{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":427,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":427,"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":"97902a144f08","filters":{"topic":"Advanced Image Processing Techniques"}},"results":[{"id":"W2098535678","doi":"10.1145/1141911.1141956","title":"Removing camera shake from a single photograph","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":1842,"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":"Shake; Computer vision; Artificial intelligence; Camera auto-calibration; Computer science; Motion blur; Photography; Deconvolution; Digital camera; Blind deconvolution; Computer graphics (images); Rotation (mathematics); Image restoration; Pinhole camera model; Image (mathematics); Camera resectioning; Image processing; Physics; Algorithm; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.0171727493652327,"gpt":0.2439858995792696,"spread":0.2268131502140369,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001481699,0.0002232582,0.0001783682,0.0004081389,0.0003718448,0.0002268194,0.0012487,0.000116635,0.00001775646],"category_scores_gemma":[0.00003657383,0.0002352708,0.0001564159,0.001372284,0.0001326486,0.0007862847,0.00002217875,0.0003881363,0.00001218132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004342765,"about_ca_system_score_gemma":0.00003964242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000402142,"about_ca_topic_score_gemma":0.0002361749,"domain_scores_codex":[0.99844,0.00005847431,0.0002781551,0.0005663448,0.0003283039,0.000328726],"domain_scores_gemma":[0.9981317,0.0002696917,0.0001054141,0.001307742,0.0001149784,0.00007045508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008884196,0.002366353,0.0009658748,0.00006500794,0.000142259,0.0001386208,0.0008360384,0.0006683096,0.2375043,0.01017266,0.001745395,0.7453064],"study_design_scores_gemma":[0.0008576253,0.0003064087,0.002416658,0.0002827876,0.00007127314,0.00005563047,0.00005202993,0.03652994,0.196641,0.7480561,0.01345622,0.00127427],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00468418,0.0002548398,0.991901,0.0009535904,0.0001893893,0.0001338173,0.0000175266,0.001436362,0.0004293177],"genre_scores_gemma":[0.3922914,0.00004582648,0.606959,0.0005744649,0.00002698082,0.00002935761,0.000004522281,0.00002062526,0.00004780187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7440321,"threshold_uncertainty_score":0.9594064,"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":"W2963610452","doi":"10.1109/cvpr.2019.00399","title":"Feedback Network for Image Super-Resolution","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":864,"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":"Computer science; Artificial intelligence; Code (set theory); Image (mathematics); Block (permutation group theory); Deep learning; Recurrent neural network; Artificial neural network; Iterative reconstruction; Computer vision; Machine learning; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.01067360849447579,"gpt":0.2656434042437729,"spread":0.2549697957492971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001808338,0.0000903508,0.0001004372,0.00002961437,0.00007457714,0.0001314444,0.0005855181,0.000038284,0.0000260632],"category_scores_gemma":[0.00002940442,0.0000802483,0.00004334025,0.0001959873,0.00002356875,0.001055635,0.0001853821,0.00005838655,0.000147516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003172568,"about_ca_system_score_gemma":0.00003057144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004232043,"about_ca_topic_score_gemma":0.000001486423,"domain_scores_codex":[0.9991742,0.00001198576,0.0001220666,0.0002986332,0.0001044345,0.0002887274],"domain_scores_gemma":[0.9993121,0.00006156748,0.00004020298,0.0004364211,0.0001126326,0.00003705045],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000415022,0.0001215348,0.001140439,0.0001637103,0.00002057203,0.000004670948,0.0002580373,0.0004331627,0.09677079,0.5100237,0.2484438,0.1425781],"study_design_scores_gemma":[0.0004025994,0.0001615028,0.0003279981,0.00004008133,0.000003036804,0.00001270162,0.000007884447,0.7251478,0.01720033,0.1987737,0.05759007,0.0003322675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000308449,0.00008374197,0.9898744,0.0008694723,0.0002013871,0.0002960016,6.999646e-7,0.000855024,0.007510845],"genre_scores_gemma":[0.01536982,0.00000416636,0.9810527,0.0005687447,0.00007792628,0.00003227139,0.000002384024,0.00001034966,0.00288166],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7247146,"threshold_uncertainty_score":0.3272431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2738579427","doi":"10.1109/cvpr.2017.33","title":"Deep Video Deblurring for Hand-Held Cameras","year":2017,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":600,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology; University of British Columbia","funders":"King Abdullah University of Science and Technology","keywords":"Deblurring; Motion blur; Computer science; Artificial intelligence; Computer vision; Shake; Frame (networking); Task (project management); Frame rate; Deep learning; Motion (physics); Image (mathematics); Image restoration; Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02547686489349839,"gpt":0.3245200094759543,"spread":0.299043144582456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000149276,0.00009962328,0.000109518,0.0000415643,0.0007843389,0.0009074309,0.001585733,0.00003581432,0.00000559103],"category_scores_gemma":[0.0003158812,0.00008728808,0.00004332449,0.00003388834,0.00008612082,0.001519857,0.0004425451,0.00006435668,0.00001440817],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002282035,"about_ca_system_score_gemma":0.00003071051,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002834556,"about_ca_topic_score_gemma":0.00002461608,"domain_scores_codex":[0.9992175,0.000005576032,0.0001183723,0.0003121978,0.0001030635,0.0002433258],"domain_scores_gemma":[0.9987203,0.00005841913,0.0001108215,0.0009447609,0.0001090484,0.00005661569],"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":[0.00001016278,0.0000475468,0.001108698,0.00006261413,0.00001501243,0.0000116481,0.0004168295,0.00001849147,0.02871811,0.09817905,0.004043649,0.8673682],"study_design_scores_gemma":[0.0003669095,0.00007402256,0.0004456361,0.00005630778,0.000004900154,0.0000160277,0.0000079644,0.5516916,0.2623896,0.1655096,0.01909383,0.0003435927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001483471,0.00009774006,0.9924284,0.001369139,0.0001382758,0.0001413319,2.284344e-7,0.0004984043,0.005178127],"genre_scores_gemma":[0.1974363,0.0000046369,0.8012679,0.0004380978,0.00004675213,0.00004811654,2.046865e-7,0.000008991549,0.0007489826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8670246,"threshold_uncertainty_score":0.8750377,"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":"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":"W3034419329","doi":"10.1109/cvpr42600.2020.00753","title":"Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting","year":2020,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":381,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Huawei Technologies (Canada)","funders":"","keywords":"Inpainting; Computer science; Residual; Artificial intelligence; Convolutional neural network; Inference; Image (mathematics); Computer vision; Deep learning; Image resolution; Pattern recognition (psychology); Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02448109100870257,"gpt":0.2774175768975865,"spread":0.252936485888884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002263568,0.0001106692,0.0001206183,0.00004314739,0.0001507207,0.0001958215,0.0004892558,0.0000452787,0.00000556926],"category_scores_gemma":[0.0007430963,0.0001066298,0.00003401979,0.0002330835,0.00005141657,0.001400256,0.000106462,0.00009508207,0.00001490312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003416093,"about_ca_system_score_gemma":0.00003967659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000136897,"about_ca_topic_score_gemma":0.000002269833,"domain_scores_codex":[0.9989861,0.00003273038,0.0002203182,0.0003702604,0.0001647803,0.0002258092],"domain_scores_gemma":[0.9992856,0.0001308893,0.0001192736,0.0001984927,0.0001972947,0.00006842993],"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":[0.0000563373,0.00005094439,0.0000670789,0.0001198981,0.00001482281,0.000007729169,0.001693021,0.0000527271,0.5015894,0.2202557,0.01956072,0.2565317],"study_design_scores_gemma":[0.0006243296,0.0002624528,0.0000885915,0.00004448559,0.000006166087,0.000006033478,0.00008050445,0.3810536,0.5736465,0.04136652,0.002501243,0.0003195857],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007351018,0.00004113362,0.9891796,0.007697964,0.00005031126,0.0002524389,0.000002788338,0.001358082,0.0006825859],"genre_scores_gemma":[0.2880342,0.000002494385,0.710529,0.001236394,0.0001013054,0.00002808502,0.000005627708,0.000009011765,0.00005393742],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3810009,"threshold_uncertainty_score":0.4348237,"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":"W2021347102","doi":"10.1145/2661229.2661260","title":"FlexISP","year":2014,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":297,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Pipeline (software); Artificial intelligence; Computer vision; Image (mathematics); Demosaicing; Noise reduction; Deconvolution; Representation (politics); Blind deconvolution; Image processing; Image restoration; Computer graphics (images); Algorithm; Color image","retraction":null,"screen_n_in":null,"score":{"opus":0.01875585242448453,"gpt":0.2772893836884317,"spread":0.2585335312639472,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001751036,0.0001189068,0.00009768434,0.0002093146,0.000234561,0.00008897305,0.001160201,0.00006468587,0.000007320406],"category_scores_gemma":[0.00005697549,0.0001158653,0.00007090682,0.0006376856,0.00007582315,0.0005243252,0.00001363215,0.0002582099,0.00003375488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001519697,"about_ca_system_score_gemma":0.00002089382,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003690049,"about_ca_topic_score_gemma":0.000004912368,"domain_scores_codex":[0.99913,0.00003953756,0.0001331083,0.0003021717,0.0001993264,0.0001958861],"domain_scores_gemma":[0.9985249,0.0001422607,0.00004276878,0.001147988,0.00007548639,0.00006661931],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008859174,0.0002218737,0.00003785413,0.00002530434,0.00002044964,0.000003556844,0.0002688385,0.0001392007,0.002721181,0.1841171,0.0004859066,0.8119499],"study_design_scores_gemma":[0.0002538033,0.0002422052,0.000183507,0.00004281916,0.000010703,0.00002369349,0.000005551282,0.05248238,0.03054943,0.8839038,0.03194112,0.0003609839],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001206449,0.00002463283,0.9950278,0.002520808,0.0001593819,0.00006258455,0.000001028092,0.00111751,0.0009655937],"genre_scores_gemma":[0.3000481,0.00003790531,0.6982906,0.001479524,0.00001449581,0.00002320206,4.083331e-7,0.00001102269,0.00009478246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8115889,"threshold_uncertainty_score":0.4724848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3011688396","doi":"10.3390/rs12091432","title":"Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network","year":2020,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":289,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Energy; Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Detector; Computer science; Residual; Artificial intelligence; Enhanced Data Rates for GSM Evolution; Computer vision; Generative adversarial network; Context (archaeology); Object detection; Overhead (engineering); Image resolution; Remote sensing; Deep learning; Pattern recognition (psychology); Telecommunications; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.016381683787962,"gpt":0.2447828910487765,"spread":0.2284012072608144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004487356,0.0004387387,0.0005180335,0.0002458192,0.0003313081,0.0004261012,0.0003168235,0.0001337291,6.666875e-7],"category_scores_gemma":[0.0004272856,0.0004372826,0.00005992942,0.001725776,0.0001238551,0.0005930422,0.0003305386,0.0005836948,0.000006377645],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001809143,"about_ca_system_score_gemma":0.0001198699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002105703,"about_ca_topic_score_gemma":0.0003279294,"domain_scores_codex":[0.9970614,0.0002221168,0.0004340803,0.001153329,0.0003427508,0.0007863578],"domain_scores_gemma":[0.9985157,0.0002202904,0.0002419871,0.0005923825,0.0002001263,0.0002295235],"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":[0.00005583007,0.00000165358,0.000001662801,0.00003985768,0.000008164203,0.000123929,0.0007441423,0.0006336356,0.2814353,0.000001094778,0.000006020961,0.7169487],"study_design_scores_gemma":[0.0002743119,0.000184765,0.0001051093,0.0005296776,0.00001188827,0.0002274999,0.00004014155,0.5841937,0.4128544,0.00104078,0.0001318869,0.0004058502],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07111364,0.0002778854,0.9258798,0.0006945456,0.0001314895,0.0004021322,5.455207e-7,0.001026739,0.0004732561],"genre_scores_gemma":[0.4821087,0.0000239934,0.5171142,0.0005581725,0.0001413366,1.888667e-8,4.794491e-7,0.00004182042,0.00001134427],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7165429,"threshold_uncertainty_score":0.9998079,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003863798","doi":"10.1016/j.media.2010.05.010","title":"Non-local MRI upsampling","year":2010,"lang":"en","type":"article","venue":"Medical Image Analysis","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Montreal Neurological Institute and Hospital; McGill University","funders":"","keywords":"Upsampling; Interpolation (computer graphics); Artificial intelligence; Computer science; Computer vision; Bicubic interpolation; Image scaling; Constraint (computer-aided design); Coherence (philosophical gambling strategy); Nearest-neighbor interpolation; Image (mathematics); Mathematics; Algorithm; Multivariate interpolation; Image processing; Bilinear interpolation; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.005285407020192026,"gpt":0.2967542073361372,"spread":0.2914688003159452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007620334,0.0001673858,0.0003322032,0.0003626524,0.0001571323,0.0002182035,0.001766351,0.0001438532,0.0003960351],"category_scores_gemma":[0.0005419854,0.0001427015,0.0002183545,0.002070073,0.0003268209,0.0007682737,0.0005455777,0.0006722446,0.0001046932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002059975,"about_ca_system_score_gemma":0.0001129351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005406667,"about_ca_topic_score_gemma":0.00006119747,"domain_scores_codex":[0.9978719,0.0000258716,0.0003289783,0.0005590096,0.0008307881,0.0003834885],"domain_scores_gemma":[0.9983027,0.0001179865,0.0001030345,0.0009366393,0.0001880155,0.0003516369],"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":[0.00001357931,0.0007092946,0.006775966,0.00008994345,0.001294996,0.001354686,0.001207883,0.000302772,0.06470112,0.01003963,0.01080802,0.9027021],"study_design_scores_gemma":[0.0001129896,0.00001446484,0.0003833112,0.000009897393,0.0001178712,0.00001769123,0.00001082007,0.9834045,0.007207192,0.006160097,0.002350816,0.0002103496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008661858,0.00003161174,0.993889,0.003061154,0.000121476,0.00004609759,6.755544e-7,0.0005498181,0.001434002],"genre_scores_gemma":[0.185953,0.00001434788,0.8128505,0.0009180659,0.0001039811,0.00001543247,0.000004823892,0.00001030197,0.000129477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9831017,"threshold_uncertainty_score":0.58192,"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":"W4282937861","doi":"10.1038/s41598-022-13658-4","title":"A new generative adversarial network for medical images super resolution","year":2022,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":175,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Qatar National Library","keywords":"Computer science; Artificial intelligence; Deep learning; Image (mathematics); Convolutional neural network; Feature (linguistics); Computer vision; Image resolution; Scale (ratio); Pattern recognition (psychology); Network architecture; Path (computing); Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01387629840832537,"gpt":0.2827171658891675,"spread":0.2688408674808421,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002889753,0.0001312607,0.0001626594,0.0001167839,0.001387384,0.0004338801,0.0007677768,0.00004471496,0.0001507872],"category_scores_gemma":[0.0005269465,0.0001292912,0.00009331912,0.000819214,0.000145133,0.0007447025,0.0009021703,0.0002016303,0.000002862047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001435042,"about_ca_system_score_gemma":0.001107612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002139431,"about_ca_topic_score_gemma":0.000007300514,"domain_scores_codex":[0.9969386,0.00009636917,0.0004240181,0.0009946292,0.001108128,0.0004382186],"domain_scores_gemma":[0.998434,0.00007051325,0.0002401079,0.0008935966,0.0001826348,0.0001791595],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001569846,0.00004282112,0.00008131485,0.000007289992,0.000009603737,0.0002702015,0.0004508666,0.001202005,0.006368477,0.00497998,0.9581545,0.02841726],"study_design_scores_gemma":[0.0002652214,0.0001089103,0.00002276854,0.00002023391,0.000009053342,0.0005997574,0.00002594223,0.09117454,0.01056368,0.4287965,0.4681093,0.0003040689],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001554073,0.0003902162,0.9867151,0.001859385,0.009614367,0.0003787978,0.000002251085,0.0004591133,0.0004253555],"genre_scores_gemma":[0.009589029,0.000001795601,0.9844861,0.0002778505,0.0004899663,0.0001838777,0.00003704584,0.00001465519,0.004919659],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4900452,"threshold_uncertainty_score":0.9999127,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2146640671","doi":"10.1109/icip.2009.5414423","title":"Nonlocal back-projection for adaptive image enlargement","year":2009,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Innovation and Technology Fund","keywords":"Artificial intelligence; Computer vision; Computer science; Iterative reconstruction; Ringing artifacts; Image (mathematics); Projection (relational algebra); Process (computing); Iterative method; Image quality; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.02103643457817597,"gpt":0.3038121174192486,"spread":0.2827756828410727,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001508968,0.0001045235,0.00009304729,0.00007080996,0.0000949062,0.0001085523,0.0004024255,0.00003288777,0.00001270677],"category_scores_gemma":[0.00002865975,0.00009106501,0.00004400555,0.0001977509,0.00002293995,0.001018046,0.00007495211,0.0000612197,0.00003589177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006332961,"about_ca_system_score_gemma":0.00003650536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003050406,"about_ca_topic_score_gemma":0.00000104539,"domain_scores_codex":[0.9991783,0.00001238007,0.0001363766,0.0003233451,0.0001271326,0.0002224821],"domain_scores_gemma":[0.9994542,0.00002485334,0.00005312061,0.0002755762,0.0001525517,0.00003970652],"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":[0.00003249523,0.0001687504,0.000003562249,0.00001179456,0.000006989257,0.000004131169,0.0001881568,0.000004234581,0.03886644,0.1089818,0.0187764,0.8329552],"study_design_scores_gemma":[0.0003702737,0.0007413498,0.00005418121,0.00001965694,0.000003640123,0.00001147396,0.00002535469,0.7149879,0.1625675,0.1111669,0.009790139,0.0002617029],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009884352,0.00002647644,0.9862832,0.001213031,0.00007112346,0.0003130599,7.919551e-7,0.0006378162,0.01144456],"genre_scores_gemma":[0.0121465,0.000004334473,0.9858447,0.001009219,0.0000464865,0.00003408892,0.00000125242,0.000005327003,0.0009081244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8326936,"threshold_uncertainty_score":0.3713523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017429172","doi":"10.1155/2010/425891","title":"MRI Superresolution Using Self‐Similarity and Image Priors","year":2010,"lang":"en","type":"article","venue":"International Journal of Biomedical Imaging","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Artificial intelligence; Superresolution; Computer vision; Interpolation (computer graphics); Similarity (geometry); Prior probability; Segmentation; Pattern recognition (psychology); Image resolution; Process (computing); Image (mathematics); Bayesian probability","retraction":null,"screen_n_in":null,"score":{"opus":0.007403015926103667,"gpt":0.3124449699740702,"spread":0.3050419540479666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006447071,0.0001051109,0.0001330416,0.0003366785,0.00007726863,0.000315165,0.0009800729,0.00004555278,0.00001078725],"category_scores_gemma":[0.0003662981,0.00009215317,0.00005579225,0.0001575644,0.0002515212,0.002024882,0.0003762556,0.0005021367,0.000001353369],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007442808,"about_ca_system_score_gemma":0.0001576216,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009544452,"about_ca_topic_score_gemma":6.321855e-7,"domain_scores_codex":[0.9985626,0.00003153458,0.0003880488,0.0001805578,0.0006623344,0.0001748936],"domain_scores_gemma":[0.9987149,0.00007171349,0.0002747557,0.0001375943,0.0006442374,0.0001567607],"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":[0.00001619886,0.0002059552,0.00368243,0.00001481282,0.00005614685,0.0005034733,0.0006256926,0.000001248606,0.8717561,0.002328333,0.0008786079,0.119931],"study_design_scores_gemma":[0.001381325,0.0000809225,0.004692537,0.0002862037,0.00003514061,0.01030249,0.00007782455,0.8816679,0.03488012,0.0441582,0.02198398,0.0004533465],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03706553,0.0001291658,0.9541604,0.007190255,0.001251748,0.000031893,0.00000159671,0.0000942092,0.00007518722],"genre_scores_gemma":[0.3331605,0.00002853546,0.6662648,0.0002758449,0.0002615032,3.623717e-7,5.285966e-7,0.000005830105,0.000002051316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8816667,"threshold_uncertainty_score":0.3757897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2982470081","doi":"10.1109/cvprw.2019.00073","title":"RUNet: A Robust UNet Architecture for Image Super-Resolution","year":2019,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Christie (Canada); University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Image resolution; Image (mathematics); Computer vision; Resolution (logic); Superresolution; Set (abstract data type); Projector; Low resolution; Iterative reconstruction; Sub-pixel resolution; Pattern recognition (psychology); High resolution; Image processing; Digital image processing; Remote sensing","retraction":null,"screen_n_in":null,"score":{"opus":0.01158302849248523,"gpt":0.2546265459964526,"spread":0.2430435175039674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001518103,0.0001325538,0.0001296096,0.0000894036,0.00007501651,0.0001501187,0.0007325489,0.00005505504,0.00002667019],"category_scores_gemma":[0.00004764022,0.000111493,0.00005686139,0.0002213141,0.00003751435,0.0006958876,0.0002115805,0.0001121645,0.00005625387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003607616,"about_ca_system_score_gemma":0.00004530339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001093579,"about_ca_topic_score_gemma":0.000006506995,"domain_scores_codex":[0.9989895,0.00001731972,0.0001425961,0.0004042065,0.0001471654,0.0002992281],"domain_scores_gemma":[0.9991887,0.00006525006,0.00004890746,0.0005417189,0.0001061978,0.00004925963],"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":[0.00009350471,0.0002956535,0.0004673667,0.0004602696,0.00004151191,0.00001647265,0.001478155,0.003478343,0.4425475,0.1620099,0.0590366,0.3300747],"study_design_scores_gemma":[0.0006209297,0.0002621455,0.000133708,0.00005246227,0.000005012379,0.00004469623,0.00001811164,0.7985026,0.03659738,0.1035386,0.05975942,0.0004649843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004925201,0.00007795724,0.992223,0.001861341,0.0001125491,0.0004155472,0.000002937554,0.0009568603,0.003857282],"genre_scores_gemma":[0.01405806,0.000002684062,0.9836937,0.0005627635,0.00003963647,0.0000484071,0.000005150803,0.00001522365,0.001574357],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7950242,"threshold_uncertainty_score":0.4546553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1586298956","doi":"10.1109/icdsp.2015.7251858","title":"Remote sensing image super-resolution: Challenges and approaches","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University","keywords":"Remote sensing; Computer science; Image resolution; Remote sensing application; Interpolation (computer graphics); High resolution; Computer vision; Image (mathematics); Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1422884682043654,"gpt":0.2880346430904428,"spread":0.1457461748860774,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003244876,0.0001115905,0.0001128536,0.00006069116,0.00006548023,0.000129635,0.0002815062,0.00004297495,4.877302e-7],"category_scores_gemma":[0.00009861747,0.00009747513,0.00001488828,0.0001024971,0.0001042653,0.00103077,0.0003866444,0.00009056515,0.00000886163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002965937,"about_ca_system_score_gemma":0.00003807399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001078069,"about_ca_topic_score_gemma":0.000005309814,"domain_scores_codex":[0.99913,0.00004016468,0.0001102276,0.0003558633,0.0001646505,0.0001990837],"domain_scores_gemma":[0.9993337,0.00003013049,0.00003351654,0.0003950359,0.00009809659,0.0001095568],"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":[0.000002022661,0.000006907469,8.771979e-7,0.00001599435,0.00000243663,0.00001280553,0.001031842,9.739825e-7,0.0008849397,0.01227368,0.0004289865,0.9853385],"study_design_scores_gemma":[0.0001999438,0.00006336428,0.00004673683,0.00003378552,0.000002921836,0.0002321954,0.000290405,0.810551,0.007693231,0.1758403,0.004785496,0.0002606593],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001374915,0.003882212,0.964081,0.004904444,0.00004404537,0.00006576136,9.53499e-8,0.0008656943,0.02601923],"genre_scores_gemma":[0.02691423,0.0001495375,0.9725325,0.0001353949,0.00004271393,3.600836e-7,2.930799e-7,0.000008635146,0.0002163187],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9850779,"threshold_uncertainty_score":0.3974921,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4387843838","doi":"10.3390/rs15205062","title":"A Review of GAN-Based Super-Resolution Reconstruction for Optical Remote Sensing Images","year":2023,"lang":"en","type":"review","venue":"Remote Sensing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Royal Military College of Canada","funders":"Natural Science Foundation of Shandong Province","keywords":"Computer science; Adversarial system; Generative grammar; Generative adversarial network; Artificial intelligence; Superresolution; Iterative reconstruction; Computer vision; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.07273384696452204,"gpt":0.3697210930233198,"spread":0.2969872460587978,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00152752,0.0006470751,0.002263096,0.0005599278,0.0002323194,0.0001516022,0.0005949612,0.0003892109,6.37464e-7],"category_scores_gemma":[0.002436412,0.0006231238,0.0008116807,0.001469171,0.0002256129,0.0003975225,0.0001660227,0.0005817874,0.00001470878],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004146026,"about_ca_system_score_gemma":0.0007487272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002733104,"about_ca_topic_score_gemma":0.000002028008,"domain_scores_codex":[0.9959513,0.0002992693,0.001519149,0.001147179,0.000435403,0.000647713],"domain_scores_gemma":[0.9956826,0.0009252841,0.001164931,0.001347967,0.0007723735,0.0001068194],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.000002287999,0.000002736842,7.122588e-10,0.1045961,0.00002605815,0.00001859051,0.000005695918,0.000002795628,0.0001783983,0.00001473782,0.0002164508,0.8949362],"study_design_scores_gemma":[0.0001045208,0.00004585384,9.250376e-9,0.4247109,0.0003452565,0.0007601611,0.000001873546,0.4227692,0.0008247674,0.002686404,0.1472157,0.0005352774],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[4.122069e-8,0.4901942,0.5079108,0.0001449901,0.0002628794,0.0007613132,0.000006541006,0.0006162315,0.0001029748],"genre_scores_gemma":[1.312946e-7,0.4996108,0.500078,0.0001028171,0.00009173594,5.802987e-8,0.0000223886,0.00007122313,0.00002286192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8944009,"threshold_uncertainty_score":0.999622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2794276902","doi":"10.3390/rs10030394","title":"Landsat Super-Resolution Enhancement Using Convolution Neural Networks and Sentinel-2 for Training","year":2018,"lang":"en","type":"article","venue":"Remote Sensing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Resources Canada; Environment and Climate Change Canada","funders":"Canadian Space Agency","keywords":"Computer science; Convolutional neural network; Remote sensing; Land cover; Artificial intelligence; Image resolution; Pattern recognition (psychology); Land use; Geology","retraction":null,"screen_n_in":null,"score":{"opus":0.04701934527246122,"gpt":0.3068762002095216,"spread":0.2598568549370603,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003006758,0.0001430119,0.000155319,0.00008050542,0.0003849378,0.000158767,0.0001207522,0.0000642031,3.671528e-7],"category_scores_gemma":[0.0000726723,0.0001484147,0.00003391063,0.0001906568,0.0001147559,0.0004984243,0.0001342271,0.00009520431,4.67521e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007572273,"about_ca_system_score_gemma":0.00002828886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001553146,"about_ca_topic_score_gemma":0.000003748422,"domain_scores_codex":[0.9988696,0.00004141186,0.0002043467,0.0003835627,0.0001225614,0.0003785259],"domain_scores_gemma":[0.9993593,0.00005803888,0.0001111121,0.0002281396,0.0001858035,0.00005760139],"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":[0.00002686387,0.000007240598,0.00001806169,0.00003561014,0.00001198678,0.000005992654,0.001012791,0.000682272,0.2169033,0.0002272666,0.00008761678,0.780981],"study_design_scores_gemma":[0.0002265741,0.00005195666,0.00001760135,0.0001072978,0.000009723566,0.00009576182,0.00002459292,0.9889324,0.008013241,0.002052467,0.0002989575,0.0001693847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06534573,0.0001941279,0.9334251,0.0002647171,0.0002533689,0.0001730396,2.304761e-7,0.0002827973,0.00006086995],"genre_scores_gemma":[0.4815719,0.000005952038,0.5180114,0.0001790966,0.0002109406,2.912935e-8,0.000001594589,0.000009598451,0.000009517954],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9882502,"threshold_uncertainty_score":0.6052175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883638418","doi":"10.1109/tip.2019.2924554","title":"SiGAN: Siamese Generative Adversarial Network for Identity-Preserving Face Hallucination","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Ministry of Science and Technology, Taiwan","keywords":"Face (sociological concept); Adversarial system; Artificial intelligence; Computer science; Pattern recognition (psychology); Identity (music); Generative adversarial network; Facial recognition system; Face hallucination; Computer vision; Mathematics; Image (mathematics); Face detection; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01596444325634168,"gpt":0.2962569778494424,"spread":0.2802925345931007,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004497223,0.0003040492,0.000288705,0.0002089054,0.0006848593,0.0008781521,0.001040259,0.0001260224,0.00002607561],"category_scores_gemma":[0.00004224405,0.0003221192,0.0001231378,0.0007897191,0.00007253085,0.007617868,0.00001827061,0.0003657021,0.00004109434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001766153,"about_ca_system_score_gemma":0.0001928066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009298512,"about_ca_topic_score_gemma":0.0000141969,"domain_scores_codex":[0.9978083,0.00007499041,0.0003821283,0.0007795573,0.0004338317,0.0005211481],"domain_scores_gemma":[0.9984642,0.0001616412,0.0002590644,0.000562957,0.0004602209,0.00009187265],"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":[0.0002546155,0.0005017637,0.00001837607,0.0008870531,0.000102639,0.00001623759,0.004382365,0.1249847,0.2797843,0.002036916,0.0009859245,0.5860452],"study_design_scores_gemma":[0.0007488371,0.0001511716,0.000007584525,0.0002383286,0.00002664175,0.00001101159,0.00007750202,0.8692436,0.111582,0.01706515,0.0004214736,0.0004267027],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003484481,0.0002074083,0.9958479,0.0006643409,0.0007297994,0.0007682937,0.000008657826,0.0008833588,0.0005417877],"genre_scores_gemma":[0.2155433,0.00001366056,0.7832468,0.0003313433,0.0001367645,0.0001593503,0.000003151612,0.0000426718,0.0005229727],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7442589,"threshold_uncertainty_score":0.9999231,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1946766895","doi":"10.1109/cvpr.2015.7299153","title":"Data-driven sparsity-based restoration of JPEG-compressed images in dual transform-pixel domain","year":2015,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University; ASTER","funders":"","keywords":"Discrete cosine transform; JPEG; Computer science; Quantization (signal processing); Artificial intelligence; Computer vision; Pixel; Transform coding; Residual; JPEG 2000; Image restoration; Compression artifact; Data compression; Pattern recognition (psychology); Image (mathematics); Image compression; Algorithm; Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.06958908130091236,"gpt":0.3210086867541357,"spread":0.2514196054532233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005603469,0.0001295312,0.0002018079,0.000195307,0.00003548581,0.00007722348,0.001069499,0.00005544181,0.000002872229],"category_scores_gemma":[0.00008106237,0.0001211176,0.000021083,0.0004454015,0.00009947097,0.002164558,0.0002495078,0.0001281645,0.000005509329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000058339,"about_ca_system_score_gemma":0.0002339572,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005219325,"about_ca_topic_score_gemma":0.00009089892,"domain_scores_codex":[0.9986442,0.00008814032,0.0003146167,0.000398819,0.0003504198,0.0002037535],"domain_scores_gemma":[0.9986295,0.0000611014,0.0001175995,0.0009549302,0.0001605624,0.00007635792],"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":[0.0005020074,0.002101197,0.004576622,0.0004702365,0.00004226539,0.0002750736,0.005554253,0.0091752,0.8176749,0.04846175,0.04150807,0.06965843],"study_design_scores_gemma":[0.002088603,0.0002712103,0.0006328482,0.0001165969,0.000008172568,0.00001360805,0.0001029966,0.6569889,0.253503,0.0793253,0.00646169,0.0004871386],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004405079,0.00005800158,0.9918066,0.001379675,0.00005159725,0.0001995817,0.00001861554,0.0003524248,0.001728415],"genre_scores_gemma":[0.2904163,0.00000207634,0.7093887,0.0001077771,0.00001174105,0.000007601294,0.00002579341,0.000006749285,0.00003328801],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6478137,"threshold_uncertainty_score":0.4939034,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891639959","doi":"10.1109/icassp.2018.8461664","title":"Edge-Based Loss Function for Single Image Super-Resolution","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial intelligence; Mean squared error; Computer science; Enhanced Data Rates for GSM Evolution; Convolutional neural network; Image (mathematics); Pixel; Convolution (computer science); Image restoration; Image quality; Function (biology); Image resolution; Salient; Computer vision; Pattern recognition (psychology); Artificial neural network; Superresolution; Mathematics; Image processing; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02239487850176264,"gpt":0.2807992077772113,"spread":0.2584043292754487,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001829569,0.0001091945,0.00008660385,0.00008770383,0.0002058626,0.000170577,0.0004150496,0.00005011519,0.00002444204],"category_scores_gemma":[0.000104838,0.0001000982,0.00004497221,0.0002544939,0.0001448685,0.001132769,0.00009185711,0.000048246,0.00005173213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007294022,"about_ca_system_score_gemma":0.00005730231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005574444,"about_ca_topic_score_gemma":0.000005061202,"domain_scores_codex":[0.9990963,0.00001775439,0.0001433509,0.0003528336,0.0001346772,0.0002550287],"domain_scores_gemma":[0.9990326,0.00005267965,0.00005400353,0.0004159476,0.0003976352,0.00004719155],"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":[0.00008194693,0.0002394746,0.00006094972,0.00005501416,0.000006861679,0.000002506071,0.00009831283,0.000006197909,0.8393642,0.02458093,0.02168669,0.1138169],"study_design_scores_gemma":[0.0003867236,0.0007081203,0.00005607939,0.00002444496,0.000005926261,0.000006915516,0.000004806096,0.3198216,0.6070079,0.04741409,0.02433612,0.000227345],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002445782,0.00002802881,0.9930429,0.0009616937,0.000274446,0.0002015965,0.00000133409,0.001302584,0.003942783],"genre_scores_gemma":[0.1988857,3.159776e-7,0.7998762,0.0006709109,0.0001499205,0.00004104374,0.000003568546,0.00001085262,0.0003614584],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3198154,"threshold_uncertainty_score":0.4081886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3177293728","doi":"10.1109/tip.2021.3092814","title":"Structure-Aware Motion Deblurring Using Multi-Adversarial Optimized CycleGAN","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":81,"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":"Hong Kong Polytechnic University; Ministry of Science and Technology, Taiwan; National Natural Science Foundation of China","keywords":"Deblurring; Computer science; Artificial intelligence; Kernel (algebra); Image restoration; Pattern recognition (psychology); Image (mathematics); Adversarial system; Computer vision; Convolutional neural network; Image processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02502573497487601,"gpt":0.2987943317873849,"spread":0.2737685968125089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001687547,0.0003865436,0.0003475179,0.0002982276,0.0009355923,0.0009121969,0.0006472821,0.0001631804,0.00003245939],"category_scores_gemma":[0.0000392412,0.0004222144,0.0001477358,0.001037665,0.0001265741,0.003863027,0.00001898502,0.0006063471,0.000007482563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002763015,"about_ca_system_score_gemma":0.0003833282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001823521,"about_ca_topic_score_gemma":0.000008826287,"domain_scores_codex":[0.9974864,0.0001194092,0.0004669482,0.0009370077,0.0004454597,0.0005447551],"domain_scores_gemma":[0.9983874,0.00005668375,0.0002294084,0.0006377705,0.0005360658,0.0001526758],"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":[0.00004653061,0.0003042298,0.000006135509,0.0002088117,0.0000370319,0.0001457139,0.0009180392,0.03968984,0.6445194,0.00002350677,0.000005884244,0.3140948],"study_design_scores_gemma":[0.0006570941,0.00001343275,0.000004638041,0.0001623649,0.00002705073,0.0001271458,0.00005437288,0.55378,0.4443566,0.0005159851,0.00001117558,0.00029007],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00162458,0.0001548356,0.9959065,0.0001691862,0.0006085426,0.0001955899,0.00001270234,0.001271624,0.00005639434],"genre_scores_gemma":[0.4201171,0.000007504127,0.5796026,0.0001315497,0.00004663998,0.00001179258,0.00000205679,0.00003814837,0.00004259986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5140902,"threshold_uncertainty_score":0.999823,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3135420168","doi":"10.1007/978-3-030-67070-2_1","title":"AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results","year":2020,"lang":"en","type":"book-chapter","venue":"Institutional Research Information System (University of Udine)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Social Innovation; McMaster University","funders":"","keywords":"Computer science; Focus (optics); FLOPS; Image (mathematics); Set (abstract data type); Resolution (logic); Magnification; Artificial intelligence; Factor (programming language); State (computer science); Computer engineering; Algorithm; Parallel computing; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.0992968842218422,"gpt":0.3435963320656298,"spread":0.2442994478437876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002034408,0.0002293689,0.0003634305,0.0007226979,0.0007362423,0.0001143666,0.00107569,0.0002580972,0.00001224253],"category_scores_gemma":[0.0004064067,0.0002578321,0.0001000429,0.0002942919,0.0006189986,0.001502075,0.001038911,0.000690578,0.0002197213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006461206,"about_ca_system_score_gemma":0.0006423884,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002831352,"about_ca_topic_score_gemma":0.000002389411,"domain_scores_codex":[0.9972209,0.0001319485,0.0004931878,0.0004304595,0.001462535,0.0002609581],"domain_scores_gemma":[0.9972201,0.0002734476,0.0004102992,0.0005207227,0.001353802,0.0002216097],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001381547,0.00001284329,1.116442e-7,0.0004785805,0.00002954329,0.00003849038,0.0008978664,0.0004449296,0.00001651528,0.9761836,0.003056889,0.01870245],"study_design_scores_gemma":[0.001015541,0.000492552,0.00001977318,0.001793866,0.00001307489,0.00008013161,0.0004218283,0.2950743,0.00005634658,0.005732225,0.6948836,0.0004167567],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002865838,0.000157703,0.6401932,0.002799512,0.00009178575,0.000341719,0.0001054535,0.0002038637,0.3561039],"genre_scores_gemma":[0.0622233,0.0005858713,0.9229909,0.0001321911,0.0002022337,0.000006488735,0.0002062984,0.00002424416,0.01362845],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9704514,"threshold_uncertainty_score":0.9999874,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2103882108","doi":"10.1186/1687-6180-2012-16","title":"SSIM-inspired image restoration using sparse representation","year":2012,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":74,"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","keywords":"Sparse approximation; Metric (unit); Image quality; Mean squared error; Computer science; Norm (philosophy); Gradient descent; Representation (politics); Artificial intelligence; Pattern recognition (psychology); Image restoration; Algorithm; Peak signal-to-noise ratio; Image (mathematics); Mathematics; Image processing; Statistics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.04963724024173807,"gpt":0.3697160182222656,"spread":0.3200787779805275,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001122457,0.0002983233,0.0003005388,0.0005184418,0.0005103322,0.0006372527,0.0007584779,0.00008365638,0.00001134739],"category_scores_gemma":[0.0002932962,0.000278245,0.00007259588,0.001172621,0.0001225044,0.01911576,0.0001328947,0.0007226226,0.00001414187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004051837,"about_ca_system_score_gemma":0.0001683457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001473758,"about_ca_topic_score_gemma":9.200804e-7,"domain_scores_codex":[0.9971806,0.0002583446,0.0007343316,0.0004332424,0.0007285684,0.0006648847],"domain_scores_gemma":[0.9982167,0.000125011,0.0008419112,0.0003090298,0.0002974281,0.0002099148],"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":[0.0001507639,0.000401871,0.007282596,0.000115029,0.000007227276,0.0001661988,0.001928777,0.005532784,0.1281357,0.001523011,0.00009405361,0.854662],"study_design_scores_gemma":[0.002543434,0.000621626,0.004113855,0.003329287,0.0000416212,0.002352995,0.000702908,0.7080686,0.1751848,0.09256894,0.008338985,0.002132924],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01326104,0.006095173,0.978242,0.0002384691,0.0003757576,0.0001580373,5.297088e-7,0.0002713155,0.001357715],"genre_scores_gemma":[0.5183977,0.0001437412,0.4808799,0.0002102387,0.0003203028,0.00000643389,9.019541e-7,0.00002415163,0.00001663057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.852529,"threshold_uncertainty_score":0.999967,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996680032","doi":"","title":"Efficient and Information-Preserving Future Frame Prediction and Beyond","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":72,"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":"Computer science; MNIST database; Autoencoder; Bottleneck; Artificial intelligence; Frame (networking); Machine learning; Feature extraction; Information bottleneck method; Margin (machine learning); Feature (linguistics); High memory; Key (lock); Deep learning; State (computer science); Algorithm; Mutual information","retraction":null,"screen_n_in":null,"score":{"opus":0.01964610070994115,"gpt":0.2979189959929102,"spread":0.2782728952829691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009212695,0.0001020082,0.0000811538,0.000125833,0.0002045282,0.0005023628,0.000357259,0.00004511972,0.00003605551],"category_scores_gemma":[0.0004697991,0.0001038563,0.00001734977,0.0001810563,0.00005850595,0.001323162,0.0003142227,0.0003022097,0.00001508954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103801,"about_ca_system_score_gemma":0.00003893799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007047091,"about_ca_topic_score_gemma":4.127548e-7,"domain_scores_codex":[0.9990683,0.00004260815,0.0001981847,0.0002750703,0.0003090713,0.0001067189],"domain_scores_gemma":[0.9992748,0.00008797596,0.0001286358,0.0001396407,0.0002738939,0.00009505299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005684548,0.00006221163,0.01242275,0.00005908002,0.00006503222,0.00001030738,0.02317927,0.01076134,0.00693497,0.8365655,0.001467044,0.1084156],"study_design_scores_gemma":[0.0002131619,0.00007154164,0.006006434,0.00002749577,0.000003340505,0.00001162301,0.0007291571,0.9822553,0.0001863676,0.00593637,0.004452943,0.0001063045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01354594,0.00004824312,0.9298532,0.03755632,0.0002060899,0.0001606389,0.00001154649,0.0005138617,0.01810416],"genre_scores_gemma":[0.9079702,0.0000796134,0.09063323,0.001082137,0.0001037286,0.00002939752,0.00002217607,0.000005757484,0.00007371716],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9714939,"threshold_uncertainty_score":0.4844296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962360676","doi":"10.1145/3306346.3322996","title":"Hyperparameter optimization in black-box image processing using differentiable proxies","year":2019,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Computer science; Black box; Software; Pipeline (software); Artificial intelligence; Convolutional neural network; Image processing; Computer engineering; Computer hardware; Real-time computing; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01982256747076111,"gpt":0.2751720322641711,"spread":0.25534946479341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001581683,0.0002144106,0.0002102171,0.0005519541,0.0001677506,0.0002914336,0.0008017256,0.0001126605,0.00001755093],"category_scores_gemma":[0.00003247841,0.0002133129,0.00007095048,0.001314658,0.0001153977,0.00209609,0.00002972559,0.0003768149,0.000009532717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007134133,"about_ca_system_score_gemma":0.00007865235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001484138,"about_ca_topic_score_gemma":0.000005430686,"domain_scores_codex":[0.9985469,0.0000526774,0.0002864831,0.0005091703,0.0002767206,0.0003280537],"domain_scores_gemma":[0.9988122,0.0000733513,0.0001142943,0.0008042484,0.0001459689,0.00004993773],"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":[0.0002455467,0.003684065,0.009179649,0.001854173,0.000151652,0.00005785752,0.007233969,0.6047156,0.1811252,0.0051885,0.00006856277,0.1864952],"study_design_scores_gemma":[0.0003248415,0.00007487624,0.000180338,0.0002079637,0.00001247066,0.00001189928,0.00004008253,0.9632347,0.02173662,0.01383867,0.0000303958,0.0003071146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03240636,0.00005379205,0.9662782,0.0002888921,0.00008173667,0.0003367685,0.000001869808,0.000448543,0.0001038419],"genre_scores_gemma":[0.3984243,0.00003568292,0.6013192,0.0001298331,0.000004838857,0.00002099696,0.000001301513,0.00001990191,0.00004399315],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3660179,"threshold_uncertainty_score":0.8698649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2896184058","doi":"10.1109/tip.2018.2874284","title":"High-quality Image Restoration Using Low-Rank Patch Regularization and Global Structure Sparsity","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; National Natural Science Foundation of China","keywords":"Image restoration; Regularization (linguistics); Artificial intelligence; Iterative reconstruction; Pixel; Computer science; Residual; Image resolution; Pattern recognition (psychology); Deblurring; Norm (philosophy); Mathematics; Computer vision; Algorithm; Image (mathematics); Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01857909878811228,"gpt":0.3071245329623622,"spread":0.2885454341742499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003199402,0.000321905,0.0002779233,0.0001586041,0.001118977,0.0008703976,0.0004678364,0.0001703031,0.000009944023],"category_scores_gemma":[0.00004122563,0.0003361622,0.00004977324,0.001009564,0.000452623,0.004644226,0.00001714188,0.0003084462,0.00000555663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002808664,"about_ca_system_score_gemma":0.0002104139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009495468,"about_ca_topic_score_gemma":0.00004411587,"domain_scores_codex":[0.9977679,0.0001441949,0.0004382115,0.000811659,0.0004518217,0.0003862679],"domain_scores_gemma":[0.9982681,0.0000322307,0.0003208552,0.0005610851,0.0006940278,0.000123745],"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":[0.0001072758,0.0001664878,0.00007610284,0.0003114922,0.00001870143,0.00001339527,0.0007124997,0.0002333674,0.7773991,0.0005712933,0.00003472244,0.2203555],"study_design_scores_gemma":[0.0006652742,0.0001229846,0.0005547369,0.0003185425,0.00004894891,0.00008845125,0.00004852613,0.3511722,0.6008618,0.04544,0.00002063613,0.0006578906],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05340414,0.00005665577,0.9448673,0.0002953565,0.0002626663,0.0002356309,0.00003135037,0.0007849039,0.00006201288],"genre_scores_gemma":[0.5016505,0.000004859629,0.4981211,0.0001230933,0.00006240298,0.000004910206,0.000002485323,0.00001498182,0.00001569768],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4482463,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3107066575","doi":"10.1007/978-3-030-58520-4_27","title":"Conditional Entropy Coding for Efficient Video Compression","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Entropy encoding; Codec; Decoding methods; Conditional entropy; Data compression; Artificial intelligence; Autoregressive model; Deep learning; Entropy (arrow of time); Algorithm; Image compression; Theoretical computer science; Speech recognition; Computer vision; Computer engineering; Image processing; Principle of maximum entropy; Image (mathematics); Computer hardware","retraction":null,"screen_n_in":null,"score":{"opus":0.020204340808647,"gpt":0.2805028317985322,"spread":0.2602984909898852,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004909619,0.0005357037,0.0005544255,0.0005361275,0.0004448326,0.0005872989,0.003323821,0.0002367136,0.0000111233],"category_scores_gemma":[0.0002516258,0.000503745,0.0001591751,0.0004309034,0.0007032607,0.000548094,0.001617282,0.0006916919,0.00002042623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003643071,"about_ca_system_score_gemma":0.000490819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001406078,"about_ca_topic_score_gemma":0.00000117912,"domain_scores_codex":[0.9960297,0.00002394238,0.0005503937,0.001792451,0.0009909401,0.0006125796],"domain_scores_gemma":[0.997342,0.0007329459,0.0004196462,0.0008932754,0.0004039042,0.0002082392],"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":[0.00004392067,0.00008829886,0.00001176939,0.0002963703,0.00002181359,0.0001211877,0.0007257967,0.06309406,0.01570796,0.4037459,0.0004996847,0.5156432],"study_design_scores_gemma":[0.000221704,0.0001109248,0.000005226902,0.0003830231,0.00000469559,0.00002773256,4.563409e-8,0.6481101,0.009629805,0.338989,0.002115519,0.0004022357],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002873829,0.0003237506,0.9952061,0.001715889,0.0008845761,0.0006968253,0.00002344469,0.000585866,0.0005606492],"genre_scores_gemma":[0.04647134,0.00001376399,0.9507409,0.002196962,0.0004077956,0.00003968576,0.0000227386,0.00004149967,0.00006531112],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5850161,"threshold_uncertainty_score":0.9997414,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2109200779","doi":"10.1109/icip.2002.1038982","title":"A new direction adaptive scheme for image interpolation","year":2003,"lang":"en","type":"article","venue":"Proceedings - International Conference on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Interpolation (computer graphics); Computer science; Scheme (mathematics); Computer vision; Artificial intelligence; Image scaling; Image (mathematics); Algorithm; Image processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04325412093976623,"gpt":0.3317851979211418,"spread":0.2885310769813756,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004497386,0.0003813264,0.0002667175,0.0004276382,0.00033095,0.001768572,0.001103334,0.0001165766,0.00006797939],"category_scores_gemma":[0.0009289181,0.0003914406,0.0001051329,0.000499297,0.00009742706,0.005961571,0.0001619739,0.0003509618,0.00003044662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002501539,"about_ca_system_score_gemma":0.0003805508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007320452,"about_ca_topic_score_gemma":0.000001114148,"domain_scores_codex":[0.9975511,0.00001580834,0.0004795732,0.0009368049,0.0005621399,0.0004545495],"domain_scores_gemma":[0.9968897,0.00005371022,0.0005243401,0.0001792571,0.002190497,0.0001624705],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001400602,0.0001374169,0.0001028113,0.0001091359,0.00003818486,0.00000349959,0.001172354,5.73425e-7,0.3583934,0.5146778,0.002845126,0.1223796],"study_design_scores_gemma":[0.0009753059,0.0002784411,0.00005839233,0.0006529092,0.00001691465,0.00007803746,0.0003848453,0.553382,0.1411129,0.298662,0.003654403,0.0007437991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001765198,0.00007440954,0.9265747,0.001466183,0.0003168535,0.0004205475,0.000004247996,0.0008665653,0.07009994],"genre_scores_gemma":[0.2032787,0.00001745768,0.795129,0.0002596586,0.0001449673,0.0001692484,0.000005872024,0.00003866219,0.0009564428],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5533814,"threshold_uncertainty_score":0.9998537,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1672651452","doi":"10.1109/iscas.2002.1009958","title":"Canny edge based image expansion","year":2003,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":56,"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; Bicubic interpolation; Canny edge detector; Stairstep interpolation; Interpolation (computer graphics); Image gradient; Artificial intelligence; Deriche edge detector; Computer vision; Mathematics; Enhanced Data Rates for GSM Evolution; Image scaling; Pixel; Demosaicing; Edge detection; Image (mathematics); Computer science; Algorithm; Image processing; Multivariate interpolation; Binary image","retraction":null,"screen_n_in":null,"score":{"opus":0.01209584733312898,"gpt":0.2691881410219382,"spread":0.2570922936888093,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001651256,0.000096452,0.00008049153,0.00006826305,0.00008395076,0.0001107419,0.0004657012,0.00003031193,0.00004783132],"category_scores_gemma":[0.0001213517,0.00008317454,0.00002722076,0.0002868862,0.00003814973,0.000768183,0.00006703025,0.00007690202,0.00004998074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003440803,"about_ca_system_score_gemma":0.0001166983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006769708,"about_ca_topic_score_gemma":0.000001727788,"domain_scores_codex":[0.9992172,0.00003731509,0.0001113081,0.0002822002,0.0001451251,0.0002068515],"domain_scores_gemma":[0.9992616,0.00003213761,0.00003707887,0.0005109982,0.00009416048,0.00006403678],"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":[0.000005301717,0.0002394211,0.0002674994,0.00005634319,0.000005320986,0.00008836513,0.0003023292,0.00001286078,0.6175336,0.252694,0.0292133,0.09958163],"study_design_scores_gemma":[0.0001905453,0.00004207476,0.00006130392,0.00001870023,0.000001356475,0.00001240273,0.000007473816,0.0404724,0.896593,0.0404386,0.02192592,0.0002362052],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001190888,0.00005883033,0.964197,0.000447021,0.00007967279,0.00006816754,2.022378e-7,0.0009545013,0.03407548],"genre_scores_gemma":[0.06389062,0.000001905383,0.9342737,0.001010768,0.000007555962,0.00001354838,3.623452e-7,0.000008098411,0.0007934979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2790594,"threshold_uncertainty_score":0.3391759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163970352","doi":"10.1109/tip.2006.873446","title":"A segmentation-based regularization term for image deconvolution","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Maximum a posteriori estimation; Blind deconvolution; Deconvolution; Image restoration; Mathematics; Artificial intelligence; Image segmentation; Regularization (linguistics); Segmentation; Pattern recognition (psychology); Prior probability; Algorithm; Bayesian probability; Image processing; Computer science; Image (mathematics); Statistics; Maximum likelihood","retraction":null,"screen_n_in":null,"score":{"opus":0.01075540239546179,"gpt":0.2777735855766936,"spread":0.2670181831812318,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002197264,0.0002586009,0.0001837612,0.0003418617,0.0007187535,0.0006411636,0.0004377895,0.00009306992,0.000008132276],"category_scores_gemma":[0.00001544002,0.0002799632,0.0001078299,0.0006369444,0.0001288068,0.002893206,0.000002642347,0.000167374,0.00001087927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002189474,"about_ca_system_score_gemma":0.0002268411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008728273,"about_ca_topic_score_gemma":0.000006363939,"domain_scores_codex":[0.998288,0.00004149338,0.0004055382,0.0006048766,0.000289394,0.0003706929],"domain_scores_gemma":[0.9987723,0.00008968277,0.0002463952,0.0003810295,0.0004513531,0.00005926161],"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":[0.00005143623,0.0003874275,0.000008565221,0.0003185245,0.000008343975,0.000005928173,0.000148553,0.002489961,0.7216957,0.0002814065,0.0002288131,0.2743753],"study_design_scores_gemma":[0.0005496316,0.00006235126,0.00002294308,0.0001019909,0.00001954289,0.000009272333,0.000009481403,0.4375057,0.5519524,0.009473664,0.00004764109,0.0002453957],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002118643,0.00007525776,0.996891,0.0005544391,0.0001607299,0.0005499348,0.0000146089,0.001281613,0.0002605949],"genre_scores_gemma":[0.2239672,0.000002247244,0.7751336,0.0001969838,0.00004600501,0.0003414898,0.00001548245,0.00003689682,0.0002600832],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4350157,"threshold_uncertainty_score":0.9999653,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2963420948","doi":"10.1109/tip.2018.2847421","title":"Deep Blur Mapping: Exploiting High-Level Semantics by Deep Neural Networks","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Image Processing","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":53,"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; Nvidia","keywords":"Artificial intelligence; Computer science; Convolutional neural network; Benchmark (surveying); Deep learning; Computer vision; Semantics (computer science); Segmentation; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.02427187580338026,"gpt":0.2688095685042937,"spread":0.2445376927009134,"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":[0.000322153,0.0004920362,0.0003720241,0.0003271789,0.001360726,0.001048756,0.001293015,0.0001797972,0.00002299399],"category_scores_gemma":[0.00003352419,0.0005159736,0.0001167401,0.001293782,0.0004076358,0.003612766,0.00002499751,0.0007381532,0.00003375136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001440618,"about_ca_system_score_gemma":0.00007219754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000142713,"about_ca_topic_score_gemma":0.00001131572,"domain_scores_codex":[0.9968991,0.00008897845,0.0006023394,0.0009982378,0.0005069482,0.0009043587],"domain_scores_gemma":[0.9980497,0.0001164943,0.0003376997,0.0007259748,0.0005615061,0.0002086641],"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":[0.00002569669,0.0002548271,0.000007963754,0.0001367399,0.00002776799,0.00003185293,0.00148073,0.003212634,0.04538034,0.00005185269,0.0002223546,0.9491673],"study_design_scores_gemma":[0.0003345657,0.0001142127,0.000008427112,0.0001606993,0.00002211903,0.00007627697,0.0001265058,0.8942471,0.1026797,0.001566013,0.0001184273,0.0005460362],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005246103,0.0003448115,0.9953185,0.0007475037,0.0005763187,0.0002413555,0.000004154873,0.002025471,0.0002173132],"genre_scores_gemma":[0.5047722,0.00001622721,0.4943746,0.0005107793,0.0001336216,0.00004867725,0.000001877069,0.0000533033,0.00008876722],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9486212,"threshold_uncertainty_score":0.9999883,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018459209","doi":"10.1117/1.3580750","title":"Single-image super-resolution based on Markov random field and contourlet transform","year":2011,"lang":"en","type":"article","venue":"Journal of Electronic Imaging","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":49,"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":"National Natural Science Foundation of China","keywords":"Contourlet; Artificial intelligence; Markov random field; Pattern recognition (psychology); Wavelet transform; Computer vision; Top-hat transform; Computer science; Random field; Mathematics; Image resolution; Pixel; Image processing; Wavelet; Image (mathematics); Image segmentation; Image texture; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.00954816042315723,"gpt":0.2367379721913679,"spread":0.2271898117682107,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007073653,0.0001537271,0.0002303034,0.0002304838,0.000108498,0.0001233029,0.0004632005,0.00003446807,0.00001511939],"category_scores_gemma":[0.0001300253,0.0001317336,0.00009080234,0.0001613234,0.00005805256,0.0013798,0.00003272356,0.000446564,8.555143e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001529759,"about_ca_system_score_gemma":0.0001699996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009253713,"about_ca_topic_score_gemma":0.000003213575,"domain_scores_codex":[0.9987206,0.00006498957,0.000349525,0.0001906407,0.0002547344,0.0004195239],"domain_scores_gemma":[0.9991592,0.0001521222,0.0002281273,0.000206251,0.0001772956,0.00007704238],"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":[0.001549926,0.0005270324,0.0004539022,0.00009085154,0.00006032463,0.0003046689,0.001724528,0.00001960032,0.1542548,0.004954746,0.002765361,0.8332942],"study_design_scores_gemma":[0.007860438,0.003026465,0.0002479654,0.0006177353,0.00008148771,0.001290426,0.00007766757,0.5034613,0.4030567,0.07234062,0.007205538,0.0007336946],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001094575,0.0009458488,0.9905329,0.003414374,0.0000830692,0.00009482704,2.560616e-7,0.00008319075,0.003750965],"genre_scores_gemma":[0.7121472,0.00005082971,0.2868209,0.0008971363,0.00004756705,0.000002479305,1.76051e-7,0.00001187517,0.00002184876],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8325605,"threshold_uncertainty_score":0.5371943,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2519597608","doi":"10.1007/978-3-319-46487-9_45","title":"Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Deblurring; Computer science; Deconvolution; Computer vision; Blind deconvolution; Artificial intelligence; Kernel (algebra); Scale (ratio); Motion blur; Image restoration; Computer graphics (images); Image (mathematics); Image processing; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0112317123347765,"gpt":0.2663833764137624,"spread":0.2551516640789859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009464217,0.0004825759,0.0005376593,0.001107406,0.0002576917,0.0002365859,0.002519052,0.0002496269,0.00001039817],"category_scores_gemma":[0.0002187322,0.0004030571,0.0001563138,0.0006342382,0.0008627942,0.0005391605,0.0009899852,0.0004589293,0.000005589706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018022,"about_ca_system_score_gemma":0.0004293969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007857554,"about_ca_topic_score_gemma":0.000006356869,"domain_scores_codex":[0.9964753,0.00003059391,0.0006316032,0.001440088,0.0007710261,0.0006513596],"domain_scores_gemma":[0.9969776,0.0005944155,0.0006507243,0.0009914042,0.0006702891,0.0001156131],"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":[0.00002844903,0.00003772004,0.0000158882,0.0001231558,0.00001718344,0.000007903204,0.0005745606,0.02878798,0.005364365,0.0193423,0.000009692772,0.9456908],"study_design_scores_gemma":[0.0009122101,0.0006506062,0.00001670399,0.001286107,0.00001581633,0.00002214127,2.960186e-7,0.4991383,0.04444839,0.451718,0.0009253582,0.0008660928],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008951389,0.0003526052,0.9969727,0.0002849816,0.0008414779,0.000729461,0.000005470418,0.000278613,0.0004452033],"genre_scores_gemma":[0.08668093,0.00004131914,0.9126462,0.0002146372,0.0001223149,0.00004352345,0.00000333269,0.00003597064,0.0002118087],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9448247,"threshold_uncertainty_score":0.9998421,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3023821242","doi":"10.20944/preprints202003.0313.v2","title":"Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Alberta Energy; Athabasca University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Detector; Computer science; Enhanced Data Rates for GSM Evolution; Artificial intelligence; Residual; Computer vision; Context (archaeology); Overhead (engineering); Image resolution; Object detection; Generative adversarial network; Deep learning; Pattern recognition (psychology); Telecommunications; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.05712182583916333,"gpt":0.3082877557819736,"spread":0.2511659299428103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00102331,0.0008104849,0.0009282608,0.0004292895,0.0002605484,0.0003143884,0.001493802,0.0003732877,0.00001072619],"category_scores_gemma":[0.0007290267,0.0008452068,0.000126954,0.001149024,0.0001943901,0.0005112548,0.004586654,0.001932834,0.0000550093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003811974,"about_ca_system_score_gemma":0.0003430796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004011848,"about_ca_topic_score_gemma":0.0003794172,"domain_scores_codex":[0.9946263,0.0003770278,0.0007499167,0.002846703,0.0005062278,0.0008938157],"domain_scores_gemma":[0.996563,0.0002312989,0.0005852454,0.002040605,0.0003022036,0.0002777113],"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":[0.0003110082,0.00004147763,0.003447966,0.0006007467,0.000108953,0.0002494792,0.003102896,0.00366669,0.4076976,0.00002163726,0.000009765554,0.5807417],"study_design_scores_gemma":[0.0004355494,0.0001436213,0.02955088,0.001655224,0.00004213751,0.0001009544,0.00003337047,0.05594475,0.8962991,0.01438627,0.0002086807,0.001199461],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1716924,0.000231545,0.823715,0.0004124043,0.0003168854,0.001074349,0.000003225981,0.001496422,0.001057818],"genre_scores_gemma":[0.62397,0.00008780181,0.3754,0.0002265469,0.000158176,0.00002748763,0.000002771044,0.00007290278,0.00005435321],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5795423,"threshold_uncertainty_score":0.9993999,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4242963054","doi":"10.1109/icpr.2004.1334046","title":"Blind super-resolution using a learning-based approach","year":2004,"lang":"en","type":"article","venue":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Point spread function; Deconvolution; Superresolution; Artificial intelligence; Blind deconvolution; Computer science; Image restoration; Measure (data warehouse); Image resolution; Computer vision; Optical transfer function; Image (mathematics); Point (geometry); Function (biology); Iterative reconstruction; Pattern recognition (psychology); Image processing; Algorithm; Mathematics; Optics; Data mining; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.07349998648637024,"gpt":0.3029519393606672,"spread":0.2294519528742969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004898692,0.0003437395,0.0002692748,0.0003927677,0.0002822879,0.0003449723,0.001858729,0.000152951,0.00005348693],"category_scores_gemma":[0.0002989867,0.0002973938,0.0001614948,0.0005598009,0.0002181894,0.001199844,0.000252193,0.0005403182,0.00003420416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003793642,"about_ca_system_score_gemma":0.000282286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008272631,"about_ca_topic_score_gemma":0.000003706154,"domain_scores_codex":[0.9974146,0.00003218799,0.0005506195,0.0006936927,0.0009125189,0.0003963142],"domain_scores_gemma":[0.9972101,0.00003299853,0.0006244499,0.0002449055,0.001787911,0.00009967902],"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":[0.001706437,0.01209174,0.0477269,0.002397282,0.001201863,0.00004447145,0.008741416,0.07721007,0.3187502,0.09160742,0.007095483,0.4314267],"study_design_scores_gemma":[0.004749823,0.0005871724,0.001388757,0.002572337,0.00008267936,0.0001806272,0.0003161123,0.6013871,0.2357562,0.1510618,0.0004963232,0.001421005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0327715,0.00005144525,0.9573346,0.002397297,0.0003412682,0.0004588113,0.00002777323,0.000372526,0.006244797],"genre_scores_gemma":[0.8512272,0.00001188689,0.1478375,0.0005371833,0.0001180029,0.00006402986,0.00002247567,0.00003247268,0.0001492914],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8184556,"threshold_uncertainty_score":0.9999478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1956263714","doi":"10.1109/icip.2001.958269","title":"A new edge-directed image expansion scheme","year":2002,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":43,"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":"Sharpening; Interpolation (computer graphics); Enhanced Data Rates for GSM Evolution; Computer science; Image (mathematics); Fidelity; Scheme (mathematics); Computer vision; Image gradient; Image scaling; Artificial intelligence; Stairstep interpolation; Algorithm; Image processing; Edge detection; Bilinear interpolation; Mathematics; Multivariate interpolation; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.01909903648790376,"gpt":0.2630388001288846,"spread":0.2439397636409808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006111208,0.0001233871,0.0001089165,0.00008710137,0.00007983593,0.0001729608,0.000746324,0.00004285646,0.000308074],"category_scores_gemma":[0.00008827871,0.0001087279,0.00003425013,0.0004875297,0.00002688656,0.00137462,0.0002820358,0.0001116968,0.0003269348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002967419,"about_ca_system_score_gemma":0.00002548625,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001350251,"about_ca_topic_score_gemma":0.000001202947,"domain_scores_codex":[0.9990522,0.00001721999,0.0001457463,0.0003550426,0.0001871366,0.0002426364],"domain_scores_gemma":[0.9991508,0.0000273459,0.00004960238,0.0005685496,0.00009384663,0.0001098266],"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":[0.000001761221,0.00006724277,0.00002719304,0.0000120078,0.000004345507,0.0000280585,0.0003629245,2.582863e-7,0.2746955,0.009406914,0.208966,0.5064279],"study_design_scores_gemma":[0.0004251166,0.00008602253,0.0001087807,0.00006228254,0.000002923724,0.00005849673,0.000008176019,0.6088753,0.3185005,0.04136872,0.02997782,0.0005259078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00007679124,0.0002821756,0.9659674,0.00141548,0.00007252534,0.00007770482,1.1225e-7,0.004602197,0.02750565],"genre_scores_gemma":[0.004335799,0.00002439887,0.9862571,0.0004703682,0.00004601015,0.000007218771,3.292024e-7,0.00001165607,0.008847136],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.608875,"threshold_uncertainty_score":0.4433794,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1988374871","doi":"10.1111/j.1467-8659.2012.03211.x","title":"Registration Based Non‐uniform Motion Deblurring","year":2012,"lang":"en","type":"article","venue":"Computer Graphics Forum","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Deblurring; Motion blur; Computer vision; Artificial intelligence; Perspective (graphical); Computer science; Motion (physics); Point spread function; Motion interpolation; Shake; Image restoration; Motion estimation; Image (mathematics); Mathematics; Image processing; Block-matching algorithm; Object (grammar); Video tracking","retraction":null,"screen_n_in":null,"score":{"opus":0.01778035064555933,"gpt":0.2634282026037313,"spread":0.245647851958172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003913705,0.0001917628,0.0001437233,0.0002630631,0.0002545766,0.0002147793,0.0007879881,0.00009520277,0.00000148474],"category_scores_gemma":[0.00001789649,0.0001936037,0.00008731049,0.0005969508,0.00006359594,0.002419478,0.0002699325,0.0002134495,0.00001332759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005213618,"about_ca_system_score_gemma":0.00003815571,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006237829,"about_ca_topic_score_gemma":0.000002999815,"domain_scores_codex":[0.9985656,0.00003036963,0.0002614819,0.0003258622,0.0002859686,0.0005307908],"domain_scores_gemma":[0.9988185,0.000046429,0.0001680859,0.0006914136,0.000138506,0.0001370226],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001064394,0.000400904,0.02164682,0.0001425647,0.00002570214,0.0000114588,0.000528331,0.0003588308,0.002087204,0.6900356,0.006178399,0.2785735],"study_design_scores_gemma":[0.0001861305,0.0000666901,0.002199705,0.00005576006,0.000004403887,0.00001978266,0.000003280878,0.9633794,0.006154994,0.02422609,0.003432412,0.0002712975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006893697,0.00009077202,0.9963738,0.0007753039,0.0005462616,0.0001652682,7.027446e-7,0.0008646248,0.0004939288],"genre_scores_gemma":[0.4427478,0.000004111098,0.5562902,0.0008168137,0.00009968122,0.00001450681,0.00000548445,0.00001168632,0.000009698078],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9630206,"threshold_uncertainty_score":0.7894928,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194484130","doi":"10.1109/tmm.2021.3102401","title":"Learning-Based Quality Assessment for Image Super-Resolution","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":41,"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":"Computer science; Artificial intelligence; Image quality; Feature extraction; Database; Data mining; Feature (linguistics); Pattern recognition (psychology); Artificial neural network; Quality (philosophy); Image (mathematics); Image resolution; Deep learning; Generalization","retraction":null,"screen_n_in":null,"score":{"opus":0.03562366763511123,"gpt":0.3555343833712776,"spread":0.3199107157361664,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003854343,0.0001832319,0.0002021514,0.00011882,0.0003541764,0.0001508027,0.0003619183,0.00009465655,0.00003552424],"category_scores_gemma":[0.00008352407,0.000196748,0.0001578911,0.0003546032,0.00008336848,0.0006107579,0.000003646719,0.0003755371,0.0000216658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001735532,"about_ca_system_score_gemma":0.0003200326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001454367,"about_ca_topic_score_gemma":0.00001904599,"domain_scores_codex":[0.9983498,0.0001726357,0.0002991055,0.0005447978,0.0003170999,0.000316506],"domain_scores_gemma":[0.9983804,0.0004987909,0.00009319509,0.0005230356,0.0004002457,0.0001043115],"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":[0.00007104942,0.001413578,0.00003157811,0.0001842239,0.00005287884,0.00003542834,0.0006267314,0.03067356,0.4217366,0.0003096361,0.0005506982,0.5443141],"study_design_scores_gemma":[0.000611609,0.0001200313,0.0001060344,0.00002842364,0.00001074263,0.000004048968,0.00002324251,0.6949009,0.3023004,0.0006705475,0.001024538,0.0001995847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003245039,0.00002598525,0.9965687,0.001326322,0.0004321971,0.0002647403,0.00002210262,0.0009142339,0.0001211892],"genre_scores_gemma":[0.2106037,0.000008242398,0.7885842,0.0002280436,0.00002691086,0.0002035909,0.00001105255,0.000018767,0.000315525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6642273,"threshold_uncertainty_score":0.8023149,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057542768","doi":"10.1137/090771260","title":"Image Sharpening via Sobolev Gradient Flows","year":2010,"lang":"en","type":"article","venue":"SIAM Journal on Imaging Sciences","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Sharpening; Sobolev space; Mathematics; Metric (unit); Mathematical analysis; Uniqueness; Balanced flow; Smoothing; Isotropy; Applied mathematics; Computer science; Artificial intelligence; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01099794572114411,"gpt":0.295250868230119,"spread":0.2842529225089749,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001975584,0.0002570446,0.0002125826,0.000495847,0.001433178,0.002227372,0.003060666,0.00003552633,0.00003600373],"category_scores_gemma":[0.0003289617,0.0002018545,0.0001154714,0.0008951215,0.000555413,0.004311479,0.0003484838,0.001055277,0.00007688407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005714336,"about_ca_system_score_gemma":0.0002093901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005311647,"about_ca_topic_score_gemma":0.000002186653,"domain_scores_codex":[0.9972764,0.00007023712,0.0004087937,0.0006281226,0.0008917159,0.0007247062],"domain_scores_gemma":[0.9985314,0.0001263074,0.0003518347,0.0004822206,0.0002393485,0.0002688924],"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":[0.00000780302,0.0001430175,0.001665282,0.00001519876,0.00000894502,0.0003376289,0.0008489654,0.00008162968,0.6162739,0.0128008,0.004034589,0.3637822],"study_design_scores_gemma":[0.0004268342,0.0002650456,0.0009492538,0.000236113,0.000009073093,0.004037353,0.00008645921,0.7361543,0.0409249,0.204317,0.01175168,0.0008419763],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009948133,0.0001769837,0.9758911,0.005912963,0.002598773,0.00009138598,6.171564e-7,0.0005059918,0.004874112],"genre_scores_gemma":[0.2614915,0.00001377753,0.7372941,0.0008796542,0.0002425278,0.0000052881,1.538779e-7,0.00001283368,0.00006007124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7360727,"threshold_uncertainty_score":0.9998668,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979618460","doi":"10.1109/tmm.2019.2946094","title":"Light Field Super-Resolution Using Edge-Preserved Graph-Based Regularization","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Multimedia","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Light field; Computer science; Computer vision; Artificial intelligence; Iterative reconstruction; Graph; Image resolution; Regularization (linguistics); Field (mathematics); Algorithm; Mathematics; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01904249539632495,"gpt":0.2674966561232707,"spread":0.2484541607269458,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001606974,0.00020649,0.000179917,0.0003626491,0.0002083711,0.0001161303,0.0006148284,0.0001655129,0.00005699591],"category_scores_gemma":[0.00002441114,0.0002122616,0.0001141666,0.0007037792,0.00003249056,0.001090461,0.000005157411,0.0003001451,0.00006540601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000982815,"about_ca_system_score_gemma":0.0001009262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000360677,"about_ca_topic_score_gemma":0.00001153101,"domain_scores_codex":[0.9985396,0.00008404453,0.0002668875,0.000506965,0.0002939597,0.0003085457],"domain_scores_gemma":[0.9986872,0.0001593173,0.00009506172,0.0007928385,0.0001706423,0.00009495327],"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":[0.0001075455,0.0005234373,0.0001522557,0.0001037525,0.00003774531,0.00001104422,0.0005080876,0.05955519,0.8472916,0.0002444082,0.000371252,0.09109367],"study_design_scores_gemma":[0.0003200328,0.00007980805,0.0000216312,0.00005911102,0.000008352578,0.000002368202,0.000003990301,0.5950823,0.4032416,0.0008731969,0.0001465213,0.0001610022],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004406594,0.00003971783,0.9926311,0.0007553407,0.0008383677,0.0003678755,0.0000035831,0.000787969,0.0001693932],"genre_scores_gemma":[0.4367834,0.000005106449,0.5626798,0.0002633418,0.00002699754,0.00002808869,0.000002470249,0.00002002195,0.0001908215],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5355272,"threshold_uncertainty_score":0.8655777,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4304084118","doi":"10.1145/3503161.3547899","title":"Quality Assessment of Image Super-Resolution: Balancing Deterministic and Statistical Fidelity","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 30th ACM International Conference on Multimedia","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Fidelity; Weighting; Computer science; Image quality; Image (mathematics); Artificial intelligence; Image resolution; Quality (philosophy); Resolution (logic); Contrast (vision); Algorithm; Pattern recognition (psychology); Machine learning; Computer vision; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0551760696404402,"gpt":0.3771203647401609,"spread":0.3219442950997207,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007987108,0.0001423296,0.0002272875,0.00009762014,0.0001652794,0.00008857749,0.002099974,0.00002895471,0.00007318544],"category_scores_gemma":[0.001940648,0.0001208865,0.00004821497,0.000159858,0.0002728366,0.0004168678,0.002010968,0.0003230421,6.230358e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001342409,"about_ca_system_score_gemma":0.0001541742,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002518154,"about_ca_topic_score_gemma":9.807659e-7,"domain_scores_codex":[0.9980822,0.00003900611,0.0004753272,0.0003786729,0.0008501678,0.0001746422],"domain_scores_gemma":[0.998213,0.0002981295,0.0004597731,0.0002721464,0.0006963107,0.00006066665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000128883,0.0004884135,0.02492752,0.000282266,0.00006388808,0.000003996438,0.001579559,0.00002755604,0.3543324,0.5729509,0.001003417,0.04421119],"study_design_scores_gemma":[0.0005570368,0.0002273559,0.08447376,0.0001104564,0.00001202182,0.0000247205,0.0003116342,0.7762513,0.01006825,0.127572,0.0001346166,0.0002568216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1927308,0.00004967162,0.7837737,0.007579996,0.00109043,0.0008569297,0.0004485942,0.0003265511,0.01314333],"genre_scores_gemma":[0.6069357,0.00000534984,0.3928917,0.00007779817,0.00001553001,0.00003530955,0.000003152854,0.000004715244,0.00003077403],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7762238,"threshold_uncertainty_score":0.4929608,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2951720195","doi":"","title":"Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Normalization (sociology); Computer science; Artificial intelligence; Convolutional neural network; Deep learning; Machine learning; Artificial neural network; Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.0711780634921327,"gpt":0.209903069066744,"spread":0.1387250055746113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004881078,0.0003663255,0.000331077,0.0001696552,0.0006324564,0.0004107509,0.001970307,0.0001883029,0.000004863275],"category_scores_gemma":[0.00005704165,0.0003060158,0.00009982022,0.0005407691,0.000247187,0.001640681,0.004595535,0.0005002741,0.000009500548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001602178,"about_ca_system_score_gemma":0.00009499789,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003371888,"about_ca_topic_score_gemma":0.00001159424,"domain_scores_codex":[0.9979944,0.0001460078,0.0002622648,0.0009482076,0.0001202166,0.0005288788],"domain_scores_gemma":[0.9980212,0.0001503866,0.0004464724,0.001083805,0.0001816146,0.0001165074],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004134582,0.00004302646,0.03787842,0.0002920663,0.0001327895,0.0001601122,0.0006037222,0.04828692,0.0003475567,0.9031309,0.0008871871,0.008195906],"study_design_scores_gemma":[0.0002879369,0.00002055161,0.0007588149,0.0006340045,0.00005055004,0.00002331627,0.00003602264,0.8281761,0.0004766812,0.1662519,0.002699448,0.0005846499],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00910972,0.0009172924,0.9862095,0.000162962,0.000322654,0.0002600573,0.000001945356,0.0007729694,0.002242938],"genre_scores_gemma":[0.9349767,0.0007348023,0.0637657,0.0001442393,0.000155245,0.000002880992,0.000004733553,0.00002672183,0.0001889894],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.925867,"threshold_uncertainty_score":0.9999392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2598009569","doi":"10.1016/j.image.2017.03.016","title":"Deblurring of motion blurred images using histogram of oriented gradients and geometric moments","year":2017,"lang":"en","type":"article","venue":"Signal Processing Image Communication","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Deblurring; Artificial intelligence; Computer vision; Histogram; Moment (physics); Computer science; Image restoration; Point spread function; Image (mathematics); Mathematics; Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.03243007458686936,"gpt":0.3240563850906596,"spread":0.2916263105037902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005872422,0.000179932,0.0002888518,0.0004302149,0.0007163418,0.0002865464,0.001714639,0.00006344518,0.000001439605],"category_scores_gemma":[0.00035641,0.0001898337,0.00004621108,0.0004979759,0.000571673,0.003399428,0.001048584,0.0001875287,4.108696e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009428745,"about_ca_system_score_gemma":0.0000701455,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001058451,"about_ca_topic_score_gemma":0.000001263942,"domain_scores_codex":[0.9985099,0.00009421442,0.0004967814,0.0003373977,0.000335743,0.0002259879],"domain_scores_gemma":[0.9964693,0.00006153508,0.00138639,0.001308874,0.0007125365,0.00006134943],"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":[0.00002301973,0.0003013081,0.007732599,0.0005143802,0.00001979819,0.000001653324,0.0007783066,0.00002551403,0.3309967,0.0003311963,0.00001154808,0.659264],"study_design_scores_gemma":[0.001152823,0.0001745659,0.01946007,0.001681663,0.00007198448,0.00002605215,0.00009831887,0.531588,0.425433,0.01970127,0.00006741799,0.0005449026],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04758722,0.001750373,0.9499292,0.00007253959,0.00002656836,0.0001839484,0.000002877295,0.0001358379,0.0003114274],"genre_scores_gemma":[0.5495201,0.00006284656,0.4503795,0.000004840105,0.00000401536,0.000006536906,0.000003246377,0.00001072357,0.000008190145],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6587191,"threshold_uncertainty_score":0.7741194,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3082578808","doi":"10.1109/tci.2020.3019137","title":"Fast Multi-Focus Ultrasound Image Recovery Using Generative Adversarial Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Imaging","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Focus (optics); Computer science; Artificial intelligence; Frame rate; Computer vision; Image resolution; Frame (networking); Image (mathematics); Boundary (topology); Mean squared error; Deep learning; Image restoration; Image processing; Mathematics; Optics; Statistics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.02655443117823754,"gpt":0.286255957119422,"spread":0.2597015259411845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001246341,0.0002902285,0.0002302402,0.0001656023,0.0005362986,0.0004508591,0.0005361207,0.00005147933,0.00001939048],"category_scores_gemma":[0.00002560753,0.0003278732,0.0001389817,0.0006413665,0.0001348234,0.002193005,0.00001127977,0.0004462579,0.00002519458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00017535,"about_ca_system_score_gemma":0.0001686628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002032664,"about_ca_topic_score_gemma":0.000002080858,"domain_scores_codex":[0.9981272,0.0001112263,0.0003707439,0.0006831769,0.0003583607,0.0003493051],"domain_scores_gemma":[0.9988346,0.0003161494,0.0001676923,0.0002282472,0.0002870955,0.0001662265],"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":[0.00002778494,0.00008969529,0.000005828554,0.000007365708,0.00003065434,0.00002694422,0.0004299579,0.9465801,0.01284777,0.0001076166,0.0001195419,0.0397267],"study_design_scores_gemma":[0.0006108555,0.00004385016,0.00001754091,0.00003596624,0.00001851365,0.00006845655,0.00003598668,0.9838972,0.0124081,0.002497738,0.00002752711,0.0003382748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001708716,0.00007342714,0.9969253,0.001200218,0.0005327596,0.000222355,0.00002256991,0.0007792375,0.00007329201],"genre_scores_gemma":[0.3232171,0.00000629479,0.6753681,0.001230721,0.0001233627,0.00001320307,0.000004492468,0.00002656606,0.0000100991],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3230462,"threshold_uncertainty_score":0.9999173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087750740","doi":"10.1007/978-3-030-67070-2_1","title":"AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results","year":2020,"lang":"en","type":"preprint","venue":"Lecture notes in computer science","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Centre for Social Innovation; McMaster University","funders":"","keywords":"Computer science; Image (mathematics); Focus (optics); Resolution (logic); Set (abstract data type); FLOPS; Magnification; Artificial intelligence; Factor (programming language); Superresolution; State (computer science); Algorithm; Parallel computing","retraction":null,"screen_n_in":null,"score":{"opus":0.0374974150302877,"gpt":0.3556962747484532,"spread":0.3181988597181655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002351852,0.0006211418,0.0006318907,0.0005051747,0.0003564709,0.0009564329,0.004529904,0.0003215861,0.000001199319],"category_scores_gemma":[0.001383607,0.0005682649,0.0000987059,0.001900295,0.0008295829,0.0003999826,0.008860965,0.001772055,0.000008053639],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003192782,"about_ca_system_score_gemma":0.0005434347,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002109033,"about_ca_topic_score_gemma":0.000005462107,"domain_scores_codex":[0.993928,0.000325383,0.0007484073,0.003242132,0.0009542725,0.0008018438],"domain_scores_gemma":[0.9961978,0.0008467112,0.0003616052,0.00202467,0.000275516,0.0002937013],"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":[0.00002722761,0.0001145237,0.00000594047,0.0001119606,0.000005633059,0.00008907912,0.002619852,0.1293226,0.001198524,0.001021029,0.00004078546,0.8654428],"study_design_scores_gemma":[0.0002548123,0.0003071685,0.00009747694,0.0004139074,0.000004001724,0.00003323664,4.371889e-7,0.8965684,0.009742605,0.09171278,0.0003240708,0.0005411583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002560117,0.001503305,0.97578,0.01952666,0.001500752,0.0005253691,0.000008603457,0.0008103159,0.00008898913],"genre_scores_gemma":[0.2199457,0.000107297,0.778221,0.001381305,0.000285899,0.00003474002,0.00000297203,0.00002047153,5.795318e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8649017,"threshold_uncertainty_score":0.9996769,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2091588468","doi":"10.1109/icip.2012.6467151","title":"Objective quality assessment for image super-resolution: A natural scene statistics approach","year":2012,"lang":"en","type":"article","venue":"","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":31,"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","keywords":"Interpolation (computer graphics); Image resolution; Computer science; Image quality; Image (mathematics); Artificial intelligence; Resolution (logic); Quality (philosophy); Scene statistics; Computer vision; Image scaling; Algorithm; Data mining; Pattern recognition (psychology); Image processing","retraction":null,"screen_n_in":null,"score":{"opus":0.04388624292770592,"gpt":0.3828827118039825,"spread":0.3389964688762765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007591276,0.000169425,0.0001949165,0.00006161888,0.0002127461,0.0001689896,0.0005670747,0.00004815535,0.000005970032],"category_scores_gemma":[0.0001927452,0.0001454632,0.00005130822,0.0002238705,0.00009935675,0.001886117,0.000296464,0.0001763279,0.000004763214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002049577,"about_ca_system_score_gemma":0.0001157671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002103964,"about_ca_topic_score_gemma":0.000001819577,"domain_scores_codex":[0.9985102,0.00009443865,0.0002583501,0.000361881,0.0002936001,0.000481528],"domain_scores_gemma":[0.9987521,0.000199281,0.0001066944,0.0004715286,0.0003659233,0.0001044415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002417054,0.000681158,0.0008061242,0.0002025652,0.00003833798,0.000001568402,0.001053796,0.00000525938,0.01661659,0.8903347,0.01109255,0.07914318],"study_design_scores_gemma":[0.0009217779,0.0001826994,0.01077534,0.00002361175,0.00002146821,0.00004722571,0.0002569038,0.8532623,0.02087733,0.1100652,0.002663142,0.0009029653],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005765862,0.0001830914,0.9945198,0.0002451757,0.0002190754,0.0004014591,0.00002454006,0.0006273123,0.003721865],"genre_scores_gemma":[0.1290778,0.000002933843,0.870043,0.0002419587,0.00009573909,0.0001396565,0.0000197987,0.00001193456,0.0003671585],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8532571,"threshold_uncertainty_score":0.5931818,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3150396707","doi":"10.1109/tci.2021.3070522","title":"SRNSSI: A Deep Light-Weight Network for Single Image Super Resolution Using Spatial and Spectral Information","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Computational Imaging","topic":"Advanced Image Processing Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Residual; Block (permutation group theory); Computer science; Feature (linguistics); Image resolution; Benchmark (surveying); Artificial intelligence; Pattern recognition (psychology); Feature extraction; Set (abstract data type); Computer vision; Algorithm; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01340199518238769,"gpt":0.2597127222508836,"spread":0.2463107270684959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001607609,0.0001900985,0.0001630408,0.0001808426,0.0005789633,0.0005055772,0.0001819301,0.00004452826,0.000007522926],"category_scores_gemma":[0.00001861078,0.000217181,0.00008139214,0.0004060045,0.00006650193,0.00324574,0.00000958573,0.0001813254,0.000005009769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001712313,"about_ca_system_score_gemma":0.000147575,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001414272,"about_ca_topic_score_gemma":0.000009190061,"domain_scores_codex":[0.9986346,0.00005539983,0.0003484623,0.0003558942,0.0002753919,0.0003302669],"domain_scores_gemma":[0.9989746,0.0001728942,0.0001197345,0.000197813,0.0004557058,0.00007926324],"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":[0.0001002408,0.000394587,0.00009865754,0.0001725026,0.00008533004,0.00004430729,0.001743523,0.6548205,0.06245971,0.005802777,0.0005365938,0.2737412],"study_design_scores_gemma":[0.0004429678,0.00003593946,0.00008518063,0.00007394284,0.00002043618,0.000215064,0.00002389624,0.9477243,0.02616785,0.0246222,0.0003502844,0.0002379132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005191675,0.0001505994,0.9968416,0.001288898,0.0004479468,0.0002177094,0.00001289368,0.0003660751,0.0001551015],"genre_scores_gemma":[0.3042913,0.000004201652,0.6951745,0.0003845642,0.00008821172,0.0000222764,0.00001448569,0.00001310464,0.000007312824],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3037722,"threshold_uncertainty_score":0.8856384,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}