpolation; Algorithm; Ringing artifacts; Pixel; Mathematics; Bilinear interpolation; Nearest-neighbor interpolation; Image scaling; Linear interpolation; Artificial intelligence; Image resolution; Computer science; Spline interpolation; Computer vision; Image processing; Image (mathematics); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02228654803323153,"gpt":0.3156827446838025,"spread":0.2933961966505709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000345632,0.0002952256,0.0002095598,0.0003327902,0.0007573171,0.0009614898,0.0009138552,0.00009193212,0.00001579995],"category_scores_gemma":[0.00001062484,0.0003097663,0.00003783105,0.0005373763,0.0001731409,0.00838815,0.00003362954,0.0003468473,0.000008843037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008698383,"about_ca_system_score_gemma":0.00009678448,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006678666,"about_ca_topic_score_gemma":0.00001259896,"domain_scores_codex":[0.997844,0.00006969902,0.000415997,0.0009734284,0.0003481689,0.0003486641],"domain_scores_gemma":[0.9985553,0.00005312587,0.0001874064,0.0008486139,0.0002538681,0.0001016971],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007510347,0.000131363,0.000002588559,0.00004255799,0.000003523971,0.000008232578,0.00009887322,0.00005305759,0.418238,0.000004642434,0.00009106551,0.5813186],"study_design_scores_gemma":[0.0002399796,0.00005611672,0.00005564485,0.0001258111,0.00001507581,0.0001525227,0.00001542614,0.8248481,0.1710286,0.003035482,0.0001196112,0.0003075858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004170073,0.000152804,0.9971861,0.0002258906,0.000241494,0.0001886967,0.000031012,0.001294288,0.0002626905],"genre_scores_gemma":[0.1807769,0.00001677288,0.8188478,0.00008700157,0.0001073281,0.00003196274,0.00002604853,0.0000364109,0.00006973642],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8247951,"threshold_uncertainty_score":0.9999354,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2150734399","doi":"10.1109/tip.2009.2025923","title":"Complex Wavelet Structural Similarity: A New Image Similarity Index","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":661,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Similarity (geometry); Artificial intelligence; Structural similarity; Wavelet; Preprocessor; Pattern recognition (psychology); Hausdorff distance; Mathematics; Image (mathematics); Wavelet transform; Image processing; Computer vision; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01699884626942973,"gpt":0.2776693428526036,"spread":0.2606704965831739,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001014379,0.0004709863,0.0003990961,0.0003055015,0.0004221841,0.0002963696,0.0003383396,0.0001843493,0.0004200024],"category_scores_gemma":[0.00001510597,0.0005027007,0.0001515953,0.0005777337,0.0001258848,0.001449559,0.000002761143,0.0009293139,0.00003100322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001994669,"about_ca_system_score_gemma":0.00008301045,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001867776,"about_ca_topic_score_gemma":0.00001759035,"domain_scores_codex":[0.9980697,0.00003150734,0.0004689865,0.0004574202,0.0003795504,0.00059286],"domain_scores_gemma":[0.9990551,0.00004141577,0.00007940834,0.0004278901,0.0001516019,0.000244622],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005732996,0.00007404239,0.000002603734,0.0001343645,0.00002246368,0.00004388565,0.0003658651,0.004850297,0.3381568,0.00000504298,0.002241473,0.6540459],"study_design_scores_gemma":[0.00117708,0.000153816,0.0008542318,0.0002038207,0.00007253826,0.0001134418,0.0001152228,0.3959412,0.5921845,0.006474402,0.001582442,0.001127299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003832324,0.00009851767,0.9899203,0.0005246091,0.0001787572,0.0003372491,0.00004867714,0.002689275,0.002370321],"genre_scores_gemma":[0.7199554,0.00003691879,0.2791209,0.0005229983,0.00009362485,0.00001387482,0.000008562532,0.00007322884,0.0001745148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.716123,"threshold_uncertainty_score":0.9997424,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1994634851","doi":"10.1109/tip.2014.2378053","title":"SuBSENSE: A Universal Change Detection Method With Local Adaptive Sensitivity","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Video Surveillance and Tracking Methods","field":"Computer Science","cited_by":651,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; Polytechnique Montréal","funders":"Fonds de Recherche du Québec - Santé; Fonds de recherche du Québec – Nature et technologies; Université Laval","keywords":"Computer science; Artificial intelligence; Pixel; Segmentation; Background subtraction; Change detection; Computer vision; Noise (video); Sensitivity (control systems); Image segmentation; Frame (networking); Adaptation (eye); Frame rate; Analytics; Fidelity; Object detection; Pattern recognition (psychology); Image (mathematics); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02707902773261169,"gpt":0.2795606137100687,"spread":0.2524815859774571,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009869662,0.0002179807,0.0002288219,0.0002066181,0.0004458554,0.0001814398,0.0001659189,0.00008524246,0.000002913422],"category_scores_gemma":[0.000008357397,0.0001948786,0.00007176258,0.0008128394,0.0001168623,0.001325608,0.000002775443,0.0003669318,0.00001716488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009182678,"about_ca_system_score_gemma":0.00006868586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001531103,"about_ca_topic_score_gemma":0.0003712278,"domain_scores_codex":[0.998124,0.0005654758,0.0001499857,0.0005346447,0.0002940205,0.0003318931],"domain_scores_gemma":[0.9989626,0.0002884037,0.0001045227,0.0003283709,0.0002130772,0.0001030721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008539109,0.00006688095,0.00000536312,0.00002688635,0.00001747278,0.00003294165,0.000739172,0.002227929,0.007350781,0.00004408103,7.307147e-7,0.9894024],"study_design_scores_gemma":[0.0005792085,0.0003299275,0.0005496033,0.00009964441,0.00003082776,0.0002186335,0.0001369597,0.7748713,0.2225111,0.0002332141,0.000109373,0.0003302374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001849262,0.00001700774,0.9967939,0.0002505658,0.0002166079,0.0001520739,0.000002446812,0.0004066957,0.0003113919],"genre_scores_gemma":[0.660217,0.000002349047,0.3395346,0.0001451205,0.00004721167,0.00001514986,1.848125e-7,0.00001597346,0.00002240874],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9890721,"threshold_uncertainty_score":0.794692,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1976478698","doi":"10.1109/tip.2012.2221725","title":"Objective Quality Assessment of Tone-Mapped Images","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":630,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Tone mapping; Computer science; Naturalness; Artificial intelligence; Image quality; Measure (data warehouse); Visualization; Computer vision; Tone (literature); High dynamic range; Pattern recognition (psychology); Ranking (information retrieval); Image (mathematics); Dynamic range; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03168889954894181,"gpt":0.3745780248808502,"spread":0.3428891253319084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007621109,0.0002148918,0.0002709231,0.000228933,0.0002485739,0.0001496974,0.0005047617,0.00006597447,0.00003701742],"category_scores_gemma":[0.00001210857,0.0002096619,0.0001126107,0.0005548054,0.0001360031,0.002988404,0.000008013461,0.0002977083,0.00001374419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001546286,"about_ca_system_score_gemma":0.0001525801,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003385946,"about_ca_topic_score_gemma":0.00000206941,"domain_scores_codex":[0.9981714,0.0001506751,0.000431891,0.0003531535,0.0004708855,0.0004219887],"domain_scores_gemma":[0.9987801,0.0001030608,0.0002484535,0.0005034478,0.0002687787,0.0000962089],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002054778,0.001275368,0.0002446768,0.0002890079,0.00005065955,0.000003131074,0.002172752,0.00007424771,0.6652518,0.0005060508,0.0001458564,0.3299659],"study_design_scores_gemma":[0.0002632468,0.00008117792,0.002637422,0.0000943291,0.00001979647,0.00000705301,0.000125544,0.003939828,0.9922668,0.0002634786,0.00004138708,0.0002599192],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004119114,0.00009329043,0.989221,0.0001610049,0.0002894927,0.0002624165,0.000008575224,0.0004807865,0.005364298],"genre_scores_gemma":[0.6651396,0.00000907396,0.3345192,0.00007709733,0.00002647368,0.00006313421,4.97393e-7,0.00001301158,0.0001519968],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6610204,"threshold_uncertainty_score":0.8549766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2768340063","doi":"10.1109/tip.2017.2774045","title":"End-to-End Blind Image Quality Assessment Using Deep Neural Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":620,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Nvidia","keywords":"Computer science; Artificial intelligence; Artificial neural network; Normalization (sociology); Stochastic gradient descent; End-to-end principle; Pattern recognition (psychology); Distortion (music); Image quality; Activation function; Identification (biology); Gradient descent; Machine learning; Data mining; Image (mathematics); Bandwidth (computing)","retraction":null,"screen_n_in":null,"score":{"opus":0.08047933492440418,"gpt":0.3992030356415521,"spread":0.3187237007171479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001249417,0.0004402796,0.0004661625,0.0002652083,0.003016797,0.004425367,0.001731281,0.0001374269,0.00007862723],"category_scores_gemma":[0.00002981016,0.0004453942,0.0002359431,0.0003857157,0.0002550355,0.004925585,0.00004255799,0.0007792626,0.00003052635],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002829612,"about_ca_system_score_gemma":0.0002767002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003073417,"about_ca_topic_score_gemma":0.000109871,"domain_scores_codex":[0.9963349,0.0002972133,0.0007298263,0.001003372,0.0008076248,0.000827033],"domain_scores_gemma":[0.9969838,0.0001503748,0.0004904331,0.001660195,0.0003793663,0.0003358643],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001017519,0.0007743385,0.00007220406,0.0002033123,0.00008325231,0.0001233352,0.001503522,0.02755613,0.04049723,0.0002306616,0.00004334213,0.9288109],"study_design_scores_gemma":[0.00108151,0.0001110831,0.001714802,0.0001116131,0.00006138761,0.00004054073,0.0001963824,0.9779703,0.01768544,0.0003058331,0.00007089252,0.000650193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009665923,0.00005185416,0.9854372,0.002013363,0.001011021,0.0004059987,0.00001091982,0.0002751506,0.001128607],"genre_scores_gemma":[0.7289674,0.000005772833,0.270003,0.000702596,0.0001451892,0.00004417703,0.000001662437,0.00003327045,0.00009698949],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9504142,"threshold_uncertainty_score":0.9997998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099474155","doi":"10.1109/tip.2011.2173206","title":"On the Mathematical Properties of the Structural Similarity Index","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":587,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Convexity; Similarity (geometry); Mathematics; Image processing; Metric (unit); Image quality; Measure (data warehouse); Mean squared error; Computer science; Triangle inequality; Algorithm; Image (mathematics); Mathematical optimization; Artificial intelligence; Pattern recognition (psychology); Data mining; Statistics; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03735659040357165,"gpt":0.2219560915102805,"spread":0.1845995011067089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006078405,0.000124166,0.0001090188,0.00003918975,0.0001907906,0.00003423231,0.0002048711,0.00005119359,0.00005452709],"category_scores_gemma":[0.000007587988,0.00006537251,0.00006882385,0.0001307861,0.0001632643,0.0001155048,0.00000167607,0.0003023962,0.000004383234],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001952084,"about_ca_system_score_gemma":0.00001597944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008487674,"about_ca_topic_score_gemma":0.000003740823,"domain_scores_codex":[0.999433,0.00002720939,0.0001560484,0.0000957548,0.0001563303,0.0001316055],"domain_scores_gemma":[0.9996115,0.00002652666,0.00003393647,0.0002549265,0.00005443399,0.00001866901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003228249,0.0005239458,0.0000516767,0.00106075,0.0003127136,0.00001267592,0.01880778,0.02286072,0.8426936,0.001785504,0.0007196965,0.1108481],"study_design_scores_gemma":[0.00005746949,0.0000163738,0.0001001357,0.0002913367,0.00002140095,0.000008053595,0.0001112635,0.08084882,0.9129818,0.005468902,0.000003692704,0.00009073886],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.501038,0.00005068499,0.494467,0.00009531977,0.0001485301,0.0002211086,0.000003515026,0.0003536485,0.003622212],"genre_scores_gemma":[0.9981142,0.000002837906,0.001739649,0.00006766357,0.00001076356,0.00001541851,3.659876e-8,0.00002219157,0.00002719907],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4970762,"threshold_uncertainty_score":0.2665814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124378283","doi":"10.1109/tip.2008.924279","title":"Image Interpolation by Adaptive 2-D Autoregressive Modeling and Soft-Decision Estimation","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":575,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Interpolation (computer graphics); Bilinear interpolation; Artificial intelligence; Pixel; Nearest-neighbor interpolation; Autoregressive model; Ringing artifacts; Computer vision; Computer science; Image scaling; Multivariate interpolation; Stairstep interpolation; Mathematics; Image resolution; Pattern recognition (psychology); Algorithm; Image processing; Image (mathematics); Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01898285852528693,"gpt":0.2834027736628383,"spread":0.2644199151375514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001926665,0.0003303427,0.0002603509,0.0003271549,0.000987057,0.0004081012,0.0004354496,0.0001192725,0.000006334477],"category_scores_gemma":[0.00004533114,0.0003281113,0.00006553542,0.0004378867,0.000230096,0.005855639,0.00001365938,0.000439741,0.00001490649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001355181,"about_ca_system_score_gemma":0.000139239,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001437752,"about_ca_topic_score_gemma":0.000001518639,"domain_scores_codex":[0.9979963,0.00005251434,0.0004327663,0.0007352622,0.0004298619,0.0003532726],"domain_scores_gemma":[0.9987842,0.0001125942,0.0002301358,0.0003651603,0.0003789653,0.0001289794],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009477833,0.0001797858,0.00000185354,0.00006963491,0.0000136137,0.00002711262,0.002633595,0.004398694,0.08975097,0.00002181511,0.0002106611,0.9025975],"study_design_scores_gemma":[0.0003530715,0.0001069899,0.000003192965,0.0003209623,0.00001412296,0.0001422132,0.00006043165,0.9555289,0.03760136,0.005530646,0.00000800192,0.0003301747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001586623,0.0004075023,0.9962395,0.0001999659,0.0001199953,0.0002432104,0.000008801915,0.001047656,0.0001467776],"genre_scores_gemma":[0.4554348,0.00004035208,0.5443406,0.00007489853,0.00001138535,0.0000390574,0.000001502561,0.00002463319,0.00003271114],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9511302,"threshold_uncertainty_score":0.9999171,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107558608","doi":"10.1109/tip.2002.802531","title":"A comparison of computational color constancy algorithms. I: Methodology and experiments with synthesized data","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":440,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Color constancy; Standard illuminant; Computer science; Algorithm; Gamut; Color balance; Artificial intelligence; Invariant (physics); ICC profile; Color space; Computer vision; Color model; Color image; Image processing; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.1468893909024121,"gpt":0.3963490003216183,"spread":0.2494596094192062,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001005135,0.00009689259,0.0001924175,0.00006013188,0.0002529114,0.00004776951,0.0001593149,0.00001861979,0.0002133187],"category_scores_gemma":[0.000001575062,0.00008507246,0.00001781596,0.0002074002,0.0002507003,0.0002890686,0.000002983042,0.00009818812,0.000005800672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007895713,"about_ca_system_score_gemma":0.00003983456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002017502,"about_ca_topic_score_gemma":0.000002626963,"domain_scores_codex":[0.9992439,0.00003954289,0.0001954048,0.0002670719,0.000128225,0.0001258767],"domain_scores_gemma":[0.9994001,0.0001876127,0.000113354,0.0001790226,0.0000729623,0.0000469863],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008834689,0.001677345,0.0008642074,0.00005799413,0.0001180832,0.000001257274,0.003633551,0.005257657,0.02591318,0.0003848676,0.0001644962,0.961839],"study_design_scores_gemma":[0.001435428,0.0001727054,0.0002263336,0.000108314,0.0001396418,0.000008240095,0.003842334,0.8643599,0.1282396,0.0008895708,0.000264299,0.0003136275],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04003079,0.00008218462,0.9587382,0.0001707256,0.00002021377,0.0001572618,0.00007626978,0.00002147515,0.0007028583],"genre_scores_gemma":[0.8155816,0.000001440189,0.1842976,0.00001654742,0.000009949279,0.00003981256,0.000005392835,0.000006516532,0.00004118843],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9615254,"threshold_uncertainty_score":0.3469154,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2293457052","doi":"10.1109/tip.2016.2522378","title":"Median Robust Extended Local Binary Pattern for Texture Classification","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":423,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Local binary patterns; Artificial intelligence; Pattern recognition (psychology); Image texture; Pixel; Gaussian noise; Noise (video); Computer science; Feature extraction; Robustness (evolution); Computer vision; Mathematics; Image segmentation; Histogram; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.03070423329259088,"gpt":0.2769505888701037,"spread":0.2462463555775128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002439933,0.0002122604,0.0001669716,0.0002192853,0.0004000687,0.0002186684,0.0005743424,0.0001373659,0.00003284438],"category_scores_gemma":[0.00001331216,0.0001524542,0.0001187945,0.0004357938,0.0001807594,0.001339443,0.000003189853,0.0001677443,0.00005614203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001417931,"about_ca_system_score_gemma":0.0001532677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003433236,"about_ca_topic_score_gemma":0.00000402813,"domain_scores_codex":[0.9984306,0.00004986807,0.0003229394,0.0005666226,0.0002989418,0.0003310524],"domain_scores_gemma":[0.9988222,0.0001209462,0.0001524735,0.0004611826,0.0003224734,0.0001207523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000177254,0.000128803,0.000001256718,0.00004921883,0.000006370601,0.000002197431,0.0001079005,0.000006218976,0.07063071,0.00008279725,0.000165979,0.9288008],"study_design_scores_gemma":[0.0008543783,0.0002422072,0.0003053438,0.0002900822,0.00003102678,0.00003094683,0.0001293104,0.5709383,0.4230973,0.002126659,0.00145828,0.0004961416],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00002924979,0.00005380324,0.9914556,0.007006455,0.0002400525,0.0003434735,0.00002186861,0.0006689891,0.0001805825],"genre_scores_gemma":[0.9557446,0.00003656207,0.04284028,0.0003151715,0.00006524073,0.0002468411,0.000002523727,0.00002849237,0.0007202975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9557154,"threshold_uncertainty_score":0.6216904,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057065563","doi":"10.1109/tip.2014.2305844","title":"A Statistical Prediction Model Based on Sparse Representations for Single Image Super-Resolution","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":414,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Intel Collaboration Research Institute for Computational Intelligence; Azrieli Foundation","keywords":"Computer science; Artificial intelligence; Computational complexity theory; Cluster analysis; Image (mathematics); Pattern recognition (psychology); Iterative reconstruction; Resolution (logic); Artificial neural network; Algorithm; Image resolution","retraction":null,"screen_n_in":null,"score":{"opus":0.02703229031682705,"gpt":0.3031759886557877,"spread":0.2761436983389606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004198516,0.0003220487,0.0002562953,0.0003953388,0.0008691662,0.0005867786,0.0005031901,0.0001194105,0.0000089776],"category_scores_gemma":[0.000167525,0.0003387919,0.0001146368,0.000521683,0.0002184571,0.002295706,0.000005698156,0.0003548057,0.00001711908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002212124,"about_ca_system_score_gemma":0.0001975901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006551798,"about_ca_topic_score_gemma":0.000003670941,"domain_scores_codex":[0.9975274,0.0001026544,0.0004742951,0.000904017,0.0004874679,0.0005041786],"domain_scores_gemma":[0.9981846,0.0003439689,0.0001695476,0.0006772017,0.0004658085,0.0001588296],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003022589,0.001767362,0.000003518353,0.0004136794,0.00001826281,0.000007787841,0.0006108322,0.203712,0.4121841,0.001475506,0.001075112,0.3784296],"study_design_scores_gemma":[0.0006576608,0.0003346935,0.000006339228,0.0001541161,0.00003419924,0.00001134325,0.00001549916,0.8653226,0.1229744,0.01012739,0.00008606802,0.0002756763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000676104,0.00001174112,0.9955841,0.0008968011,0.0001870411,0.0005355312,0.0001082934,0.001418933,0.00118996],"genre_scores_gemma":[0.3898147,0.000001670858,0.6094173,0.0003012847,0.00003882582,0.0002912759,0.00001266713,0.00003859182,0.0000836982],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6616107,"threshold_uncertainty_score":0.9999064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152178471","doi":"10.1109/tip.2005.857260","title":"Color demosaicking via directional linear minimum mean square-error estimation","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":381,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Demosaicing; Color filter array; Mean squared error; Mathematics; Artificial intelligence; Color difference; Bayer filter; Minimum mean square error; Computer vision; Primary color; Color image; Color gel; Filter (signal processing); Computer science; Image (mathematics); Image processing; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02469161643321526,"gpt":0.3084163698651311,"spread":0.2837247534319158,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005684721,0.0002597821,0.0002290087,0.0003095034,0.0008518657,0.0004183167,0.0004301674,0.0001089123,0.00004800729],"category_scores_gemma":[0.00002146931,0.0002624239,0.0001346971,0.0007246102,0.00009146694,0.002281758,0.000004560762,0.0003720089,0.0001496686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001630918,"about_ca_system_score_gemma":0.0001759189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000170444,"about_ca_topic_score_gemma":0.00001558806,"domain_scores_codex":[0.9980055,0.0001515999,0.0004143104,0.0005514208,0.0004774997,0.0003996629],"domain_scores_gemma":[0.9989687,0.0001743698,0.0001522454,0.0003225102,0.0002526558,0.0001295142],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004666001,0.00021648,0.000001612177,0.00004933282,0.0000167279,0.00001204193,0.001235071,0.04307155,0.04488102,0.00001297015,0.00006319868,0.9103934],"study_design_scores_gemma":[0.0004771461,0.00006455751,0.00002313256,0.00008233391,0.0000250206,0.00007780129,0.00002169079,0.732765,0.2656659,0.0002831331,0.0002747085,0.0002396591],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004202287,0.000102319,0.9927041,0.00114165,0.0005108347,0.000180082,0.000003527253,0.0005302224,0.0006250063],"genre_scores_gemma":[0.477471,0.000002711031,0.5216525,0.0003514069,0.0001107477,0.0000256279,9.814275e-7,0.00002042588,0.0003646115],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9101537,"threshold_uncertainty_score":0.9999828,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102740494","doi":"10.1109/83.846244","title":"Reversible integer-to-integer wavelet transforms for image compression: performance evaluation and analysis","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":372,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Lossless compression; Lossy compression; Data compression; Integer (computer science); Image compression; Wavelet; Wavelet transform; Mathematics; Integer programming; Algorithm; Computer science; Image processing; Image (mathematics); Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.019644011928643,"gpt":0.3088845074331082,"spread":0.2892404955044652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005407458,0.0002907363,0.0003493011,0.0005675147,0.0006593753,0.0003631908,0.0006171628,0.00009312382,0.0002330244],"category_scores_gemma":[0.00001130335,0.0002537812,0.0001449931,0.001392824,0.00009729392,0.00318607,0.000006598656,0.0002925707,0.00002562084],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001085233,"about_ca_system_score_gemma":0.00009257681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008597804,"about_ca_topic_score_gemma":0.00000537217,"domain_scores_codex":[0.9978419,0.00006659023,0.0004271171,0.0007741989,0.0005013503,0.0003888502],"domain_scores_gemma":[0.9986292,0.00009969742,0.0001016982,0.0006076507,0.0003855353,0.0001762357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009573164,0.000103957,0.000002340139,0.00007616668,0.00004163548,0.000001510208,0.0005990792,0.003151439,0.01134426,0.000007529489,0.0002142684,0.9843621],"study_design_scores_gemma":[0.0005611739,0.0001526458,0.00006733804,0.000223951,0.0001754197,0.00001405989,0.00004293973,0.7659596,0.2307843,0.0004074696,0.001269789,0.0003413117],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006459496,0.00008287896,0.9910004,0.0005283377,0.0000847597,0.0007795898,0.0000517091,0.0004168733,0.0005959593],"genre_scores_gemma":[0.5140962,0.00008242927,0.4848365,0.0002707452,0.00001981473,0.0003001267,0.00001339442,0.00002219687,0.0003586411],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9840208,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170965888","doi":"10.1109/tip.2005.851684","title":"Image up-sampling using total-variation regularization with a new observation model","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":352,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Total variation denoising; Fidelity; Regularization (linguistics); Ringing artifacts; Ringing; Image processing; Mathematics; Artificial intelligence; Computer science; Human visual system model; Motion estimation; Algorithm; Sampling (signal processing); Computer vision; Image (mathematics); Enhanced Data Rates for GSM Evolution","retraction":null,"screen_n_in":null,"score":{"opus":0.04136828378637498,"gpt":0.2987543564115658,"spread":0.2573860726251908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002483511,0.0003556978,0.0002485531,0.0003651392,0.000742246,0.0009613686,0.0004717176,0.000128515,0.000007489378],"category_scores_gemma":[0.0000244729,0.000359603,0.00008403665,0.001178837,0.0000828117,0.009336212,0.000008093901,0.0003787725,0.00001032238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000363848,"about_ca_system_score_gemma":0.0005747968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002179598,"about_ca_topic_score_gemma":0.000007705697,"domain_scores_codex":[0.9977596,0.00003736266,0.0004702462,0.000764513,0.0005269233,0.0004413019],"domain_scores_gemma":[0.9984042,0.00004102088,0.0003534629,0.0005460563,0.0005162525,0.0001390271],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005701898,0.0001356445,0.000001974027,0.00009623814,0.00001740046,0.000002043989,0.001876049,0.3115555,0.4220032,0.0001383838,0.00001569025,0.2641008],"study_design_scores_gemma":[0.0004766394,0.00004497952,0.00001331069,0.0002799625,0.00004299957,0.00005054004,0.00002166699,0.8768388,0.1180362,0.003799204,0.00001395039,0.0003817884],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001377521,0.00007529562,0.9958256,0.000848002,0.00010192,0.0003261007,0.000003184319,0.001328839,0.000113468],"genre_scores_gemma":[0.1579955,0.000008394743,0.841057,0.0002528758,0.00008237483,0.00003296303,0.000003523199,0.00005976093,0.0005076454],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5652833,"threshold_uncertainty_score":0.9998856,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133807827","doi":"10.1109/tip.2002.802529","title":"A comparison of computational color constancy Algorithms. II. Experiments with image data","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Color Science and Applications","field":"Physics and Astronomy","cited_by":335,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Color constancy; Gamut; Standard illuminant; Computer science; Artificial intelligence; Algorithm; Color quantization; Data set; Color balance; Chromaticity; Color image; Preprocessor; Set (abstract data type); Computer vision; Image (mathematics); Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.05631455797539033,"gpt":0.3520835118445335,"spread":0.2957689538691432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005555313,0.0001298689,0.0001794647,0.00007195419,0.0005210381,0.00008275446,0.0002908352,0.00001871973,0.0005409598],"category_scores_gemma":[5.983467e-7,0.0001182124,0.0000327122,0.0003638667,0.0002429915,0.0006144001,0.000005049395,0.0001377035,0.00002868643],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001735162,"about_ca_system_score_gemma":0.00006824052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002195126,"about_ca_topic_score_gemma":0.000002929647,"domain_scores_codex":[0.998998,0.00001363374,0.0002524008,0.0003189256,0.0002390326,0.0001779489],"domain_scores_gemma":[0.9993371,0.00003881671,0.0001427326,0.0002813303,0.0001369617,0.00006304454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001140603,0.009502247,0.001080978,0.0001241716,0.0002264213,0.000004533145,0.009051237,0.0215854,0.06633377,0.0005366443,0.003067503,0.888373],"study_design_scores_gemma":[0.001320003,0.0002170348,0.000118848,0.0001261716,0.0000946728,0.000004078781,0.002779684,0.8671185,0.1267644,0.0003636896,0.0007263766,0.0003666216],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03936934,0.00004462248,0.9565727,0.0002120872,0.00003466215,0.000212286,0.0001937264,0.00004027442,0.003320323],"genre_scores_gemma":[0.9250572,8.200999e-7,0.0746278,0.00002283011,0.00002264583,0.00005802369,0.00002314781,0.00001165739,0.0001758554],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8880064,"threshold_uncertainty_score":0.592313,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978479866","doi":"10.1109/tip.2013.2282897","title":"Saliency-Aware Video Compression","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Visual Attention and Saliency Detection","field":"Computer Science","cited_by":328,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Computer vision; Region of interest; Artificial intelligence; Coding (social sciences); Multiview Video Coding; Data compression; Salient; Video tracking; Video processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01602340534697727,"gpt":0.271601545481045,"spread":0.2555781401340678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001158037,0.0001842671,0.0001446766,0.0002195956,0.0006151702,0.0005815729,0.0004420079,0.00007783732,0.0002284688],"category_scores_gemma":[0.000003700733,0.0001636777,0.00009826739,0.000586953,0.00006393457,0.00238852,0.00000423837,0.0002699948,0.0007346921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005490553,"about_ca_system_score_gemma":0.00005211076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004512263,"about_ca_topic_score_gemma":0.000004578213,"domain_scores_codex":[0.9985312,0.00006744153,0.0002856381,0.0004531223,0.0003565974,0.0003059985],"domain_scores_gemma":[0.999197,0.00003065767,0.00009595091,0.0003369847,0.0002066389,0.0001327616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007818702,0.000316916,0.000007619504,0.00007005638,0.000008587737,0.000004814027,0.0006412059,0.0007166662,0.09618976,0.00005656123,0.0005797379,0.9014003],"study_design_scores_gemma":[0.0007124616,0.0002139227,0.0005264776,0.0002370922,0.00001689094,0.00006405076,0.0002776587,0.7218831,0.2731273,0.001738084,0.0006584569,0.0005445218],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009058808,0.00003047351,0.9875393,0.0006985179,0.0006221477,0.0002153757,0.00000143038,0.0006142468,0.001219728],"genre_scores_gemma":[0.9802625,0.000009326546,0.01839284,0.000397661,0.00003335246,0.00009180316,6.913405e-7,0.00001699907,0.0007948514],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9712037,"threshold_uncertainty_score":0.9443226,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2618902759","doi":"10.1109/tip.2017.2708503","title":"dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Australian Research Council; Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Image quality; Robustness (evolution); Ground truth; Pairwise comparison; Image (mathematics); Image processing; Pattern recognition (psychology); Contextual image classification; Perception; Automatic image annotation","retraction":null,"screen_n_in":null,"score":{"opus":0.05090376900713953,"gpt":0.3795690622439164,"spread":0.3286652932367768,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001744289,0.0005646732,0.0005894256,0.0002715683,0.004109459,0.005585475,0.002137985,0.0001518165,0.0001381206],"category_scores_gemma":[0.00008666245,0.0005566371,0.0002855604,0.0003430552,0.0003629217,0.006422008,0.00005523099,0.001074173,0.0003017781],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003087029,"about_ca_system_score_gemma":0.0004281813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004813555,"about_ca_topic_score_gemma":0.00005237021,"domain_scores_codex":[0.9953563,0.0004218861,0.0008270322,0.001331964,0.001057798,0.001005055],"domain_scores_gemma":[0.9965227,0.0001865047,0.0005654133,0.001809002,0.0004893885,0.0004270317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002326063,0.002823962,0.00009507838,0.001020617,0.000165792,0.0001623144,0.006582985,0.0005475704,0.4352764,0.0003291326,0.005197329,0.5475662],"study_design_scores_gemma":[0.00897271,0.001622098,0.006069235,0.001108103,0.0004107407,0.00009218531,0.005576351,0.1554297,0.8002633,0.003359772,0.01206541,0.005030344],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006411296,0.00005302344,0.9783934,0.007229899,0.0005381498,0.0005418882,0.00003874151,0.0005047432,0.006288832],"genre_scores_gemma":[0.7848831,0.00003016158,0.2108975,0.0005965321,0.00008890436,0.0001899133,0.000008369342,0.00006209146,0.00324336],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7784718,"threshold_uncertainty_score":0.9996885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2021586009","doi":"10.1109/tip.2007.902329","title":"Median Filtering in Constant Time","year":2007,"lang":"en","type":"letter","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":313,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Kernel (algebra); Constant (computer programming); Algorithm; Computational complexity theory; Filter (signal processing); Simple (philosophy); Image processing; Computer science; Mathematics; Image (mathematics); Computer vision; Artificial intelligence; Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02287642240894619,"gpt":0.2833681163560103,"spread":0.2604916939470641,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0008501298,0.0004769799,0.0005189164,0.001112337,0.0002834065,0.0007474018,0.001036764,0.0005628977,0.0001004409],"category_scores_gemma":[0.000016602,0.0004872579,0.0001758565,0.00097239,0.0001749211,0.001084082,0.000006749529,0.002750909,0.000239157],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002223186,"about_ca_system_score_gemma":0.000329672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003149993,"about_ca_topic_score_gemma":0.000006503119,"domain_scores_codex":[0.9968593,0.000221364,0.0006063178,0.0008567902,0.0006465429,0.0008096725],"domain_scores_gemma":[0.9985892,0.0003475844,0.0001953135,0.0006190427,0.0001524647,0.00009638811],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004668478,0.0001503644,3.147813e-7,0.0006474651,0.00003729622,0.008844186,0.001532451,0.0003401701,0.03448611,0.000002743996,0.06806857,0.8858436],"study_design_scores_gemma":[0.005370737,0.0005054764,0.000008239118,0.007345425,0.0002396477,0.002398621,0.00008905344,0.2967605,0.4788018,0.004338935,0.1982124,0.005929161],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000008765676,0.000145617,0.931965,0.0628042,0.0007194959,0.0002059442,0.00001259949,0.0003152029,0.003823189],"genre_scores_gemma":[0.002321246,0.0000351315,0.6439173,0.3474577,0.0009435032,0.00006110522,0.00001277293,0.0001500406,0.005101198],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8799145,"threshold_uncertainty_score":0.9997579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117644767","doi":"10.1109/tip.2013.2251643","title":"Image Sharpness Assessment Based on Local Phase Coherence","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":294,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Coherence (philosophical gambling strategy); Image quality; Computation; Visualization; Computer vision; Wavelet; Wavelet transform; Human visual system model; Image (mathematics); Pattern recognition (psychology); Perspective (graphical); Algorithm; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02610278820586157,"gpt":0.340748928605825,"spread":0.3146461403999634,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000396144,0.0003794016,0.0003134951,0.0002787249,0.0006369383,0.001487208,0.0008816205,0.00009910604,0.0004596375],"category_scores_gemma":[0.000007142768,0.0003526254,0.0001515586,0.0006761694,0.0002066426,0.003026654,0.00000708361,0.0005916121,0.0004568493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002737057,"about_ca_system_score_gemma":0.0004845638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009636828,"about_ca_topic_score_gemma":0.000006257294,"domain_scores_codex":[0.997147,0.0001857612,0.000491888,0.0008124483,0.0007704372,0.0005924378],"domain_scores_gemma":[0.9982385,0.0001783353,0.0001768145,0.000787375,0.0003824369,0.0002365229],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003648361,0.002672769,0.000002632579,0.0002413568,0.00002318926,0.00006231923,0.0004308222,0.002783212,0.04599112,0.0001021994,0.000686184,0.9469677],"study_design_scores_gemma":[0.001659469,0.000415453,0.00007306638,0.0002203906,0.00002294622,0.00001107902,0.0001989283,0.888195,0.1082095,0.000394105,0.0001419156,0.0004581666],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001093278,0.00001638614,0.9921263,0.002387885,0.0003435766,0.0005170097,0.00001396322,0.0004383257,0.003063284],"genre_scores_gemma":[0.7767739,0.000002206852,0.2209328,0.001735615,0.00003709569,0.0002912128,0.000003524339,0.00002829735,0.0001954208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9465095,"threshold_uncertainty_score":0.9998926,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133251102","doi":"10.1109/tip.2005.864165","title":"Quality-aware images","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":291,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Image quality; Computer vision; Digital watermarking; Quantization (signal processing); Decoding methods; Image (mathematics); Pattern recognition (psychology); Image processing; Transform coding; Information hiding; Wavelet; Wavelet transform; Discrete cosine transform; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01561779813647675,"gpt":0.2873651539594971,"spread":0.2717473558230203,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001825502,0.0001845061,0.0001574046,0.0002260045,0.0004883495,0.000347446,0.0004801094,0.00006372971,0.000006416196],"category_scores_gemma":[0.00000152386,0.0001738037,0.0001146646,0.000526679,0.000101877,0.001500535,0.000002975669,0.0002420176,0.00001415872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003295246,"about_ca_system_score_gemma":0.00003711138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003424008,"about_ca_topic_score_gemma":0.000005861255,"domain_scores_codex":[0.9987211,0.00005844689,0.0002780468,0.0003974844,0.000244821,0.0003000816],"domain_scores_gemma":[0.9993148,0.0000486619,0.00009857881,0.0003762514,0.0001142075,0.00004749195],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003580502,0.0005110157,0.0000702067,0.0002019231,0.00001727551,0.00005370246,0.0003840255,0.001220976,0.07505111,0.001277154,0.0006115785,0.9205652],"study_design_scores_gemma":[0.0003882887,0.00007404172,0.0004273785,0.000145989,0.00001194114,0.00004156394,0.00003437394,0.009186012,0.9642153,0.02396335,0.0009455106,0.0005663042],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007373951,0.00007952465,0.9948207,0.0003047689,0.0001461106,0.0001043117,0.000007450421,0.001260081,0.002539643],"genre_scores_gemma":[0.7600801,0.000007706373,0.2394117,0.0001296431,0.00003292799,0.00003299334,9.365738e-7,0.00001378592,0.0002902033],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9199989,"threshold_uncertainty_score":0.7087508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158546915","doi":"10.1109/tip.2011.2161092","title":"A Psychovisual Quality Metric in Free-Energy Principle","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":277,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Metric (unit); Artificial intelligence; Image quality; Computer science; Generative model; Quality (philosophy); Computer vision; Distortion (music); Inference; Free energy principle; Perception; Pattern recognition (psychology); Energy (signal processing); Visual perception; Human visual system model; Mathematics; Image (mathematics); Generative grammar; Machine learning; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.07274054522858554,"gpt":0.3658557537077318,"spread":0.2931152084791463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006876179,0.0002059327,0.000235008,0.0005446755,0.0001891135,0.00023227,0.0008492753,0.00008900734,0.0000613931],"category_scores_gemma":[0.00001812632,0.0002097467,0.0001035469,0.001583026,0.00007641257,0.00206295,0.000008995016,0.0003107149,0.00003735758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001199139,"about_ca_system_score_gemma":0.000187006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006340573,"about_ca_topic_score_gemma":0.000201408,"domain_scores_codex":[0.9978986,0.0002090525,0.0005002185,0.0005525247,0.0004112957,0.0004282778],"domain_scores_gemma":[0.9988542,0.00007532062,0.0001367436,0.0006899112,0.000128704,0.000115109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009811395,0.00306538,0.00007151337,0.0002432605,0.00004132465,0.00008964065,0.006227995,0.0001829733,0.003111523,0.007516926,0.0002432153,0.9791082],"study_design_scores_gemma":[0.009204481,0.001345921,0.01033041,0.000893257,0.000120137,0.000185705,0.001967306,0.1992965,0.6987928,0.06875799,0.005247177,0.003858323],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00165971,0.0002272494,0.9921186,0.0004061364,0.0003971369,0.0001017322,0.000004743555,0.0002219866,0.004862725],"genre_scores_gemma":[0.8444598,0.00002373562,0.1542465,0.00056937,0.00002773294,0.00005034369,4.866627e-7,0.00001746469,0.0006046146],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9752498,"threshold_uncertainty_score":0.8553223,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115514375","doi":"10.1109/tip.2005.871116","title":"Lossless compression of color mosaic images","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Lossless compression; Lossy compression; Data compression; Decorrelation; Wavelet transform; Computer science; Artificial intelligence; Computer vision; Image compression; Mathematics; Pattern recognition (psychology); Algorithm; Wavelet; Image processing; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01108228063322351,"gpt":0.2715032746363414,"spread":0.2604209940031179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001398638,0.0002261953,0.0002707975,0.000258126,0.0003177296,0.0001630898,0.0008523181,0.00008313718,0.00002320417],"category_scores_gemma":[0.000004987919,0.0002060405,0.00008707745,0.0005731596,0.0001827435,0.001811323,0.000013336,0.0002695593,0.00001517909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005077527,"about_ca_system_score_gemma":0.0000762675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004131548,"about_ca_topic_score_gemma":0.000003335069,"domain_scores_codex":[0.9983192,0.00006542793,0.000438461,0.0004866053,0.0003969851,0.0002933148],"domain_scores_gemma":[0.998734,0.0001007721,0.0002522186,0.0006197681,0.000227712,0.00006552742],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004650028,0.0006209322,0.00001116267,0.0001901143,0.000008138526,0.00002019362,0.0001073562,0.004926986,0.6924867,0.0002808611,0.001867527,0.2994335],"study_design_scores_gemma":[0.0003336734,0.00006193418,0.00006823812,0.0002691603,0.00001034471,0.00001764558,0.00001523792,0.04932609,0.9470801,0.00213744,0.0004543758,0.0002258076],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002049309,0.0001851129,0.9957672,0.0001394519,0.0001576899,0.000205453,0.00005091149,0.0006561596,0.0007886792],"genre_scores_gemma":[0.6394745,0.00001235246,0.3601928,0.00004843238,0.00001930909,0.00003977638,0.000003837505,0.00001822223,0.000190807],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6374251,"threshold_uncertainty_score":0.8402087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1971155098","doi":"10.1109/tip.2012.2197011","title":"Reduced-Reference Image Quality Assessment by Structural Similarity Estimation","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":273,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Image quality; Deblurring; Normalization (sociology); Artificial intelligence; Distortion (music); Pattern recognition (psychology); Computer science; Measure (data warehouse); Mathematics; Image (mathematics); Image processing; Image warping; Computer vision; Image restoration; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.05673192634484304,"gpt":0.3860202134126988,"spread":0.3292882870678558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009601257,0.0003441599,0.0003171129,0.0001431962,0.0008244822,0.0008618578,0.0006434137,0.0001246082,0.00009097117],"category_scores_gemma":[0.00001996539,0.0003319047,0.0001161624,0.0004846081,0.0001397391,0.00623257,0.00001175185,0.0006415516,0.00005815921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002946438,"about_ca_system_score_gemma":0.0002466718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009245455,"about_ca_topic_score_gemma":0.000006007304,"domain_scores_codex":[0.9970712,0.0003312086,0.0006062817,0.0005760351,0.0007334177,0.0006818578],"domain_scores_gemma":[0.9984215,0.000142037,0.0002781399,0.0006485526,0.0002582753,0.0002515308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003822305,0.001074896,0.00007292556,0.0004629131,0.00006408687,0.000005979567,0.002982515,0.000589256,0.2630461,0.001315234,0.001216154,0.7291318],"study_design_scores_gemma":[0.001386647,0.0001953888,0.004871518,0.0001903045,0.0001044899,0.00005821037,0.000570983,0.3577159,0.6296369,0.003224431,0.0005208544,0.0015244],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01418141,0.00009726352,0.9817386,0.00136829,0.0004838831,0.0002596795,0.00004302443,0.000399182,0.001428611],"genre_scores_gemma":[0.7137914,0.000006823216,0.2855725,0.0003658676,0.00004159834,0.00004807136,0.00001215886,0.00001711726,0.0001444403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7276074,"threshold_uncertainty_score":0.9999133,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3035441328","doi":"10.1109/tip.2020.2999855","title":"MEF-GAN: Multi-Exposure Image Fusion via Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Fusion Techniques","field":"Engineering","cited_by":269,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Natural Science Foundation of Hubei Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Discriminator; Computer science; Artificial intelligence; Generator (circuit theory); Ground truth; Image (mathematics); Code (set theory); Representation (politics); Distortion (music); Pattern recognition (psychology); Computer vision; Luminance; Fusion rules; Adversarial system; Image fusion; Power (physics); Detector","retraction":null,"screen_n_in":null,"score":{"opus":0.01247397889139607,"gpt":0.2429420180283638,"spread":0.2304680391369678,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009206434,0.0004248784,0.0003449797,0.0001358621,0.0004092221,0.0001620772,0.0002526116,0.0001926712,0.0002329234],"category_scores_gemma":[0.00001428849,0.0004441262,0.0001460079,0.0005501086,0.0001195081,0.001145122,0.00000394758,0.0008155978,0.00006774588],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001197447,"about_ca_system_score_gemma":0.00003902272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005728297,"about_ca_topic_score_gemma":0.000007516003,"domain_scores_codex":[0.9982999,0.00005217186,0.0004403435,0.0004871904,0.0002752482,0.0004451626],"domain_scores_gemma":[0.9992264,0.00004254948,0.00008498726,0.0002458247,0.0001761096,0.0002241403],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007665569,0.00008183822,8.688401e-7,0.0001096627,0.00003051178,0.0000372943,0.0008775787,0.1572012,0.6410043,3.662361e-7,0.0004329285,0.2001468],"study_design_scores_gemma":[0.0005745672,0.00008065336,0.000003517379,0.0000589683,0.00003655821,0.000009102556,0.00009008704,0.562203,0.4363379,0.00001525487,0.0002680974,0.0003222325],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006793462,0.0003709168,0.995023,0.0002415482,0.0004564947,0.0004112017,0.00002825366,0.00229259,0.000496661],"genre_scores_gemma":[0.7127944,0.0001425882,0.2861301,0.0003690046,0.0002778054,0.00008393497,0.000009687074,0.0001326515,0.00005977827],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7121151,"threshold_uncertainty_score":0.999801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136001449","doi":"10.1109/tip.2011.2150235","title":"Generalized Random Walks for Fusion of Multi-Exposure Images","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":236,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Beihang University","keywords":"Image fusion; Artificial intelligence; Computer science; Probabilistic logic; Fusion; Computer vision; Image (mathematics); Image quality; Consistency (knowledge bases); Random walk; Random walker algorithm; Pattern recognition (psychology); Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03384658412296238,"gpt":0.2831074663206645,"spread":0.2492608821977021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000343461,0.0002135874,0.0002734224,0.0002392468,0.0002705983,0.00009983799,0.0005708917,0.00008246017,0.00003804391],"category_scores_gemma":[0.0000128064,0.0001967015,0.0001590286,0.0003223741,0.0001067004,0.001185484,0.00000533321,0.0001544253,0.000006531116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003516636,"about_ca_system_score_gemma":0.00007769632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002730007,"about_ca_topic_score_gemma":0.000004933694,"domain_scores_codex":[0.9985878,0.00005819934,0.0004059118,0.000418071,0.0002313808,0.0002986736],"domain_scores_gemma":[0.9989386,0.00005254753,0.0001976441,0.0004177491,0.0003335812,0.00005992758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001989703,0.0005325271,0.000003978724,0.0001992817,0.00002347019,0.000004603652,0.00178847,0.00003940672,0.6260961,0.00004063559,0.0001253687,0.3709472],"study_design_scores_gemma":[0.002216116,0.0001980673,0.00002994998,0.0001111207,0.00003070249,0.000006503648,0.00002966313,0.03529455,0.961476,0.0003391658,0.00005089869,0.0002172085],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002283947,0.0001718093,0.9958271,0.00006329237,0.0002488368,0.0005667948,0.00001207117,0.0004723285,0.0003537555],"genre_scores_gemma":[0.4702047,0.00002490715,0.5292849,0.00006262217,0.00001274875,0.0001397986,7.849465e-7,0.00001774341,0.0002518295],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4679207,"threshold_uncertainty_score":0.8021254,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091659514","doi":"10.1109/tip.2006.888341","title":"Adaptive Directional Lifting-Based Wavelet Transform for Image Coding","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":218,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Artificial intelligence; Wavelet transform; Computer vision; Lifting scheme; Wavelet; Computer science; Second-generation wavelet transform; Transform coding; Pixel; Discrete wavelet transform; Image resolution; Coding (social sciences); Stationary wavelet transform; Mathematics; Pattern recognition (psychology); Image (mathematics); Discrete cosine transform","retraction":null,"screen_n_in":null,"score":{"opus":0.02839448410608021,"gpt":0.3048546841069855,"spread":0.2764602000009053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00144934,0.0002994215,0.0002742001,0.0004144634,0.001028089,0.0004748448,0.000453449,0.0001164925,0.0000203225],"category_scores_gemma":[0.00003076636,0.0002997913,0.0002461564,0.0007524765,0.0001360697,0.001470912,0.000001861577,0.0003913386,0.00001737443],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602053,"about_ca_system_score_gemma":0.0002520086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001498611,"about_ca_topic_score_gemma":0.00001302525,"domain_scores_codex":[0.9978096,0.00006896399,0.000453729,0.0006090729,0.0004278019,0.0006308061],"domain_scores_gemma":[0.998405,0.0005976391,0.0001357555,0.0002735503,0.0004271321,0.0001608865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003340894,0.0002543033,4.421074e-7,0.0001252401,0.00002730061,0.00003711248,0.0007496567,0.0007670952,0.09881482,0.00008514259,0.00008010397,0.8987247],"study_design_scores_gemma":[0.001405377,0.0002036374,0.00001994526,0.000146584,0.00003667788,0.0000410738,0.00007461571,0.2488366,0.7474216,0.001085143,0.0003585436,0.0003701435],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002040165,0.00005991962,0.9954101,0.000577092,0.0005611022,0.0003817801,0.00001889984,0.0004545835,0.002332468],"genre_scores_gemma":[0.3913676,0.000002364181,0.607785,0.0004096055,0.00009615226,0.00004475349,0.000001724914,0.00003150365,0.0002612542],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8983545,"threshold_uncertainty_score":0.9999454,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132817297","doi":"10.1109/83.855434","title":"Comparametric equations with practical applications in quantigraphic image processing","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Vision and Imaging","field":"Computer Science","cited_by":217,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Massachusetts Institute of Technology","keywords":"Homomorphic filtering; Image processing; Homomorphic encryption; Filter (signal processing); Computer vision; Function (biology); Monotonic function; Computer science; Artificial intelligence; Image (mathematics); Mathematics; Algorithm; Mathematical analysis; Image enhancement","retraction":null,"screen_n_in":null,"score":{"opus":0.02724392700817486,"gpt":0.3300497000328361,"spread":0.3028057730246612,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002413698,0.0002936308,0.0002781909,0.0008063257,0.0007741681,0.0007345506,0.0004667819,0.00006670585,0.0000794568],"category_scores_gemma":[0.00001660724,0.0002626255,0.0000737454,0.004337246,0.0002276381,0.003955989,0.000003244198,0.0006465783,0.0001011553],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008750283,"about_ca_system_score_gemma":0.0002918507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001973638,"about_ca_topic_score_gemma":0.0000242006,"domain_scores_codex":[0.9977494,0.0000806622,0.0004616047,0.0007304978,0.0004763915,0.000501471],"domain_scores_gemma":[0.9987461,0.0002392253,0.0001487909,0.0004842176,0.0002154196,0.0001662459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003846486,0.0008391996,0.00002819025,0.00008887616,0.00000839998,0.00002248526,0.0007215392,0.005358444,0.002389924,0.0002133778,0.00001411642,0.990277],"study_design_scores_gemma":[0.001061365,0.0001154172,0.0004281324,0.0003283189,0.00003544087,0.00009886046,0.0003827453,0.9841176,0.0110401,0.001071005,0.0007140919,0.0006069199],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001765395,0.0001747791,0.9943017,0.001120842,0.00003296008,0.0004301097,0.000003534335,0.0004238585,0.001746868],"genre_scores_gemma":[0.6032949,0.00002781125,0.3962069,0.0001874734,0.00001312947,0.0001334685,0.000001649795,0.00002293371,0.0001116768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.98967,"threshold_uncertainty_score":0.9999826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142916759","doi":"10.1109/tip.2010.2066982","title":"Multiregion Image Segmentation by Parametric Kernel Graph Cuts","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Medical Image Segmentation Techniques","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"General Electric (Canada); Institut National de la Recherche Scientifique","funders":"","keywords":"Piecewise; Synthetic aperture radar; Cut; Image segmentation; Kernel (algebra); Mathematics; Algorithm; Graph; Artificial intelligence; Computer science; Segmentation; Pattern recognition (psychology); Discrete mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01199099904626377,"gpt":0.2887294864777191,"spread":0.2767384874314553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003478265,0.0002752194,0.00020182,0.0005201803,0.0004476474,0.0006639208,0.0006597695,0.0001390339,0.00009820223],"category_scores_gemma":[0.00003738108,0.000271724,0.0001115996,0.001369221,0.0002380154,0.002829962,0.000005314942,0.0006850855,0.0001048322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006622836,"about_ca_system_score_gemma":0.00009498875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004725183,"about_ca_topic_score_gemma":0.000008277012,"domain_scores_codex":[0.9978142,0.00008366338,0.0004336112,0.0006441681,0.0006313021,0.0003930294],"domain_scores_gemma":[0.9987096,0.0001250594,0.0002148198,0.000483456,0.000238503,0.0002286011],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006695616,0.0002245774,0.000003898137,0.00003936391,0.000007211813,0.000007481672,0.000289961,0.000008811054,0.5296564,0.000005503203,0.001233238,0.4685169],"study_design_scores_gemma":[0.0005780043,0.00007847014,0.00002986832,0.00004540166,0.00002167028,0.00003246927,0.00007050623,0.03442559,0.9638802,0.0004168332,0.0001039553,0.0003170565],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004099212,0.00004221783,0.9930835,0.000512337,0.0005063855,0.0003811372,0.00001053178,0.0009743909,0.0003902453],"genre_scores_gemma":[0.3645551,0.00004049214,0.6342663,0.0005834053,0.00003216162,0.0001359824,0.000006959135,0.00003044051,0.0003492323],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4681999,"threshold_uncertainty_score":0.9999735,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121490093","doi":"10.1109/tip.2008.920761","title":"Segmentation by Fusion of Histogram-Based $K$-Means Clusters in Different Color Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":212,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Artificial intelligence; Segmentation; Scale-space segmentation; Histogram; Image segmentation; Computer science; Segmentation-based object categorization; Pattern recognition (psychology); Cluster analysis; Computer vision; Minimum spanning tree-based segmentation; Partition (number theory); Region growing; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01456037304867612,"gpt":0.2304219958023646,"spread":0.2158616227536885,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000716208,0.0002018864,0.0002121469,0.0002978913,0.0001368571,0.00003822655,0.00008533608,0.00008594163,0.00001703761],"category_scores_gemma":[0.000005208276,0.0002045238,0.00006486219,0.0003667095,0.0001298136,0.0003061933,4.986694e-7,0.0002110004,0.00000906298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003078429,"about_ca_system_score_gemma":0.0000383175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002536539,"about_ca_topic_score_gemma":0.0000293386,"domain_scores_codex":[0.9989325,0.00003929051,0.000352278,0.000220405,0.0002462456,0.0002092341],"domain_scores_gemma":[0.9995691,0.00005250045,0.00008859216,0.0001639138,0.00007133448,0.00005455098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004462305,0.0001938375,0.00004834039,0.0002361867,0.000008215648,0.000004596426,0.0007540923,0.1042096,0.8468335,8.728131e-8,0.0001966784,0.04747019],"study_design_scores_gemma":[0.000571596,0.00003276215,0.0002553797,0.0001324387,0.00001802386,0.000005126642,0.000151061,0.5014843,0.4971523,0.000001971866,0.00004560561,0.0001494632],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.351449,0.0000736181,0.6477578,0.00009718201,0.0001418978,0.000177918,0.000009085115,0.0001589157,0.0001345854],"genre_scores_gemma":[0.9845334,0.0000470954,0.01522207,0.00002741319,0.00001215304,0.00002075948,0.00001451116,0.00004656032,0.00007601187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6330844,"threshold_uncertainty_score":0.8340238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028735463","doi":"10.1109/tip.2014.2325777","title":"BRINT: Binary Rotation Invariant and Noise Tolerant Texture Classification","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":206,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Local binary patterns; Pattern recognition (psychology); Artificial intelligence; Histogram; Robustness (evolution); Gaussian noise; Mathematics; Binary number; Noise (video); Noise measurement; Computer science; Speckle noise; Cluster analysis; Invariant (physics); Salt-and-pepper noise; Computer vision; Noise reduction; Image processing; Median filter; Speckle pattern; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01719277211950108,"gpt":0.255102214181843,"spread":0.2379094420623419,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003248448,0.0001769324,0.0001507136,0.0002040567,0.0004410393,0.0004608835,0.0003011879,0.00009575428,0.0000111948],"category_scores_gemma":[0.00001541582,0.0001629338,0.00004898055,0.0004952375,0.00009952256,0.001284565,0.000003776879,0.0002558937,0.00003361552],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005294471,"about_ca_system_score_gemma":0.0000677522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001053684,"about_ca_topic_score_gemma":0.000001992879,"domain_scores_codex":[0.9986919,0.00009253394,0.000281845,0.0004709236,0.0002582951,0.0002044872],"domain_scores_gemma":[0.9991521,0.00006382511,0.0001419594,0.0003509352,0.0001962063,0.00009493936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001535125,0.0001105303,0.000004703777,0.00007087254,0.00000461005,0.000001731748,0.0004291255,0.00003852979,0.1578722,0.000883804,0.00002926661,0.8405393],"study_design_scores_gemma":[0.0003012167,0.0001059381,0.001334292,0.0001083129,0.0000174545,0.00003514849,0.00006328033,0.8372194,0.1587293,0.001333023,0.0004948636,0.000257761],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001289807,0.0000696673,0.9948277,0.002201623,0.0001122361,0.0002115612,0.000002492257,0.0004763384,0.0008085367],"genre_scores_gemma":[0.9497463,0.00004275884,0.04951815,0.0003596831,0.00003584374,0.00006184239,0.000002117303,0.0000162387,0.0002170952],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9484565,"threshold_uncertainty_score":0.6644246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147176572","doi":"10.1109/83.892442","title":"Multiscale MAP filtering of SAR images","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":197,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Wavelet; Artificial intelligence; Synthetic aperture radar; Filter (signal processing); Multiplicative noise; Maximum a posteriori estimation; Probability density function; Pattern recognition (psychology); Mathematics; Computer science; Radar imaging; Noise (video); Wavelet transform; Computer vision; Algorithm; Radar; Image (mathematics); Statistics; Transmission (telecommunications)","retraction":null,"screen_n_in":null,"score":{"opus":0.02296851443374905,"gpt":0.2917137893126666,"spread":0.2687452748789175,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000312576,0.0001792775,0.0002184485,0.0002250997,0.000280093,0.0002350327,0.0005059224,0.00005862866,0.00004617868],"category_scores_gemma":[0.000009373901,0.0001740633,0.0001129088,0.0004851918,0.0001057009,0.00130858,0.000005087678,0.0002285704,0.00004140546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003205191,"about_ca_system_score_gemma":0.00005759959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002514653,"about_ca_topic_score_gemma":0.000001609297,"domain_scores_codex":[0.998642,0.00008787221,0.0003142494,0.000368654,0.0002805726,0.0003067132],"domain_scores_gemma":[0.9991782,0.00009593333,0.0001097688,0.0003790493,0.0001578057,0.00007923532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003445488,0.0001516388,0.000006998951,0.0001047408,0.00001148721,0.00005431056,0.0005925266,0.001189409,0.3852157,0.00000683642,0.00008040419,0.6125515],"study_design_scores_gemma":[0.0006662167,0.00008217755,0.000105368,0.0002028456,0.00001956606,0.00009269729,0.00004516445,0.06826844,0.9293551,0.0004021079,0.0005003317,0.0002599787],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002963896,0.0001872736,0.9945917,0.0002477064,0.0003325934,0.00009488805,0.000004084493,0.000208,0.001369819],"genre_scores_gemma":[0.5228794,0.0000167799,0.475949,0.00008692029,0.0000302652,0.000005912969,2.549829e-7,0.0000159876,0.001015495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6122916,"threshold_uncertainty_score":0.7098094,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171033838","doi":"10.1109/83.846242","title":"Context-based lossless interband compression-extending CALIC","year":2000,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Data Compression Techniques","field":"Computer Science","cited_by":196,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Lossless compression; Computer science; Context (archaeology); Data compression; Theoretical computer science; Computer engineering; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01610106005243912,"gpt":0.2858564250416775,"spread":0.2697553649892384,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001709003,0.0003171389,0.0002942701,0.0002695899,0.0006602614,0.0004715081,0.001102797,0.0001012679,0.0003668366],"category_scores_gemma":[0.000006152717,0.0002898711,0.0001147288,0.0005670828,0.0001734749,0.002048697,0.000007171298,0.0004912132,0.0001082875],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001003968,"about_ca_system_score_gemma":0.0001030981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002183965,"about_ca_topic_score_gemma":0.000005562669,"domain_scores_codex":[0.9979082,0.0001002891,0.0004220782,0.0007145826,0.0004132507,0.0004415804],"domain_scores_gemma":[0.9986503,0.0001361266,0.0001312998,0.0007768656,0.0001273017,0.000178099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004681536,0.0002164734,0.000001996977,0.00005309049,0.000006553034,0.00002668927,0.0001790371,0.001944222,0.01570798,0.00003326073,0.0003583987,0.9814255],"study_design_scores_gemma":[0.0008213892,0.0001017313,0.00001925251,0.00092136,0.00001620145,0.0000456991,0.00003892879,0.3564899,0.6336393,0.0008391533,0.006532142,0.0005349444],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001686324,0.0002149092,0.9951234,0.0003767635,0.0002097686,0.0002354674,0.00002514678,0.001243407,0.0008848166],"genre_scores_gemma":[0.8315367,0.00002485226,0.1671509,0.0007548376,0.00002795977,0.0000818897,0.000003218238,0.00003376479,0.0003859168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9808905,"threshold_uncertainty_score":0.9999554,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160966992","doi":"10.1109/tip.2005.849319","title":"Design-based texture feature fusion using Gabor filters and co-occurrence probabilities","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":195,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Feature (linguistics); Gabor filter; Segmentation; Feature vector; Image segmentation; Feature extraction; Computer science; Dimensionality reduction; Filter (signal processing); Image texture; Computer vision; Mathematics; Curse of dimensionality; Principal component analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.03100211643617404,"gpt":0.2887564253924473,"spread":0.2577543089562733,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002391691,0.0002233516,0.0001649081,0.0001955522,0.0005572727,0.0004838381,0.0003324146,0.0001126377,0.00001774373],"category_scores_gemma":[0.00001011949,0.0001975964,0.00005496692,0.0004791702,0.0001816617,0.001263977,0.000002749501,0.000330316,0.000007065823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001036431,"about_ca_system_score_gemma":0.0002310443,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003019566,"about_ca_topic_score_gemma":9.664851e-7,"domain_scores_codex":[0.9986643,0.0000851745,0.0002088746,0.0004737291,0.0002925971,0.0002753034],"domain_scores_gemma":[0.9992135,0.00008713712,0.0001145666,0.0002989607,0.0001899224,0.00009591865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004566242,0.0001856359,0.000004409665,0.0002000091,0.000006444906,0.000004141045,0.0008793328,0.001371436,0.1126471,0.00001853539,0.000201922,0.8844354],"study_design_scores_gemma":[0.000216149,0.00006397519,0.00001160311,0.0001519442,0.00001342509,0.00002233969,0.00004433229,0.5278739,0.4707729,0.0001147755,0.0004863263,0.0002283338],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005775324,0.0002226064,0.9967446,0.00152932,0.0000679136,0.0003139897,0.00002263608,0.0004644642,0.00005692937],"genre_scores_gemma":[0.5200142,0.00002319386,0.4794263,0.0003538321,0.00002710335,0.00003529127,0.000001963191,0.00001189579,0.0001062351],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.884207,"threshold_uncertainty_score":0.8057747,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152594362","doi":"10.1109/tip.2004.834664","title":"Unsupervised Learning of a Finite Mixture Model Based on the Dirichlet Distribution and Its Application","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Bayesian Methods and Mixture Models","field":"Computer Science","cited_by":194,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec en Outaouais; Université de Sherbrooke","funders":"","keywords":"Automatic summarization; Mixture model; Computer science; Dirichlet distribution; Artificial intelligence; Pattern recognition (psychology); Data modeling; Latent Dirichlet allocation; Machine learning; Mathematics; Topic model","retraction":null,"screen_n_in":null,"score":{"opus":0.01421025074941218,"gpt":0.2553749113308786,"spread":0.2411646605814664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003241954,0.0001469859,0.0001331382,0.00007449997,0.0003749863,0.0001029872,0.0002398677,0.00007517565,0.000001593396],"category_scores_gemma":[0.00001922836,0.0001102283,0.00005634189,0.0004402828,0.00005028451,0.0003612473,0.00000233341,0.00033219,0.00000237718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003952438,"about_ca_system_score_gemma":0.0001003167,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005105428,"about_ca_topic_score_gemma":0.000001114703,"domain_scores_codex":[0.9990277,0.00008138143,0.0001845306,0.0003211839,0.000216534,0.0001686467],"domain_scores_gemma":[0.9993622,0.0001208829,0.00009845414,0.0002352044,0.0001297109,0.0000535948],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005191093,0.0002636525,0.000001226003,0.0001564237,0.00001071047,0.000001779563,0.001269705,0.5259038,0.06427754,0.006384107,0.000005353042,0.4016738],"study_design_scores_gemma":[0.000321152,0.00005251138,0.000007706667,0.00009902601,0.0000154368,0.000002233352,0.000008751651,0.8963209,0.09646642,0.00658583,0.00001188126,0.0001081522],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001909945,0.00007811659,0.9960406,0.001484249,0.00002690083,0.000221656,0.00001349517,0.00009428993,0.0001307788],"genre_scores_gemma":[0.852046,0.00001288194,0.1475876,0.0002578177,0.000009408475,0.00005017927,0.000002691228,0.00001037688,0.00002299484],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8501361,"threshold_uncertainty_score":0.4494978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127786001","doi":"10.1109/tip.2009.2024578","title":"$n$-SIFT: $n$-Dimensional Scale Invariant Feature Transform","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":180,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"","keywords":"Scale-invariant feature transform; Artificial intelligence; Curse of dimensionality; Pattern recognition (psychology); Histogram; Feature extraction; Computer science; Invariant (physics); Matching (statistics); Salient; Computer vision; Feature (linguistics); Image registration; Mathematics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01169971106401026,"gpt":0.2738951675905187,"spread":0.2621954565265084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001886657,0.0002770055,0.0002373633,0.0002306781,0.0005299897,0.0003270312,0.0005498845,0.0001300951,0.00002201264],"category_scores_gemma":[0.000005411461,0.0002484094,0.0001430137,0.0007885174,0.00007916254,0.002491697,0.000002165159,0.0005384083,0.00003644353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008014536,"about_ca_system_score_gemma":0.0001320963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003781383,"about_ca_topic_score_gemma":0.000003399389,"domain_scores_codex":[0.998307,0.00003409958,0.0002633905,0.0005569884,0.0004152705,0.0004232433],"domain_scores_gemma":[0.9991427,0.00004141935,0.00008175647,0.0004083862,0.000171394,0.0001543341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004270478,0.000235293,2.829475e-7,0.00002394037,0.000006376868,0.00003738966,0.0003365865,0.000165378,0.05950809,0.0001001819,0.0003324202,0.9392114],"study_design_scores_gemma":[0.0005528905,0.0003352574,0.00006441106,0.0001960999,0.00002212516,0.0001575868,0.00001904994,0.02687632,0.9610901,0.008592115,0.001629574,0.0004644308],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003246198,0.0002384501,0.9921453,0.004206271,0.0001426146,0.0002452097,0.000006909409,0.00083672,0.001853915],"genre_scores_gemma":[0.5808595,0.00004328557,0.416707,0.001664199,0.00004587799,0.00001841703,0.000001441387,0.00001840349,0.0006418832],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9387469,"threshold_uncertainty_score":0.9999968,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990566152","doi":"10.1109/tip.2007.891794","title":"A New Orientation-Adaptive Interpolation Method","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Bilinear interpolation; Interpolation (computer graphics); Stairstep interpolation; Orientation (vector space); Computer vision; Nearest-neighbor interpolation; Kernel (algebra); Artificial intelligence; Bicubic interpolation; Curvature; Trilinear interpolation; Multivariate interpolation; Pixel; Mathematics; Computer science; Geometry; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01958786123059618,"gpt":0.3384977403219513,"spread":0.3189098790913551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000540639,0.0002394667,0.0001805096,0.0004292671,0.0004125464,0.0003794117,0.0005470795,0.000086639,0.00002465892],"category_scores_gemma":[0.00002121473,0.0002462024,0.00007958901,0.001121478,0.00005586747,0.003441044,0.000005659953,0.0003788364,0.0000343774],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000155083,"about_ca_system_score_gemma":0.0002289705,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000286984,"about_ca_topic_score_gemma":0.00001368611,"domain_scores_codex":[0.9982187,0.00004719352,0.0003930101,0.0005846496,0.0003697564,0.0003867525],"domain_scores_gemma":[0.998814,0.0001543646,0.0002075353,0.0003684226,0.0002961878,0.000159421],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004564156,0.00006216078,0.000001634914,0.00001998666,0.000008321266,0.00001009055,0.001474486,0.0001017058,0.059701,0.0003887262,0.0000745718,0.9381117],"study_design_scores_gemma":[0.0004647312,0.0001595541,0.0000296226,0.0001814517,0.00002378298,0.00007317271,0.0002278144,0.362046,0.6167886,0.01933599,0.0002427228,0.0004265053],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002272344,0.00007583106,0.9962934,0.0002676541,0.0002795029,0.0002000842,0.000001435348,0.001160322,0.001699021],"genre_scores_gemma":[0.1611452,0.000003537491,0.8381109,0.0002806172,0.00005163389,0.00001717842,5.848826e-7,0.0000269177,0.0003634421],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9376852,"threshold_uncertainty_score":0.999999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391697048","doi":"10.1109/tip.2024.3362153","title":"UCL-Dehaze: Toward Real-World Image Dehazing via Unsupervised Contrastive Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Shenzhen Science and Technology Innovation Program; National Defense Basic Scientific Research Program of China; Lingnan University; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Image editing; Embedding; Image (mathematics); Generalization; Leverage (statistics); Deep learning; Computer vision; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0164759686231717,"gpt":0.2886161093988815,"spread":0.2721401407757099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004711862,0.0004449171,0.0003526292,0.0007251224,0.0006455448,0.001798511,0.0007421912,0.0001028113,0.0001022188],"category_scores_gemma":[0.00001731548,0.0004494738,0.0001948541,0.001659383,0.0001855842,0.003809652,0.00001368253,0.00103063,0.0002202924],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002620303,"about_ca_system_score_gemma":0.0002584505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009033078,"about_ca_topic_score_gemma":0.00003336962,"domain_scores_codex":[0.9970806,0.0001452364,0.0005251963,0.0009980578,0.0005528735,0.0006980964],"domain_scores_gemma":[0.9988453,0.0001928824,0.0001105418,0.0004107819,0.0002834884,0.00015697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000286381,0.000144238,0.000005700404,0.0003783916,0.00005492444,0.0001911632,0.002602553,0.0002613786,0.3813348,0.0001551123,0.0002055004,0.6146376],"study_design_scores_gemma":[0.0003284032,0.0001313148,0.00003570845,0.000748451,0.00006184889,0.00003898628,0.0001201935,0.3416024,0.6550458,0.0005884283,0.0007403865,0.0005581049],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007930048,0.0003109986,0.987183,0.0007288659,0.0005928361,0.0003999594,0.000005912646,0.003990937,0.00599447],"genre_scores_gemma":[0.7714406,0.00009040889,0.2264341,0.0001649537,0.00009135491,0.0001204272,0.000002673767,0.00007439772,0.001581051],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7706476,"threshold_uncertainty_score":0.9997957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2156291710","doi":"10.1109/tip.2003.814252","title":"Removing the blocking artifacts of block-based DCT compressed images","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Discrete cosine transform; Block (permutation group theory); Computer vision; Artificial intelligence; Smoothing; Pixel; Quantization (signal processing); Classification of discontinuities; Discontinuity (linguistics); Computer science; Blocking (statistics); Blocking effect; Transform coding; Color Cell Compression; Enhanced Data Rates for GSM Evolution; Mathematics; Algorithm; Image compression; Image processing; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02364186474799729,"gpt":0.2777265679184133,"spread":0.254084703170416,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009494875,0.000243225,0.0002687616,0.0002241376,0.0007209739,0.000446396,0.0006766561,0.00006892397,0.00002043081],"category_scores_gemma":[0.00006689629,0.0001901662,0.0001577721,0.0008215322,0.0001969016,0.0007333288,0.000003529439,0.0004012093,0.00001228551],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004062911,"about_ca_system_score_gemma":0.0002413378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000187255,"about_ca_topic_score_gemma":0.00000222726,"domain_scores_codex":[0.9978954,0.0003960927,0.0004220216,0.0004337232,0.000455407,0.0003973945],"domain_scores_gemma":[0.9983177,0.0004771376,0.0002208579,0.0006222309,0.0002801062,0.00008203727],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004980194,0.0003403686,0.0000109662,0.0002063835,0.00003573215,0.0000438778,0.001060207,0.03744344,0.7356,0.00008655527,0.00007512578,0.2250475],"study_design_scores_gemma":[0.0005794816,0.00005042766,0.00004049475,0.0001985093,0.00003575987,0.00003894937,0.00005145836,0.09861007,0.8996131,0.0004008314,0.0001678582,0.0002130681],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004713366,0.000239919,0.9922659,0.0003563889,0.0002939251,0.0001748622,0.000002381556,0.0001889078,0.001764377],"genre_scores_gemma":[0.7625034,0.000003748188,0.2370025,0.0003086229,0.00001634198,0.00001216079,1.579872e-7,0.00002057365,0.000132498],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7577901,"threshold_uncertainty_score":0.7754753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2171775321","doi":"10.1109/tip.2004.832920","title":"Primary-Consistent Soft-Decision Color Demosaicking for Digital Cameras (Patent Pending)","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Demosaicing; Artificial intelligence; Color filter array; Computer vision; Color image; Interpolation (computer graphics); Computer science; Sample (material); Primary color; Digital camera; Mathematics; Pattern recognition (psychology); Color gel; Image (mathematics); Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.03729791529568903,"gpt":0.2853431932711355,"spread":0.2480452779754465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004673318,0.0003118597,0.0003298731,0.0002886717,0.0009285498,0.001543832,0.0005876161,0.000104755,0.000008845474],"category_scores_gemma":[0.00004640132,0.0002925542,0.0002553336,0.0005218424,0.0001119594,0.002394872,0.000009264865,0.0003002176,0.00004254895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003351594,"about_ca_system_score_gemma":0.0003539755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001336425,"about_ca_topic_score_gemma":0.000003174616,"domain_scores_codex":[0.9977418,0.00003877709,0.0004853701,0.0007051873,0.0004786857,0.0005501753],"domain_scores_gemma":[0.9986744,0.0002954553,0.0001720826,0.0004002743,0.0002930771,0.000164736],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001546009,0.0003016577,0.000002188595,0.000115311,0.00002652852,0.00004250885,0.0008284302,0.007257634,0.03421272,0.000071881,0.000040032,0.9569465],"study_design_scores_gemma":[0.01341996,0.001605262,0.000214427,0.002133523,0.0002829363,0.000940641,0.0003131502,0.1796475,0.7722883,0.02418746,0.002400246,0.002566647],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006882894,0.0001694275,0.9905598,0.0005098676,0.0006902326,0.0004306753,0.00001735127,0.0003530099,0.0003867669],"genre_scores_gemma":[0.5637988,0.000006592556,0.4355014,0.0004105968,0.00004767848,0.00005892495,0.000002449692,0.00003078008,0.0001427763],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9543799,"threshold_uncertainty_score":0.9999527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991385629","doi":"10.1109/tip.2011.2168413","title":"Color Local Texture Features for Color Face Recognition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial intelligence; Local binary patterns; Computer vision; Pattern recognition (psychology); Computer science; Color histogram; Color space; Local color; Texture (cosmology); Discriminative model; Image texture; Color normalization; Texture filtering; Facial recognition system; Feature (linguistics); Face (sociological concept); Color image; Histogram; Image segmentation; Image processing; Segmentation; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.03530760119805725,"gpt":0.2611929479513447,"spread":0.2258853467532874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001562809,0.0002071881,0.0001720934,0.0001673832,0.0005312936,0.0002121547,0.0003393806,0.0001652143,0.00006945477],"category_scores_gemma":[0.00001002203,0.00018645,0.0001163832,0.000330711,0.00009420509,0.001313952,0.000002893022,0.0002658228,0.0001302083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005048779,"about_ca_system_score_gemma":0.00009456329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001450549,"about_ca_topic_score_gemma":0.00001708086,"domain_scores_codex":[0.9987189,0.00004256443,0.0002352395,0.0004702241,0.0002047227,0.0003284191],"domain_scores_gemma":[0.9992303,0.00007429,0.0001103307,0.0002168414,0.0002567794,0.0001114958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001983932,0.0003248688,5.120326e-7,0.0001287149,0.00001875059,0.000007781699,0.002108447,0.0001968489,0.02300417,0.00001768618,0.00166612,0.9723277],"study_design_scores_gemma":[0.001202453,0.0004651802,0.00005530187,0.0003291173,0.0000630812,0.0000628674,0.0008699367,0.09523211,0.8975,0.002834126,0.0008637618,0.0005220658],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003571783,0.00006947523,0.9934806,0.0003756681,0.0004512908,0.0004456183,0.00004126208,0.000354633,0.001209628],"genre_scores_gemma":[0.8119138,0.00001675765,0.1865637,0.0006425498,0.00004118671,0.0002464168,0.000007720102,0.0000239883,0.00054389],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9718056,"threshold_uncertainty_score":0.760321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140557988","doi":"10.1109/tip.2010.2095866","title":"Optimizing a Tone Curve for Backward-Compatible High Dynamic Range Image and Video Compression","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Enhancement Techniques","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Tone mapping; High dynamic range; Data compression; Tone (literature); Computer science; Algorithm; Image compression; Distortion (music); Computer vision; Range (aeronautics); Mean squared error; Dynamic range; Image quality; High-dynamic-range imaging; Artificial intelligence; Iterative reconstruction; Dynamic range compression; Mathematics; Image (mathematics); Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01182586325777499,"gpt":0.2934184721824124,"spread":0.2815926089246374,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000383385,0.0003124396,0.0003100253,0.0002986794,0.000684783,0.0007386318,0.0005742135,0.0001162832,0.00003168453],"category_scores_gemma":[0.00001540455,0.0003065305,0.00009296444,0.0003776453,0.0001801893,0.002646177,0.00001382282,0.0005165471,0.00001348834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005734483,"about_ca_system_score_gemma":0.0000802564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003493939,"about_ca_topic_score_gemma":0.00003311507,"domain_scores_codex":[0.9981303,0.00004834706,0.0003685196,0.0006930964,0.0002972467,0.0004624691],"domain_scores_gemma":[0.9987683,0.0001511006,0.0001731307,0.0005195553,0.0002638898,0.0001240256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005027335,0.0002004978,0.000002114148,0.0002148347,0.00001346543,0.000006798401,0.0007372713,0.00008467607,0.7756016,0.00003929342,0.0001453559,0.2229039],"study_design_scores_gemma":[0.000984581,0.0001312588,0.00004624112,0.0002246572,0.00002966979,0.00002661138,0.00003388776,0.35528,0.6418867,0.0008010521,0.0001680273,0.0003873335],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01306545,0.0001092631,0.9840062,0.000610915,0.0004826146,0.0006681129,0.00001926671,0.0008129249,0.0002252205],"genre_scores_gemma":[0.4860067,0.00001895349,0.5135448,0.0001035469,0.00002335911,0.0001595531,0.000002231487,0.00002815262,0.0001127007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4729413,"threshold_uncertainty_score":0.9999387,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100846049","doi":"10.1109/tip.2006.877363","title":"CCD noise removal in digital images","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Computer vision; Brightness; Artificial intelligence; Noise reduction; Computer science; Noise (video); Image restoration; Filter (signal processing); Image processing; Optics; Image (mathematics); Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01275566478385539,"gpt":0.265026578066734,"spread":0.2522709132828787,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002918337,0.0002119464,0.0002018776,0.0003480155,0.0002556304,0.00108689,0.0004739502,0.00006950708,0.00001215556],"category_scores_gemma":[0.00001286574,0.0002088869,0.0001001073,0.0007989808,0.00009587259,0.002900471,0.000004083867,0.0003252242,0.00007531654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000841079,"about_ca_system_score_gemma":0.0001248564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005954845,"about_ca_topic_score_gemma":0.000008506388,"domain_scores_codex":[0.9984192,0.00005228417,0.0003409539,0.0004797281,0.0003116489,0.0003962397],"domain_scores_gemma":[0.9993109,0.0001001899,0.00007638585,0.0003321035,0.0001184142,0.0000620682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005546909,0.0004972788,0.00002386282,0.00007038465,0.000006217994,0.000521145,0.0003471913,0.003141941,0.1017145,0.00008939971,0.0002302501,0.8933024],"study_design_scores_gemma":[0.003497406,0.0001784927,0.001067685,0.000443944,0.00003280892,0.0007660349,0.00009328946,0.158713,0.8178108,0.01500642,0.001084524,0.001305555],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007372924,0.0001674904,0.9818527,0.0002617655,0.0002330922,0.0001052944,0.000005312687,0.0002767141,0.009724671],"genre_scores_gemma":[0.7703093,0.000003572227,0.2276965,0.0001318461,0.00005899613,0.00001321559,9.039445e-7,0.00002126491,0.001764375],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8919968,"threshold_uncertainty_score":0.9999501,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2155311268","doi":"10.1109/tip.2008.2011384","title":"PCA-Based Spatially Adaptive Denoising of CFA Images for Single-Sensor Digital Cameras","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Noise reduction; Artificial intelligence; Computer vision; Computer science; Video denoising; Color filter array; Noise (video); Median filter; Filter (signal processing); Color image; Image sensor; Process (computing); Image processing; Pattern recognition (psychology); Image (mathematics); Color gel; Video processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02891400673190719,"gpt":0.2809607570402935,"spread":0.2520467503083863,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003199228,0.0003031977,0.0003731912,0.0003437557,0.0004076971,0.0006975142,0.0005064395,0.0000949581,0.00000579549],"category_scores_gemma":[0.00005366144,0.0002989121,0.0002362495,0.0005801321,0.0001517564,0.001849945,0.000002448646,0.0002349232,0.000007113826],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008762015,"about_ca_system_score_gemma":0.0002578414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001075005,"about_ca_topic_score_gemma":0.000001222689,"domain_scores_codex":[0.9980276,0.000083425,0.000485822,0.0005582912,0.0003985574,0.0004463643],"domain_scores_gemma":[0.9983723,0.0003375523,0.0002551636,0.000388228,0.0005329375,0.0001138823],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001822268,0.0003586894,7.929136e-7,0.00005769666,0.00001422657,0.00001829949,0.0003253655,0.004202135,0.3779032,0.00001693295,0.00002289717,0.6168976],"study_design_scores_gemma":[0.001208573,0.0007645227,0.00002053045,0.0002566201,0.00004795269,0.00002952135,0.00004867206,0.08368915,0.9123138,0.001211496,0.00004976969,0.0003594166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001820382,0.00013275,0.9958449,0.0004763344,0.0002096665,0.000321553,0.00003316054,0.0002393015,0.0009219318],"genre_scores_gemma":[0.5915529,0.000001184431,0.4080281,0.0002445613,0.00003804372,0.000009910973,0.000001300623,0.0000195736,0.0001043954],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6165382,"threshold_uncertainty_score":0.9999463,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112545418","doi":"10.1109/tip.2006.881992","title":"Translation-Invariant Contourlet Transform and Its Application to Image Denoising","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image and Signal Denoising Methods","field":"Computer Science","cited_by":150,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Contourlet; Invariant (physics); Wavelet transform; Filter bank; Noise reduction; Artificial intelligence; Image denoising; Pattern recognition (psychology); Mathematics; Redundancy (engineering); Wavelet; Filter (signal processing); Computer science; Algorithm; Computer vision","retraction":null,"screen_n_in":null,"score":{"opus":0.01614987512096629,"gpt":0.2776312431378795,"spread":0.2614813680169132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005103085,0.0002716831,0.0002522939,0.0003179631,0.0006619405,0.000700406,0.0003627641,0.00009675012,0.000009831816],"category_scores_gemma":[0.000006262767,0.0002761415,0.00008631653,0.0007374232,0.00005621334,0.001924099,0.000002211436,0.0002595763,0.00004262893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006782251,"about_ca_system_score_gemma":0.00009621546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007875296,"about_ca_topic_score_gemma":0.00003802566,"domain_scores_codex":[0.9980966,0.00009437218,0.0004210249,0.0006267027,0.0003524754,0.0004087526],"domain_scores_gemma":[0.9991463,0.0001244369,0.00008631278,0.0002864606,0.0002107828,0.0001457196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003707991,0.00008866,3.805568e-7,0.00006585767,0.000006667191,0.00001233409,0.0006752785,0.0008600435,0.4761337,0.0001813615,0.00002028857,0.5219184],"study_design_scores_gemma":[0.001209541,0.00009753958,0.00006326505,0.0001268322,0.00005161681,0.00008998404,0.00004325125,0.2505589,0.7435754,0.003024132,0.0006569928,0.0005025842],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001735606,0.0003506495,0.9928997,0.002124,0.000120771,0.0004972203,0.00001034613,0.0003269587,0.0019348],"genre_scores_gemma":[0.6717343,0.00001073726,0.3275645,0.0003446795,0.00006774751,0.00006697333,0.000001802528,0.00002754212,0.0001816857],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6699987,"threshold_uncertainty_score":0.9999691,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2292934097","doi":"10.1109/tip.2016.2528042","title":"LBP-Based Segmentation of Defocus Blur","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Image Processing Techniques and Applications","field":"Engineering","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Artificial intelligence; Computer vision; Computer science; Metric (unit); Image restoration; Segmentation; Image segmentation; Pattern recognition (psychology); Local binary patterns; Binary number; Binary image; Image (mathematics); Mathematics; Image processing; Histogram","retraction":null,"screen_n_in":null,"score":{"opus":0.01071623322709941,"gpt":0.2489694103632278,"spread":0.2382531771361284,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008211935,0.0001515328,0.0001327191,0.0001622588,0.0001284359,0.00004300247,0.0001282147,0.00006314761,0.00008266803],"category_scores_gemma":[0.000003020251,0.0001218958,0.00006477367,0.0002924407,0.0000904858,0.0003608883,5.025623e-7,0.0001020233,0.00002582711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007316451,"about_ca_system_score_gemma":0.0000469281,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002935191,"about_ca_topic_score_gemma":0.000004003809,"domain_scores_codex":[0.999211,0.00001083309,0.0002614937,0.0001738793,0.0001543473,0.00018841],"domain_scores_gemma":[0.9995524,0.00003982732,0.00006053513,0.0001852744,0.0001135672,0.0000484109],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000105662,0.00006599168,0.000003752344,0.0001734298,0.00000788036,7.204742e-7,0.00006313199,0.002116118,0.5449474,0.000005423243,0.00009413221,0.4525115],"study_design_scores_gemma":[0.0003504163,0.00002930375,0.00001224042,0.0002396941,0.00002958351,0.00000350454,0.00002398891,0.02538726,0.9732568,0.000317424,0.0001825048,0.0001672996],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005765572,0.00008912606,0.9922369,0.0001854241,0.00006409896,0.0001524062,0.00003654539,0.0006911998,0.0007787261],"genre_scores_gemma":[0.8941025,0.00002466622,0.1055626,0.00003339461,0.00001757576,0.0001212104,0.000001231324,0.0000423111,0.00009457904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8883369,"threshold_uncertainty_score":0.4970767,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3186910762","doi":"10.1109/tip.2022.3160602","title":"Scalable Image Coding for Humans and Machines","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Codec; Scalability; Artificial intelligence; Coding (social sciences); Computer vision; Machine vision; Machine learning; Task (project management); Computer hardware; Database; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02030060063684558,"gpt":0.3022955667161125,"spread":0.2819949660792669,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0002750657,0.0001647802,0.0001661921,0.0001923309,0.00157499,0.0003569352,0.0003798566,0.00002588149,0.00002955232],"category_scores_gemma":[0.00001081089,0.0001701839,0.00006997752,0.0004278802,0.00008125203,0.001553026,0.00001309622,0.0002773582,0.000002396094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000685732,"about_ca_system_score_gemma":0.00006184261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007420593,"about_ca_topic_score_gemma":0.000001687023,"domain_scores_codex":[0.9988074,0.00003811042,0.0002084656,0.0004430321,0.0002142422,0.0002887843],"domain_scores_gemma":[0.9994105,0.00009246545,0.0000857241,0.0002437574,0.0001027391,0.00006488057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00005443331,0.0001805498,0.000006110153,0.0001908588,0.00001305815,0.0000147058,0.0007625477,0.0002058085,0.1374791,0.0003532064,0.0003566754,0.860383],"study_design_scores_gemma":[0.001088189,0.0005420066,0.0000322362,0.00009466768,0.0000443454,0.000117572,0.000244026,0.2165877,0.7618147,0.01325014,0.005503143,0.0006812985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006578437,0.0002348789,0.9972026,0.0005200668,0.0001427151,0.0003027382,0.00002440843,0.0004919647,0.0004227607],"genre_scores_gemma":[0.5093091,0.00004511134,0.4892448,0.0003908453,0.0000294392,0.0002631751,0.000001611139,0.00002950219,0.0006864642],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8597016,"threshold_uncertainty_score":0.9997248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119047398","doi":"10.1109/tip.2014.2360122","title":"Bayesian Nonparametric Dictionary Learning for Compressed Sensing MRI","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":148,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Pattern recognition (psychology); Bayesian probability; Nonparametric statistics; Compressed sensing; Machine learning; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01031610926605511,"gpt":0.2357773531748147,"spread":0.2254612439087596,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014402,0.0002507577,0.0002473362,0.0003733435,0.0005036424,0.0001708292,0.000116641,0.0001158775,0.00001289379],"category_scores_gemma":[0.00001460026,0.0002757872,0.0001211785,0.00042797,0.00006318102,0.0003153009,0.000001165843,0.0004147062,0.00001234147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006723213,"about_ca_system_score_gemma":0.00001843641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007676676,"about_ca_topic_score_gemma":0.000002663,"domain_scores_codex":[0.9988636,0.00004435122,0.0002680444,0.0002983832,0.0001801635,0.000345422],"domain_scores_gemma":[0.9993077,0.0002084538,0.00005835848,0.0002029052,0.0001373384,0.00008523656],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003463843,0.000046852,0.000003738525,0.0001242239,0.00003794801,0.00000319999,0.0001621402,0.5455279,0.06799005,0.000004347535,0.0003871333,0.3856778],"study_design_scores_gemma":[0.0002753267,0.00006101285,0.00001060942,0.0001676156,0.00004311055,0.00002008684,0.00003718475,0.7816061,0.2155155,0.0002798484,0.001734347,0.0002492664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002292717,0.0001107677,0.9928435,0.00006003758,0.0003579046,0.0002314588,0.00000362654,0.002023273,0.002076703],"genre_scores_gemma":[0.8809168,0.00002718462,0.1186635,0.00007105312,0.0001153026,0.00002310346,0.00000428117,0.00008738344,0.00009132419],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8786241,"threshold_uncertainty_score":0.9999694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}